1
|
Jahn LR, Marquet C, Heinzinger M, Rost B. Protein embeddings predict binding residues in disordered regions. Sci Rep 2024; 14:13566. [PMID: 38866950 DOI: 10.1038/s41598-024-64211-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2024] [Accepted: 06/06/2024] [Indexed: 06/14/2024] Open
Abstract
The identification of protein binding residues helps to understand their biological processes as protein function is often defined through ligand binding, such as to other proteins, small molecules, ions, or nucleotides. Methods predicting binding residues often err for intrinsically disordered proteins or regions (IDPs/IDPRs), often also referred to as molecular recognition features (MoRFs). Here, we presented a novel machine learning (ML) model trained to specifically predict binding regions in IDPRs. The proposed model, IDBindT5, leveraged embeddings from the protein language model (pLM) ProtT5 to reach a balanced accuracy of 57.2 ± 3.6% (95% confidence interval). Assessed on the same data set, this did not differ at the 95% CI from the state-of-the-art (SOTA) methods ANCHOR2 and DeepDISOBind that rely on expert-crafted features and evolutionary information from multiple sequence alignments (MSAs). Assessed on other data, methods such as SPOT-MoRF reached higher MCCs. IDBindT5's SOTA predictions are much faster than other methods, easily enabling full-proteome analyses. Our findings emphasize the potential of pLMs as a promising approach for exploring and predicting features of disordered proteins. The model and a comprehensive manual are publicly available at https://github.com/jahnl/binding_in_disorder .
Collapse
Affiliation(s)
- Laura R Jahn
- School of Computation, Information, and Technology (CIT), Department of Informatics, Bioinformatics and Computational Biology, TUM (Technical University of Munich), 85748, Garching/Munich, Germany
| | - Céline Marquet
- School of Computation, Information, and Technology (CIT), Department of Informatics, Bioinformatics and Computational Biology, TUM (Technical University of Munich), 85748, Garching/Munich, Germany.
| | - Michael Heinzinger
- School of Computation, Information, and Technology (CIT), Department of Informatics, Bioinformatics and Computational Biology, TUM (Technical University of Munich), 85748, Garching/Munich, Germany
| | - Burkhard Rost
- School of Computation, Information, and Technology (CIT), Department of Informatics, Bioinformatics and Computational Biology, TUM (Technical University of Munich), 85748, Garching/Munich, Germany
- Institute for Advanced Study (TUM-IAS), Lichtenbergstr. 2a, 85748, Garching/Munich, Germany
- TUM School of Life Sciences Weihenstephan (TUM-WZW), Alte Akademie 8, Freising, Germany
| |
Collapse
|
2
|
Saar KL, Qian D, Good LL, Morgunov AS, Collepardo-Guevara R, Best RB, Knowles TPJ. Theoretical and Data-Driven Approaches for Biomolecular Condensates. Chem Rev 2023; 123:8988-9009. [PMID: 37171907 PMCID: PMC10375482 DOI: 10.1021/acs.chemrev.2c00586] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2022] [Indexed: 05/14/2023]
Abstract
Biomolecular condensation processes are increasingly recognized as a fundamental mechanism that living cells use to organize biomolecules in time and space. These processes can lead to the formation of membraneless organelles that enable cells to perform distinct biochemical processes in controlled local environments, thereby supplying them with an additional degree of spatial control relative to that achieved by membrane-bound organelles. This fundamental importance of biomolecular condensation has motivated a quest to discover and understand the molecular mechanisms and determinants that drive and control this process. Within this molecular viewpoint, computational methods can provide a unique angle to studying biomolecular condensation processes by contributing the resolution and scale that are challenging to reach with experimental techniques alone. In this Review, we focus on three types of dry-lab approaches: theoretical methods, physics-driven simulations and data-driven machine learning methods. We review recent progress in using these tools for probing biomolecular condensation across all three fields and outline the key advantages and limitations of each of the approaches. We further discuss some of the key outstanding challenges that we foresee the community addressing next in order to develop a more complete picture of the molecular driving forces behind biomolecular condensation processes and their biological roles in health and disease.
