Alpha shape and Delaunay triangulation in studies of protein-related interactions

Repurposing FDA-Approved Drugs Against Potential Drug Targets Involved in Brain Inflammation Contributing to Alzheimer's Disease

Alzheimer's disease is a neurodegenerative disease that continues to have a rising number of cases. While extensive research has been conducted in the last few decades, only a few drugs have been approved by the FDA for treatment, and even fewer aim to be curative rather than manage symptoms. There remains an urgent need for understanding disease pathogenesis, as well as identifying new targets for further drug discovery. Alzheimer's disease (AD) is known to stem from a build-up of amyloid beta (Aβ) plaques as well as tangles of tau proteins. Furthermore, inflammation in the brain is known to arise from the degeneration of tissue and the build-up of insoluble material. Therefore, there is a potential link between the pathology of AD and inflammation in the brain, especially as the disease progresses to later stages where neuronal death and degeneration levels are higher. Proteins that are relevant to both brain inflammation and AD thus make ideal potential targets for therapeutics; however, the proteins need to be evaluated to determine which targets would be ideal for potential drug therapeutic treatments, or 'druggable'. Druggability analysis was conducted using two structure-based methods (i.e., Drug-Like Density analysis and SiteMap), as well as a sequence-based approach, SPIDER. The most druggable targets were then evaluated using single-nuclei sequencing data for their clinical relevance to inflammation in AD. For each of the top five targets, small molecule docking was used to evaluate which FDA approved drugs were able to bind with the chosen proteins. The top targets included DRD2 (inhibits adenylyl cyclase activity), C9 (binds with C5B8 to form the membrane attack complex), C4b (binds with C2a to form C3 convertase), C5AR1 (GPCR that binds C5a), and GABA-A-R (GPCR involved in inhibiting neurotransmission). Each target had multiple potential inhibitors from the FDA-approved drug list with decent binding infinities. Among these inhibitors, two drugs were found as top inhibitors for more than one protein target. They are C15H14N2O2 and v316 (Paracetamol), used to treat pain/inflammation originally for cataracts and relieve headaches/fever, respectively. These results provide the groundwork for further experimental investigation or clinical trials.

Improving Predictive Efficacy for Drug Resistance in Novel HIV-1 Protease Inhibitors through Transfer Learning Mechanisms

The human immunodeficiency virus presents a significant global health challenge due to its rapid mutation and the development of resistance mechanisms against antiretroviral drugs. Recent studies demonstrate the impressive performance of machine learning (ML) and deep learning (DL) models in predicting the drug resistance profile of specific FDA-approved inhibitors. However, generalizing ML and DL models to learn not only from isolates but also from inhibitor representations remains challenging for HIV-1 infection. We propose a novel drug-isolate-fold change (DIF) model framework that aims to predict drug resistance score directly from the protein sequence and inhibitor representation. Various ML and DL models, inhibitor representations, and protein representations were analyzed through realistic validation mechanisms. To enhance the molecular learning capacity of DIF models, we employ a transfer learning approach by pretraining a graph neural network (GNN) model for activity prediction on a data set of 4855 HIV-1 protease inhibitors (PIs). By performing various realistic validation strategies on internal and external genotype-phenotype data sets, we statistically show that the learned representations of inhibitors improve the predictive ability of DIF-based ML and DL models. We achieved an accuracy of 0.802, AUROC of 0.874, and r of 0.727 for the unseen external PIs. By comparing the DIF-based models with a null model consisting of isolate-fold change (IF) architecture, it is observed that the DIF models significantly benefit from molecular representations. Combined results from various testing strategies and statistical tests confirm the effectiveness of DIF models in testing novel PIs for drug resistance in the presence of an isolate.

AI in drug discovery and its clinical relevance

The COVID-19 pandemic has emphasized the need for novel drug discovery process. However, the journey from conceptualizing a drug to its eventual implementation in clinical settings is a long, complex, and expensive process, with many potential points of failure. Over the past decade, a vast growth in medical information has coincided with advances in computational hardware (cloud computing, GPUs, and TPUs) and the rise of deep learning. Medical data generated from large molecular screening profiles, personal health or pathology records, and public health organizations could benefit from analysis by Artificial Intelligence (AI) approaches to speed up and prevent failures in the drug discovery pipeline. We present applications of AI at various stages of drug discovery pipelines, including the inherently computational approaches of de novo design and prediction of a drug's likely properties. Open-source databases and AI-based software tools that facilitate drug design are discussed along with their associated problems of molecule representation, data collection, complexity, labeling, and disparities among labels. How contemporary AI methods, such as graph neural networks, reinforcement learning, and generated models, along with structure-based methods, (i.e., molecular dynamics simulations and molecular docking) can contribute to drug discovery applications and analysis of drug responses is also explored. Finally, recent developments and investments in AI-based start-up companies for biotechnology, drug design and their current progress, hopes and promotions are discussed in this article.

