1
|
Reis PBPS, Clevert DA, Machuqueiro M. PypKa server: online pKa predictions and biomolecular structure preparation with precomputed data from PDB and AlphaFold DB. Nucleic Acids Res 2024:gkae255. [PMID: 38619040 DOI: 10.1093/nar/gkae255] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2024] [Revised: 03/14/2024] [Accepted: 03/28/2024] [Indexed: 04/16/2024] Open
Abstract
When preparing biomolecular structures for molecular dynamics simulations, pKa calculations are required to provide at least a representative protonation state at a given pH value. Neglecting this step and adopting the reference protonation states of the amino acid residues in water, often leads to wrong electrostatics and nonphysical simulations. Fortunately, several methods have been developed to prepare structures considering the protonation preference of residues in their specific environments (pKa values), and some are even available for online usage. In this work, we present the PypKa server, which allows users to run physics-based, as well as ML-accelerated methods suitable for larger systems, to obtain pKa values, isoelectric points, titration curves, and structures with representative pH-dependent protonation states compatible with commonly used force fields (AMBER, CHARMM, GROMOS). The user may upload a custom structure or submit an identifier code from PBD or UniProtKB. The results for over 200k structures taken from the Protein Data Bank and the AlphaFold DB have been precomputed, and their data can be retrieved without extra calculations. All this information can also be obtained from an application programming interface (API) facilitating its usage and integration into existing pipelines as well as other web services. The web server is available at pypka.org.
Collapse
Affiliation(s)
- Pedro B P S Reis
- BioISI - Instituto de Biossistemas e Ciências Integrativas, Faculdade de Ciências, Universidade de Lisboa, 1749-016 Lisboa, Portugal
- Machine Learning Research, Bayer AG, Müllerstraße 178, 13353 Berlin, Germany
| | - Djork-Arné Clevert
- Machine Learning Research, Bayer AG, Müllerstraße 178, 13353 Berlin, Germany
- Machine Learning Research, Pfizer, Berlin, Germany
| | - Miguel Machuqueiro
- BioISI - Instituto de Biossistemas e Ciências Integrativas, Faculdade de Ciências, Universidade de Lisboa, 1749-016 Lisboa, Portugal
| |
Collapse
|
2
|
Heyndrickx W, Mervin L, Morawietz T, Sturm N, Friedrich L, Zalewski A, Pentina A, Humbeck L, Oldenhof M, Niwayama R, Schmidtke P, Fechner N, Simm J, Arany A, Drizard N, Jabal R, Afanasyeva A, Loeb R, Verma S, Harnqvist S, Holmes M, Pejo B, Telenczuk M, Holway N, Dieckmann A, Rieke N, Zumsande F, Clevert DA, Krug M, Luscombe C, Green D, Ertl P, Antal P, Marcus D, Do Huu N, Fuji H, Pickett S, Acs G, Boniface E, Beck B, Sun Y, Gohier A, Rippmann F, Engkvist O, Göller AH, Moreau Y, Galtier MN, Schuffenhauer A, Ceulemans H. MELLODDY: Cross-pharma Federated Learning at Unprecedented Scale Unlocks Benefits in QSAR without Compromising Proprietary Information. J Chem Inf Model 2024; 64:2331-2344. [PMID: 37642660 PMCID: PMC11005050 DOI: 10.1021/acs.jcim.3c00799] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2023] [Indexed: 08/31/2023]
Abstract
Federated multipartner machine learning has been touted as an appealing and efficient method to increase the effective training data volume and thereby the predictivity of models, particularly when the generation of training data is resource-intensive. In the landmark MELLODDY project, indeed, each of ten pharmaceutical companies realized aggregated improvements on its own classification or regression models through federated learning. To this end, they leveraged a novel implementation extending multitask learning across partners, on a platform audited for privacy and security. The experiments involved an unprecedented cross-pharma data set of 2.6+ billion confidential experimental activity data points, documenting 21+ million physical small molecules and 40+ thousand assays in on-target and secondary pharmacodynamics and pharmacokinetics. Appropriate complementary metrics were developed to evaluate the predictive performance in the federated setting. In addition to predictive performance increases in labeled space, the results point toward an extended applicability domain in federated learning. Increases in collective training data volume, including by means of auxiliary data resulting from single concentration high-throughput and imaging assays, continued to boost predictive performance, albeit with a saturating return. Markedly higher improvements were observed for the pharmacokinetics and safety panel assay-based task subsets.
Collapse
Affiliation(s)
| | - Lewis Mervin
- AstraZeneca
R&D, Biomedical Campus, 1 Francis Crick Ave, Cambridge CB2 0SL, U.K.
| | - Tobias Morawietz
- Bayer
Pharma
AG, Global Drug Discovery, Chemical Research,
Computational Chemistry, Aprather Weg 18 a, Wuppertal 42096, Germany
| | - Noé Sturm
- Novartis
Institutes for BioMedical Research, Novartis Campus, Basel 4002, Switzerland
| | - Lukas Friedrich
- Merck KGaA, Global Research & Development, Frankfurter Strasse 250, Darmstadt 64293, Germany
| | - Adam Zalewski
- Amgen Research
(Munich) GmbH, Staffelseestraße
2, Munich 81477, Germany
| | - Anastasia Pentina
- Bayer AG, Machine Learning Research, Research & Development,
Pharmaceuticals, Berlin 10117, Germany
| | - Lina Humbeck
- BI Medicinal
Chemistry Department, Boehringer Ingelheim
Pharma GmbH & Co. KG, Birkendorfer Str. 65, Biberach an der Riss 88397, Germany
| | - Martijn Oldenhof
- KU
Leuven, ESAT-STADIUS, Kasteelpark Arenberg 10, Heverlee 3001, Belgium
| | - Ritsuya Niwayama
- Institut
de recherches Servier, 125 chemin de ronde Croissy-sur-Seine, Île-de-France 78290, France
| | | | - Nikolas Fechner
- Novartis
Institutes for BioMedical Research, Novartis Campus, Basel 4002, Switzerland
| | - Jaak Simm
- KU
Leuven, ESAT-STADIUS, Kasteelpark Arenberg 10, Heverlee 3001, Belgium
| | - Adam Arany
- KU
Leuven, ESAT-STADIUS, Kasteelpark Arenberg 10, Heverlee 3001, Belgium
| | | | - Rama Jabal
- Iktos, 65 rue de Prony, Paris 75017, France
| | - Arina Afanasyeva
- Modality
Informatics Group, Digital Research Solutions, Advanced Informatics
& Analytics, Astellas Pharma Inc., 21 Miyukigaoka, Tsukuba-shi, Ibaraki 305-8585, Japan
| | - Regis Loeb
- KU
Leuven, ESAT-STADIUS, Kasteelpark Arenberg 10, Heverlee 3001, Belgium
| | - Shlok Verma
- GlaxoSmithKline, Computational Sciences, Gunnels Wood Road Stevenage, Herts SG1 2NY, U.K.
| | - Simon Harnqvist
- GlaxoSmithKline, Computational Sciences, Gunnels Wood Road Stevenage, Herts SG1 2NY, U.K.
| | - Matthew Holmes
- GlaxoSmithKline, Computational Sciences, Gunnels Wood Road Stevenage, Herts SG1 2NY, U.K.
| | - Balazs Pejo
- Budapest
University of Technology and Economics, Department of Networked Systems and Services, Műegyetem rkp. 3, Budapest 1111, Hungary
| | | | - Nicholas Holway
- Novartis
Institutes for BioMedical Research, Novartis Campus, Basel 4002, Switzerland
| | - Arne Dieckmann
- Bayer
AG, API Production, Product Supply, Pharmaceuticals, Ernst-Schering-Straße 14, Bergkamen 59192, Germany
| | - Nicola Rieke
- NVIDIA
GmbH, Floessergasse 2, Munich 81369, Germany
| | | | - Djork-Arné Clevert
- Bayer AG, Machine Learning Research, Research & Development,
Pharmaceuticals, Berlin 10117, Germany
| | - Michael Krug
- Merck KGaA, Global Research & Development, Frankfurter Strasse 250, Darmstadt 64293, Germany
| | - Christopher Luscombe
- GlaxoSmithKline, Computational Sciences, Gunnels Wood Road Stevenage, Herts SG1 2NY, U.K.
| | - Darren Green
- GlaxoSmithKline, Computational Sciences, Gunnels Wood Road Stevenage, Herts SG1 2NY, U.K.
| | - Peter Ertl
- Novartis
Institutes for BioMedical Research, Novartis Campus, Basel 4002, Switzerland
| | - Peter Antal
- Budapest
University of Technology and Economics, Department of Measurement and Information Systems, Műegyetem rkp. 3, Budapest 1111, Hungary
| | - David Marcus
- GlaxoSmithKline, Computational Sciences, Gunnels Wood Road Stevenage, Herts SG1 2NY, U.K.
| | | | - Hideyoshi Fuji
- Modality
Informatics Group, Digital Research Solutions, Advanced Informatics
& Analytics, Astellas Pharma Inc., 21 Miyukigaoka, Tsukuba-shi, Ibaraki 305-8585, Japan
| | - Stephen Pickett
- GlaxoSmithKline, Computational Sciences, Gunnels Wood Road Stevenage, Herts SG1 2NY, U.K.
| | - Gergely Acs
- Budapest
University of Technology and Economics, Department of Networked Systems and Services, Műegyetem rkp. 3, Budapest 1111, Hungary
| | - Eric Boniface
- Substra
Foundation - Labelia Labs, 4 rue Voltaire, Nantes 44000, France
| | - Bernd Beck
- BI Medicinal
Chemistry Department, Boehringer Ingelheim
Pharma GmbH & Co. KG, Birkendorfer Str. 65, Biberach an der Riss 88397, Germany
| | - Yax Sun
- Amgen
Research, 1 Amgen Center
Drive, Thousand Oaks, California 92130, United States
| | - Arnaud Gohier
- Institut
de recherches Servier, 125 chemin de ronde Croissy-sur-Seine, Île-de-France 78290, France
| | - Friedrich Rippmann
- Merck KGaA, Global Research & Development, Frankfurter Strasse 250, Darmstadt 64293, Germany
| | - Ola Engkvist
- AstraZeneca, Molecular AI, Discovery Sciences,
R&D, Pepparedsleden
1, Mölndal 431 50, Sweden
| | - Andreas H. Göller
- Bayer
Pharma
AG, Global Drug Discovery, Chemical Research,
Computational Chemistry, Aprather Weg 18 a, Wuppertal 42096, Germany
| | - Yves Moreau
- KU
Leuven, ESAT-STADIUS, Kasteelpark Arenberg 10, Heverlee 3001, Belgium
| | | | - Ansgar Schuffenhauer
- Novartis
Institutes for BioMedical Research, Novartis Campus, Basel 4002, Switzerland
| | - Hugo Ceulemans
- Janssen
Pharmaceutica NV, Turnhoutseweg 30, Beerse 2340, Belgium
| |
Collapse
|
3
|
Retel JS, Poehlmann A, Chiou J, Steffen A, Clevert DA. A fast machine learning dataloader for epigenetic tracks from BigWig files. Bioinformatics 2024; 40:btad767. [PMID: 38175786 PMCID: PMC10782802 DOI: 10.1093/bioinformatics/btad767] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/02/2023] [Revised: 12/12/2023] [Indexed: 01/06/2024] Open
Abstract
SUMMARY We created bigwig-loader, a data-loader for epigenetic profiles from BigWig files that decompresses and processes information for multiple intervals from multiple BigWig files in parallel. This is an access pattern needed to create training batches for typical machine learning models on epigenetics data. Using a new codec, the decompression can be done on a graphical processing unit (GPU) making it fast enough to create the training batches during training, mitigating the need for saving preprocessed training examples to disk. AVAILABILITY AND IMPLEMENTATION The bigwig-loader installation instructions and source code can be accessed at https://github.com/pfizer-opensource/bigwig-loader.
Collapse
Affiliation(s)
- Joren Sebastian Retel
- Machine Learning Research, Pfizer Worldwide Research Development and Medical, Friedrichstraße 110, Berlin 10117, Germany
| | - Andreas Poehlmann
- Machine Learning Research, Pfizer Worldwide Research Development and Medical, Friedrichstraße 110, Berlin 10117, Germany
| | - Josh Chiou
- Machine Learning Research, Pfizer Worldwide Research Development and Medical, Friedrichstraße 110, Berlin 10117, Germany
| | - Andreas Steffen
- Machine Learning Research, Pfizer Worldwide Research Development and Medical, Friedrichstraße 110, Berlin 10117, Germany
| | - Djork-Arné Clevert
- Machine Learning Research, Pfizer Worldwide Research Development and Medical, Friedrichstraße 110, Berlin 10117, Germany
| |
Collapse
|
4
|
Mullowney MW, Duncan KR, Elsayed SS, Garg N, van der Hooft JJJ, Martin NI, Meijer D, Terlouw BR, Biermann F, Blin K, Durairaj J, Gorostiola González M, Helfrich EJN, Huber F, Leopold-Messer S, Rajan K, de Rond T, van Santen JA, Sorokina M, Balunas MJ, Beniddir MA, van Bergeijk DA, Carroll LM, Clark CM, Clevert DA, Dejong CA, Du C, Ferrinho S, Grisoni F, Hofstetter A, Jespers W, Kalinina OV, Kautsar SA, Kim H, Leao TF, Masschelein J, Rees ER, Reher R, Reker D, Schwaller P, Segler M, Skinnider MA, Walker AS, Willighagen EL, Zdrazil B, Ziemert N, Goss RJM, Guyomard P, Volkamer A, Gerwick WH, Kim HU, Müller R, van Wezel GP, van Westen GJP, Hirsch AKH, Linington RG, Robinson SL, Medema MH. Artificial intelligence for natural product drug discovery. Nat Rev Drug Discov 2023; 22:895-916. [PMID: 37697042 DOI: 10.1038/s41573-023-00774-7] [Citation(s) in RCA: 16] [Impact Index Per Article: 16.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 07/20/2023] [Indexed: 09/13/2023]
Abstract
Developments in computational omics technologies have provided new means to access the hidden diversity of natural products, unearthing new potential for drug discovery. In parallel, artificial intelligence approaches such as machine learning have led to exciting developments in the computational drug design field, facilitating biological activity prediction and de novo drug design for molecular targets of interest. Here, we describe current and future synergies between these developments to effectively identify drug candidates from the plethora of molecules produced by nature. We also discuss how to address key challenges in realizing the potential of these synergies, such as the need for high-quality datasets to train deep learning algorithms and appropriate strategies for algorithm validation.