Collapse
Affiliation(s)
- Kadi L. Saar
- Yusuf
Hamied Department of Chemistry, University
of Cambridge, Cambridge CB2 1EW, United Kingdom
- Transition
Bio Ltd., Cambridge, United Kingdom
| | - Daoyuan Qian
- Yusuf
Hamied Department of Chemistry, University
of Cambridge, Cambridge CB2 1EW, United Kingdom
| | - Lydia L. Good
- Yusuf
Hamied Department of Chemistry, University
of Cambridge, Cambridge CB2 1EW, United Kingdom
- Laboratory
of Chemical Physics, National Institute of Diabetes and Digestive
and Kidney Diseases, National Institutes
of Health, Bethesda, Maryland 20892, United States
| | - Alexey S. Morgunov
- Yusuf
Hamied Department of Chemistry, University
of Cambridge, Cambridge CB2 1EW, United Kingdom
| | - Rosana Collepardo-Guevara
- Yusuf
Hamied Department of Chemistry, University
of Cambridge, Cambridge CB2 1EW, United Kingdom
- Department
of Genetics, University of Cambridge, Cambridge CB2 3EH, United Kingdom
| | - Robert B. Best
- Laboratory
of Chemical Physics, National Institute of Diabetes and Digestive
and Kidney Diseases, National Institutes
of Health, Bethesda, Maryland 20892, United States
| | - Tuomas P. J. Knowles
- Yusuf
Hamied Department of Chemistry, University
of Cambridge, Cambridge CB2 1EW, United Kingdom
- Cavendish
Laboratory, Department of Physics, University
of Cambridge, Cambridge CB3 0HE, United Kingdom
| |
Collapse
|
3
|
Olenyi T, Marquet C, Heinzinger M, Kröger B, Nikolova T, Bernhofer M, Sändig P, Schütze K, Littmann M, Mirdita M, Steinegger M, Dallago C, Rost B. LambdaPP: Fast and accessible protein-specific phenotype predictions. Protein Sci 2023; 32:e4524. [PMID: 36454227 PMCID: PMC9793974 DOI: 10.1002/pro.4524] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2022] [Revised: 11/09/2022] [Accepted: 11/21/2022] [Indexed: 12/04/2022]
Abstract
The availability of accurate and fast artificial intelligence (AI) solutions predicting aspects of proteins are revolutionizing experimental and computational molecular biology. The webserver LambdaPP aspires to supersede PredictProtein, the first internet server making AI protein predictions available in 1992. Given a protein sequence as input, LambdaPP provides easily accessible visualizations of protein 3D structure, along with predictions at the protein level (GeneOntology, subcellular location), and the residue level (binding to metal ions, small molecules, and nucleotides; conservation; intrinsic disorder; secondary structure; alpha-helical and beta-barrel transmembrane segments; signal-peptides; variant effect) in seconds. The structure prediction provided by LambdaPP-leveraging ColabFold and computed in minutes-is based on MMseqs2 multiple sequence alignments. All other feature prediction methods are based on the pLM ProtT5. Queried by a protein sequence, LambdaPP computes protein and residue predictions almost instantly for various phenotypes, including 3D structure and aspects of protein function. LambdaPP is freely available for everyone to use under embed.predictprotein.org, the interactive results for the case study can be found under https://embed.predictprotein.org/o/Q9NZC2. The frontend of LambdaPP can be found on GitHub (github.com/sacdallago/embed.predictprotein.org), and can be freely used and distributed under the academic free use license (AFL-2). For high-throughput applications, all methods can be executed locally via the bio-embeddings (bioembeddings.com) python package, or docker image at ghcr.io/bioembeddings/bio_embeddings, which also includes the backend of LambdaPP.
Collapse
Affiliation(s)
- Tobias Olenyi
- TUM (Technical University of Munich) Department of InformaticsBioinformatics‐ & Computational Biology—i12GarchingGermany,TUM Graduate SchoolCenter of Doctoral Studies in Informatics and its Applications (CeDoSIA)GarchingGermany
| | - Céline Marquet
- TUM (Technical University of Munich) Department of InformaticsBioinformatics‐ & Computational Biology—i12GarchingGermany,TUM Graduate SchoolCenter of Doctoral Studies in Informatics and its Applications (CeDoSIA)GarchingGermany
| | - Michael Heinzinger
- TUM (Technical University of Munich) Department of InformaticsBioinformatics‐ & Computational Biology—i12GarchingGermany,TUM Graduate SchoolCenter of Doctoral Studies in Informatics and its Applications (CeDoSIA)GarchingGermany
| | - Benjamin Kröger
- TUM (Technical University of Munich) Department of InformaticsBioinformatics‐ & Computational Biology—i12GarchingGermany
| | - Tiha Nikolova
- TUM (Technical University of Munich) Department of InformaticsBioinformatics‐ & Computational Biology—i12GarchingGermany
| | - Michael Bernhofer
- TUM Graduate SchoolCenter of Doctoral Studies in Informatics and its Applications (CeDoSIA)GarchingGermany
| | - Philip Sändig
- TUM (Technical University of Munich) Department of InformaticsBioinformatics‐ & Computational Biology—i12GarchingGermany
