Comparison Study of Computational Prediction Tools for Drug-Target Binding Affinities

Binding affinity prediction for binary drug-target interactions using semi-supervised transfer learning

In the field of drug-target interactions prediction, the majority of approaches formulated the problem as a simple binary classification task. These methods used binary drug-target interaction datasets to train their models. The prediction of drug-target interactions is inherently a regression problem and these interactions would be identified according to the binding affinity between drugs and targets. This paper deals the binary drug-target interactions and tries to identify the binary interactions based on the binding strength of a drug and its target. To this end, we propose a semi-supervised transfer learning approach to predict the binding affinity in a continuous spectrum for binary interactions. Due to the lack of training data with continuous binding affinity in the target domain, the proposed method makes use of the information available in other domains (i.e. source domain), via the transfer learning approach. The general framework of our algorithm is based on an objective function, which considers the performance in both source and target domains as well as the unlabeled data in the target domain via a regularization term. To optimize this objective function, we make use of a gradient boosting machine which constructs the final model. To assess the performance of the proposed method, we have used some benchmark datasets with binary interactions for four classes of human proteins. Our algorithm identifies interactions in a more realistic situation. According to the experimental results, our regression model performs better than the state-of-the-art methods in some procedures.

Binding characteristics of staphylococcal protein A and streptococcal protein G for fragment crystallizable portion of human immunoglobulin G

In the wide array of physiological processes, protein-protein interactions and their binding are the most basal activities for achieving adequate biological metabolism. Among the studies on binding proteins, the examination of interactions between immunoglobulin G (IgG) and natural immunoglobulin-binding ligands, such as staphylococcal protein A (spA) and streptococcal protein G (spG), is essential in the development of pharmaceutical science, biotechnology, and affinity chromatography. The widespread utilization of IgG-spA/spG binding characteristics has allowed researchers to investigate these molecular interactions. However, the detailed binding strength of each ligand and the corresponding binding mechanisms have yet to be fully investigated. In this study, the authors analyzed the binding strengths of IgG-spA and IgG-spG complexes and identified the mechanisms enabling these bindings using molecular dynamics simulation, steered molecular dynamics, and advanced Poisson-Boltzmann Solver simulations. Based on the presented data, the binding strength of the spA ligand was found to significantly exceed that of the spG ligand. To find out which non-covalent interactions or amino acid sites have a dominant role in the tight binding of these ligands, further detailed analyses of electrostatic interactions, hydrophobic bonding, and binding free energies have been performed. In investigating their binding affinity, a relatively independent and different unbinding mechanism was found in each ligand. These distinctly different mechanisms were observed to be highly correlated to the protein secondary and tertiary structures of spA and spG ligands, as explicated from the perspective of hydrogen bonding.

Artificial Intelligence in Aptamer-Target Binding Prediction

Aptamers are short single-stranded DNA, RNA, or synthetic Xeno nucleic acids (XNA) molecules that can interact with corresponding targets with high affinity. Owing to their unique features, including low cost of production, easy chemical modification, high thermal stability, reproducibility, as well as low levels of immunogenicity and toxicity, aptamers can be used as an alternative to antibodies in diagnostics and therapeutics. Systematic evolution of ligands by exponential enrichment (SELEX), an experimental approach for aptamer screening, allows the selection and identification of in vitro aptamers with high affinity and specificity. However, the SELEX process is time consuming and characterization of the representative aptamer candidates from SELEX is rather laborious. Artificial intelligence (AI) could help to rapidly identify the potential aptamer candidates from a vast number of sequences. This review discusses the advancements of AI pipelines/methods, including structure-based and machine/deep learning-based methods, for predicting the binding ability of aptamers to targets. Structure-based methods are the most used in computer-aided drug design. For this part, we review the secondary and tertiary structure prediction methods for aptamers, molecular docking, as well as molecular dynamic simulation methods for aptamer-target binding. We also performed analysis to compare the accuracy of different secondary and tertiary structure prediction methods for aptamers. On the other hand, advanced machine-/deep-learning models have witnessed successes in predicting the binding abilities between targets and ligands in drug discovery and thus potentially offer a robust and accurate approach to predict the binding between aptamers and targets. The research utilizing machine-/deep-learning techniques for prediction of aptamer-target binding is limited currently. Therefore, perspectives for models, algorithms, and implementation strategies of machine/deep learning-based methods are discussed. This review could facilitate the development and application of high-throughput and less laborious in silico methods in aptamer selection and characterization.

