DeepDrug3D: Classification of ligand-binding pockets in proteins with a convolutional neural network

Systematic computational strategies for identifying protein targets and lead discovery

Computational algorithms and tools have retrenched the drug discovery and development timeline. The applicability of computational approaches has gained immense relevance owing to the dramatic surge in the structural information of biomacromolecules and their heteromolecular complexes. Computational methods are now extensively used in identifying new protein targets, druggability assessment, pharmacophore mapping, molecular docking, the virtual screening of lead molecules, bioactivity prediction, molecular dynamics of protein-ligand complexes, affinity prediction, and for designing better ligands. Herein, we provide an overview of salient components of recently reported computational drug-discovery workflows that includes algorithms, tools, and databases for protein target identification and optimized ligand selection.

Topological Learning Approach to Characterizing Biological Membranes

Biological membranes play key roles in cellular compartmentalization, structure, and its signaling pathways. At varying temperatures, individual membrane lipids sample from different configurations, a process that frequently leads to higher-order phase behavior and phenomena. Here, we present a persistent homology (PH)-based method for quantifying the structural features of individual and bulk lipids, providing local and contextual information on lipid tail organization. Our method leverages the mathematical machinery of algebraic topology and machine learning to infer temperature-dependent structural information on lipids from static coordinates. To train our model, we generated multiple molecular dynamics trajectories of dipalmitoyl-phosphatidylcholine membranes at varying temperatures. A fingerprint was then constructed for each set of lipid coordinates by PH filtration, in which interaction spheres were grown around the lipid atoms while tracking their intersections. The sphere filtration formed a simplicial complex that captures enduring key topological features of the configuration landscape using homology, yielding persistence data. Following fingerprint extraction for physiologically relevant temperatures, the persistence data were used to train an attention-based neural network for assignment of effective temperature values to selected membrane regions. Our persistence homology-based method captures the local structural effects, via effective temperature, of lipids adjacent to other membrane constituents, e.g., sterols and proteins. This topological learning approach can predict lipid effective temperatures from static coordinates across multiple spatial resolutions. The tool, called MembTDA, can be accessed at https://github.com/hyunp2/Memb-TDA.

Identification of a Cryptic Pocket in Methionine Aminopeptidase-II Using Adaptive Bandit Molecular Dynamics Simulations and Markov State Models

Methionine aminopeptidase-II (MetAP-II) is a metalloprotease, primarily responsible for the cotranslational removal of the N-terminal initiator methionine from the nascent polypeptide chain during protein synthesis. MetAP-II has been implicated in angiogenesis and endothelial cell proliferation and is therefore considered a validated target for cancer therapeutics. However, there is no effective drug available against MetAP-II. In this study, we employ Adaptive Bandit molecular dynamics simulations to investigate the structural dynamics of the apo and ligand-bound MetAP-II. Our results focus on the dynamic behavior of the disordered loop that is not resolved in most of the crystal structures. Further analysis of the conformational flexibility of the disordered loop reveals a hidden cryptic pocket that is predicted to be potentially druggable. The network analysis indicates that the disordered loop region has a direct signaling route to the active site. These findings highlight a new way to target MetAP-II by designing inhibitors for the allosteric site within this disordered loop region.

In silico fragment-based discovery of CIB1-directed anti-tumor agents by FRASE-bot

Chemical probes are an indispensable tool for translating biological discoveries into new therapies, though are increasingly difficult to identify since novel therapeutic targets are often hard-to-drug proteins. We introduce FRASE-based hit-finding robot (FRASE-bot), to expedite drug discovery for unconventional therapeutic targets. FRASE-bot mines available 3D structures of ligand-protein complexes to create a database of FRAgments in Structural Environments (FRASE). The FRASE database can be screened to identify structural environments similar to those in the target protein and seed the target structure with relevant ligand fragments. A neural network model is used to retain fragments with the highest likelihood of being native binders. The seeded fragments then inform ultra-large-scale virtual screening of commercially available compounds. We apply FRASE-bot to identify ligands for Calcium and Integrin Binding protein 1 (CIB1), a promising drug target implicated in triple negative breast cancer. FRASE-based virtual screening identifies a small-molecule CIB1 ligand (with binding confirmed in a TR-FRET assay) showing specific cell-killing activity in CIB1-dependent cancer cells, but not in CIB1-depletion-insensitive cells.

SiteMine: Large-scale binding site similarity searching in protein structure databases

Drug discovery and design challenges, such as drug repurposing, analyzing protein-ligand and protein-protein complexes, ligand promiscuity studies, or function prediction, can be addressed by protein binding site similarity analysis. Although numerous tools exist, they all have individual strengths and drawbacks with regard to run time, provision of structure superpositions, and applicability to diverse application domains. Here, we introduce SiteMine, an all-in-one database-driven, alignment-providing binding site similarity search tool to tackle the most pressing challenges of binding site comparison. The performance of SiteMine is evaluated on the ProSPECCTs benchmark, showing a promising performance on most of the data sets. The method performs convincingly regarding all quality criteria for reliable binding site comparison, offering a novel state-of-the-art approach for structure-based molecular design based on binding site comparisons. In a SiteMine showcase, we discuss the high structural similarity between cathepsin L and calpain 1 binding sites and give an outlook on the impact of this finding on structure-based drug design. SiteMine is available at https://uhh.de/naomi.