| | - Konstantin Schütze
- TUM (Technical University of Munich) Department of InformaticsBioinformatics‐ & Computational Biology—i12GarchingGermany
| | - Maria Littmann
- TUM (Technical University of Munich) Department of InformaticsBioinformatics‐ & Computational Biology—i12GarchingGermany
| | - Milot Mirdita
- School of Biological SciencesSeoul National UniversitySeoulSouth Korea
| | - Martin Steinegger
- School of Biological SciencesSeoul National UniversitySeoulSouth Korea,Korea Artificial Intelligence InstituteSeoul National UniversitySeoulSouth Korea,Korea Institute of Molecular Biology and GeneticsSeoul National UniversitySeoulSouth Korea
| | - Christian Dallago
- TUM (Technical University of Munich) Department of InformaticsBioinformatics‐ & Computational Biology—i12GarchingGermany,VantAINew YorkUSA
| | - Burkhard Rost
- TUM (Technical University of Munich) Department of InformaticsBioinformatics‐ & Computational Biology—i12GarchingGermany,Institute for Advanced Study (TUM‐IAS)Lichtenbergstr. 2a, 85748 Garching/Munich, Germany & TUM School of Life Sciences Weihenstephan (WZW)FreisingGermany
| |
Collapse
|
4
|
Elnaggar A, Heinzinger M, Dallago C, Rehawi G, Wang Y, Jones L, Gibbs T, Feher T, Angerer C, Steinegger M, Bhowmik D, Rost B. ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2022; 44:7112-7127. [PMID: 34232869 DOI: 10.1109/tpami.2021.3095381] [Citation(s) in RCA: 304] [Impact Index Per Article: 152.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/10/2023]
Abstract
Computational biology and bioinformatics provide vast data gold-mines from protein sequences, ideal for Language Models (LMs) taken from Natural Language Processing (NLP). These LMs reach for new prediction frontiers at low inference costs. Here, we trained two auto-regressive models (Transformer-XL, XLNet) and four auto-encoder models (BERT, Albert, Electra, T5) on data from UniRef and BFD containing up to 393 billion amino acids. The protein LMs (pLMs) were trained on the Summit supercomputer using 5616 GPUs and TPU Pod up-to 1024 cores. Dimensionality reduction revealed that the raw pLM-embeddings from unlabeled data captured some biophysical features of protein sequences. We validated the advantage of using the embeddings as exclusive input for several subsequent tasks: (1) a per-residue (per-token) prediction of protein secondary structure (3-state accuracy Q3=81%-87%); (2) per-protein (pooling) predictions of protein sub-cellular location (ten-state accuracy: Q10=81%) and membrane versus water-soluble (2-state accuracy Q2=91%). For secondary structure, the most informative embeddings (ProtT5) for the first time outperformed the state-of-the-art without multiple sequence alignments (MSAs) or evolutionary information thereby bypassing expensive database searches. Taken together, the results implied that pLMs learned some of the grammar of the language of life. All our models are available through https://github.com/agemagician/ProtTrans.
Collapse
|
5
|
Elnaggar A, Heinzinger M, Dallago C, Rehawi G, Wang Y, Jones L, Gibbs T, Feher T, Angerer C, Steinegger M, Bhowmik D, Rost B. ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2022. [PMID: 34232869 DOI: 10.1101/2020.07.12.199554] [Citation(s) in RCA: 66] [Impact Index Per Article: 33.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/15/2023]
Abstract
Computational biology and bioinformatics provide vast data gold-mines from protein sequences, ideal for Language Models (LMs) taken from Natural Language Processing (NLP). These LMs reach for new prediction frontiers at low inference costs. Here, we trained two auto-regressive models (Transformer-XL, XLNet) and four auto-encoder models (BERT, Albert, Electra, T5) on data from UniRef and BFD containing up to 393 billion amino acids. The protein LMs (pLMs) were trained on the Summit supercomputer using 5616 GPUs and TPU Pod up-to 1024 cores. Dimensionality reduction revealed that the raw pLM-embeddings from unlabeled data captured some biophysical features of protein sequences. We validated the advantage of using the embeddings as exclusive input for several subsequent tasks: (1) a per-residue (per-token) prediction of protein secondary structure (3-state accuracy Q3=81%-87%); (2) per-protein (pooling) predictions of protein sub-cellular location (ten-state accuracy: Q10=81%) and membrane versus water-soluble (2-state accuracy Q2=91%). For secondary structure, the most informative embeddings (ProtT5) for the first time outperformed the state-of-the-art without multiple sequence alignments (MSAs) or evolutionary information thereby bypassing expensive database searches. Taken together, the results implied that pLMs learned some of the grammar of the language of life. All our models are available through https://github.com/agemagician/ProtTrans.