Collapse
Affiliation(s)
| | - Katherine R Duncan
- Strathclyde Institute of Pharmacy and Biomedical Sciences, University of Strathclyde, Glasgow, UK
| | - Somayah S Elsayed
- Department of Molecular Biotechnology, Institute of Biology, Leiden University, Leiden, The Netherlands
| | - Neha Garg
- School of Chemistry and Biochemistry, Center for Microbial Dynamics and Infection, Georgia Institute of Technology, Atlanta, GA, USA
| | - Justin J J van der Hooft
- Bioinformatics Group, Wageningen University, Wageningen, The Netherlands
- Department of Biochemistry, University of Johannesburg, Johannesburg, South Africa
| | - Nathaniel I Martin
- Biological Chemistry Group, Institute of Biology, Leiden University, Leiden, The Netherlands
| | - David Meijer
- Bioinformatics Group, Wageningen University, Wageningen, The Netherlands
| | - Barbara R Terlouw
- Bioinformatics Group, Wageningen University, Wageningen, The Netherlands
| | - Friederike Biermann
- Bioinformatics Group, Wageningen University, Wageningen, The Netherlands
- Institute of Molecular Bio Science, Goethe-University Frankfurt, Frankfurt am Main, Germany
- LOEWE Center for Translational Biodiversity Genomics (TBG), Frankfurt am Main, Germany
| | - Kai Blin
- The Novo Nordisk Foundation Center for Biosustainability, Technical University of Denmark, Kongens Lyngby, Denmark
| | | | - Marina Gorostiola González
- Drug Discovery and Safety, Leiden Academic Centre for Drug Research, Leiden, The Netherlands
- ONCODE institute, Leiden, The Netherlands
| | - Eric J N Helfrich
- Institute of Molecular Bio Science, Goethe-University Frankfurt, Frankfurt am Main, Germany
- LOEWE Center for Translational Biodiversity Genomics (TBG), Frankfurt am Main, Germany
| | - Florian Huber
- Center for Digitalization and Digitality, Hochschule Düsseldorf, Düsseldorf, Germany
| | - Stefan Leopold-Messer
- Institut für Mikrobiologie, Eidgenössische Technische Hochschule (ETH) Zürich, Zürich, Switzerland
| | - Kohulan Rajan
- Institute for Inorganic and Analytical Chemistry, Friedrich-Schiller-University Jena, Jena, Germany
| | - Tristan de Rond
- School of Chemical Sciences, University of Auckland, Auckland, New Zealand
| | - Jeffrey A van Santen
- Department of Chemistry, Simon Fraser University, Burnaby, British Columbia, Canada
| | - Maria Sorokina
- Institute for Inorganic and Analytical Chemistry, Friedrich-Schiller University, Jena, Germany
- Pharmaceuticals R&D, Bayer AG, Berlin, Germany
| | - Marcy J Balunas
- Department of Microbiology and Immunology, University of Michigan, Ann Arbor, MI, USA
- Department of Medicinal Chemistry, University of Michigan, Ann Arbor, MI, USA
| | - Mehdi A Beniddir
- Équipe "Chimie des Substances Naturelles", Université Paris-Saclay, CNRS, BioCIS, Orsay, France
| | - Doris A van Bergeijk
- Department of Molecular Biotechnology, Institute of Biology, Leiden University, Leiden, The Netherlands
| | - Laura M Carroll
- Structural and Computational Biology Unit, EMBL, Heidelberg, Germany
| | - Chase M Clark
- Division of Pharmaceutical Sciences, School of Pharmacy, University of Wisconsin-Madison, Madison, WI, USA
| | | | | | - Chao Du
- Department of Molecular Biotechnology, Institute of Biology, Leiden University, Leiden, The Netherlands
| | | | - Francesca Grisoni
- Institute for Complex Molecular Systems, Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands
- Centre for Living Technologies, Alliance TU/e, WUR, UU, UMC Utrecht, Utrecht, The Netherlands
| | | | - Willem Jespers
- Drug Discovery and Safety, Leiden Academic Centre for Drug Research, Leiden, The Netherlands
| | - Olga V Kalinina
- Helmholtz Institute for Pharmaceutical Research Saarland (HIPS), Helmholtz Centre for Infection Research (HZI), Saarbrücken, Germany
- Drug Bioinformatics, Medical Faculty, Saarland University, Homburg, Germany
- Center for Bioinformatics, Saarland University, Saarbrücken, Germany
| | | | - Hyunwoo Kim
- College of Pharmacy and Integrated Research Institute for Drug Development, Dongguk University Seoul, Goyang-si, Republic of Korea
| | - Tiago F Leao
- Center for Nuclear Energy in Agriculture, University of São Paulo, Piracicaba, Brazil
| | - Joleen Masschelein
- Center for Microbiology, VIB-KU Leuven, Heverlee, Belgium
- Department of Biology, KU Leuven, Heverlee, Belgium
| | - Evan R Rees
- Division of Pharmaceutical Sciences, School of Pharmacy, University of Wisconsin-Madison, Madison, WI, USA
| | - Raphael Reher
- Institute of Pharmaceutical Biology and Biotechnology, University of Marburg, Marburg, Germany
- Institute of Pharmacy, Martin-Luther-University Halle-Wittenberg, Halle (Saale), Germany
| | - Daniel Reker
- Department of Biomedical Engineering, Duke University, Durham, NC, USA
- Duke Microbiome Center, Duke University, Durham, NC, USA
| | - Philippe Schwaller
- Laboratory of Artificial Chemical Intelligence, Institut des Sciences et Ingénierie Chimiques, Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
| | | | - Michael A Skinnider
- Adapsyn Bioscience, Hamilton, Ontario, Canada
- Michael Smith Laboratories, University of British Columbia, Vancouver, British Columbia, Canada
| | - Allison S Walker
- Department of Chemistry, Vanderbilt University, Nashville, TN, USA
- Department of Biological Sciences, Vanderbilt University, Nashville, TN, USA
| | - Egon L Willighagen
- Department of Bioinformatics - BiGCaT, NUTRIM, Maastricht University, Maastricht, The Netherlands
| | - Barbara Zdrazil
- European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Cambridgeshire, UK
| | - Nadine Ziemert
- Interfaculty Institute for Microbiology and Infection Medicine Tuebingen (IMIT), Institute for Bioinformatics and Medical Informatics (IBMI), University of Tuebingen, Tuebingen, Germany
| | | | - Pierre Guyomard
- Bonsai team, CRIStAL - Centre de Recherche en Informatique Signal et Automatique de Lille, Université de Lille, Villeneuve d'Ascq Cedex, France
| | - Andrea Volkamer
- Center for Bioinformatics, Saarland University, Saarbrücken, Germany
- In silico Toxicology and Structural Bioinformatics, Institute of Physiology, Charité - Universitätsmedizin Berlin, Berlin, Germany
| | - William H Gerwick
- Scripps Institution of Oceanography, University of California San Diego, La Jolla, CA, USA
| | - Hyun Uk Kim
- Department of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea
| | - Rolf Müller
- Helmholtz Institute for Pharmaceutical Research Saarland (HIPS), Helmholtz Centre for Infection Research (HZI), Saarbrücken, Germany
- Department of Pharmacy, Saarland University, Saarbrücken, Germany
- German Center for infection research (DZIF), Braunschweig, Germany
- Helmholtz International Lab for Anti-Infectives, Saarbrücken, Germany
| | - Gilles P van Wezel
- Department of Molecular Biotechnology, Institute of Biology, Leiden University, Leiden, The Netherlands
- Netherlands Institute of Ecology, NIOO-KNAW, Wageningen, The Netherlands
| | - Gerard J P van Westen
- Drug Discovery and Safety, Leiden Academic Centre for Drug Research, Leiden, The Netherlands.
| | - Anna K H Hirsch
- Helmholtz Institute for Pharmaceutical Research Saarland (HIPS), Helmholtz Centre for Infection Research (HZI), Saarbrücken, Germany.
- Department of Pharmacy, Saarland University, Saarbrücken, Germany.
- German Center for infection research (DZIF), Braunschweig, Germany.
- Helmholtz International Lab for Anti-Infectives, Saarbrücken, Germany.
| | - Roger G Linington
- Department of Chemistry, Simon Fraser University, Burnaby, British Columbia, Canada.
| | - Serina L Robinson
- Department of Environmental Microbiology, Eawag: Swiss Federal Institute for Aquatic Science and Technology, Dübendorf, Switzerland.
| | - Marnix H Medema
- Bioinformatics Group, Wageningen University, Wageningen, The Netherlands.
- Institute of Biology, Leiden University, Leiden, The Netherlands.
| |
Collapse
|
5
|
Cremer J, Medrano Sandonas L, Tkatchenko A, Clevert DA, De Fabritiis G. Equivariant Graph Neural Networks for Toxicity Prediction. Chem Res Toxicol 2023; 36. [PMID: 37690056 PMCID: PMC10583285 DOI: 10.1021/acs.chemrestox.3c00032] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2023] [Indexed: 09/12/2023]
Abstract
Predictive modeling of toxicity is a crucial step in the drug discovery pipeline. It can help filter out molecules with a high probability of failing in the early stages of de novo drug design. Thus, several machine learning (ML) models have been developed to predict the toxicity of molecules by combining classical ML techniques or deep neural networks with well-known molecular representations such as fingerprints or 2D graphs. But the more natural, accurate representation of molecules is expected to be defined in physical 3D space like in ab initio methods. Recent studies successfully used equivariant graph neural networks (EGNNs) for representation learning based on 3D structures to predict quantum-mechanical properties of molecules. Inspired by this, we investigated the performance of EGNNs to construct reliable ML models for toxicity prediction. We used the equivariant transformer (ET) model in TorchMD-NET for this. Eleven toxicity data sets taken from MoleculeNet, TDCommons, and ToxBenchmark have been considered to evaluate the capability of ET for toxicity prediction. Our results show that ET adequately learns 3D representations of molecules that can successfully correlate with toxicity activity, achieving good accuracies on most data sets comparable to state-of-the-art models. We also test a physicochemical property, namely, the total energy of a molecule, to inform the toxicity prediction with a physical prior. However, our work suggests that these two properties can not be related. We also provide an attention weight analysis for helping to understand the toxicity prediction in 3D space and thus increase the explainability of the ML model. In summary, our findings offer promising insights considering 3D geometry information via EGNNs and provide a straightforward way to integrate molecular conformers into ML-based pipelines for predicting and investigating toxicity prediction in physical space. We expect that in the future, especially for larger, more diverse data sets, EGNNs will be an essential tool in this domain.
Collapse
Affiliation(s)
- Julian Cremer
- Computational
Science Laboratory, Universitat Pompeu Fabra,
Barcelona Biomedical Research Park (PRBB), Carrer Dr. Aiguader 88, 08003 Barcelona, Spain
- Machine
Learning Research, Pfizer Worldwide Research
Development and Medical, Linkstr. 10, 10785 Berlin, Germany
| | - Leonardo Medrano Sandonas
- Department
of Physics and Materials Science, University
of Luxembourg, L-1511 Luxembourg City, Luxembourg
| | - Alexandre Tkatchenko
- Department
of Physics and Materials Science, University
of Luxembourg, L-1511 Luxembourg City, Luxembourg
| | - Djork-Arné Clevert
- Machine
Learning Research, Pfizer Worldwide Research
Development and Medical, Linkstr. 10, 10785 Berlin, Germany
| | - Gianni De Fabritiis
- Computational
Science Laboratory, Universitat Pompeu Fabra,
Barcelona Biomedical Research Park (PRBB), Carrer Dr. Aiguader 88, 08003 Barcelona, Spain
- ICREA, Passeig Lluis Companys 23, 08010 Barcelona, Spain
| |
Collapse
|
6
|
Klambauer G, Clevert DA, Shah I, Benfenati E, Tetko IV. Introduction to the Special Issue: AI Meets Toxicology. Chem Res Toxicol 2023; 36:1163-1167. [PMID: 37599584 DOI: 10.1021/acs.chemrestox.3c00217] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/22/2023]
Affiliation(s)
- Günter Klambauer
- ELLIS Unit Linz, LIT AI Lab & Institute for Machine Learning, Johannes Kepler University Linz, Altenbergerstraße 69, Linz 4040, Austria
| | - Djork-Arné Clevert
- Machine Learning Research, Pfizer Worldwide Research Development and Medical, Linkstr. 10, Berlin 10785, Germany
| | - Imran Shah
- Center for Computational Toxicology and Exposure, Office of Research and Development, U.S. Environmental Protection Agency, Research Triangle Park, North Carolina 27711, United States
| | - Emilio Benfenati
- Department of Environmental Health Sciences, Istituto di Ricerche Farmacologiche Mario Negri IRCCS, Milano 20156, Italy
| | - Igor V Tetko
- Institute of Structural Biology, Molecular Targets and Therapeutics Center, Helmholtz Munich - Deutsches Forschungszentrum für Gesundheit und Umwelt (GmbH), 85764 Neuherberg, Germany
- BIGCHEM GmbH, Valerystr. 49, 85716 Unterschleißheim, Germany
| |
Collapse
|
7
|
Andronov M, Voinarovska V, Andronova N, Wand M, Clevert DA, Schmidhuber J. Reagent prediction with a molecular transformer improves reaction data quality. Chem Sci 2023; 14:3235-3246. [PMID: 36970100 PMCID: PMC10034139 DOI: 10.1039/d2sc06798f] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/09/2022] [Accepted: 02/12/2023] [Indexed: 03/05/2023] Open
Abstract
A molecular transformer predicts reagents for organic reactions. It is also able to replace questionable reagents in reaction data, e.g. USPTO, to enable better product prediction models to be trained on these new data.