Graph Attention Site Prediction (GrASP): Identifying Druggable Binding Sites Using Graph Neural Networks with Attention

Identifying and discovering druggable protein binding sites is an important early step in computer-aided drug discovery, but it remains a difficult task where most campaigns rely on a priori knowledge of binding sites from experiments. Here, we present a binding site prediction method called Graph Attention Site Prediction (GrASP) and re-evaluate assumptions in nearly every step in the site prediction workflow from data set preparation to model evaluation. GrASP is able to achieve state-of-the-art performance at recovering binding sites in PDB structures while maintaining a high degree of precision which will minimize wasted computation in downstream tasks such as docking and free energy perturbation.

Generative artificial intelligence in drug discovery: basic framework, recent advances, challenges, and opportunities

There are two main ways to discover or design small drug molecules. The first involves fine-tuning existing molecules or commercially successful drugs through quantitative structure-activity relationships and virtual screening. The second approach involves generating new molecules through de novo drug design or inverse quantitative structure-activity relationship. Both methods aim to get a drug molecule with the best pharmacokinetic and pharmacodynamic profiles. However, bringing a new drug to market is an expensive and time-consuming endeavor, with the average cost being estimated at around $2.5 billion. One of the biggest challenges is screening the vast number of potential drug candidates to find one that is both safe and effective. The development of artificial intelligence in recent years has been phenomenal, ushering in a revolution in many fields. The field of pharmaceutical sciences has also significantly benefited from multiple applications of artificial intelligence, especially drug discovery projects. Artificial intelligence models are finding use in molecular property prediction, molecule generation, virtual screening, synthesis planning, repurposing, among others. Lately, generative artificial intelligence has gained popularity across domains for its ability to generate entirely new data, such as images, sentences, audios, videos, novel chemical molecules, etc. Generative artificial intelligence has also delivered promising results in drug discovery and development. This review article delves into the fundamentals and framework of various generative artificial intelligence models in the context of drug discovery via de novo drug design approach. Various basic and advanced models have been discussed, along with their recent applications. The review also explores recent examples and advances in the generative artificial intelligence approach, as well as the challenges and ongoing efforts to fully harness the potential of generative artificial intelligence in generating novel drug molecules in a faster and more affordable manner. Some clinical-level assets generated form generative artificial intelligence have also been discussed in this review to show the ever-increasing application of artificial intelligence in drug discovery through commercial partnerships.

Topological Learning Approach to Characterizing Biological Membranes

Biological membranes play key roles in cellular compartmentalization, structure, and its signaling pathways. At varying temperatures, individual membrane lipids sample from different configurations, a process that frequently leads to higher-order phase behavior and phenomena. Here we present a persistent homology-based method for quantifying the structural features of individual and bulk lipids, providing local and contextual information on lipid tail organization. Our method leverages the mathematical machinery of algebraic topology and machine learning to infer temperature-dependent structural information of lipids from static coordinates. To train our model, we generated multiple molecular dynamics trajectories of DPPC membranes at varying temperatures. A fingerprint was then constructed for each set of lipid coordinates by a persistent homology filtration, in which interactions spheres were grown around the lipid atoms while tracking their intersections. The sphere filtration formed a simplicial complex that captures enduring key topological features of the configuration landscape, using homology, yielding persistence data. Following fingerprint extraction for physiologically relevant temperatures, the persistence data were used to train an attention-based neural network for assignment of effective temperature values to selected membrane regions. Our persistence homology-based method captures the local structural effects, via effective temperature, of lipids adjacent to other membrane constituents, e.g. sterols and proteins. This topological learning approach can predict lipid effective temperatures from static coordinates across multiple spatial resolutions. The tool, called MembTDA, can be accessed at https://github.com/hyunp2/Memb-TDA.

PocketAnchor: Learning structure-based pocket representations for protein-ligand interaction prediction

Protein-ligand interactions are essential for cellular activities and drug discovery processes. Appropriately and effectively representing protein features is of vital importance for developing computational approaches, especially data-driven methods, for predicting protein-ligand interactions. However, existing approaches may not fully investigate the features of the ligand-occupying regions in the protein pockets. Here, we design a structure-based protein representation method, named PocketAnchor, for capturing the local environmental and spatial features of protein pockets to facilitate protein-ligand interaction-related learning tasks. We define "anchors" as probe points reaching into the cavities and those located near the surface of proteins, and we design a specific message passing strategy for gathering local information from the atoms and surface neighboring these anchors. Comprehensive evaluation of our method demonstrated its successful applications in pocket detection and binding affinity prediction, which indicated that our anchor-based approach can provide effective protein feature representations for improving the prediction of protein-ligand interactions.