Collapse
|
6
|
Marquet C, Heinzinger M, Olenyi T, Dallago C, Erckert K, Bernhofer M, Nechaev D, Rost B. Embeddings from protein language models predict conservation and variant effects. Hum Genet 2022; 141:1629-1647. [PMID: 34967936 PMCID: PMC8716573 DOI: 10.1007/s00439-021-02411-y] [Citation(s) in RCA: 33] [Impact Index Per Article: 16.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/01/2021] [Accepted: 12/06/2021] [Indexed: 12/13/2022]
Abstract
The emergence of SARS-CoV-2 variants stressed the demand for tools allowing to interpret the effect of single amino acid variants (SAVs) on protein function. While Deep Mutational Scanning (DMS) sets continue to expand our understanding of the mutational landscape of single proteins, the results continue to challenge analyses. Protein Language Models (pLMs) use the latest deep learning (DL) algorithms to leverage growing databases of protein sequences. These methods learn to predict missing or masked amino acids from the context of entire sequence regions. Here, we used pLM representations (embeddings) to predict sequence conservation and SAV effects without multiple sequence alignments (MSAs). Embeddings alone predicted residue conservation almost as accurately from single sequences as ConSeq using MSAs (two-state Matthews Correlation Coefficient-MCC-for ProtT5 embeddings of 0.596 ± 0.006 vs. 0.608 ± 0.006 for ConSeq). Inputting the conservation prediction along with BLOSUM62 substitution scores and pLM mask reconstruction probabilities into a simplistic logistic regression (LR) ensemble for Variant Effect Score Prediction without Alignments (VESPA) predicted SAV effect magnitude without any optimization on DMS data. Comparing predictions for a standard set of 39 DMS experiments to other methods (incl. ESM-1v, DeepSequence, and GEMME) revealed our approach as competitive with the state-of-the-art (SOTA) methods using MSA input. No method outperformed all others, neither consistently nor statistically significantly, independently of the performance measure applied (Spearman and Pearson correlation). Finally, we investigated binary effect predictions on DMS experiments for four human proteins. Overall, embedding-based methods have become competitive with methods relying on MSAs for SAV effect prediction at a fraction of the costs in computing/energy. Our method predicted SAV effects for the entire human proteome (~ 20 k proteins) within 40 min on one Nvidia Quadro RTX 8000. All methods and data sets are freely available for local and online execution through bioembeddings.com, https://github.com/Rostlab/VESPA , and PredictProtein.
Collapse
Affiliation(s)
- Céline Marquet
- Department of Informatics, Bioinformatics and Computational Biology - i12, TUM-Technical University of Munich, Boltzmannstr. 3, Garching, 85748, Munich, Germany.
- TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), Boltzmannstr. 11, 85748, Garching, Germany.
| | - Michael Heinzinger
- Department of Informatics, Bioinformatics and Computational Biology - i12, TUM-Technical University of Munich, Boltzmannstr. 3, Garching, 85748, Munich, Germany
- TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), Boltzmannstr. 11, 85748, Garching, Germany
| | - Tobias Olenyi
- Department of Informatics, Bioinformatics and Computational Biology - i12, TUM-Technical University of Munich, Boltzmannstr. 3, Garching, 85748, Munich, Germany
- TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), Boltzmannstr. 11, 85748, Garching, Germany
| | - Christian Dallago
- Department of Informatics, Bioinformatics and Computational Biology - i12, TUM-Technical University of Munich, Boltzmannstr. 3, Garching, 85748, Munich, Germany
- TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), Boltzmannstr. 11, 85748, Garching, Germany
| | - Kyra Erckert
- Department of Informatics, Bioinformatics and Computational Biology - i12, TUM-Technical University of Munich, Boltzmannstr. 3, Garching, 85748, Munich, Germany
- TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), Boltzmannstr. 11, 85748, Garching, Germany
| | - Michael Bernhofer
- Department of Informatics, Bioinformatics and Computational Biology - i12, TUM-Technical University of Munich, Boltzmannstr. 3, Garching, 85748, Munich, Germany
- TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), Boltzmannstr. 11, 85748, Garching, Germany
| | - Dmitrii Nechaev
- Department of Informatics, Bioinformatics and Computational Biology - i12, TUM-Technical University of Munich, Boltzmannstr. 3, Garching, 85748, Munich, Germany
- TUM Graduate School, Center of Doctoral Studies in Informatics and its Applications (CeDoSIA), Boltzmannstr. 11, 85748, Garching, Germany
| | - Burkhard Rost
- Department of Informatics, Bioinformatics and Computational Biology - i12, TUM-Technical University of Munich, Boltzmannstr. 3, Garching, 85748, Munich, Germany
- Institute for Advanced Study (TUM-IAS), Lichtenbergstr. 2a, Garching, 85748, Munich, Germany
- TUM School of Life Sciences Weihenstephan (TUM-WZW), Alte Akademie 8, Freising, Germany
| |
Collapse
|
7
|
Littmann M, Heinzinger M, Dallago C, Weissenow K, Rost B. Protein embeddings and deep learning predict binding residues for various ligand classes. Sci Rep 2021; 11:23916. [PMID: 34903827 PMCID: PMC8668950 DOI: 10.1038/s41598-021-03431-4] [Citation(s) in RCA: 35] [Impact Index Per Article: 11.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/06/2021] [Accepted: 12/02/2021] [Indexed: 01/27/2023] Open
Abstract
One important aspect of protein function is the binding of proteins to ligands, including small molecules, metal ions, and macromolecules such as DNA or RNA. Despite decades of experimental progress many binding sites remain obscure. Here, we proposed bindEmbed21, a method predicting whether a protein residue binds to metal ions, nucleic acids, or small molecules. The Artificial Intelligence (AI)-based method exclusively uses embeddings from the Transformer-based protein Language Model (pLM) ProtT5 as input. Using only single sequences without creating multiple sequence alignments (MSAs), bindEmbed21DL outperformed MSA-based predictions. Combination with homology-based inference increased performance to F1 = 48 ± 3% (95% CI) and MCC = 0.46 ± 0.04 when merging all three ligand classes into one. All results were confirmed by three independent data sets. Focusing on very reliably predicted residues could complement experimental evidence: For the 25% most strongly predicted binding residues, at least 73% were correctly predicted even when ignoring the problem of missing experimental annotations. The new method bindEmbed21 is fast, simple, and broadly applicable-neither using structure nor MSAs. Thereby, it found binding residues in over 42% of all human proteins not otherwise implied in binding and predicted about 6% of all residues as binding to metal ions, nucleic acids, or small molecules.