A Modelling Framework for Embedding-based Predictions for Compound-Viral Protein Activity

Motivation

A global effort is underway to identify compounds for the treatment of COVID-19. Since de novo compound design is an extremely long, time-consuming, and expensive process, efforts are underway to discover existing compounds that can be repurposed for COVID-19 and new viral diseases.

Model

We propose a machine learning representation framework that uses deep learning induced vector embeddings of compounds and viral proteins as features to predict compound-viral protein activity. The prediction model in-turn uses a consensus framework to rank approved compounds against viral proteins of interest.

Results

Our consensus framework achieves a highmean Pearson correlation of 0.916, mean R2 of 0.840 and a low mean squared error of 0.313 for the task of compound-viral protein activity prediction on an independent test set. As a use case, we identify a ranked list of 47 compounds common to three main proteins of SARS-COV-2 virus (PL-PRO, 3CL-PRO and Spike protein) as potential targets including 21 antivirals, 15 anticancer, 5 antibiotics and 6 other investigationalhuman compounds.We performadditional molecular docking simulations to demonstrate thatmajority of these compounds have low binding energies and thus high binding affinity with the potential to be effective against the SARS-COV-2 virus.

Availability

All the source code and data is available at: https://github.com/raghvendra5688/Drug-Repurposing and https://dx.doi.org/10.17632/8rrwnbcgmx.3. We also implemented a web-server at: https://machinelearning-protein.qcri.org/index.html.

Supplementary information

Supplementary data are available at Bioinformatics online.

Application and evaluation of knowledge graph embeddings in biomedical data

Linked data and bio-ontologies enabling knowledge representation, standardization, and dissemination are an integral part of developing biological and biomedical databases. That is, linked data and bio-ontologies are employed in databases to maintain data integrity, data organization, and to empower search capabilities. However, linked data and bio-ontologies are more recently being used to represent information as multi-relational heterogeneous graphs, "knowledge graphs". The reason being, entities and relations in the knowledge graph can be represented as embedding vectors in semantic space, and these embedding vectors have been used to predict relationships between entities. Such knowledge graph embedding methods provide a practical approach to data analytics and increase chances of building machine learning models with high prediction accuracy that can enhance decision support systems. Here, we present a comparative assessment and a standard benchmark for knowledge graph-based representation learning methods focused on the link prediction task for biological relations. We systematically investigated and compared state-of-the-art embedding methods based on the design settings used for training and evaluation. We further tested various strategies aimed at controlling the amount of information related to each relation in the knowledge graph and its effects on the final performance. We also assessed the quality of the knowledge graph features through clustering and visualization and employed several evaluation metrics to examine their uses and differences. Based on this systematic comparison and assessments, we identify and discuss the limitations of knowledge graph-based representation learning methods and suggest some guidelines for the development of more improved methods.

Artificial intelligence in drug discovery and development

Artificial intelligence-integrated drug discovery and development has accelerated the growth of the pharmaceutical sector, leading to a revolutionary change in the pharma industry. Here, we discuss areas of integration, tools, and techniques utilized in enforcing AI, ongoing challenges, and ways to overcome them.