Machine Learning-driven Fragment-based Discovery of CIB1-directed Anti-Tumor Agents by FRASE-bot

Chemical probes are an indispensable tool for translating biological discoveries into new therapies, though are increasingly difficult to identify. Novel therapeutic targets are often hard-to-drug proteins, such as messengers or transcription factors. Computational strategies arise as a promising solution to expedite drug discovery for unconventional therapeutic targets. FRASE-bot exploits big data and machine learning (ML) to distill 3D information relevant to the target protein from thousands of protein-ligand complexes to seed it with ligand fragments. The seeded fragments can then inform either (i) de novo design of 3D ligand structures or (ii) ultra-large-scale virtual screening of commercially available compounds. Here, FRASE-bot was applied to identify ligands for Calcium and Integrin Binding protein 1 (CIB1), a promising but ligand-orphan drug target implicated in triple negative breast cancer. The signaling function of CIB1 relies on protein-protein interactions and its structure does not feature any natural ligand-binding pocket. FRASE-based virtual screening identified the first small-molecule CIB1 ligand (with binding confirmed in a TR-FRET assay) showing specific cell-killing activity in CIB1-dependent cancer cells, but not in CIB1-depleted cells.

Computer-Aided Designing Peptide Inhibitors of Human Hematopoietic Prostaglandin D2 Synthase Combined Molecular Docking and Molecular Dynamics Simulation

Human hematopoietic prostaglandin D2 synthase (HPGDS) is involved in the production of prostaglandin D2, which participates in various physiological processes, including inflammation, allergic reactions, and sleep regulation. Inhibitors of HPGDS have been investigated as potential anti-inflammatory agents. For the investigation of potent HPGDS inhibitors, we carried out a computational modeling study combining molecular docking and molecular dynamics simulation for selecting and virtual confirming the designed binders. We selected the structure of HPGDS (PDB ID: 2CVD) carrying its native inhibitor compound HQL as our research target. The random 5-mer peptide library was created by building the 3-D structure of random peptides using Rosetta Buildpeptide and performing conformational optimization. Molecular docking was carried out by accommodating the peptides into the location of their native binder and then conducting docking using FlexPepDock. The two peptides RMYYY and VMYMI, which display the lowest binding energy against HPGDS, were selected to perform a comparative study. The interaction of RMYYY and VMYMI against HPGDS was further confirmed using molecular dynamics simulation and aligned with its native binder, HQL. We show the selected binders to have stronger binding energy and more frequent interactions against HPGDS than HQL. In addition, we analyzed the solubility, hydrophobicity, charge, and bioactivity of the generated peptides, and we show that the selected strong binder may be further used as therapeutic drugs.

Past, Present, and Future Perspectives on Computer-Aided Drug Design Methodologies

The application of computational approaches in drug discovery has been consolidated in the last decades. These families of techniques are usually grouped under the common name of "computer-aided drug design" (CADD), and they now constitute one of the pillars in the pharmaceutical discovery pipelines in many academic and industrial environments. Their implementation has been demonstrated to tremendously improve the speed of the early discovery steps, allowing for the proficient and rational choice of proper compounds for a desired therapeutic need among the extreme vastness of the drug-like chemical space. Moreover, the application of CADD approaches allows the rationalization of biochemical and interactive processes of pharmaceutical interest at the molecular level. Because of this, computational tools are now extensively used also in the field of rational 3D design and optimization of chemical entities starting from the structural information of the targets, which can be experimentally resolved or can also be obtained with other computer-based techniques. In this work, we revised the state-of-the-art computer-aided drug design methods, focusing on their application in different scenarios of pharmaceutical and biological interest, not only highlighting their great potential and their benefits, but also discussing their actual limitations and eventual weaknesses. This work can be considered a brief overview of computational methods for drug discovery.

Advancing Targeted Protein Degradation via Multiomics Profiling and Artificial Intelligence

Only around 20% of the human proteome is considered to be druggable with small-molecule antagonists. This leaves some of the most compelling therapeutic targets outside the reach of ligand discovery. The concept of targeted protein degradation (TPD) promises to overcome some of these limitations. In brief, TPD is dependent on small molecules that induce the proximity between a protein of interest (POI) and an E3 ubiquitin ligase, causing ubiquitination and degradation of the POI. In this perspective, we want to reflect on current challenges in the field, and discuss how advances in multiomics profiling, artificial intelligence, and machine learning (AI/ML) will be vital in overcoming them. The presented roadmap is discussed in the context of small-molecule degraders but is equally applicable for other emerging proximity-inducing modalities.

Prediction of Protein Function from Tertiary Structure of the Active Site in Heme Proteins by Convolutional Neural Network

Structure-function relationships in proteins have been one of the crucial scientific topics in recent research. Heme proteins have diverse and pivotal biological functions. Therefore, clarifying their structure-function correlation is significant to understand their functional mechanism and is informative for various fields of science. In this study, we constructed convolutional neural network models for predicting protein functions from the tertiary structures of heme-binding sites (active sites) of heme proteins to examine the structure-function correlation. As a result, we succeeded in the classification of oxygen-binding protein (OB), oxidoreductase (OR), proteins with both functions (OB-OR), and electron transport protein (ET) with high accuracy. Although the misclassification rate for OR and ET was high, the rates between OB and ET and between OB and OR were almost zero, indicating that the prediction model works well between protein groups with quite different functions. However, predicting the function of proteins modified with amino acid mutation(s) remains a challenge. Our findings indicate a structure-function correlation in the active site of heme proteins. This study is expected to be applied to the prediction of more detailed protein functions such as catalytic reactions.