Collapse
Affiliation(s)
- Maria Littmann
- Department of Informatics, Bioinformatics and Computational Biology, I12, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany.
| | - Michael Heinzinger
- Department of Informatics, Bioinformatics and Computational Biology, I12, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany
- TUM Graduate School, Center of Doctoral Studies in Informatics and Its Applications (CeDoSIA), Boltzmannstr. 11, 85748, Garching, Germany
| | - Christian Dallago
- Department of Informatics, Bioinformatics and Computational Biology, I12, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany
- TUM Graduate School, Center of Doctoral Studies in Informatics and Its Applications (CeDoSIA), Boltzmannstr. 11, 85748, Garching, Germany
| | - Konstantin Weissenow
- Department of Informatics, Bioinformatics and Computational Biology, I12, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany
- TUM Graduate School, Center of Doctoral Studies in Informatics and Its Applications (CeDoSIA), Boltzmannstr. 11, 85748, Garching, Germany
| | - Burkhard Rost
- Department of Informatics, Bioinformatics and Computational Biology, I12, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany
- Institute for Advanced Study (TUM-IAS), Lichtenbergstr. 2a, Garching, 85748, Munich, Germany
- TUM School of Life Sciences Weihenstephan (TUM-WZW), Alte Akademie 8, Freising, Germany
- Department of Biochemistry and Molecular Biophysics, Columbia University, 701 West, 168th Street, New York, NY, 10032, USA
| |
Collapse
|
8
|
Quadir F, Roy RS, Soltanikazemi E, Cheng J. DeepComplex: A Web Server of Predicting Protein Complex Structures by Deep Learning Inter-chain Contact Prediction and Distance-Based Modelling. Front Mol Biosci 2021; 8:716973. [PMID: 34497831 PMCID: PMC8419425 DOI: 10.3389/fmolb.2021.716973] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2021] [Accepted: 08/12/2021] [Indexed: 11/13/2022] Open
Abstract
Proteins interact to form complexes. Predicting the quaternary structure of protein complexes is useful for protein function analysis, protein engineering, and drug design. However, few user-friendly tools leveraging the latest deep learning technology for inter-chain contact prediction and the distance-based modelling to predict protein quaternary structures are available. To address this gap, we develop DeepComplex, a web server for predicting structures of dimeric protein complexes. It uses deep learning to predict inter-chain contacts in a homodimer or heterodimer. The predicted contacts are then used to construct a quaternary structure of the dimer by the distance-based modelling, which can be interactively viewed and analysed. The web server is freely accessible and requires no registration. It can be easily used by providing a job name and an email address along with the tertiary structure for one chain of a homodimer or two chains of a heterodimer. The output webpage provides the multiple sequence alignment, predicted inter-chain residue-residue contact map, and predicted quaternary structure of the dimer. DeepComplex web server is freely available at http://tulip.rnet.missouri.edu/deepcomplex/web_index.html.
Collapse
Affiliation(s)
| | | | | | - Jianlin Cheng
- Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO, United States
| |
Collapse
|
9
|
Rauer C, Sen N, Waman VP, Abbasian M, Orengo CA. Computational approaches to predict protein functional families and functional sites. Curr Opin Struct Biol 2021; 70:108-122. [PMID: 34225010 DOI: 10.1016/j.sbi.2021.05.012] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/29/2021] [Revised: 05/13/2021] [Accepted: 05/25/2021] [Indexed: 01/06/2023]
Abstract
Understanding the mechanisms of protein function is indispensable for many biological applications, such as protein engineering and drug design. However, experimental annotations are sparse, and therefore, theoretical strategies are needed to fill the gap. Here, we present the latest developments in building functional subclassifications of protein superfamilies and using evolutionary conservation to detect functional determinants, for example, catalytic-, binding- and specificity-determining residues important for delineating the functional families. We also briefly review other features exploited for functional site detection and new machine learning strategies for combining multiple features.
Collapse
Affiliation(s)
- Clemens Rauer
- Institute of Structural and Molecular Biology, University College London, London, WC1E 6BT, UK
| | - Neeladri Sen
- Institute of Structural and Molecular Biology, University College London, London, WC1E 6BT, UK
| | - Vaishali P Waman
- Institute of Structural and Molecular Biology, University College London, London, WC1E 6BT, UK
| | - Mahnaz Abbasian
- Institute of Structural and Molecular Biology, University College London, London, WC1E 6BT, UK
| | - Christine A Orengo
- Institute of Structural and Molecular Biology, University College London, London, WC1E 6BT, UK.
| |
Collapse
|
10
|
Sun J, Frishman D. Improved sequence-based prediction of interaction sites in α-helical transmembrane proteins by deep learning. Comput Struct Biotechnol J 2021; 19:1512-1530. [PMID: 33815689 PMCID: PMC7985279 DOI: 10.1016/j.csbj.2021.03.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2020] [Revised: 03/02/2021] [Accepted: 03/02/2021] [Indexed: 11/10/2022] Open
Abstract
Fast and accurate prediction of transmembrane protein interaction sites. First ever computational survey of interaction sites in membrane proteins. 10-30% of amino acid positions predicted to be involved in interactions.