PointSite: A Point Cloud Segmentation Tool for Identification of Protein Ligand Binding Atoms

Accurate identification of ligand binding sites (LBS) on a protein structure is critical for understanding protein function and designing structure-based drugs. As the previous pocket-centric methods are usually based on the investigation of pseudo-surface-points outside the protein structure, they cannot fully take advantage of the local connectivity of atoms within the protein, as well as the global 3D geometrical information from all the protein atoms. In this paper, we propose a novel point clouds segmentation method, PointSite, for accurate identification of protein ligand binding atoms, which performs protein LBS identification at the atom-level in a protein-centric manner. Specifically, we first transfer the original 3D protein structure to point clouds and then conduct segmentation through Submanifold Sparse Convolution based U-Net. With the fine-grained atom-level binding atoms representation and enhanced feature learning, PointSite can outperform previous methods in atom Intersection over Union (atom-IoU) by a large margin. Furthermore, our segmented binding atoms, that is, atoms with high probability predicted by our model can work as a filter on predictions achieved by previous pocket-centric approaches, which significantly decreases the false-positive of LBS candidates. Besides, we further directly extend PointSite trained on bound proteins for LBS identification on unbound proteins, which demonstrates the superior generalization capacity of PointSite. Through cascaded filter and reranking aided by the segmented atoms, state-of-the-art performance can be achieved over various canonical benchmarks, CAMEO hard targets, and unbound proteins in terms of the commonly used DCA criteria.

Graph representation learning for structural proteomics

The field of structural proteomics, which is focused on studying the structure-function relationship of proteins and protein complexes, is experiencing rapid growth. Since the early 2000s, structural databases such as the Protein Data Bank are storing increasing amounts of protein structural data, in addition to modeled structures becoming increasingly available. This, combined with the recent advances in graph-based machine-learning models, enables the use of protein structural data in predictive models, with the goal of creating tools that will advance our understanding of protein function. Similar to using graph learning tools to molecular graphs, which currently undergo rapid development, there is also an increasing trend in using graph learning approaches on protein structures. In this short review paper, we survey studies that use graph learning techniques on proteins, and examine their successes and shortcomings, while also discussing future directions.

2D alpha-shapes to quantify retinal microvasculature morphology and their application to proliferative diabetic retinopathy characterisation in fundus photographs

The use of 2D alpha-shapes (α-shapes) to quantify morphological features of the retinal microvasculature could lead to imaging biomarkers for proliferative diabetic retinopathy (PDR). We tested our approach using the MESSIDOR dataset that consists of colour fundus photographs from 547 healthy individuals, 149 with mild diabetic retinopathy (DR), 239 with moderate DR, 199 pre-PDR and 53 PDR. The skeleton (centrelines) of the automatically segmented retinal vasculature was represented as an α-shape and the proposed parameters, complexity (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${Op\alpha }_{min}$$\end{document}Opαmin), spread (OpA), global shape (VS) and presence of abnormal angiogenesis (Grad_α) were computed. In cross-sectional analysis, individuals with PDR had a lower \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${Op\alpha }_{min}$$\end{document}Opαmin, OpA and Grad_α indicating a vasculature that is more complex, less spread (i.e. dense) and the presence of numerous small vessels. The results show that α-shape parameters characterise vascular abnormalities predictive of PDR (AUC 0.73; 95% CI [0.73 0.74]) and have therefore potential to reveal changes in retinal microvascular morphology.

Understanding crown shyness from a 3-D perspective

BACKGROUND AND AIMS

Crown shyness describes the phenomenon whereby tree crowns avoid growing into each other, producing a puzzle-like pattern of complementary tree crowns in the canopy. Previous studies found that tree slenderness plays a role in the development of crown shyness. Attempts to quantify crown shyness have largely been confined to 2-D approaches. This study aimed to expand the current set of metrics for crown shyness by quantifying the characteristic of 3-D surface complementarity between trees displaying crown shyness, using LiDAR-derived tree point clouds. Subsequently, the relationship between crown surface complementarity and slenderness of trees was assessed.

METHODS

Fourteen trees were scanned using a laser scanning device. Individual tree points clouds were extracted semi-automatically and manually corrected where needed. A metric that quantifies the surface complementarity (Sc) of a pair of protein molecules is applied to point clouds of pairs of adjacent trees. Then 3-D tree crown surfaces were generated from point clouds by computing their α shapes.