Beyond sequence: Structure-based machine learning

Recent breakthroughs in protein structure prediction demarcate the start of a new era in structural bioinformatics. Combined with various advances in experimental structure determination and the uninterrupted pace at which new structures are published, this promises an age in which protein structure information is as prevalent and ubiquitous as sequence. Machine learning in protein bioinformatics has been dominated by sequence-based methods, but this is now changing to make use of the deluge of rich structural information as input. Machine learning methods making use of structures are scattered across literature and cover a number of different applications and scopes; while some try to address questions and tasks within a single protein family, others aim to capture characteristics across all available proteins. In this review, we look at the variety of structure-based machine learning approaches, how structures can be used as input, and typical applications of these approaches in protein biology. We also discuss current challenges and opportunities in this all-important and increasingly popular field.

Classification of Protein-Binding Sites Using a Spherical Convolutional Neural Network

The analysis and comparison of protein-binding sites aid various applications in the drug discovery process, e.g., hit finding, drug repurposing, and polypharmacology. Classification of binding sites has been a hot topic for the past 30 years, and many different methods have been published. The rapid development of machine learning computational algorithms, coupled with the large volume of publicly available protein-ligand 3D structures, makes it possible to apply deep learning techniques in binding site comparison. Our method uses a cutting-edge spherical convolutional neural network based on the DeepSphere architecture to learn global representations of protein-binding sites. The model was trained on TOUGH-C1 and TOUGH-M1 data and validated with the ProSPECCTs datasets. Our results show that our model can (1) perform well in protein-binding site similarity and classification tasks and (2) learn and separate the physicochemical properties of binding sites. Lastly, we tested the model on a set of kinases, where the results show that it is able to cluster the different kinase subfamilies effectively. This example demonstrates the method's promise for lead hopping within or outside a protein target, directly based on binding site information.

Artificial intelligence to guide precision anticancer therapy with multitargeted kinase inhibitors

BACKGROUND

Vast amounts of rapidly accumulating biological data related to cancer and a remarkable progress in the field of artificial intelligence (AI) have paved the way for precision oncology. Our recent contribution to this area of research is CancerOmicsNet, an AI-based system to predict the therapeutic effects of multitargeted kinase inhibitors across various cancers. This approach was previously demonstrated to outperform other deep learning methods, graph kernel models, molecular docking, and drug binding pocket matching.

METHODS

CancerOmicsNet integrates multiple heterogeneous data by utilizing a deep graph learning model with sophisticated attention propagation mechanisms to extract highly predictive features from cancer-specific networks. The AI-based system was devised to provide more accurate and robust predictions than data-driven therapeutic discovery using gene signature reversion.

RESULTS

Selected CancerOmicsNet predictions obtained for "unseen" data are positively validated against the biomedical literature and by live-cell time course inhibition assays performed against breast, pancreatic, and prostate cancer cell lines. Encouragingly, six molecules exhibited dose-dependent antiproliferative activities, with pan-CDK inhibitor JNJ-7706621 and Src inhibitor PP1 being the most potent against the pancreatic cancer cell line Panc 04.03.

CONCLUSIONS

CancerOmicsNet is a promising AI-based platform to help guide the development of new approaches in precision oncology involving a variety of tumor types and therapeutics.

A multilayer dynamic perturbation analysis method for predicting ligand-protein interactions

BACKGROUND

Ligand-protein interactions play a key role in defining protein function, and detecting natural ligands for a given protein is thus a very important bioengineering task. In particular, with the rapid development of AI-based structure prediction algorithms, batch structural models with high reliability and accuracy can be obtained at low cost, giving rise to the urgent requirement for the prediction of natural ligands based on protein structures. In recent years, although several structure-based methods have been developed to predict ligand-binding pockets and ligand-binding sites, accurate and rapid methods are still lacking, especially for the prediction of ligand-binding regions and the spatial extension of ligands in the pockets.

RESULTS

In this paper, we proposed a multilayer dynamics perturbation analysis (MDPA) method for predicting ligand-binding regions based solely on protein structure, which is an extended version of our previously developed fast dynamic perturbation analysis (FDPA) method. In MDPA/FDPA, ligand binding tends to occur in regions that cause large changes in protein conformational dynamics. MDPA, examined using a standard validation dataset of ligand-protein complexes, yielded an averaged ligand-binding site prediction Matthews coefficient of 0.40, with a prediction precision of at least 50% for 71% of the cases. In particular, for 80% of the cases, the predicted ligand-binding region overlaps the natural ligand by at least 50%. The method was also compared with other state-of-the-art structure-based methods.

CONCLUSIONS

MDPA is a structure-based method to detect ligand-binding regions on protein surface. Our calculations suggested that a range of spaces inside the protein pockets has subtle interactions with the protein, which can significantly impact on the overall dynamics of the protein. This work provides a valuable tool as a starting point upon which further docking and analysis methods can be used for natural ligand detection in protein functional annotation. The source code of MDPA method is freely available at: https://github.com/mingdengming/mdpa .

In Silico Methods for Identification of Potential Active Sites of Therapeutic Targets

Target identification is an important step in drug discovery, and computer-aided drug target identification methods are attracting more attention compared with traditional drug target identification methods, which are time-consuming and costly. Computer-aided drug target identification methods can greatly reduce the searching scope of experimental targets and associated costs by identifying the diseases-related targets and their binding sites and evaluating the druggability of the predicted active sites for clinical trials. In this review, we introduce the principles of computer-based active site identification methods, including the identification of binding sites and assessment of druggability. We provide some guidelines for selecting methods for the identification of binding sites and assessment of druggability. In addition, we list the databases and tools commonly used with these methods, present examples of individual and combined applications, and compare the methods and tools. Finally, we discuss the challenges and limitations of binding site identification and druggability assessment at the current stage and provide some recommendations and future perspectives.