Explainable Deep Relational Networks for Predicting Compound-Protein Affinities and Contacts

Predicting compound-protein affinity is beneficial for accelerating drug discovery. Doing so without the often-unavailable structure data is gaining interest. However, recent progress in structure-free affinity prediction, made by machine learning, focuses on accuracy but leaves much to be desired for interpretability. Defining intermolecular contacts underlying affinities as a vehicle for interpretability; our large-scale interpretability assessment finds previously used attention mechanisms inadequate. We thus formulate a hierarchical multiobjective learning problem, where predicted contacts form the basis for predicted affinities. We solve the problem by embedding protein sequences (by hierarchical recurrent neural networks) and compound graphs (by graph neural networks) with joint attentions between protein residues and compound atoms. We further introduce three methodological advances to enhance interpretability: (1) structure-aware regularization of attentions using protein sequence-predicted solvent exposure and residue-residue contact maps; (2) supervision of attentions using known intermolecular contacts in training data; and (3) an intrinsically explainable architecture where atomic-level contacts or "relations" lead to molecular-level affinity prediction. The first two and all three advances result in DeepAffinity+ and DeepRelations, respectively. Our methods show generalizability in affinity prediction for molecules that are new and dissimilar to training examples. Moreover, they show superior interpretability compared to state-of-the-art interpretable methods: with similar or better affinity prediction, they boost the AUPRC of contact prediction by around 33-, 35-, 10-, and 9-fold for the default test, new-compound, new-protein, and both-new sets, respectively. We further demonstrate their potential utilities in contact-assisted docking, structure-free binding site prediction, and structure-activity relationship studies without docking. Our study represents the first model development and systematic model assessment dedicated to interpretable machine learning for structure-free compound-protein affinity prediction.

Genome-Wide Prediction of Complex Traits in Two Outcrossing Plant Species Through Deep Learning and Bayesian Regularized Neural Network

Genomic selection models were investigated to predict several complex traits in breeding populations of Zea mays L. and Eucalyptus globulus Labill. For this, the following methods of Machine Learning (ML) were implemented: (i) Deep Learning (DL) and (ii) Bayesian Regularized Neural Network (BRNN) both in combination with different hyperparameters. These ML methods were also compared with Genomic Best Linear Unbiased Prediction (GBLUP) and different Bayesian regression models [Bayes A, Bayes B, Bayes Cπ, Bayesian Ridge Regression, Bayesian LASSO, and Reproducing Kernel Hilbert Space (RKHS)]. DL models, using Rectified Linear Units (as the activation function), had higher predictive ability values, which varied from 0.27 (pilodyn penetration of 6 years old eucalypt trees) to 0.78 (flowering-related traits of maize). Moreover, the larger mini-batch size (100%) had a significantly higher predictive ability for wood-related traits than the smaller mini-batch size (10%). On the other hand, in the BRNN method, the architectures of one and two layers that used only the pureline function showed better results of prediction, with values ranging from 0.21 (pilodyn penetration) to 0.71 (flowering traits). A significant increase in the prediction ability was observed for DL in comparison with other methods of genomic prediction (Bayesian alphabet models, GBLUP, RKHS, and BRNN). Another important finding was the usefulness of DL models (through an iterative algorithm) as an SNP detection strategy for genome-wide association studies. The results of this study confirm the importance of DL for genome-wide analyses and crop/tree improvement strategies, which holds promise for accelerating breeding progress.

The role of NMR in leveraging dynamics and entropy in drug design

Nuclear magnetic resonance (NMR) spectroscopy has contributed to structure-based drug development (SBDD) in a unique way compared to the other biophysical methods. The potency of a ligand binding to a protein is dictated by the binding free energy, which is an intricate interplay between entropy and enthalpy. In addition to providing the atomic resolution structural information, NMR can help to identify protein-ligand interactions that potentially contribute to the enthalpic component of the free energy. NMR can also illuminate dynamic aspects of the interaction, which correspond to the entropic term of the free energy. The ability of NMR to access both terms in the free energy equation stems from the suite of experiments developed to shed light on various aspects that contribute to both entropy and enthalpy, deepening our understanding of the biological function of macromolecules and assisting to target them in physiological conditions. Here we provide a brief account of the contribution of NMR to SBDD, highlighting hallmark examples and discussing the challenges that demand further method development. In the era of integrated biology, the unique ability of NMR to directly ascertain structural and dynamical aspects of macromolecule and monitor changes in these properties upon engaging a ligand can be combined with computational and other structural and biophysical methods to provide a more complete picture of the energetics of drug engagement with the target. Such efforts can be used to engineer better drugs.