Collapse
Affiliation(s)
- Mikhail Andronov
- IDSIA, USI, SUPSI, 6900 Lugano, Switzerland
- Machine Learning Research, Pfizer Worldwide Research Development and Medical, Linkstr.10, Berlin, Germany
| | - Varvara Voinarovska
- Institute of Structural Biology, Molecular Targets and Therapeutics Center, Helmholtz Munich – Deutsches Forschungszentrum für Gesundheit und Umwelt (GmbH), 85764 Neuherberg, Germany
| | | | - Michael Wand
- IDSIA, USI, SUPSI, 6900 Lugano, Switzerland
- Institute for Digital Technologies for Personalized Healthcare, SUPSI, 6900 Lugano, Switzerland
| | - Djork-Arné Clevert
- Machine Learning Research, Pfizer Worldwide Research Development and Medical, Linkstr.10, Berlin, Germany
| | | |
Collapse
|
8
|
Affiliation(s)
- Igor V Tetko
- Institute of Structural Biology, Molecular Targets and Therapeutics Center, Helmholtz Munich-Deutsches Forschungszentrum für Gesundheit und Umwelt (GmbH), 85764 Neuherberg, Germany
- BIGCHEM GmbH, Valerystr. 49, 85716 Unterschleißheim, Germany
| | - Günter Klambauer
- ELLIS Unit Linz, LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Altenbergerstraße 69, 4040 Linz, Austria
| | | | - Imran Shah
- Center for Computational Toxicology and Exposure, Office of Research and Development, United States Environmental Protection Agency, Research Triangle Park, North Carolina 27711, United States
| | - Emilio Benfenati
- Department of Environmental Health Sciences, Istituto di Ricerche Farmacologiche Mario Negri IRCCS, 20156 Milano, Italy
| |
Collapse
|
9
|
Reis PBPS, Bertolini M, Montanari F, Rocchia W, Machuqueiro M, Clevert DA. A Fast and Interpretable Deep Learning Approach for Accurate Electrostatics-Driven p Ka Predictions in Proteins. J Chem Theory Comput 2022; 18:5068-5078. [PMID: 35837736 DOI: 10.1021/acs.jctc.2c00308] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
Abstract
Existing computational methods for estimating pKa values in proteins rely on theoretical approximations and lengthy computations. In this work, we use a data set of 6 million theoretically determined pKa shifts to train deep learning models, which are shown to rival the physics-based predictors. These neural networks managed to infer the electrostatic contributions of different chemical groups and learned the importance of solvent exposure and close interactions, including hydrogen bonds. Although trained only using theoretical data, our pKAI+ model displayed the best accuracy in a test set of ∼750 experimental values. Inference times allow speedups of more than 1000× compared to physics-based methods. By combining speed, accuracy, and a reasonable understanding of the underlying physics, our models provide a game-changing solution for fast estimations of macroscopic pKa values from ensembles of microscopic values as well as for many downstream applications such as molecular docking and constant-pH molecular dynamics simulations.
Collapse
Affiliation(s)
| | - Marco Bertolini
- Machine Learning Research, Bayer A.G., Berlin 13353, Germany
| | | | - Walter Rocchia
- CONCEPT Lab, Istituto Italiano di Tecnologia (IIT), Via Melen 83, B Block, Genoa 16152, Italy
| | - Miguel Machuqueiro
- Biosystems and Integrative Sciences Institute (BioISI), Faculty of Sciences, University of Lisboa, Campo Grande, Lisboa 1749-016, Portugal
| | | |
Collapse
|
10
|
Reis PBPS, Clevert DA, Machuqueiro M. pKPDB: a protein data bank extension database of pKa and pI theoretical values. Bioinformatics 2021; 38:297-298. [PMID: 34260689 DOI: 10.1093/bioinformatics/btab518] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/30/2021] [Revised: 07/02/2021] [Accepted: 07/08/2021] [Indexed: 02/03/2023] Open
Abstract
SUMMARY pKa values of ionizable residues and isoelectric points of proteins provide valuable local and global insights about their structure and function. These properties can be estimated with reasonably good accuracy using Poisson-Boltzmann and Monte Carlo calculations at a considerable computational cost (from some minutes to several hours). pKPDB is a database of over 12 M theoretical pKa values calculated over 120k protein structures deposited in the Protein Data Bank. By providing precomputed pKa and pI values, users can retrieve results instantaneously for their protein(s) of interest while also saving countless hours and resources that would be spent on repeated calculations. Furthermore, there is an ever-growing imbalance between experimental pKa and pI values and the number of resolved structures. This database will complement the experimental and computational data already available and can also provide crucial information regarding buried residues that are under-represented in experimental measurements. AVAILABILITY AND IMPLEMENTATION Gzipped csv files containing p Ka and isoelectric point values can be downloaded from https://pypka.org/pKPDB. To query a single PDB code please use the PypKa free server at https://pypka.org. The pKPDB source code can be found at https://github.com/mms-fcul/pKPDB. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Pedro B P S Reis
- Department of Chemistry and Biochemistry, Faculty of Sciences, University of Lisbon, 1749-016 Lisboa, Portugal.,Bayer AG, Research & Development, Pharmaceuticals. Machine Learning Research, 13353 Berlin, Germany
| | - Djork-Arné Clevert
- Bayer AG, Research & Development, Pharmaceuticals. Machine Learning Research, 13353 Berlin, Germany
| | - Miguel Machuqueiro
- Department of Chemistry and Biochemistry, Faculty of Sciences, University of Lisbon, 1749-016 Lisboa, Portugal
| |
Collapse
|
11
|
Clevert DA, Le T, Winter R, Montanari F. Img2Mol - accurate SMILES recognition from molecular graphical depictions. Chem Sci 2021; 12:14174-14181. [PMID: 34760202 PMCID: PMC8565361 DOI: 10.1039/d1sc01839f] [Citation(s) in RCA: 18] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2021] [Accepted: 09/22/2021] [Indexed: 11/25/2022] Open
Abstract
The automatic recognition of the molecular content of a molecule's graphical depiction is an extremely challenging problem that remains largely unsolved despite decades of research. Recent advances in neural machine translation enable the auto-encoding of molecular structures in a continuous vector space of fixed size (latent representation) with low reconstruction errors. In this paper, we present a fast and accurate model combining deep convolutional neural network learning from molecule depictions and a pre-trained decoder that translates the latent representation into the SMILES representation of the molecules. This combination allows us to precisely infer a molecular structure from an image. Our rigorous evaluation shows that Img2Mol is able to correctly translate up to 88% of the molecular depictions into their SMILES representation. A pretrained version of Img2Mol is made publicly available on GitHub for non-commercial users.
Collapse
Affiliation(s)
| | - Tuan Le
- Machine Learning Research, Bayer AG Berlin Germany
| | - Robin Winter
- Machine Learning Research, Bayer AG Berlin Germany
| | | |
Collapse
|
12
|
Vinken M, Benfenati E, Busquet F, Castell J, Clevert DA, de Kok TM, Dirven H, Fritsche E, Geris L, Gozalbes R, Hartung T, Jennen D, Jover R, Kandarova H, Kramer N, Krul C, Luechtefeld T, Masereeuw R, Roggen E, Schaller S, Vanhaecke T, Yang C, Piersma AH. Safer chemicals using less animals: kick-off of the European ONTOX project. Toxicology 2021; 458:152846. [PMID: 34216698 DOI: 10.1016/j.tox.2021.152846] [Citation(s) in RCA: 22] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/20/2021] [Revised: 06/23/2021] [Accepted: 06/29/2021] [Indexed: 12/27/2022]
Abstract
The 3Rs concept, calling for replacement, reduction and refinement of animal experimentation, is receiving increasing attention around the world, and has found its way to legislation, in particular in the European Union. This is aligned by continuing high-level efforts of the European Commission to support development and implementation of 3Rs methods. In this respect, the European project called "ONTOX: ontology-driven and artificial intelligence-based repeated dose toxicity testing of chemicals for next generation risk assessment" was recently initiated with the goal to provide a functional and sustainable solution for advancing human risk assessment of chemicals without the use of animals in line with the principles of 21st century toxicity testing and next generation risk assessment. ONTOX will deliver a generic strategy to create new approach methodologies (NAMs) in order to predict systemic repeated dose toxicity effects that, upon combination with tailored exposure assessment, will enable human risk assessment. For proof-of-concept purposes, focus is put on NAMs addressing adversities in the liver, kidneys and developing brain induced by a variety of chemicals. The NAMs each consist of a computational system based on artificial intelligence and are fed by biological, toxicological, chemical and kinetic data. Data are consecutively integrated in physiological maps, quantitative adverse outcome pathway networks and ontology frameworks. Supported by artificial intelligence, data gaps are identified and are filled by targeted in vitro and in silico testing. ONTOX is anticipated to have a deep and long-lasting impact at many levels, in particular by consolidating Europe's world-leading position regarding the development, exploitation, regulation and application of animal-free methods for human risk assessment of chemicals.
Collapse
Affiliation(s)
- Mathieu Vinken
- Research Group of In VitroToxicology and Dermato-Cosmetology, Department of Pharmaceutical and Pharmacological Sciences, Vrije Universiteit Brussel, Brussels, Belgium.