Estimating the Similarity between Protein Pockets

With the exponential increase in publicly available protein structures, the comparison of protein binding sites naturally emerged as a scientific topic to explain observations or generate hypotheses for ligand design, notably to predict ligand selectivity for on- and off-targets, explain polypharmacology, and design target-focused libraries. The current review summarizes the state-of-the-art computational methods applied to pocket detection and comparison as well as structural druggability estimates. The major strengths and weaknesses of current pocket descriptors, alignment methods, and similarity search algorithms are presented. Lastly, an exhaustive survey of both retrospective and prospective applications in diverse medicinal chemistry scenarios illustrates the capability of the existing methods and the hurdle that still needs to be overcome for more accurate predictions.

Defining A Global Map of Functional Group-based 3D Ligand-binding Motifs

Uncovering conserved 3D protein-ligand binding patterns on the basis of functional groups (FGs) shared by a variety of small molecules can greatly expand our knowledge of protein-ligand interactions. Despite that conserved binding patterns for a few commonly used FGs have been reported in the literature, large-scale identification and evaluation of FG-based 3D binding motifs are still lacking. Here, we propose a computational method, Automatic FG-based Three-dimensional Motif Extractor (AFTME), for automatic mapping of 3D motifs to different FGs of a specific ligand. Applying our method to 233 naturally-occurring ligands, we define 481 FG-binding motifs that are highly conserved across different ligand-binding pockets. Systematic analysis further reveals four main classes of binding motifs corresponding to distinct sets of FGs. Combinations of FG-binding motifs facilitate the binding of proteins to a wide spectrum of ligands with various binding affinities. Finally, we show that our FG-motif map can be used to nominate FGs that potentially bind to specific drug targets, thus providing useful insights and guidance for rational design of small-molecule drugs.

GraphSite: Ligand Binding Site Classification with Deep Graph Learning

The binding of small organic molecules to protein targets is fundamental to a wide array of cellular functions. It is also routinely exploited to develop new therapeutic strategies against a variety of diseases. On that account, the ability to effectively detect and classify ligand binding sites in proteins is of paramount importance to modern structure-based drug discovery. These complex and non-trivial tasks require sophisticated algorithms from the field of artificial intelligence to achieve a high prediction accuracy. In this communication, we describe GraphSite, a deep learning-based method utilizing a graph representation of local protein structures and a state-of-the-art graph neural network to classify ligand binding sites. Using neural weighted message passing layers to effectively capture the structural, physicochemical, and evolutionary characteristics of binding pockets mitigates model overfitting and improves the classification accuracy. Indeed, comprehensive cross-validation benchmarks against a large dataset of binding pockets belonging to 14 diverse functional classes demonstrate that GraphSite yields the class-weighted F1-score of 81.7%, outperforming other approaches such as molecular docking and binding site matching. Further, it also generalizes well to unseen data with the F1-score of 70.7%, which is the expected performance in real-world applications. We also discuss new directions to improve and extend GraphSite in the future.

A review of deep learning applications in human genomics using next-generation sequencing data

Genomics is advancing towards data-driven science. Through the advent of high-throughput data generating technologies in human genomics, we are overwhelmed with the heap of genomic data. To extract knowledge and pattern out of this genomic data, artificial intelligence especially deep learning methods has been instrumental. In the current review, we address development and application of deep learning methods/models in different subarea of human genomics. We assessed over- and under-charted area of genomics by deep learning techniques. Deep learning algorithms underlying the genomic tools have been discussed briefly in later part of this review. Finally, we discussed briefly about the late application of deep learning tools in genomic. Conclusively, this review is timely for biotechnology or genomic scientists in order to guide them why, when and how to use deep learning methods to analyse human genomic data.

Probabilistic Pocket Druggability Prediction via One-Class Learning

The choice of target pocket is a key step in a drug discovery campaign. This step can be supported by in silico druggability prediction. In the literature, druggability prediction is often approached as a two-class classification task that distinguishes between druggable and non-druggable (or less druggable) pockets (or voxels). Apart from obvious cases, however, the non-druggable class is conceptually ambiguous. This is because any pocket (or target) is only non-druggable until a drug is found for it. It is therefore more appropriate to adopt a one-class approach, which uses only unambiguous information, namely, druggable pockets. Here, we propose using the import vector domain description (IVDD) algorithm to support this task. IVDD is a one-class probabilistic kernel machine that we previously introduced. To feed the algorithm, we use customized DrugPred descriptors computed via NanoShaper. Our results demonstrate the feasibility and effectiveness of the approach. In particular, we can remove or mitigate biases chiefly due to the labeling.