Interactions between transmembrane (TM) proteins are fundamental for a wide spectrum of cellular functions, but precise molecular details of these interactions remain largely unknown due to the scarcity of experimentally determined three-dimensional complex structures. Computational techniques are therefore required for a large-scale annotation of interaction sites in TM proteins. Here, we present a novel deep-learning approach, DeepTMInter, for sequence-based prediction of interaction sites in α-helical TM proteins based on their topological, physiochemical, and evolutionary properties. Using a combination of ultra-deep residual neural networks with a stacked generalization ensemble technique DeepTMInter significantly outperforms existing methods, achieving the AUC/AUCPR values of 0.689/0.598. Across the main functional families of human transmembrane proteins, the percentage of amino acid sites predicted to be involved in interactions typically ranges between 10% and 25%, and up to 30% in ion channels. DeepTMInter is available as a standalone package at https://github.com/2003100127/deeptminter. The training and benchmarking datasets are available at https://data.mendeley.com/datasets/2t8kgwzp35.
Collapse
Affiliation(s)
- Jianfeng Sun
- Department of Bioinformatics, Wissenschaftzentrum Weihenstephan, Technical University of Munich, Maximus-von-Imhof-Forum 3, 85354 Freising, Germany
| | - Dmitrij Frishman
- Department of Bioinformatics, Wissenschaftzentrum Weihenstephan, Technical University of Munich, Maximus-von-Imhof-Forum 3, 85354 Freising, Germany
| |
Collapse
|
11
|
Zaucha J, Heinzinger M, Kulandaisamy A, Kataka E, Salvádor ÓL, Popov P, Rost B, Gromiha MM, Zhorov BS, Frishman D. Mutations in transmembrane proteins: diseases, evolutionary insights, prediction and comparison with globular proteins. Brief Bioinform 2020; 22:5872174. [PMID: 32672331 DOI: 10.1093/bib/bbaa132] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/14/2020] [Revised: 05/26/2020] [Accepted: 05/28/2020] [Indexed: 12/18/2022] Open
Abstract
Membrane proteins are unique in that they interact with lipid bilayers, making them indispensable for transporting molecules and relaying signals between and across cells. Due to the significance of the protein's functions, mutations often have profound effects on the fitness of the host. This is apparent both from experimental studies, which implicated numerous missense variants in diseases, as well as from evolutionary signals that allow elucidating the physicochemical constraints that intermembrane and aqueous environments bring. In this review, we report on the current state of knowledge acquired on missense variants (referred to as to single amino acid variants) affecting membrane proteins as well as the insights that can be extrapolated from data already available. This includes an overview of the annotations for membrane protein variants that have been collated within databases dedicated to the topic, bioinformatics approaches that leverage evolutionary information in order to shed light on previously uncharacterized membrane protein structures or interaction interfaces, tools for predicting the effects of mutations tailored specifically towards the characteristics of membrane proteins as well as two clinically relevant case studies explaining the implications of mutated membrane proteins in cancer and cardiomyopathy.