Synthesis, Biochemical Characterization, and Theoretical Studies of Novel β-Keto-enol Pyridine and Furan Derivatives as Potent Antifungal Agents

In the present study, we report the design and synthesis of new derivatives of the β-keto-enol grafted on pyridine and furan moieties (L ₁ -L ₁₁ ). Structures of compounds were fully confirmed by Fourier transform infrared spectroscopy (FT-IR), ¹H NMR, ¹³C NMR, electrospray ionization/liquid chromatography-mass spectrometry (ESI/LC-MS), and elemental analysis. The compounds were screened for antifungal and antibacterial activities (Escherichia coli, Bacillus subtilis, and Micrococcus luteus). In vitro evaluation showed significant fungicidal activity for L ₁ , L ₄ , and L ₅ against fungal strains (Fusarium oxysporum f.sp albedinis) compared to the reference standard. Especially, the exceptional activity has been demonstrated for L ₁ with IC₅₀ = 12.83 μg/mL. This compound and the reference benomyl molecule also showed a correlation between experimental antifungal activity and theoretical predictions by Petra/Osiris/Molinspiration (POM) calculations and molecular coupling against the Fgb1 protein. The highest inhibition of bacterial growth for L ₁ is due to its strongest binding to the target protein. This report may stimulate the further synthesis of examples of this substance class for the development of new drugs.

DTiGEMS+: drug-target interaction prediction using graph embedding, graph mining, and similarity-based techniques

In silico prediction of drug–target interactions is a critical phase in the sustainable drug development process, especially when the research focus is to capitalize on the repositioning of existing drugs. However, developing such computational methods is not an easy task, but is much needed, as current methods that predict potential drug–target interactions suffer from high false-positive rates. Here we introduce DTiGEMS+, a computational method that predicts Drug–Target interactions using Graph Embedding, graph Mining, and Similarity-based techniques. DTiGEMS+ combines similarity-based as well as feature-based approaches, and models the identification of novel drug–target interactions as a link prediction problem in a heterogeneous network. DTiGEMS+ constructs the heterogeneous network by augmenting the known drug–target interactions graph with two other complementary graphs namely: drug–drug similarity, target–target similarity. DTiGEMS+ combines different computational techniques to provide the final drug target prediction, these techniques include graph embeddings, graph mining, and machine learning. DTiGEMS+ integrates multiple drug–drug similarities and target–target similarities into the final heterogeneous graph construction after applying a similarity selection procedure as well as a similarity fusion algorithm. Using four benchmark datasets, we show DTiGEMS+ substantially improves prediction performance compared to other state-of-the-art in silico methods developed to predict of drug-target interactions by achieving the highest average AUPR across all datasets (0.92), which reduces the error rate by 33.3% relative to the second-best performing model in the state-of-the-art methods comparison.

Recent Strategic Advances in CFTR Drug Discovery: An Overview

Cystic fibrosis transmembrane conductance regulator (CFTR)-rescuing drugs have already transformed cystic fibrosis (CF) from a fatal disease to a treatable chronic condition. However, new-generation drugs able to bind CFTR with higher specificity/affinity and to exert stronger therapeutic benefits and fewer side effects are still awaited. Computational methods and biosensors have become indispensable tools in the process of drug discovery for many important human pathologies. Instead, they have been used only piecemeal in CF so far, calling for their appropriate integration with well-tried CF biochemical and cell-based models to speed up the discovery of new CFTR-rescuing drugs. This review will give an overview of the available structures and computational models of CFTR and of the biosensors, biochemical and cell-based assays already used in CF-oriented studies. It will also give the reader some insights about how to integrate these tools as to improve the efficiency of the drug discovery process targeted to CFTR.