Simulation and Machine Learning Methods for Ion-Channel Structure Determination, Mechanistic Studies and Drug Design

Ion channels are expressed in almost all living cells, controlling the in-and-out communications, making them ideal drug targets, especially for central nervous system diseases. However, owing to their dynamic nature and the presence of a membrane environment, ion channels remain difficult targets for the past decades. Recent advancement in cryo-electron microscopy and computational methods has shed light on this issue. An explosion in high-resolution ion channel structures paved way for structure-based rational drug design and the state-of-the-art simulation and machine learning techniques dramatically improved the efficiency and effectiveness of computer-aided drug design. Here we present an overview of how simulation and machine learning-based methods fundamentally changed the ion channel-related drug design at different levels, as well as the emerging trends in the field.

Scoring Functions for Protein-Ligand Binding Affinity Prediction using Structure-Based Deep Learning: A Review

The rapid and accurate in silico prediction of protein-ligand binding free energies or binding affinities has the potential to transform drug discovery. In recent years, there has been a rapid growth of interest in deep learning methods for the prediction of protein-ligand binding affinities based on the structural information of protein-ligand complexes. These structure-based scoring functions often obtain better results than classical scoring functions when applied within their applicability domain. Here we review structure-based scoring functions for binding affinity prediction based on deep learning, focussing on different types of architectures, featurization strategies, data sets, methods for training and evaluation, and the role of explainable artificial intelligence in building useful models for real drug-discovery applications.

Deep learning methods for 3D structural proteome and interactome modeling

Bolstered by recent methodological and hardware advances, deep learning has increasingly been applied to biological problems and structural proteomics. Such approaches have achieved remarkable improvements over traditional machine learning methods in tasks ranging from protein contact map prediction to protein folding, prediction of protein-protein interaction interfaces, and characterization of protein-drug binding pockets. In particular, emergence of ab initio protein structure prediction methods including AlphaFold2 has revolutionized protein structural modeling. From a protein function perspective, numerous deep learning methods have facilitated deconvolution of the exact amino acid residues and protein surface regions responsible for binding other proteins or small molecule drugs. In this review, we provide a comprehensive overview of recent deep learning methods applied in structural proteomics.

Structure-based drug repurposing: traditional and advanced AI/ML-aided methods

The current global health emergency in the form of the Coronavirus 2019 (COVID-19) pandemic has highlighted the need for fast, accurate, and efficient drug discovery pipelines. Traditional drug discovery projects relying on in vitro high-throughput screening (HTS) involve large investments and sophisticated experimental set-ups, affordable only to big biopharmaceutical companies. In this scenario, application of efficient state-of-the-art computational methods and modern artificial intelligence (AI)-based algorithms for rapid screening of repurposable chemical space [approved drugs and natural products (NPs) with proven pharmacokinetic profiles] to identify the initial leads is a powerful option to save resources and time. Structure-based drug repurposing is a popular in silico repurposing approach. In this review, we discuss traditional and modern AI-based computational methods and tools applied at various stages for structure-based drug discovery (SBDD) pipelines. Additionally, we highlight the role of generative models in generating molecules with scaffolds from repurposable chemical space. Teaser: This review highlights the importance of repurposable chemical space, and the contributions of conventional in silico approaches and modern machine-learning algorithms for rapid structure-based drug repurposing.

Pocket2Drug: An Encoder-Decoder Deep Neural Network for the Target-Based Drug Design

Computational modeling is an essential component of modern drug discovery. One of its most important applications is to select promising drug candidates for pharmacologically relevant target proteins. Because of continuing advances in structural biology, putative binding sites for small organic molecules are being discovered in numerous proteins linked to various diseases. These valuable data offer new opportunities to build efficient computational models predicting binding molecules for target sites through the application of data mining and machine learning. In particular, deep neural networks are powerful techniques capable of learning from complex data in order to make informed drug binding predictions. In this communication, we describe Pocket2Drug, a deep graph neural network model to predict binding molecules for a given a ligand binding site. This approach first learns the conditional probability distribution of small molecules from a large dataset of pocket structures with supervised training, followed by the sampling of drug candidates from the trained model. Comprehensive benchmarking simulations show that using Pocket2Drug significantly improves the chances of finding molecules binding to target pockets compared to traditional drug selection procedures. Specifically, known binders are generated for as many as 80.5% of targets present in the testing set consisting of dissimilar data from that used to train the deep graph neural network model. Overall, Pocket2Drug is a promising computational approach to inform the discovery of novel biopharmaceuticals.

Three-Dimensional Convolutional Neural Networks Utilizing Molecular Topological Features for Accurate Atomization Energy Predictions

Deep learning methods provide a novel way to establish a correlation between two quantities. In this context, computer vision techniques such as three-dimensional (3D)-convolutional neural networks become a natural choice to associate a molecular property with its structure due to the inherent 3D nature of a molecule. However, traditional 3D input data structures are intrinsically sparse in nature, which tend to induce instabilities during the learning process, which in turn may lead to underfitted results. To address this deficiency, in this project, we propose to use quantum-chemically derived molecular topological features, namely, localized orbital locator and electron localization function, as molecular descriptors, which provide a relatively denser input representation in a 3D space. Such topological features provide a detailed picture of the atomic and electronic configuration and interatomic interactions in the molecule and hence are ideal for predicting properties that are highly dependent on the physical or electronic structure of the molecule. Herein, we demonstrate the efficacy of our proposed model by applying it to the task of predicting atomization energies for the QM9-G4MP2 data set, which contains ∼134k molecules. Furthermore, we incorporated the Δ-machine learning approach into our model, which enabled us to reach beyond benchmark accuracy levels (∼1.0 kJ mol^-1). As a result, we consistently obtain impressive mean absolute errors of the order 0.1 kcal mol^-1 (∼0.42 kJ mol^-1) versus the G4(MP2) theory using relatively modest models, which could potentially be improved further in a systematic manner using additional compute resources.