KEY RESULTS

Tree pairs that were visually determined to have overlapping crowns scored significantly lower Sc values than pairs that did not overlap (n = 14, P < 0.01). Furthermore, average slenderness of pairs of trees correlated positively with their Sc score (R2 = 0.484, P < 0.01), showing agreement with previous studies on crown shyness.

CONCLUSIONS

The characteristic of crown surface complementarity present in trees displaying crown shyness was succesfully quantified using a 3-D surface complementarity metric adopted from molecular biology. Crown surface complementarity showed a positive relationship to tree slenderness, similar to other metrics used for measuring crown shyness. The 3-D metric developed in this study revealed how trees adapt the shape of their crowns to those of adjacent trees and how this is linked to the slenderness of the trees.

High Throughput Virtual Screening and Molecular Dynamics Simulation for Identifying a Putative Inhibitor of Bacterial CTX-M-15

Background: Multidrug resistant bacteria are a major therapeutic challenge. CTX-M-type enzymes are an important group of class A extended-spectrum β-lactamases (ESBLs). ESBLs are the enzymes that arm bacterial pathogens with drug resistance to an array of antibiotics, notably the advanced-generation cephalosporins. The current need for an effective CTX-M-inhibitor is high. Objective: The aim of the current study was to identify a promising anti-CTX-M-15 ligand whose chemical skeleton could be used as a ‘seed-molecule’ for future drug design against resistant bacteria. Methods: Virtual screening of 5,000,000 test molecules was performed by ‘MCULE Drug Discovery Platform’. ‘ADME analyses’ was performed by ‘SWISS ADME’. TOXICITY CHECKER of MCULE was employed to predict the safety profile of the test molecules. The complex of the ‘Top inhibitor’ with the ‘bacterial CTX-M-15 enzyme’ was subjected to 102.25 ns molecular dynamics simulation. This simulation was run for 3 days on a HP ZR30w workstation. Trajectory analyses were performed by employing the macro ‘md_analyze.mcr’ of YASARA STRUCTURE version 20.12.24.W.64 using AMBER14 force field. YANACONDA macro language was used for complex tasks. Figures, including RMSD and RMSF plots, were generated. Snapshots were acquired after every 250 ps. Finally, two short videos of ‘41 s’ and ‘1 min and 22 s’ duration were recorded. Results: 5-Amino-1-(2H-[1,2,4]triazino[5,6-b]indol-3-yl)-1H-pyrazole-4-carbonitrile, denoted by the MCULE-1352214421-0-56, displayed the most efficient binding with bacterial CTX-M-15 enzyme. This screened molecule significantly interacted with CTX-M-15 via 13 amino acid residues. Notably, nine amino acid residues were found common to avibactam binding (the reference ligand). Trajectory analysis yielded 410 snapshots. The RMSD plot revealed that around 26 ns, equilibrium was achieved and, thereafter, the complex remained reasonably stable. After a duration of 26 ns and onwards until 102.25 ns, the backbone RMSD fluctuations were found to be confined within a range of 0.8–1.4 Å. Conclusion: 5-Amino-1-(2H-[1,2,4]triazino[5,6-b]indol-3-yl)-1H-pyrazole-4-carbonitrile could emerge as a promising seed molecule for CTX-M-15-inhibitor design. It satisfied ADMET features and displayed encouraging ‘simulation results’. Advanced plots obtained by trajectory analyses predicted the stability of the proposed protein-ligand complex. ‘Hands on’ wet laboratory validation is warranted.

Characterizing and Predicting Protein Hinges for Mechanistic Insight

The functioning of proteins requires highly specific dynamics, which depend critically on the details of how amino acids are packed. Hinge motions are the most common type of large motion, typified by the opening and closing of enzymes around their substrates. The packing and geometries of residues are characterized here by graph theory. This characterization is sufficient to enable reliable hinge predictions from a single static structure, and notably, this can be from either the open or the closed form of a structure. This new method to identify hinges within protein structures is called PACKMAN. The predicted hinges are validated by using permutation tests on B-factors. Hinge prediction results are compared against lists of manually curated hinge residues, and the results suggest that PACKMAN is robust enough to reproduce the known conformational changes and is able to predict hinge regions equally well from either the open or the closed forms of a protein. A group of 167 protein pairs with open and closed structures has been investigated Examples are shown for several additional proteins, including Zika virus nonstructured (NS) proteins where there are 6 hinge regions in the NS5 protein, 5 hinge regions in the NS2B bound in the NS3 protease complex and 5 hinges in the NS3- helicase protein. Results obtained from this method can be important for generating conformational ensembles of protein targets for drug design. PACKMAN is freely accessible at (https://PACKMAN.bb.iastate.edu/).