Collapse
Affiliation(s)
- Jan Zaucha
- Department of Bioinformatics of the TUM School of Life Sciences Weihenstephan in Freising, Germany
| | - Michael Heinzinger
- Department of Informatics, Bioinformatics and Computational Biology of the TUM Faculty of Informatics in Garching, Germany
| | - A Kulandaisamy
- Department of Biotechnology of the IIT Bhupat and Jyoti Mehta School of BioSciences in Madras, India
| | - Evans Kataka
- Department of Bioinformatics of the TUM School of Life Sciences Weihenstephan in Freising, Germany
| | - Óscar Llorian Salvádor
- Department of Informatics, Bioinformatics and Computational Biology of the TUM Faculty of Informatics in Garching, Germany
| | - Petr Popov
- Center for Computational and Data-Intensive Science and Engineering of the Skolkovo Institute of Science and Technology in Moscow, Russia
| | - Burkhard Rost
- Department of Informatics, Bioinformatics and Computational Biology at the TUM Faculty of Informatics in Garching, Germany
| | | | - Boris S Zhorov
- Department of Biochemistry and Biomedical Sciences, McMaster University in Hamilton, Canada
| | - Dmitrij Frishman
- Department of Bioinformatics at the TUM School of Life Sciences Weihenstephan in Freising, Germany
| |
Collapse
|
12
|
Zhang H, Saravanan KM, Lin J, Liao L, Ng JTY, Zhou J, Wei Y. DeepBindPoc: a deep learning method to rank ligand binding pockets using molecular vector representation. PeerJ 2020; 8:e8864. [PMID: 32292649 PMCID: PMC7144620 DOI: 10.7717/peerj.8864] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2019] [Accepted: 03/08/2020] [Indexed: 11/30/2022] Open
Abstract
Accurate identification of ligand-binding pockets in a protein is important for structure-based drug design. In recent years, several deep learning models were developed to learn important physical–chemical and spatial information to predict ligand-binding pockets in a protein. However, ranking the native ligand binding pockets from a pool of predicted pockets is still a hard task for computational molecular biologists using a single web-based tool. Hence, we believe, by using closer to real application data set as training and by providing ligand information, an enhanced model to identify accurate pockets can be obtained. In this article, we propose a new deep learning method called DeepBindPoc for identifying and ranking ligand-binding pockets in proteins. The model is built by using information about the binding pocket and associated ligand. We take advantage of the mol2vec tool to represent both the given ligand and pocket as vectors to construct a densely fully connected layer model. During the training, important features for pocket-ligand binding are automatically extracted and high-level information is preserved appropriately. DeepBindPoc demonstrated a strong complementary advantage for the detection of native-like pockets when combined with traditional popular methods, such as fpocket and P2Rank. The proposed method is extensively tested and validated with standard procedures on multiple datasets, including a dataset with G-protein Coupled receptors. The systematic testing and validation of our method suggest that DeepBindPoc is a valuable tool to rank near-native pockets for theoretically modeled protein with unknown experimental active site but have known ligand. The DeepBindPoc model described in this article is available at GitHub (https://github.com/haiping1010/DeepBindPoc) and the webserver is available at (http://cbblab.siat.ac.cn/DeepBindPoc/index.php).
Collapse
Affiliation(s)
- Haiping Zhang
- Center for High Performance Computing, Joint Engineering Research Center for Health Big Data Intelligent Analysis Technology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong Province, China
| | - Konda Mani Saravanan
- Center for High Performance Computing, Joint Engineering Research Center for Health Big Data Intelligent Analysis Technology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong Province, China
| | - Jinzhi Lin
- Center for High Performance Computing, Joint Engineering Research Center for Health Big Data Intelligent Analysis Technology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong Province, China
| | - Linbu Liao
- College of Software Technology, Zhejiang University, Zhejiang Province, Zhejiang, China
| | - Justin Tze-Yang Ng
- School of Biological Sciences, Nanyang Technological University, Singapore, Singapore
| | - Jiaxiu Zhou
- Shenzhen Children's Hospital, Shenzhen, Guangdong Province, China
| | - Yanjie Wei
- Center for High Performance Computing, Joint Engineering Research Center for Health Big Data Intelligent Analysis Technology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong Province, China
| |
Collapse
|
13
|
Qin W, Yang F, Wang C. Chemoproteomic profiling of protein-metabolite interactions. Curr Opin Chem Biol 2019; 54:28-36. [PMID: 31812894 DOI: 10.1016/j.cbpa.2019.11.003] [Citation(s) in RCA: 16] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2019] [Revised: 10/23/2019] [Accepted: 11/03/2019] [Indexed: 12/29/2022]
Abstract
Small molecule metabolites play important roles in regulating protein functions, which are acted through either covalent non-enzymatic post-translational modifications or non-covalent binding interactions. Chemical proteomic strategies can help delineate global landscapes of cellular protein-metabolite interactions and provide molecular insights about their mechanisms of action. In this review, we summarized the recent progress in developments and applications of chemoproteomic strategies to profile protein-metabolite interactions.
Collapse
Affiliation(s)
- Wei Qin
- Synthetic and Functional Biomolecules Center, Peking University, Beijing, China; Beijing National Laboratory for Molecular Sciences, Peking University, Beijing, China; Key Laboratory of Bioorganic Chemistry and Molecular Engineering of Ministry of Education, Peking University, Beijing, China; Peking-Tsinghua Center for Life Sciences, Peking University, Beijing, China
| | - Fan Yang
- Synthetic and Functional Biomolecules Center, Peking University, Beijing, China; Beijing National Laboratory for Molecular Sciences, Peking University, Beijing, China; Key Laboratory of Bioorganic Chemistry and Molecular Engineering of Ministry of Education, Peking University, Beijing, China; College of Chemistry and Molecular Engineering, Peking University, Beijing, China
| | - Chu Wang
- Synthetic and Functional Biomolecules Center, Peking University, Beijing, China; Beijing National Laboratory for Molecular Sciences, Peking University, Beijing, China; Key Laboratory of Bioorganic Chemistry and Molecular Engineering of Ministry of Education, Peking University, Beijing, China; Peking-Tsinghua Center for Life Sciences, Peking University, Beijing, China; College of Chemistry and Molecular Engineering, Peking University, Beijing, China.