| | - Emilio Benfenati
- Department of Environmental Health Sciences, Istituto di Ricerche Farmacologiche Mario Negri IRCCS, Milano, Italy
| | | | - José Castell
- Department of Biochemistry and Molecular Biology, University of Valencia-Spain, and Experimental Hepatology Unit, IIS Hospital La Fe of Valencia, CIBERehd, Spain
| | | | - Theo M de Kok
- Department of Toxicogenomics, GROW School for Oncology and Developmental Biology, Maastricht University, the Netherlands
| | - Hubert Dirven
- Department of Environmental Health, Norwegian Institute of Public Health, Oslo, Norway
| | - Ellen Fritsche
- IUF-Leibniz Research Institute for Environmental Medicine, Düsseldorf, Germany, and Medical Faculty, Heinrich-Heine-University, Düsseldorf, Germany
| | - Liesbet Geris
- Biomechanics Research Unit, GIGA In Silico Medicine, University of Liège, Belgium
| | - Rafael Gozalbes
- ProtoQSAR SL, European Center of Innovative Companies, Technological Park of Valencia, Spain
| | - Thomas Hartung
- Center for Alternatives to Animal Testing, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, USA; Center for Alternatives to Animal Testing-Europe, University of Konstanz, Konstanz, Germany
| | - Danyel Jennen
- Department of Toxicogenomics, GROW School for Oncology and Developmental Biology, Maastricht University, the Netherlands
| | - Ramiro Jover
- Department of Biochemistry and Molecular Biology, University of Valencia-Spain, and Experimental Hepatology Unit, IIS Hospital La Fe of Valencia, CIBERehd, Spain
| | - Helena Kandarova
- Centre of Experimental Medicine SAS, Slovak Academy of Sciences, Bratislava, Slovakia
| | - Nynke Kramer
- Institute for Risk Assessment Sciences, Utrecht University, Utrecht, the Netherlands
| | - Cyrille Krul
- Innovative Testing in Life Sciences and Chemistry, Hogeschool Utrecht University of Applied Sciences Utrecht, the Netherlands
| | | | - Rosalinde Masereeuw
- Division of Pharmacology, Utrecht Institute for Pharmaceutical Sciences, Utrecht University, Utrecht, the Netherlands
| | - Erwin Roggen
- 3Rs Management and Consulting ApS, Lyngby, Denmark
| | | | - Tamara Vanhaecke
- Research Group of In VitroToxicology and Dermato-Cosmetology, Department of Pharmaceutical and Pharmacological Sciences, Vrije Universiteit Brussel, Brussels, Belgium
| | | | - Aldert H Piersma
- Institute for Risk Assessment Sciences, Utrecht University, Utrecht, the Netherlands; Centre for Health Protection (RIVM), Bilthoven, the Netherlands
| |
Collapse
|
13
|
Marin Zapata PA, Roth S, Schmutzler D, Wolf T, Manesso E, Clevert DA. Self-supervised feature extraction from image time series in plant phenotyping using triplet networks. Bioinformatics 2021; 37:861-867. [PMID: 33241296 DOI: 10.1093/bioinformatics/btaa905] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2020] [Revised: 08/04/2020] [Accepted: 10/08/2020] [Indexed: 11/14/2022] Open
Abstract
MOTIVATION Image-based profiling combines high-throughput screening with multiparametric feature analysis to capture the effect of perturbations on biological systems. This technology has attracted increasing interest in the field of plant phenotyping, promising to accelerate the discovery of novel herbicides. However, the extraction of meaningful features from unlabeled plant images remains a big challenge. RESULTS We describe a novel data-driven approach to find feature representations from plant time-series images in a self-supervised manner by using time as a proxy for image similarity. In the spirit of transfer learning, we first apply an ImageNet-pretrained architecture as a base feature extractor. Then, we extend this architecture with a triplet network to refine and reduce the dimensionality of extracted features by ranking relative similarities between consecutive and non-consecutive time points. Without using any labels, we produce compact, organized representations of plant phenotypes and demonstrate their superior applicability to clustering, image retrieval and classification tasks. Besides time, our approach could be applied using other surrogate measures of phenotype similarity, thus providing a versatile method of general interest to the phenotypic profiling community. AVAILABILITY AND IMPLEMENTATION Source code is provided in https://github.com/bayer-science-for-a-better-life/plant-triplet-net. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Paula A Marin Zapata
- Bayer AG, Machine Learning Research, Research and Development, Pharmaceuticals, Berlin, Germany
| | - Sina Roth
- Bayer AG, High Throughput Biology - Weed Control, Research & Development, Crop Science, Frankfurt, Germany
| | - Dirk Schmutzler
- Bayer AG, High Throughput Biology - Weed Control, Research & Development, Crop Science, Frankfurt, Germany
| | - Thomas Wolf
- Bayer AG, Computational Life Sciences - Weed Control, Research & Development, Crop Science, Frankfurt, Germany
| | - Erica Manesso
- Bayer AG, Computational Life Sciences - Weed Control, Research & Development, Crop Science, Frankfurt, Germany
| | - Djork-Arné Clevert
- Bayer AG, Machine Learning Research, Research and Development, Pharmaceuticals, Berlin, Germany
| |
Collapse
|
14
|
Le T, Winter R, Noé F, Clevert DA. Neuraldecipher - reverse-engineering extended-connectivity fingerprints (ECFPs) to their molecular structures. Chem Sci 2020; 11:10378-10389. [PMID: 34094299 PMCID: PMC8162443 DOI: 10.1039/d0sc03115a] [Citation(s) in RCA: 16] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/03/2020] [Accepted: 09/10/2020] [Indexed: 12/22/2022] Open
Abstract
Protecting molecular structures from disclosure against external parties is of great relevance for industrial and private associations, such as pharmaceutical companies. Within the framework of external collaborations, it is common to exchange datasets by encoding the molecular structures into descriptors. Molecular fingerprints such as the extended-connectivity fingerprints (ECFPs) are frequently used for such an exchange, because they typically perform well on quantitative structure-activity relationship tasks. ECFPs are often considered to be non-invertible due to the way they are computed. In this paper, we present a fast reverse-engineering method to deduce the molecular structure given revealed ECFPs. Our method includes the Neuraldecipher, a neural network model that predicts a compact vector representation of compounds, given ECFPs. We then utilize another pre-trained model to retrieve the molecular structure as SMILES representation. We demonstrate that our method is able to reconstruct molecular structures to some extent, and improves, when ECFPs with larger fingerprint sizes are revealed. For example, given ECFP count vectors of length 4096, we are able to correctly deduce up to 69% of molecular structures on a validation set (112 K unique samples) with our method.
Collapse
Affiliation(s)
- Tuan Le
- Department of Digital Technologies, Bayer AG Berlin Germany
- Department of Mathematics and Computer Science, Freie Universität Berlin Berlin Germany
| | - Robin Winter
- Department of Digital Technologies, Bayer AG Berlin Germany
- Department of Mathematics and Computer Science, Freie Universität Berlin Berlin Germany
| | - Frank Noé
- Department of Mathematics and Computer Science, Freie Universität Berlin Berlin Germany
| | | |
Collapse
|
15
|
Winter R, Retel J, Noé F, Clevert DA, Steffen A. grünifai: interactive multiparameter optimization of molecules in a continuous vector space. Bioinformatics 2020; 36:4093-4094. [PMID: 32369561 DOI: 10.1093/bioinformatics/btaa271] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2019] [Revised: 03/09/2020] [Accepted: 04/27/2020] [Indexed: 11/14/2022] Open
Abstract
SUMMARY Optimizing small molecules in a drug discovery project is a notoriously difficult task as multiple molecular properties have to be considered and balanced at the same time. In this work, we present our novel interactive in silico compound optimization platform termed grünifai to support the ideation of the next generation of compounds under the constraints of a multiparameter objective. grünifai integrates adjustable in silico models, a continuous representation of the chemical space, a scalable particle swarm optimization algorithm and the possibility to actively steer the compound optimization through providing feedback on generated intermediate structures. AVAILABILITY AND IMPLEMENTATION Source code and documentation are freely available under an MIT license and are openly available on GitHub (https://github.com/jrwnter/gruenifai). The backend, including the optimization method and distribution on multiple GPU nodes is written in Python 3. The frontend is written in ReactJS.
Collapse
Affiliation(s)
- Robin Winter
- Department of Digital Technologies, Bayer AG, Berlin 13353, Germany.,Department of Mathematics and Computer Science, Freie Universität Berlin, Berlin 14195, Germany
| | - Joren Retel
- Department of Digital Technologies, Bayer AG, Berlin 13353, Germany
| | - Frank Noé
- Department of Mathematics and Computer Science, Freie Universität Berlin, Berlin 14195, Germany
| | | | - Andreas Steffen
- Department of Digital Technologies, Bayer AG, Berlin 13353, Germany
| |
Collapse
|
16
|
Mittlmeier LM, Unterrainer M, Todica A, Clevert DA, Cyran CC, Schmoeckel E, Rodler S, Bartenstein P, Stief CG, Ilhan H, Staehler M. Advanced Molecular Imaging in Histologically Verified Metanephric Adenoma. Urology 2020; 140:e10-e11. [PMID: 32171695 DOI: 10.1016/j.urology.2020.02.025] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/28/2019] [Revised: 02/22/2020] [Accepted: 02/25/2020] [Indexed: 10/24/2022]
Abstract
Metanephric adenoma (MA) describes a rare renal tumor and is generally considered a benign lesion. However, there are cases with regional lymphogenic and distant metastases. Noninvasive diagnosis of MA using conventional imaging remains challenging. Here, we describe a case of histologically verified MA with additional advanced molecular imaging consisting of 18F-PSMA-1007 PET/CT, 99mTc-Sestamibi SPECT and contrast-enhanced ultrasound.
Collapse
Affiliation(s)
- L M Mittlmeier
- Department of Urology, University Hospital, LMU Munich, Munich, Germany; Department of Nuclear Medicine, University Hospital, LMU Munich, Munich, Germany
| | - M Unterrainer
- Department of Nuclear Medicine, University Hospital, LMU Munich, Munich, Germany
| | - A Todica
- Department of Nuclear Medicine, University Hospital, LMU Munich, Munich, Germany
| | - D A Clevert
- Department of Radiology, University Hospital, LMU Munich, Munich, Germany
| | - C C Cyran
- Department of Radiology, University Hospital, LMU Munich, Munich, Germany
| | - E Schmoeckel
- Institute of Pathology, University Hospital, LMU Munich, Munich, Germany
| | - S Rodler
- Department of Urology, University Hospital, LMU Munich, Munich, Germany
| | - P Bartenstein
- Department of Nuclear Medicine, University Hospital, LMU Munich, Munich, Germany
| | - C G Stief
- Department of Urology, University Hospital, LMU Munich, Munich, Germany
| | - H Ilhan
- Department of Nuclear Medicine, University Hospital, LMU Munich, Munich, Germany
| | - M Staehler
- Department of Urology, University Hospital, LMU Munich, Munich, Germany.
| |
Collapse
|
17
|
Negrão de Figueiredo G, Mueller-Peltzer K, Schwarze V, Zhang L, Rübenthaler J, Clevert DA. Performance of contrast-enhanced ultrasound (CEUS) compared to MRI in the diagnostic of gallbladder diseases. Clin Hemorheol Microcirc 2020; 73:85-93. [PMID: 31561332 DOI: 10.3233/ch-199202] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/30/2022]
Abstract
BACKGROUND Conventional ultrasound and MRI are very important techniques for the detection of gallbladder alterations. In the past years, studies showed that the additional use of contrast media to the conventional ultrasound allows the early depiction of pathological microvessels and their flow elucidating suspect findings stipulating the prompt therapy approach. OBJECTIVE The study aims to evaluate the performance of CEUS in gallbladder diseases and compare it to MR imaging using histopathological findings as a gold standard. MATERIAL AND METHODS The retrospective mono-center study analysed 18 patients with gallbladder alterations between 2009 and 2017. All patients underwent CEUS and MRI examinations and all results were confirmed in the pathology. CEUS images were performed and interpreted by a single experienced physician. RESULTS CEUS imaging results compared to MR imaging of the gallbladder demonstrated a sensitivity of 100%, specificity of 93%, a positive predictive value of 67% and a negative predictive value of 100%. CONCLUSION CEUS enables the depiction and characterization of important vascularization's patterns facilitating the early differentiation between malignant and benign findings. In this study, CEUS displayed a better diagnostic accuracy than MRI proving to be a valuable additional tool to the established imaging modalities.
Collapse
Affiliation(s)
- G Negrão de Figueiredo
- Department of Radiology, Interdisciplinary Ultrasound-Center Ludwig-Maximilians-University of Munich - Grosshadern Campus, Munich, Germany
| | - K Mueller-Peltzer
- Department of Radiology, Interdisciplinary Ultrasound-Center Ludwig-Maximilians-University of Munich - Grosshadern Campus, Munich, Germany
| | - V Schwarze
- Department of Radiology, Interdisciplinary Ultrasound-Center Ludwig-Maximilians-University of Munich - Grosshadern Campus, Munich, Germany
| | - L Zhang
- Department of Radiology, Interdisciplinary Ultrasound-Center Ludwig-Maximilians-University of Munich - Grosshadern Campus, Munich, Germany
| | - J Rübenthaler
- Department of Radiology, Interdisciplinary Ultrasound-Center Ludwig-Maximilians-University of Munich - Grosshadern Campus, Munich, Germany
| | - D A Clevert
- Department of Radiology, Interdisciplinary Ultrasound-Center Ludwig-Maximilians-University of Munich - Grosshadern Campus, Munich, Germany
| |
Collapse
|
18
|
Winter R, Montanari F, Steffen A, Briem H, Noé F, Clevert DA. Efficient multi-objective molecular optimization in a continuous latent space. Chem Sci 2019; 10:8016-8024. [PMID: 31853357 PMCID: PMC6836962 DOI: 10.1039/c9sc01928f] [Citation(s) in RCA: 105] [Impact Index Per Article: 21.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2019] [Accepted: 07/02/2019] [Indexed: 12/21/2022] Open
Abstract
One of the main challenges in small molecule drug discovery is finding novel chemical compounds with desirable properties. In this work, we propose a novel method that combines in silico prediction of molecular properties such as biological activity or pharmacokinetics with an in silico optimization algorithm, namely Particle Swarm Optimization. Our method takes a starting compound as input and proposes new molecules with more desirable (predicted) properties. It navigates a machine-learned continuous representation of a drug-like chemical space guided by a defined objective function. The objective function combines multiple in silico prediction models, defined desirability ranges and substructure constraints. We demonstrate that our proposed method is able to consistently find more desirable molecules for the studied tasks in relatively short time. We hope that our method can support medicinal chemists in accelerating and improving the lead optimization process.
Collapse
Affiliation(s)
- Robin Winter
- Department of Digital Technologies , Bayer AG , Berlin , Germany .
- Department of Mathematics and Computer Science , Freie Universität Berlin , Berlin , Germany
| | | | - Andreas Steffen
- Department of Digital Technologies , Bayer AG , Berlin , Germany .
| | - Hans Briem
- Department of Digital Technologies , Bayer AG , Berlin , Germany .
| | - Frank Noé
- Department of Mathematics and Computer Science , Freie Universität Berlin , Berlin , Germany
| | | |
Collapse
|
19
|
Abstract
CLINICAL/METHODICAL ISSUE Focal liver lesions are commonly seen during routine ultrasound examinations. STANDARD RADIOLOGICAL METHODS With native ultrasound there are lesions that cannot be sufficiently characterized. In these cases additional imaging might be necessary. METHODICAL INNOVATIONS With contrast-enhanced ultrasound (CEUS), focal liver lesions can be characterized with high diagnostic accuracy. After the ultrasound contrast agent has been injected into a peripheral vein, the examiner saves video loops of the arterial, portal venous and late contrast phases. Combing the findings of native and contrast-enhanced ultrasound allows not only assessment of the etiology as benign or malignant but also detailed characterization of the focal liver lesion in most cases. PERFORMANCE Using CEUS, focal liver lesions can be characterized with a sensitivity of over 95% and a specificity of about 83%. ACHIEVEMENTS The advantages of CEUS include that there is no radiation exposure and that the ultrasound contrast agent has no effects on the function of the liver, kidneys or the thyroid gland. The main limiting factors for CEUS are bowel gas and obesity of the patient. PRACTICAL RECOMMENDATIONS CEUS can visualize micro- and macrovascularization of benign focal liver lesions in real time. It is a useful imaging modality in unclear cases.