A Novel Geometry-Based Approach to Infer Protein Interface Similarity

The protein interface is key to understand protein function, providing a vital insight on how proteins interact with each other and with other molecules. Over the years, many computational methods to compare protein structures were developed, yet evaluating interface similarity remains a very difficult task. Here, we present PatchBag – a geometry based method for efficient comparison of protein surfaces and interfaces. PatchBag is a Bag-Of-Words approach, which represents complex objects as vectors, enabling to search interface similarity in a highly efficient manner. Using a novel framework for evaluating interface similarity, we show that PatchBag performance is comparable to state-of-the-art alignment-based structural comparison methods. The great advantage of PatchBag is that it does not rely on sequence or fold information, thus enabling to detect similarities between interfaces in unrelated proteins. We propose that PatchBag can contribute to reveal novel evolutionary and functional relationships between protein interfaces.

A roadmap for the computation of persistent homology

Persistent homology (PH) is a method used in topological data analysis (TDA) to study qualitative features of data that persist across multiple scales. It is robust to perturbations of input data, independent of dimensions and coordinates, and provides a compact representation of the qualitative features of the input. The computation of PH is an open area with numerous important and fascinating challenges. The field of PH computation is evolving rapidly, and new algorithms and software implementations are being updated and released at a rapid pace. The purposes of our article are to (1) introduce theory and computational methods for PH to a broad range of computational scientists and (2) provide benchmarks of state-of-the-art implementations for the computation of PH. We give a friendly introduction to PH, navigate the pipeline for the computation of PH with an eye towards applications, and use a range of synthetic and real-world data sets to evaluate currently available open-source implementations for the computation of PH. Based on our benchmarking, we indicate which algorithms and implementations are best suited to different types of data sets. In an accompanying tutorial, we provide guidelines for the computation of PH. We make publicly available all scripts that we wrote for the tutorial, and we make available the processed version of the data sets used in the benchmarking.

ELECTRONIC SUPPLEMENTARY MATERIAL

The online version of this article (doi:10.1140/epjds/s13688-017-0109-5) contains supplementary material.

Dissecting the roles of local packing density and longer-range effects in protein sequence evolution

What are the structural determinants of protein sequence evolution? A number of site-specific structural characteristics have been proposed, most of which are broadly related to either the density of contacts or the solvent accessibility of individual residues. Most importantly, there has been disagreement in the literature over the relative importance of solvent accessibility and local packing density for explaining site-specific sequence variability in proteins. We show that this discussion has been confounded by the definition of local packing density. The most commonly used measures of local packing, such as contact number and the weighted contact number, represent the combined effects of local packing density and longer-range effects. As an alternative, we propose a truly local measure of packing density around a single residue, based on the Voronoi cell volume. We show that the Voronoi cell volume, when calculated relative to the geometric center of amino-acid side chains, behaves nearly identically to the relative solvent accessibility, and each individually can explain, on average, approximately 34% of the site-specific variation in evolutionary rate in a data set of 209 enzymes. An additional 10% of variation can be explained by nonlocal effects that are captured in the weighted contact number. Consequently, evolutionary variation at a site is determined by the combined effects of the immediate amino-acid neighbors of that site and effects mediated by more distant amino acids. We conclude that instead of contrasting solvent accessibility and local packing density, future research should emphasize on the relative importance of immediate contacts and longer-range effects on evolutionary variation. Proteins 2016; 84:841-854. © 2016 Wiley Periodicals, Inc.

Alpha shape theory for 3D visualization and volumetric measurement of brain tumor progression using magnetic resonance images

Resection of brain tumors is a tricky task in surgery due to its direct influence on the patients' survival rate. Determining the tumor resection extent for its complete information via-à-vis volume and dimensions in pre- and post-operative Magnetic Resonance Images (MRI) requires accurate estimation and comparison. The active contour segmentation technique is used to segment brain tumors on pre-operative MR images using self-developed software. Tumor volume is acquired from its contours via alpha shape theory. The graphical user interface is developed for rendering, visualizing and estimating the volume of a brain tumor. Internet Brain Segmentation Repository dataset (IBSR) is employed to analyze and determine the repeatability and reproducibility of tumor volume. Accuracy of the method is validated by comparing the estimated volume using the proposed method with that of gold-standard. Segmentation by active contour technique is found to be capable of detecting the brain tumor boundaries. Furthermore, the volume description and visualization enable an interactive examination of tumor tissue and its surrounding. Admirable features of our results demonstrate that alpha shape theory in comparison to other existing standard methods is superior for precise volumetric measurement of tumor.