| |
Collapse
|
14
|
Jiang M, Li Z, Bian Y, Wei Z. A novel protein descriptor for the prediction of drug binding sites. BMC Bioinformatics 2019; 20:478. [PMID: 31533611 PMCID: PMC6749706 DOI: 10.1186/s12859-019-3058-0] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2019] [Accepted: 08/27/2019] [Indexed: 12/23/2022] Open
Abstract
Background Binding sites are the pockets of proteins that can bind drugs; the discovery of these pockets is a critical step in drug design. With the help of computers, protein pockets prediction can save manpower and financial resources. Results In this paper, a novel protein descriptor for the prediction of binding sites is proposed. Information on non-bonded interactions in the three-dimensional structure of a protein is captured by a combination of geometry-based and energy-based methods. Moreover, due to the rapid development of deep learning, all binding features are extracted to generate three-dimensional grids that are fed into a convolution neural network. Two datasets were introduced into the experiment. The sc-PDB dataset was used for descriptor extraction and binding site prediction, and the PDBbind dataset was used only for testing and verification of the generalization of the method. The comparison with previous methods shows that the proposed descriptor is effective in predicting the binding sites. Conclusions A new protein descriptor is proposed for the prediction of the drug binding sites of proteins. This method combines the three-dimensional structure of a protein and non-bonded interactions with small molecules to involve important factors influencing the formation of binding site. Analysis of the experiments indicates that the descriptor is robust for site prediction. Electronic supplementary material The online version of this article (10.1186/s12859-019-3058-0) contains supplementary material, which is available to authorized users.
Collapse
Affiliation(s)
- Mingjian Jiang
- Department of Computer Science and Technology, Ocean University of China, 238 Songling Road, Qingdao, 266100, China
| | - Zhen Li
- Department of Computer Science and Technology, Ocean University of China, 238 Songling Road, Qingdao, 266100, China.,Pilot National Laboratory for Marine Science and Technology (Qingdao), 1 Wenhai Road Aoshanwei, Qingdao, 266237, China
| | - Yujie Bian
- Department of Computer Science and Technology, Ocean University of China, 238 Songling Road, Qingdao, 266100, China
| | - Zhiqiang Wei
- Department of Computer Science and Technology, Ocean University of China, 238 Songling Road, Qingdao, 266100, China. .,Pilot National Laboratory for Marine Science and Technology (Qingdao), 1 Wenhai Road Aoshanwei, Qingdao, 266237, China.
| |
Collapse
|
15
|
Scheibenreif L, Littmann M, Orengo C, Rost B. FunFam protein families improve residue level molecular function prediction. BMC Bioinformatics 2019; 20:400. [PMID: 31319797 PMCID: PMC6639920 DOI: 10.1186/s12859-019-2988-x] [Citation(s) in RCA: 17] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2019] [Accepted: 07/09/2019] [Indexed: 01/16/2023] Open
Abstract
BACKGROUND The CATH database provides a hierarchical classification of protein domain structures including a sub-classification of superfamilies into functional families (FunFams). We analyzed the similarity of binding site annotations in these FunFams and incorporated FunFams into the prediction of protein binding residues. RESULTS FunFam members agreed, on average, in 36.9 ± 0.6% of their binding residue annotations. This constituted a 6.7-fold increase over randomly grouped proteins and a 1.2-fold increase (1.1-fold on the same dataset) over proteins with the same enzymatic function (identical Enzyme Commission, EC, number). Mapping de novo binding residue prediction methods (BindPredict-CCS, BindPredict-CC) onto FunFam resulted in consensus predictions for those residues that were aligned and predicted alike (binding/non-binding) within a FunFam. This simple consensus increased the F1-score (for binding) 1.5-fold over the original prediction method. Variation of the threshold for how many proteins in the consensus prediction had to agree provided a convenient control of accuracy/precision and coverage/recall, e.g. reaching a precision as high as 60.8 ± 0.4% for a stringent threshold. CONCLUSIONS The FunFams outperformed even the carefully curated EC numbers in terms of agreement of binding site residues. Additionally, we assume that our proof-of-principle through the prediction of protein binding residues will be relevant for many other solutions profiting from FunFams to infer functional information at the residue level.
Collapse
Affiliation(s)
- Linus Scheibenreif
- Department of Informatics, Bioinformatics & Computational Biology - i12, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany.
| | - Maria Littmann
- Department of Informatics, Bioinformatics & Computational Biology - i12, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany.
| | - Christine Orengo
- Department of Structural and Molecular Biology, University College London, London, WC1E 6BT, UK
| | - Burkhard Rost
- Department of Informatics, Bioinformatics & Computational Biology - i12, TUM (Technical University of Munich), Boltzmannstr. 3, 85748, Garching/Munich, Germany
- Institute for Advanced Study (TUM-IAS), Lichtenbergstr. 2a, 85748, Garching/Munich, Germany
- TUM School of Life Sciences Weihenstephan (WZW), Alte Akademie 8, Freising, Germany
- Department of Biochemistry and Molecular Biophysics & New York Consortium on Membrane Protein Structure (NYCOMPS), Columbia University, 701 West, 168th Street, New York, NY 10032, USA
| |
Collapse
|