Collapse
Affiliation(s)
- K Müller-Peltzer
- Klinik und Poliklinik für Radiologie, Interdisziplinäres Ultraschall-Zentrum, Universitätsklinikum der Ludwig-Maximilians-Universität München, Marchioninistr. 15, 81377, München, Deutschland.
| | - J Rübenthaler
- Klinik und Poliklinik für Radiologie, Interdisziplinäres Ultraschall-Zentrum, Universitätsklinikum der Ludwig-Maximilians-Universität München, Marchioninistr. 15, 81377, München, Deutschland
| | - G Negrao de Figueiredo
- Klinik und Poliklinik für Radiologie, Interdisziplinäres Ultraschall-Zentrum, Universitätsklinikum der Ludwig-Maximilians-Universität München, Marchioninistr. 15, 81377, München, Deutschland
| | - D A Clevert
- Klinik und Poliklinik für Radiologie, Interdisziplinäres Ultraschall-Zentrum, Universitätsklinikum der Ludwig-Maximilians-Universität München, Marchioninistr. 15, 81377, München, Deutschland
| |
Collapse
|
20
|
Abstract
CLINICAL/METHODICAL ISSUE Cystic renal lesions are common incidental findings in radiological imaging and they should be adequately examined to be able to characterize them as benign or malignant. STANDARD RADIOLOGICAL METHODS It is not always possible to sufficiently characterize cystic renal lesion solely using native B‑mode sonography and color-Doppler sonography. METHODICAL INNOVATIONS Using contrast-enhanced ultrasound (CEUS), it is possible to dynamically evaluate the perfusion of cystic renal lesions and to characterize the potential malignancy of these lesions using the Bosniak classification in order to give recommendations regarding further work-up. CEUS can also be used in patients with contraindications for other radiological imaging modalities as it uses a contrast agent with almost no side effects. PERFORMANCE Using CEUS, cystic renal lesions can be reliably characterized with a diagnostic accuracy greater than 90%. ACHIEVEMENTS CEUS is a useful method in diagnosing and characterizing unclear cystic renal lesions and should always be considered as a viable diagnostic tool. PRACTICAL RECOMMENDATIONS CEUS should always be performed in initially unclear cases and is a useful additional tool for the diagnosis and characterization of unclear cystic renal lesions.
Collapse
Affiliation(s)
- J Rübenthaler
- Klinik und Poliklinik für Radiologie, Interdisziplinäres Ultraschall-Zentrum, Universitätsklinikum, Ludwig-Maximilians-Universität München, Marchioninistr. 15, 81377, München, Deutschland.
| | - K Mueller-Peltzer
- Klinik und Poliklinik für Radiologie, Interdisziplinäres Ultraschall-Zentrum, Universitätsklinikum, Ludwig-Maximilians-Universität München, Marchioninistr. 15, 81377, München, Deutschland
| | - G Negrão de Figueiredo
- Klinik und Poliklinik für Radiologie, Interdisziplinäres Ultraschall-Zentrum, Universitätsklinikum, Ludwig-Maximilians-Universität München, Marchioninistr. 15, 81377, München, Deutschland
| | - E Gresser
- Klinik und Poliklinik für Radiologie, Interdisziplinäres Ultraschall-Zentrum, Universitätsklinikum, Ludwig-Maximilians-Universität München, Marchioninistr. 15, 81377, München, Deutschland
| | - D A Clevert
- Klinik und Poliklinik für Radiologie, Interdisziplinäres Ultraschall-Zentrum, Universitätsklinikum, Ludwig-Maximilians-Universität München, Marchioninistr. 15, 81377, München, Deutschland
| |
Collapse
|
21
|
Schaefer M, Clevert DA, Weiss B, Steffen A. PAVOOC: designing CRISPR sgRNAs using 3D protein structures and functional domain annotations. Bioinformatics 2019; 35:2309-2310. [PMID: 30445568 PMCID: PMC6596878 DOI: 10.1093/bioinformatics/bty935] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/22/2018] [Revised: 10/01/2018] [Accepted: 11/09/2018] [Indexed: 12/26/2022] Open
Abstract
SUMMARY Single-guide RNAs (sgRNAs) targeting the same gene can significantly vary in terms of efficacy and specificity. PAVOOC (Prediction And Visualization of On- and Off-targets for CRISPR) is a web-based CRISPR sgRNA design tool that employs state of the art machine learning models to prioritize most effective candidate sgRNAs. In contrast to other tools, it maps sgRNAs to functional domains and protein structures and visualizes cut sites on corresponding protein crystal structures. Furthermore, PAVOOC supports homology-directed repair template generation for genome editing experiments and the visualization of the mutated amino acids in 3D. AVAILABILITY AND IMPLEMENTATION PAVOOC is available under https://pavooc.me and accessible using modern browsers (Chrome/Chromium recommended). The source code is hosted at github.com/moritzschaefer/pavooc under the MIT License. The backend, including data processing steps, and the frontend are implemented in Python 3 and ReactJS, respectively. All components run in a simple Docker environment. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
|
22
|
Negrão de Figueiredo G, Mueller-Peltzer K, Zengel P, Armbruster M, Rübenthaler J, Clevert DA. Contrast-enhanced ultrasound (CEUS) and gallbladder diseases - A retrospective mono-center analysis of imaging findings with histopathological correlation. Clin Hemorheol Microcirc 2019; 71:151-158. [PMID: 30584127 DOI: 10.3233/ch-189405] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/22/2022]
Abstract
BACKGROUND Radiologic imaging, especially ultrasound has an important role in the assessment of gallbladder alteration. Contrast-enhanced ultrasound (CEUS) is an easy and fast imaging technique that overcomes the limitations of greyscale ultrasonography. It is a safe tool that can be used as an additional imaging modality in order to elucidate and differentiate gallbladder pathological findings. OBJECTIVE The aim of this retrospective study analysis is to assess the diagnostic performance of CEUS in gallbladder alterations and compare the results to the histopathological findings. METHODS A total of 17 patients between 2009 and 2017 with uncertain gallbladder appearance were retrospectively analysed. A single experienced physician with more than fifteen years' experience performed CEUS examinations by applying a second-generation blood pool agent (SonoVue®, Bracco, Milan, Italy). Archived images were interpreted by the same physician and compared to the histopathological findings. RESULTS CEUS results, when correlated to the respectively pathologic findings, presented a sensitivity of 100%, a specificity of 100%, a positive predictive value (PPV) of 100% and a negative predictive value (NPV) of 100%. All patients were successfully examined without any adverse reaction. CONCLUSION In conclusion, the excellent results in this study acknowledged that CEUS is a feasible alternative tool to differentiate gallbladder pathologic alterations.
Collapse
Affiliation(s)
- G Negrão de Figueiredo
- Department of Radiology, Interdisciplinary Ultrasound-Center Ludwig-Maximilians-University of Munich - Grosshadern Campus, Munich, Germany
| | - K Mueller-Peltzer
- Department of Radiology, Interdisciplinary Ultrasound-Center Ludwig-Maximilians-University of Munich - Grosshadern Campus, Munich, Germany
| | - P Zengel
- Department of Otorhinolaryngology, Head and Neck Surgery, Ludwig-Maximilians-Universität München, Munich, Germany
| | - M Armbruster
- Department of Radiology, Interdisciplinary Ultrasound-Center Ludwig-Maximilians-University of Munich - Grosshadern Campus, Munich, Germany
| | - J Rübenthaler
- Department of Radiology, Interdisciplinary Ultrasound-Center Ludwig-Maximilians-University of Munich - Grosshadern Campus, Munich, Germany
| | - D A Clevert
- Department of Radiology, Interdisciplinary Ultrasound-Center Ludwig-Maximilians-University of Munich - Grosshadern Campus, Munich, Germany
| |
Collapse
|
23
|
Hofmarcher M, Rumetshofer E, Clevert DA, Hochreiter S, Klambauer G. Accurate Prediction of Biological Assays with High-Throughput Microscopy Images and Convolutional Networks. J Chem Inf Model 2019; 59:1163-1171. [DOI: 10.1021/acs.jcim.8b00670] [Citation(s) in RCA: 35] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/20/2022]
Affiliation(s)
- Markus Hofmarcher
- LIT AI Lab & Institute for Machine Learning, Johannes Kepler University, Linz 4040, Austria
| | - Elisabeth Rumetshofer
- LIT AI Lab & Institute for Machine Learning, Johannes Kepler University, Linz 4040, Austria
| | | | - Sepp Hochreiter
- LIT AI Lab & Institute for Machine Learning, Johannes Kepler University, Linz 4040, Austria
| | - Günter Klambauer
- LIT AI Lab & Institute for Machine Learning, Johannes Kepler University, Linz 4040, Austria
| |
Collapse
|
24
|
Winter R, Montanari F, Noé F, Clevert DA. Learning continuous and data-driven molecular descriptors by translating equivalent chemical representations. Chem Sci 2019; 10:1692-1701. [PMID: 30842833 PMCID: PMC6368215 DOI: 10.1039/c8sc04175j] [Citation(s) in RCA: 227] [Impact Index Per Article: 45.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/19/2018] [Accepted: 11/17/2018] [Indexed: 12/23/2022] Open
Abstract
There has been a recent surge of interest in using machine learning across chemical space in order to predict properties of molecules or design molecules and materials with the desired properties. Most of this work relies on defining clever feature representations, in which the chemical graph structure is encoded in a uniform way such that predictions across chemical space can be made. In this work, we propose to exploit the powerful ability of deep neural networks to learn a feature representation from low-level encodings of a huge corpus of chemical structures. Our model borrows ideas from neural machine translation: it translates between two semantically equivalent but syntactically different representations of molecular structures, compressing the meaningful information both representations have in common in a low-dimensional representation vector. Once the model is trained, this representation can be extracted for any new molecule and utilized as a descriptor. In fair benchmarks with respect to various human-engineered molecular fingerprints and graph-convolution models, our method shows competitive performance in modelling quantitative structure-activity relationships in all analysed datasets. Additionally, we show that our descriptor significantly outperforms all baseline molecular fingerprints in two ligand-based virtual screening tasks. Overall, our descriptors show the most consistent performances in all experiments. The continuity of the descriptor space and the existence of the decoder that permits deducing a chemical structure from an embedding vector allow for exploration of the space and open up new opportunities for compound optimization and idea generation.
Collapse
Affiliation(s)
- Robin Winter
- Department of Bioinformatics , Bayer AG , Berlin , Germany .
- Department of Mathematics and Computer Science , Freie Universität Berlin , Berlin , Germany
| | | | - Frank Noé
- Department of Mathematics and Computer Science , Freie Universität Berlin , Berlin , Germany
| | | |
Collapse
|
25
|
Mayr A, Klambauer G, Unterthiner T, Steijaert M, Wegner JK, Ceulemans H, Clevert DA, Hochreiter S. Large-scale comparison of machine learning methods for drug target prediction on ChEMBL. Chem Sci 2018; 9:5441-5451. [PMID: 30155234 PMCID: PMC6011237 DOI: 10.1039/c8sc00148k] [Citation(s) in RCA: 244] [Impact Index Per Article: 40.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2018] [Accepted: 05/16/2018] [Indexed: 12/24/2022] Open
Abstract
Deep learning is currently the most successful machine learning technique in a wide range of application areas and has recently been applied successfully in drug discovery research to predict potential drug targets and to screen for active molecules. However, due to (1) the lack of large-scale studies, (2) the compound series bias that is characteristic of drug discovery datasets and (3) the hyperparameter selection bias that comes with the high number of potential deep learning architectures, it remains unclear whether deep learning can indeed outperform existing computational methods in drug discovery tasks. We therefore assessed the performance of several deep learning methods on a large-scale drug discovery dataset and compared the results with those of other machine learning and target prediction methods. To avoid potential biases from hyperparameter selection or compound series, we used a nested cluster-cross-validation strategy. We found (1) that deep learning methods significantly outperform all competing methods and (2) that the predictive performance of deep learning is in many cases comparable to that of tests performed in wet labs (i.e., in vitro assays).