PyUUL provides an interface between biological structures and deep learning algorithms

Structural bioinformatics suffers from the lack of interfaces connecting biological structures and machine learning methods, making the application of modern neural network architectures impractical. This negatively affects the development of structure-based bioinformatics methods, causing a bottleneck in biological research. Here we present PyUUL ( https://pyuul.readthedocs.io/ ), a library to translate biological structures into 3D tensors, allowing an out-of-the-box application of state-of-the-art deep learning algorithms. The library converts biological macromolecules to data structures typical of computer vision, such as voxels and point clouds, for which extensive machine learning research has been performed. Moreover, PyUUL allows an out-of-the box GPU and sparse calculation. Finally, we demonstrate how PyUUL can be used by researchers to address some typical bioinformatics problems, such as structure recognition and docking.

Computational prediction of protein functional sites-Applications in biotechnology and biomedicine

There are many computational approaches for predicting protein functional sites based on different sequence and structural features. These methods are essential to cope with the sequence deluge that is filling databases with uncharacterized protein sequences. They complement the more expensive and time-consuming experimental approaches by pointing them to possible candidate positions. In many cases they are jointly used to characterize the functional sites in proteins of biotechnological and biomedical interest and eventually modify them for different purposes. There is a clear trend towards approaches based on machine learning and those using structural information, due to the recent developments in these areas. Nevertheless, "classic" methods based on sequence and evolutionary features are still playing an important role as these features are strongly related to functionality. In this review, the main approaches for predicting general functional sites in a protein are discussed, with a focus on sequence-based approaches.

Assessing the impact of substrate-level enzyme regulations limiting ethanol titer in Clostridium thermocellum using a core kinetic model

Clostridium thermocellum is a promising candidate for consolidated bioprocessing because it can directly ferment cellulose to ethanol. Despite significant efforts, achieved yields and titers fall below industrially relevant targets. This implies that there still exist unknown enzymatic, regulatory, and/or possibly thermodynamic bottlenecks that can throttle back metabolic flow. By (i) elucidating internal metabolic fluxes in wild-type C. thermocellum grown on cellobiose via ¹³C-metabolic flux analysis (¹³C-MFA), (ii) parameterizing a core kinetic model, and (iii) subsequently deploying an ensemble-docking workflow for discovering substrate-level regulations, this paper aims to reveal some of these factors and expand our knowledgebase governing C. thermocellum metabolism. Generated ¹³C labeling data were used with ¹³C-MFA to generate a wild-type flux distribution for the metabolic network. Notably, flux elucidation through MFA alluded to serine generation via the mercaptopyruvate pathway. Using the elucidated flux distributions in conjunction with batch fermentation process yield data for various mutant strains, we constructed a kinetic model of C. thermocellum core metabolism (i.e. k-ctherm138). Subsequently, we used the parameterized kinetic model to explore the effect of removing substrate-level regulations on ethanol yield and titer. Upon exploring all possible simultaneous (up to four) regulation removals we identified combinations that lead to many-fold model predicted improvement in ethanol titer. In addition, by coupling a systematic method for identifying putative competitive inhibitory mechanisms using K-FIT kinetic parameterization with the ensemble-docking workflow, we flagged 67 putative substrate-level inhibition mechanisms across central carbon metabolism supported by both kinetic formalism and docking analysis.

Applications of Artificial Intelligence in Drug Design: Opportunities and Challenges

Artificial intelligence (AI) has undergone rapid development in recent years and has been successfully applied to real-world problems such as drug design. In this chapter, we review recent applications of AI to problems in drug design including virtual screening, computer-aided synthesis planning, and de novo molecule generation, with a focus on the limitations of the application of AI therein and opportunities for improvement. Furthermore, we discuss the broader challenges imposed by AI in translating theoretical practice to real-world drug design; including quantifying prediction uncertainty and explaining model behavior.

The rise of deep learning and transformations in bioactivity prediction power of molecular modeling tools

The search and design for the better use of bioactive compounds are used in many experiments to best mimic compounds' functions in the human body. However, finding a cost-effective and timesaving approach is a top priority in different disciplines. Nowadays, artificial intelligence (AI) and particularly deep learning (DL) methods are widely applied to improve the precision and accuracy of models used in the drug discovery process. DL approaches have been used to provide more opportunities for a faster, efficient, cost-effective, and reliable computer-aided drug discovery. Moreover, the increasing biomedical data volume in areas, like genome sequences, medical images, protein structures, etc., has made data mining algorithms very important in finding novel compounds that could be drugs, uncovering or repurposing drugs and improving the area of genetic markers-based personalized medicine. Furthermore, deep neural networks (DNNs) have been demonstrated to outperform other techniques such as random forests and SVMs for QSAR studies and ligand-based virtual screening. Despite this, in QSAR studies, the quality of different data sources and potential experimental errors has greatly affected the accuracy of QSAR predictions. Therefore, further researches are still needed to improve the accuracy, selectivity, and sensitivity of the DL approach in building the best models of drug discovery.