Collapse
Affiliation(s)
- Andreas Mayr
- LIT AI Lab and Institute of Bioinformatics , Johannes Kepler University Linz , Austria . ; ; Tel: +43-732-2468-4521
| | - Günter Klambauer
- LIT AI Lab and Institute of Bioinformatics , Johannes Kepler University Linz , Austria . ; ; Tel: +43-732-2468-4521
| | - Thomas Unterthiner
- LIT AI Lab and Institute of Bioinformatics , Johannes Kepler University Linz , Austria . ; ; Tel: +43-732-2468-4521
| | | | | | | | | | - Sepp Hochreiter
- LIT AI Lab and Institute of Bioinformatics , Johannes Kepler University Linz , Austria . ; ; Tel: +43-732-2468-4521
| |
Collapse
|
26
|
Mumm JN, Clevert DA, Ziegelmüller B. [Unclear renal masses in ultrasound]. MMW Fortschr Med 2018; 160:48-50. [PMID: 29556996 DOI: 10.1007/s15006-018-0291-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/08/2023]
Affiliation(s)
- Jan-Niclas Mumm
- Urologische Klinik und Poliklinik, LMU München, Campus Großhadern, Marchioninistr. 15, D-81377, München, Deutschland.
| | - D A Clevert
- Klinik für Radiologie, LMU München, München, Deutschland
| | | |
Collapse
|
27
|
Rübenthaler J, Paprottka KJ, Hameister E, Hoffmann K, Joiko N, Reiser M, Rjosk-Dendorfer R, Clevert DA. Contrast-enhanced ultrasound (CEUS) prediction of focal liver lesions in patients after liver transplantation in comparison to histopathology results. Clin Hemorheol Microcirc 2018; 66:303-310. [PMID: 28527201 DOI: 10.3233/ch-179104] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Abstract
PURPOSE To investigate the value of contrast-enhanced ultrasound (CEUS) in histologic prediction of focal liver lesions after liver transplantation. MATERIALS AND METHODS 10 focal liver lesions in 10 patients after liver transplantation were scanned using CEUS and the CEUS results were compared with the histopathological results. RESULTS Among 10 focal liver lesions, 7 proofed to be histopathological benign and 3 lesions proofed to be histopathological malignant. All lesions (100%) were correctly report as benign or malignant in the report of the CEUS examination. CONCLUSION CEUS can be helpful in the differentiation of benign and malignant focal liver lesions in patients after liver transplantation and can be used in clinical management of focal liver lesions.
Collapse
Affiliation(s)
- J Rübenthaler
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - K J Paprottka
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - E Hameister
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - K Hoffmann
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - N Joiko
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - M Reiser
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - R Rjosk-Dendorfer
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - D A Clevert
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| |
Collapse
|
28
|
Rübenthaler J, Paprottka KJ, Hameister E, Hoffmann K, Joiko N, Reiser M, Rjosk-Dendorfer D, Clevert DA. Diagnostic accuracy of contrast-enhanced ultrasound (CEUS) in monitoring vascular complications in patients after liver transplantation - diagnostic performance compared with histopathological results. Clin Hemorheol Microcirc 2018; 66:311-316. [PMID: 28527202 DOI: 10.3233/ch-179105] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022]
Abstract
PURPOSE To analyse the diagnostic performance of contrast-enhanced ultrasound (CEUS) in patients with vascular complications and transplant rejection compared to histopathological results. MATERIALS AND METHODS Our study consisted of 45 retrospectively analysed patients that underwent liver transplantations between January 1993 and December 2015 and developed post-transplant vascular complications with transplant rejection. CEUS examinations took place between September 2006 and December 2015. CEUS findings were correlated with histopathological results. RESULTS CEUS showed a sensitivity of 61.5%, a specificity of 100.0%, a positive predictive value (PPV) of 100.0% and a negative predictive value (NPV) of 86,5% in the detection of vascular complications with post-transplant rejection. 5 examinations were reported as normal whereas the histopathological result showed a transplant rejection (false-negative). CONCLUSION CEUS might be a useful additional non-invasive technique for the assessment of vascular complications with post-transplant rejection in patients after liver transplantation.
Collapse
Affiliation(s)
- J Rübenthaler
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - K J Paprottka
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - E Hameister
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - K Hoffmann
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - N Joiko
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - M Reiser
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - D Rjosk-Dendorfer
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - D A Clevert
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| |
Collapse
|
29
|
Abstract
MOTIVATION Biclustering has become a major tool for analyzing large datasets given as matrix of samples times features and has been successfully applied in life sciences and e-commerce for drug design and recommender systems, respectively. actor nalysis for cluster cquisition (FABIA), one of the most successful biclustering methods, is a generative model that represents each bicluster by two sparse membership vectors: one for the samples and one for the features. However, FABIA is restricted to about 20 code units because of the high computational complexity of computing the posterior. Furthermore, code units are sometimes insufficiently decorrelated and sample membership is difficult to determine. We propose to use the recently introduced unsupervised Deep Learning approach Rectified Factor Networks (RFNs) to overcome the drawbacks of existing biclustering methods. RFNs efficiently construct very sparse, non-linear, high-dimensional representations of the input via their posterior means. RFN learning is a generalized alternating minimization algorithm based on the posterior regularization method which enforces non-negative and normalized posterior means. Each code unit represents a bicluster, where samples for which the code unit is active belong to the bicluster and features that have activating weights to the code unit belong to the bicluster. RESULTS On 400 benchmark datasets and on three gene expression datasets with known clusters, RFN outperformed 13 other biclustering methods including FABIA. On data of the 1000 Genomes Project, RFN could identify DNA segments which indicate, that interbreeding with other hominins starting already before ancestors of modern humans left Africa. AVAILABILITY AND IMPLEMENTATION https://github.com/bioinf-jku/librfn. CONTACT djork-arne.clevert@bayer.com or hochreit@bioinf.jku.at.
Collapse
Affiliation(s)
| | - Thomas Unterthiner
- Institute of Bioinformatics, Johannes Kepler University Linz, Linz, Austria
| | - Gundula Povysil
- Institute of Bioinformatics, Johannes Kepler University Linz, Linz, Austria
| | - Sepp Hochreiter
- Institute of Bioinformatics, Johannes Kepler University Linz, Linz, Austria
| |
Collapse
|
30
|
Rübenthaler J, Paprottka K, D'Anastasi M, Reiser M, Clevert DA. Diagnosis of perinephric retroperitoneal lymphangioma supported by contrast-enhanced ultrasound (CEUS). Clin Hemorheol Microcirc 2017; 65:43-47. [PMID: 27716656 DOI: 10.3233/ch-169000] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Lymphangiomas are a rare condition, which are characterized by multiple cystic lesions of a single or multiple organs that are thought to originate from intrauterine atypically distended and connected lymphatic tissue. We describe a case of a 56 years old woman with the final diagnosis of a perinephric lymphangioma. With the use of contrast-enhanced ultrasound (CEUS) it was possible to add valuable diagnostic information regarding the extent of the lymphangioma to surrounding tissue without the necessity to use additional ionizing radiation or nephrotoxic contrast agents.
Collapse
|
31
|
Abstract
New clinical and technological advances in the field of magnetic resonance imaging (MRI) and targeted image-guided biopsy techniques have significantly improved the detection, localization and staging as well as active surveillance of prostate cancer in recent years. Multiparametric MRI (mpMRI) is currently the main imaging technique for the detection, characterization and diagnostics of metastasizing prostate cancer and is of high diagnostic importance for local staging within the framework of the detection of prostate cancer.
Collapse
Affiliation(s)
- D Nörenberg
- Institut für Klinische Radiologie, Klinikum der Universität München, Campus Großhadern, Marchioninistrasse 15, 81377, München, Deutschland.
| | - O Solyanik
- Institut für Klinische Radiologie, Klinikum der Universität München, Campus Großhadern, Marchioninistrasse 15, 81377, München, Deutschland
| | - B Schlenker
- Urologische Klinik und Poliklinik, Klinikum der Universität München, Campus Großhadern, München, Deutschland
| | - G Magistro
- Urologische Klinik und Poliklinik, Klinikum der Universität München, Campus Großhadern, München, Deutschland
| | - B Ertl-Wagner
- Institut für Klinische Radiologie, Klinikum der Universität München, Campus Großhadern, Marchioninistrasse 15, 81377, München, Deutschland
| | - D A Clevert
- Institut für Klinische Radiologie, Klinikum der Universität München, Campus Großhadern, Marchioninistrasse 15, 81377, München, Deutschland
| | - C Stief
- Urologische Klinik und Poliklinik, Klinikum der Universität München, Campus Großhadern, München, Deutschland
| | - M F Reiser
- Institut für Klinische Radiologie, Klinikum der Universität München, Campus Großhadern, Marchioninistrasse 15, 81377, München, Deutschland
| | - M D'Anastasi
- Institut für Klinische Radiologie, Klinikum der Universität München, Campus Großhadern, Marchioninistrasse 15, 81377, München, Deutschland
| |
Collapse
|
32
|
Rübenthaler J, Paprottka KJ, Marcon J, Reiser M, Clevert DA. MRI and contrast enhanced ultrasound (CEUS) image fusion of renal lesions. Clin Hemorheol Microcirc 2017; 64:457-466. [PMID: 27886003 DOI: 10.3233/ch-168116] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/20/2023]
Abstract
Ultrasound is a common and established imaging method for the initial characterization of renal lesions. The widespread used Bosniak classification (I-IV) classifies renal lesions in five individual groups using contrast-enhanced computer tomography (CE-CT), magnetic resonance imaging (MRI) and/or contrast-enhanced ultrasound (CEUS) imaging criteria. For complex pathologies, CEUS/MRI image fusion is a novel imaging technique for the differentiation of benign and malignant renal lesions. Compared to CE-CT and MRI alone, ultrasound image fusion offers the additional possibility of being a real-time imaging technique that can be used together with other cross-sectional imaging techniques.This article describes the newest possibilities of image fusion with CEUS and MRI in detection and characterization of unclear renal lesions.
Collapse
Affiliation(s)
- J Rübenthaler
- Department of Clinical Radiology, Interdisciplinary Ultrasound Center, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Marchioninistr., Munich, Germany
| | - K J Paprottka
- Department of Clinical Radiology, Interdisciplinary Ultrasound Center, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Marchioninistr., Munich, Germany
| | - J Marcon
- Department of Urology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Marchioninistr., Munich, Germany
| | - M Reiser
- Department of Clinical Radiology, Interdisciplinary Ultrasound Center, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Marchioninistr., Munich, Germany
| | - D A Clevert
- Department of Clinical Radiology, Interdisciplinary Ultrasound Center, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Marchioninistr., Munich, Germany
| |
Collapse
|
33
|
Rübenthaler J, Paprottka KJ, Hameister E, Hoffmann K, Joiko N, Reiser M, Clevert DA. Malignancies after liver transplantation: Value of contrast-enhanced ultrasound (CEUS). Clin Hemorheol Microcirc 2017; 64:467-473. [PMID: 27935549 DOI: 10.3233/ch-168117] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/21/2022]
Abstract
PURPOSE To evaluate the sensitivity and specificity of contrast-enhanced ultrasound (CEUS) and computed tomography (CT) in the diagnosis of malignancies after liver transplantation. MATERIALS AND METHODS A total of 23 patients with suspicious liver masses after liver transplantation with initial imaging series between September 2006 and September 2015 were statistically analysed. CEUS and CT were compared in their diagnosis of malignancy with CT being the gold standard. Out of 23 patients 9 patients showed malignant masses in CT, which could also be detected in 7 out 9 of cases using CEUS. RESULTS CEUS showed a sensitivity of 77.8%, a specificity of 100.0%, a positive predictive value (PPV) of 100.0% and a negative predictive value (NPV) of 87,5% in comparison with CT being the gold standard. In 2 cases CT showed a malignancy, contrary to the CEUS examination that was reported as normal. CONCLUSION CEUS seems to be an alternative option for the evaluation of malignant masses in liver transplant patients. CEUS shows a high specificity and PPV in the detection of malignant liver masses.
Collapse
|
34
|
Rübenthaler J, Paprottka K, Marcon J, Hameister E, Hoffmann K, Joiko N, Reiser M, Clevert DA. Comparison of magnetic resonance imaging (MRI) and contrast-enhanced ultrasound (CEUS) in the evaluation of unclear solid renal lesions. Clin Hemorheol Microcirc 2017; 64:757-763. [PMID: 27767985 DOI: 10.3233/ch-168034] [Citation(s) in RCA: 25] [Impact Index Per Article: 3.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/22/2022]
Abstract
PURPOSE To compare the sensitivity and specificity of contrast-enhanced ultrasound (CEUS) and magnetic resonance imaging (MRI) in the evaluation of unclear renal lesions to the histopathological outcome. MATERIALS AND METHODS A total of 36 patients with a single unclear solid renal lesion with initial imaging studies between 2005 and 2015 were included. CEUS and MRI were used for determining malignancy or benignancy and initial findings were correlated with the histopathological outcome. Out of the 36 renal masses a total of 28 lesions were malignant (77.8%) and 8 were found to be benign (22.2%). Diagnostic accuracy was testes by using the histopathological diagnosis as the gold standard. RESULTS CEUS showed a sensitivity of 96.4%, a specificity of 100.0%, a positive predictive value (PPV) of 100.0% and a negative predictive value (NPV) of 88,9%. MRI showed a sensitivity of 96.4%, a specificity of 75.0%, a PPV of 93.1% and a NPV of 85.7%. Out of the 28 malignant lesions a total of 18 clear cell renal carcinomas, 6 papillary renal cell carcinomas and 4 other malignant lesions, e.g. metastases, were diagnosed. Out of the 8 benign lesions a total 3 angiomyolipomas, 2 oncocytomas, 1 benign renal cyst and 2 other benign lesions, e.g. renal adenomas were diagnosed. Using CEUS, 1 lesion was falsely identified as benign. Using MRI, 2 lesions were falsely identified as benign and 1 lesion was falsely identified as malignant. CONCLUSION CEUS is an useful method which can be additionally used to clinically differentiate between malignant and benign renal lesions. CEUS shows a comparable sensitivity, specificity, PPV and NPV to MRI. In daily clinical routine, patients with contraindications for other imaging modalities can particularly benefit using this method.
Collapse
Affiliation(s)
- J Rübenthaler
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - K Paprottka
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - J Marcon
- Department of Urology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - E Hameister
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - K Hoffmann
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - N Joiko
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - M Reiser
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| | - D A Clevert
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Munich, Germany
| |
Collapse
|
35
|
Reimann R, Rübenthaler J, Hristova P, Staehler M, Reiser M, Clevert DA. Characterization of histological subtypes of clear cell renal cell carcinoma using contrast-enhanced ultrasound (CEUS). Clin Hemorheol Microcirc 2017; 63:77-87. [PMID: 26484711 DOI: 10.3233/ch-152009] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/27/2022]
Abstract
INTRODUCTION The aim of this study was to analyze the histological subtypes of clear cell renal cell carcinoma (RCC) examined by means of contrast-enhanced ultrasound (CEUS) and a second generation blood pool agent (SonoVue®, Bracco, Milan, Italy) during the pre-operative phase. MATERIALS AND METHODS 29 patients with histologically proven subtypes of clear cell RCC were examined. A total of three patients were diagnosed with highly differentiated clear cell RCC, 21 out of 29 cases with moderately differentiated clear cell RCC and five out of 29 patients had insufficiently differentiated clear cell RCC. An experienced radiologist examined the patients with CEUS. The following parameters were analyzed: maximum signal intensity (PEAK), time elapsed until PEAK is reached (MTT), local blood flow (RBF), area under the time intensity curve (AUC) and the signal intensity (SI) during the course of time. For the groups all comparisons are made based on healthy renal parenchyma. RESULTS In the clear cell RCC significant differences (significance level p < 0.05) between cancerous tissue and the healthy renal parenchyma were noticed in all four parameters. Therefore, the clear cell RCC stands out due to its reduced blood volume. However, it reached the PEAK reading relatively rapidly and its signal intensity was always lower than that of the healthy renal parenchyma. In the arterial phase retarded absorption of the contrast agent was observed, followed by fast washing out of the contrast agent bubbles.In all three histological subgroups no significant differences were noticed in PEAK and SI. However, the diagrams showed the possible bias, that the group of the insufficiently differentiated clear cell RCC had the highest PEAK-value and the highest signal intensity when compared with highly and moderately differentiated clear cell RCC. CONCLUSION Our study suggests that CEUS may be an additional tool for non-invasive characterisation and differentiation of the three histological subtypes of clear cell RCC. Furthermore, it seems to have an additional diagnostic value in daily clinical.
Collapse
Affiliation(s)
- R Reimann
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Marchioninistr., Munich, Germany
| | - J Rübenthaler
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Marchioninistr., Munich, Germany
| | - P Hristova
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Marchioninistr., Munich, Germany
| | - M Staehler
- Department of Urology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Marchioninistr., Munich, Germany
| | - M Reiser
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Marchioninistr., Munich, Germany
| | - D A Clevert
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Marchioninistr., Munich, Germany
| |
Collapse
|
36
|
Zimmermann H, Rübenthaler J, Rjosk-Dendorfer D, Helck A, Reimann R, Reiser M, Clevert DA. Comparison of portable ultrasound system and high end ultrasound system in detection of endoleaks. Clin Hemorheol Microcirc 2017; 63:99-111. [PMID: 26484713 DOI: 10.3233/ch-152011] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [MESH Headings] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
Abstract
PURPOSE To compare the value of a portable ultrasound system and a high end ultrasound system in detection of endoleaks after EVAR. MATERIAL AND METHODS In this retrospective study, a cohort of 25 patients underwent both standard examination using a portable ultrasound system (Philips VISIQ) and a second examination using a high end ultrasound system (Philips EPIQ 7). The examination included B-mode and color Doppler in detection of endoleaks. Additional the maximum diameter of the aneurysm was measured in two planes (right-left and ventral-dorsal). The gold standard was contrast-enhanced ultrasound (CEUS) in detection of endoleaks. RESULTS 25 patients were included in the study. Patients were predominantly male (n = 23) with an average age of 73,30±7.82 years (range 54-85). Diameters of the treated aneurysms were in the right-left plane 5,32±1.88 cm and ventral-dorsal 4,99±1.78 cm using the high end system. Diameters of the treated aneurysms were in the right-left plane 5,30±1.82 cm and ventral-dorsal 4,87±1.74 cm using portable ultrasound system. In 80% of the cases CEUS could detect an endoleak. Whereas the high end system could detect in B-mode 40% and color Doppler 45% of the cases an endoleak. The portable system could detect in B-mode 30% and in color Doppler 35% of the cases an endoleak. On both systems in B-mode a false positive endoleak was found on the same patient. All high flow endoleaks, which needed intervention, could be detected on all systems. CONCLUSION The high end ultrasound system does not seem to have an additional advantage in the measurement of the aneurysm diameter. Due to a higher resolution, more endoleaks could be detected in B-mode and color Doppler by using the high end system. The presence of small endoleaks could only be detected by using contrast enhanced ultrasound on an high end ultrasound system. High flow endoleaks could be reliable seen on both systems.
Collapse
|
37
|
Rübenthaler J, Reimann R, Hristova P, Staehler M, Reiser M, Clevert DA. Parametric imaging of clear cell and papillary renal cell carcinoma using contrast-enhanced ultrasound (CEUS). Clin Hemorheol Microcirc 2017; 63:89-97. [PMID: 26484712 DOI: 10.3233/ch-152010] [Citation(s) in RCA: 12] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/04/2023]
Abstract
PURPOSE The aim of this study was to analyse clear cell and papillary renal cell carcinoma (RCC) examined with contrast-enhanced ultrasound (CEUS) and a second generation blood pool agent (SonoVue®, Bracco, Milan, Italy) before clinical intervention. MATERIALS AND METHODS A total of 41 patients with histologically proven subtypes of RCC were examined. 29 patients had a clear cell RCC and 12 patients showed a papillary RCC. Average size in the clear cell RCC group was 6.07 cm and 1.88 cm in the papillary RCC group. An experienced radiologist examined all patients with CEUS. The following parameters were analysed: maximum signal intensity (PEAK), time elapsed until PEAK is reached (MTT), local blood flow (RBF), area under the time intensity curve (AUC) and the signal intensity (SI) during the course of time. For both groups all comparisons were made based on healthy renal parenchyma. RESULTS In the clear cell RCC significant differences (significance level p < 0.05) between cancerous tissue and the healthy renal parenchyma were noticed in all four parameters. The clear cell RCC showed a significant reduced blood volume. It reached the PEAK reading relatively rapidly and its signal intensity was always lower than that of the healthy renal parenchyma. In the arterial phase retarded absorption of the contrast agent was observed, followed by fast washing out of the contrast agent bubbles.In the papillary RCC group, significant findings as to PEAK and RBF as well as a slightly significant difference as to AUC were recorded. The papillary RCC had a lower blood supply and reached its PEAK reading later. Its signal intensity was also reduced. The signal intensity of papillary NCC was significantly lower compared with clear cell RCC; absorption and washing out of the contrast agent was delayed. CONCLUSION CEUS seems to be an useful additional method to clinically differentiate between clear cell and papillary RCC. In daily clinical use, patients with contraindication for other imaging methods, especially the magnetic resonance imaging, might particularly benefit from this method.
Collapse
Affiliation(s)
- J Rübenthaler
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Marchioninistr., Munich, Germany
| | - R Reimann
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Marchioninistr., Munich, Germany
| | - P Hristova
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Marchioninistr., Munich, Germany
| | - M Staehler
- Department of Urology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Marchioninistr., Munich, Germany
| | - M Reiser
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Marchioninistr., Munich, Germany
| | - D A Clevert
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Grosshadern Campus, Marchioninistr., Munich, Germany
| |
Collapse
|
38
|
Paprottka PM, Zengel P, Cyran CC, Paprottka KJ, Ingrisch M, Nikolaou K, Reiser MF, Clevert DA. Evaluation of multimodality imaging using image fusion with MRI and CEUS in an experimental animal model. Clin Hemorheol Microcirc 2016; 61:143-50. [PMID: 26519228 DOI: 10.3233/ch-151986] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/17/2023]
Abstract
PURPOSE To evaluate the diagnostic benefits of multimodality imaging using image fusion with magnetic-resonance-imaging (MRI) and contrast-enhanced-ultrasound (CEUS) in an experimental small-animal-squamous-cell-carcinoma-model for the assessment of tissue hemodynamics and morphology. MATERIAL AND METHODS Human hypopharynx-carcinoma-cells were injected subcutaneously into the left flank of 15 female athymic nude rats. After 10 daysof subcutaneous tumor growth, CEUS and MRI measurements were performed using a high-end-ultrasound-system and 3-T-MRI. After successful point-to-point or plan registration, the registered MR-images were simultaneously shown with the respective ultrasound sectional plane. Data evaluation was performed using the digitally stored video sequence data sets by two experienced radiologists using a subjective 5-point scale. RESULTS CEUS and MRI are well-known techniques for the assessment of tissue hemodynamics (score: mean 3.8 ± 0.4 SD and score 3.8 ± 0.4 SD). Real-time image fusion of MRI and CEUS yielded a significant (p < 0.001) improvement in score (score 4.8 ± 0.4 SD). Reliable detection of small necrotic areas was possible in all animals with necrotic tumors. No significant intraobserver and interobserver variability was detected (kappa coefficient = +1). CONCLUSION Image fusion of MRI and CEUS gives a significant improvement for reliable differentiation between different tumor tissue areas and simplifies investigations by showing the morphology as well as surrounding macro-/microvascularization.
Collapse
Affiliation(s)
- P M Paprottka
- Institute for Clinical Radiology, Ludwig Maximilian University Hospital, Munich, Germany
| | - P Zengel
- Institute for Ear, Nose and Throat Medicine, Munich, Germany
| | - C C Cyran
- Institute for Clinical Radiology, Ludwig Maximilian University Hospital, Munich, Germany
| | - K J Paprottka
- Institute for Clinical Radiology, Ludwig Maximilian University Hospital, Munich, Germany
| | - M Ingrisch
- Institute for Clinical Radiology, Ludwig Maximilian University Hospital, Munich, Germany
| | - K Nikolaou
- Institute for Clinical Radiology, Ludwig Maximilian University Hospital, Munich, Germany
| | - M F Reiser
- Institute for Clinical Radiology, Ludwig Maximilian University Hospital, Munich, Germany
| | - D A Clevert
- Institute for Clinical Radiology, Ludwig Maximilian University Hospital, Munich, Germany
| |
Collapse
|
39
|
Rübenthaler J, Bogner F, Reiser M, Clevert DA. Contrast-Enhanced Ultrasound (CEUS) of the Kidneys by Using the Bosniak Classification. Ultraschall Med 2016; 37:234-251. [PMID: 27058636 DOI: 10.1055/s-0042-104646] [Citation(s) in RCA: 30] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/05/2023]
Abstract
Ultrasound is the most used interdisciplinary non-ionizing imaging technique in clinical routine. Therefore, ultrasound has a special value in the diagnosis and monitoring of cystic renal lesions, which can be classified as non-complicated or complicated and by means of occurrence as solitary or multifocal lesions. The Bosniak classification (I-IV) classifies renal cysts in 5 different categories with the help of ultrasound and computed tomography image criteria and is used for decisions of further clinical treatment. Additionally to normal native B-mode sonography, several new methods are in clinical use to improve diagnostic accuracy of unclear cases. Contrast enhanced ultrasound and MRI/CT are able to find and characterize difficult pathologies. This review explains the most important pathologies of cystic lesions of the kidney and stresses the different imaging methods of native B-mode sonography and the new techniques of contrast enhanced ultrasound.
Collapse
Affiliation(s)
- J Rübenthaler
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Großhadern Campus, Munich, Germany
| | - F Bogner
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Großhadern Campus, Munich, Germany
| | - M Reiser
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Großhadern Campus, Munich, Germany
| | - D A Clevert
- Department of Clinical Radiology, Ludwig-Maximilians-University of Munich-Großhadern Campus, Munich, Germany
| |
Collapse
|
40
|
Paprottka PM, Zengel P, Cyran CC, Ingrisch M, Nikolaou K, Reiser MF, Clevert DA. Evaluation of multimodality imaging using image fusion with ultrasound tissue elasticity imaging in an experimental animal model. Clin Hemorheol Microcirc 2016; 57:101-10. [PMID: 24577380 DOI: 10.3233/ch-141821] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
PURPOSE To evaluate the ultrasound tissue elasticity imaging by comparison to multimodality imaging using image fusion with Magnetic Resonance Imaging (MRI) and conventional grey scale imaging with additional elasticity-ultrasound in an experimental small-animal-squamous-cell carcinoma-model for the assessment of tissue morphology. METHOD AND MATERIALS Human hypopharynx carcinoma cells were subcutaneously injected into the left flank of 12 female athymic nude rats. After 10 days (SD ± 2) of subcutaneous tumor growth, sonographic grey scale including elasticity imaging and MRI measurements were performed using a high-end ultrasound system and a 3T MR. For image fusion the contrast-enhanced MRI DICOM data set was uploaded in the ultrasonic device which has a magnetic field generator, a linear array transducer (6-15 MHz) and a dedicated software package (GE Logic E9), that can detect transducers by means of a positioning system. Conventional grey scale and elasticity imaging were integrated in the image fusion examination. After successful registration and image fusion the registered MR-images were simultaneously shown with the respective ultrasound sectional plane. Data evaluation was performed using the digitally stored video sequence data sets by two experienced radiologist using a modified Tsukuba Elasticity score. The colors "red and green" are assigned for an area of soft tissue, "blue" indicates hard tissue. RESULTS In all cases a successful image fusion and plan registration with MRI and ultrasound imaging including grey scale and elasticity imaging was possible. The mean tumor volume based on caliper measurements in 3 dimensions was ~323 mm3. 4/12 rats were evaluated with Score I, 5/12 rates were evaluated with Score II, 3/12 rates were evaluated with Score III. There was a close correlation in the fused MRI with existing small necrosis in the tumor. None of the scored II or III lesions was visible by conventional grey scale. CONCLUSION The comparison of ultrasound tissue elasticity imaging enables a secure differentiation between different tumor tissue areas in comparison to image fusion with MRI in our small study group. Therefore ultrasound tissue elasticity imaging might be used for fast detection of tumor response in the future whereas conventional grey scale imaging alone could not provide the additional information. By using standard, contrast-enhanced MRI images for reliable and reproducible slice positioning, the strongly user-dependent limitation of ultrasound tissue elasticity imaging may be overcome, especially for a comparison between baseline and follow-up measurements.
Collapse
Affiliation(s)
- P M Paprottka
- Department of Clinical Radiology, University of Munich, Munich, Germany
| | - P Zengel
- Institute for Ear, Nose and Throat Medicine, University of Munich, Munich, Germany
| | - C C Cyran
- Department of Clinical Radiology, University of Munich, Munich, Germany
| | - M Ingrisch
- Department of Clinical Radiology, University of Munich, Munich, Germany
| | - K Nikolaou
- Department of Clinical Radiology, University of Munich, Munich, Germany
| | - M F Reiser
- Department of Clinical Radiology, University of Munich, Munich, Germany
| | - D A Clevert
- Department of Clinical Radiology, University of Munich, Munich, Germany
| |
Collapse
|
41
|
Strobl FF, D'Anastasi M, Hinzpeter R, Franke PS, Trumm CG, Waggershauser T, Staehler M, Clevert DA, Reiser M, Graser A, Paprottka PM. Renal Pseudoaneurysms and Arteriovenous Fistulas as a Complication of Nephron-Sparing Partial Nephrectomy: Technical and Functional Outcomes of Patients Treated With Selective Microcoil Embolization During a Ten-Year Period. ROFO-FORTSCHR RONTG 2016; 188:188-94. [PMID: 26756934 DOI: 10.1055/s-0041-110136] [Citation(s) in RCA: 12] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/22/2022]
Abstract
PURPOSE The aim of this study was to evaluate the clinical and functional outcomes in patients who underwent selective interventional embolization of renal pseudoaneurysms or arteriovenous fistulas at our center. MATERIALS AND METHODS Our retrospective analysis included all consecutive patients who received selective transcatheter embolization of renal pseudoaneurysms or arteriovenous fistulas after partial nephrectomy in our department from January, 2003 to September, 2013. The technical and clinical success rate and functional outcome of every procedure was collected and analyzed. Furthermore, the change in renal parenchymal volume before and after embolization was determined in a subgroup. RESULTS A total of 1425 patients underwent partial nephrectomy at our hospital. Of these, 39 (2.7 %) were identified with a pseudoaneurysm or an arteriovenous fistula after partial nephrectomy. The diagnosis of the vascular lesions was made by means of biphasic CT or CEUS. Technical success by means of selective microcoil embolization was achieved in all 39 patients (100 %). Clinical success, defined as no need for further operation or nephrectomy during follow-up, was achieved in 35 of 39 patients (85.7 %). Renal function, as measured by eGFR before and after the intervention, did not change significantly. However, a mean loss of parenchymal volume of 25.2 % was observed in a subgroup. No major or minor complications were attributable to the embolization procedure. CONCLUSION Transcatheter embolization is a promising method for treating vascular complications which may occur after partial nephrectomy. We confirm the high success rate of this technique while discussing renal functional outcomes and potential safety aspects. KEY POINTS Arterial pseudoaneurysms and arteriovenous fistulas are rare but severe complications after partial nephrectomy. Selective microcoil embolization is a safe and effective kidney-preserving procedure for treating these complications. Embolization leads to a significant loss of renal parenchymal volume but not to a loss of renal function.
Collapse
Affiliation(s)
- F F Strobl
- Institute for Clinical Radiology, Ludwig-Maximilians-University Hospital, Munich, Germany
| | - M D'Anastasi
- Institute for Clinical Radiology, Ludwig-Maximilians-University Hospital, Munich, Germany
| | - R Hinzpeter
- Institute for Clinical Radiology, Ludwig-Maximilians-University Hospital, Munich, Germany
| | - P S Franke
- Institute for Clinical Radiology, Ludwig-Maximilians-University Hospital, Munich, Germany
| | - C G Trumm
- Institute for Clinical Radiology, Ludwig-Maximilians-University Hospital, Munich, Germany
| | - T Waggershauser
- Institute for Clinical Radiology, Ludwig-Maximilians-University Hospital, Munich, Germany
| | - M Staehler
- Department of Urology, Ludwig-Maximilians-University Hospital, Munich, Germany
| | - D A Clevert
- Institute for Clinical Radiology, Ludwig-Maximilians-University Hospital, Munich, Germany
| | - M Reiser
- Institute for Clinical Radiology, Ludwig-Maximilians-University Hospital, Munich, Germany
| | - A Graser
- Institute for Clinical Radiology, Ludwig-Maximilians-University Hospital, Munich, Germany
| | - P M Paprottka
- Institute for Clinical Radiology, Ludwig-Maximilians-University Hospital, Munich, Germany
| |
Collapse
|
42
|
Rübenthaler J, Lutz J, Reiser M, Clevert DA. [Title Page - Paraganglioma of the Head and Neck: Follow-Up of Interventional Procedures with CEUS]. Ultraschall Med 2015; 36:541-543. [PMID: 26841712 DOI: 10.1055/s-0035-1552392] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [What about the content of this article? (0)] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/05/2023]
|
43
|
Abstract
Accurate identification of the location of carcinoma in the prostate is essential for long-term therapeutic success, in particular for minimally invasive procedures. In recent years many new positive study results for prostate imaging have been reported which must be compared and evaluated and previous conservative assessments may need to be re-evaluated. In addition, combinations of different imaging techniques are increasingly being used in daily clinical routine. Due to technical advancements in sonographic imaging, such as elastography and contrast-enhanced ultrasound (CEUS), the detection rate of prostate cancer can be increased. An overview of the different imaging modalities and current literature are presented in this article.
Collapse
Affiliation(s)
- B Schlenker
- Urologische Klinik und Poliklinik des Klinikums der Universität München, Marchioninistraße 15, 81377, München, Deutschland,
| | | | | |
Collapse
|
44
|
Zimmermann H, Reiser M, Meimarakis G, Paprottka P, Clevert DA. [New Applications and Indications for Contrast-Enhanced Sonography in Endovascular Aortic Repair]. Zentralbl Chir 2015. [PMID: 26212620 DOI: 10.1055/s-0035-1546147] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
Abstract
After edovascular repair of infrarenal aortic aneurysms (EVAR) endoleaks may occur necessitating further therapy. Therefore a reliable method for follow-up imaging after EVAR for detection and control of endoleaks is of high importance. Contrast-enhanced sonography (CEUS) does not require the application of nephrotoxid contrast media and does not stress the patient. CEUS is increasingly used and enables a quick, non-invasive follow-up examination for patient after EVAR. In addition, interventions as therapy for endoleaks may be executed using ultrasound. Initial experience with CEUS-guided aortic stenting shows that the amount of contrast media as well as X-ray time may be reduced.
Collapse
Affiliation(s)
- H Zimmermann
- Institut für klinische Radiologie, Klinikum der Ludwig-Maximilians-Universität München, Deutschland
| | - M Reiser
- Institut für klinische Radiologie, Klinikum der Ludwig-Maximilians-Universität München, Deutschland
| | - G Meimarakis
- Abteilung für Gefäßchirurgie, Klinikum der Ludwig-Maximilians-Universität München, Deutschland
| | - P Paprottka
- Institut für klinische Radiologie, Klinikum der Ludwig-Maximilians-Universität München, Deutschland
| | - D A Clevert
- Institut für klinische Radiologie, Klinikum der Ludwig-Maximilians-Universität München, Deutschland
| |
Collapse
|
45
|
Rjosk-Dendorfer D, Reu S, Deak Z, Hetterich H, Kolben T, Reiser M, Clevert DA. High resolution compression elastography and color doppler sonography in characterization of breast fibroadenoma. Clin Hemorheol Microcirc 2015; 58:115-25. [PMID: 25227197 DOI: 10.3233/ch-141884] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
PURPOSE To evaluate the use of color Doppler sonography and free hand sonoelastography in the assessment of breast fibroadenomas according to their size and shape. MATERIALS AND METHODS From December 2012 to March 2013 women with 16 solid breast masses, classified as BI-RADS category 3 or 4 were examined with B-mode ultrasound, sonoelastography and color Doppler sonography. Lesions were subdivided according to their shape in round, ovoid or macrolobulated and according to their size (<2.0 cm or ≥2.0 cm). Two readers assessed sonoelastographic findings at 12.5 MHz using the tsukuba elasticity score and results of Doppler sonography using a score of 0, 1 or 2, depending on the degree of perfusion. RESULTS Among the 16 examined lesions 3 showed a round shape, 9 were ovoid and in 4 cases a macrolobulated appearance could be seen. No significant differences concerning Tsukuba-score depending on various shapes of fibroadenomas in B-mode sonography could be shown (p = 0.91) and also comparison of Tsukuba-scores and size of masses revealed no significant differences (p = 1.0). Sizes of fibroadenomas ≥2 cm were significantly associated with an increased vascularization of the lesions (p = 0.04) and a macrolobulated appearance in B-mode sonography (p = 0.04). CONCLUSION The combination of color Doppler sonography and sonoelastography in addition to B-mode sonography leads to an increased accuracy in distinguishing benign from malignant breast masses and to an improvement in characterization of fibroadenomas independent of their shape or size.
Collapse
Affiliation(s)
- D Rjosk-Dendorfer
- Department for Clinical Radiology, Ludwig-Maximilians-University Hospital, Munich, Germany
| | - S Reu
- Institute of Pathology, Ludwig-Maximilians-University, Munich, Germany
| | - Z Deak
- Department for Clinical Radiology, Ludwig-Maximilians-University Hospital, Munich, Germany
| | - H Hetterich
- Department for Clinical Radiology, Ludwig-Maximilians-University Hospital, Munich, Germany
| | - T Kolben
- Department of Gynecology and Obstetrics, Ludwig-Maximilians-University Hospital, Munich, Germany
| | - M Reiser
- Department for Clinical Radiology, Ludwig-Maximilians-University Hospital, Munich, Germany
| | - D A Clevert
- Department for Clinical Radiology, Ludwig-Maximilians-University Hospital, Munich, Germany
| |
Collapse
|
46
|
Clevert DA, Gürtler VM, Meimarakis G, D'Anastasi M, Weidenhagen R, Reiser MF, Becker CR. Classification of endoleaks in the follow-up after EVAR using the time-to-peak of the contrast agent in CEUS examinations. Clin Hemorheol Microcirc 2014; 55:183-91. [PMID: 23455839 DOI: 10.3233/ch-131701] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
PURPOSE To evaluate the feasibility of the classification of endoleaks following endovascular aortic aneurysm repair using the time-to-peak of the contrast agent in CEUS examinations. MATERIAL AND METHODS In this retrospective study, a cohort of 171 patients with a total of 489 CEUS follow-up examinations after EVAR were included. In 254 of the 489 examinations, an endoleak was seen and the time-to-peak was measured in seconds. Existence of an endoleak was confirmed by CT as the gold standard. RESULTS We evaluated 254 CEUS video sequences showing an endoleak out of a total of 489 examinations. Kruskal-Wallis test revealed with p = 0.001 differences between the single endoleak types based on the time to peak. Correction after Bonferroni showed significant differences between type Ia compared to Ib and to IIa over inferior mesenteric artery (IMA) and IIa over lumbar artery (LA). There are also disparities between type Ib and type IIa IMA and type III, furthermore between type IIa IMA compared to IIa LA and type III as well as type IIa LA matched to type III. CONCLUSION CEUS is an important method for the follow-up after EVAR. The time-to-peak does not seem to be a useful additional feature in classifying endoleaks, although there are differences between the time-to-peak of the single endoleak types and it is possible to make an order of the different endoleak types referring to the mean values.
Collapse
Affiliation(s)
- D A Clevert
- Department for Clinical Radiology, Ludwig-Maximilians-University Hospital Munich-Grosshadern, Munich, Germany
| | | | | | | | | | | | | |
Collapse
|
47
|
Clevert DA. Kontrastmittelverstärkter Ultraschall im Follow-up nach endovaskulärer Stentversorgung des infrarenalen Bauchaortenaneurysmas. ROFO-FORTSCHR RONTG 2014. [DOI: 10.1055/s-0034-1372944] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|
48
|
Clevert DA. Elastografie der Leber, ein neuer Weg der Diagnostik. ROFO-FORTSCHR RONTG 2014. [DOI: 10.1055/s-0034-1373443] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|
49
|
Jung EM, Clevert DA. Bildfusion und Volumennavigation US/CEUS mti CT/MRT/PET. ROFO-FORTSCHR RONTG 2014. [DOI: 10.1055/s-0034-1373434] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|
50
|
Clevert DA. CEUS in der vaskulären Diagnostik und bei Gefäßinterventionen. ROFO-FORTSCHR RONTG 2014. [DOI: 10.1055/s-0034-1373433] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|