Comprehensive Survey of Recent Drug Discovery Using Deep Learning

Drug discovery based on artificial intelligence has been in the spotlight recently as it significantly reduces the time and cost required for developing novel drugs. With the advancement of deep learning (DL) technology and the growth of drug-related data, numerous deep-learning-based methodologies are emerging at all steps of drug development processes. In particular, pharmaceutical chemists have faced significant issues with regard to selecting and designing potential drugs for a target of interest to enter preclinical testing. The two major challenges are prediction of interactions between drugs and druggable targets and generation of novel molecular structures suitable for a target of interest. Therefore, we reviewed recent deep-learning applications in drug-target interaction (DTI) prediction and de novo drug design. In addition, we introduce a comprehensive summary of a variety of drug and protein representations, DL models, and commonly used benchmark datasets or tools for model training and testing. Finally, we present the remaining challenges for the promising future of DL-based DTI prediction and de novo drug design.

GraphDTI: A robust deep learning predictor of drug-target interactions from multiple heterogeneous data

Traditional techniques to identify macromolecular targets for drugs utilize solely the information on a query drug and a putative target. Nonetheless, the mechanisms of action of many drugs depend not only on their binding affinity toward a single protein, but also on the signal transduction through cascades of molecular interactions leading to certain phenotypes. Although using protein-protein interaction networks and drug-perturbed gene expression profiles can facilitate system-level investigations of drug-target interactions, utilizing such large and heterogeneous data poses notable challenges. To improve the state-of-the-art in drug target identification, we developed GraphDTI, a robust machine learning framework integrating the molecular-level information on drugs, proteins, and binding sites with the system-level information on gene expression and protein-protein interactions. In order to properly evaluate the performance of GraphDTI, we compiled a high-quality benchmarking dataset and devised a new cluster-based cross-validation protocol. Encouragingly, GraphDTI not only yields an AUC of 0.996 against the validation dataset, but it also generalizes well to unseen data with an AUC of 0.939, significantly outperforming other predictors. Finally, selected examples of identified drugtarget interactions are validated against the biomedical literature. Numerous applications of GraphDTI include the investigation of drug polypharmacological effects, side effects through offtarget binding, and repositioning opportunities.

Applications of artificial intelligence to enzyme and pathway design for metabolic engineering

Metabolic engineering for developing industrial strains capable of overproducing bioproducts requires good understanding of cellular metabolism, including metabolic reactions and enzymes. However, metabolic pathways and enzymes involved are still unknown for many products of interest, which presents a key challenge in their biological production. This challenge can be partly overcome by constructing novel biosynthetic pathways through enzyme and pathway design approaches. With the increase in bio-big data, data-driven approaches using artificial intelligence (AI) techniques are allowing more advanced protein and pathway design. In this paper, we review recent studies on AI-aided protein engineering and design, focusing on directed evolution that uses AI approaches to efficiently construct mutant libraries. Also, recent works of AI-aided pathway design strategies, including template-based and template-free approaches, are discussed.

CHARMM-GUI LBS Finder & Refiner for Ligand Binding Site Prediction and Refinement

A protein performs its task by binding a variety of ligands in its local region that is also known as the ligand-binding-site (LBS). Therefore, accurate prediction, characterization, and refinement of LBS can facilitate protein functional annotations and structure-based drug design. In this work, we present CHARMM-GUI LBS Finder & Refiner (https://www.charmm-gui.org/input/lbsfinder) that predicts potential LBS, offers interactive features for local LBS structure analysis, and prepares various molecular dynamics (MD) systems and inputs by setting up distance restraint potentials for LBS structure refinement. LBS Finder & Refiner supports 5 different commonly used simulation programs, such as NAMD, AMBER, GROMACS, GENESIS, and OpenMM, for LBS structure refinement together with hydrogen mass repartitioning. The capability of LBS Finder & Refiner is illustrated through LBS structure predictions and refinements of 48 modeled and 20 apo benchmark target proteins. Overall, successful LBS structure predictions and refinements are seen in our benchmark tests. We hope that LBS Finder & Refiner is useful to predict, characterize, and refine potential LBS on any given protein of interest.

MCCS, a novel characterization method for protein-ligand complex

Delineating the fingerprint or feature vector of a receptor/protein will facilitate the structural and biological studies, as well as the rational design and development of drugs with high affinities and selectivity. However, protein is complicated by its different functional regions that can bind to some of its protein partner(s), substrate(s), orthosteric ligand(s) or allosteric modulator(s) where cogent methods like molecular fingerprints do not work well. We here elaborate a scoring-function-based computing protocol Molecular Complex Characterizing System to help characterize the binding feature of protein-ligand complexes. Based on the reported receptor-ligand interactions, we first quantitate the energy contribution of each individual residue which may be an alternative of MD-based energy decomposition. We then construct a vector for the energy contribution to represent the pattern of the ligand recognition at a receptor and qualitatively analyze the matching level with other receptors. Finally, the energy contribution vector is explored for extensive use in similarity and clustering. The present work provides a new approach to cluster proteins, a perspective counterpart for determining the protein characteristics in the binding, and an advanced screening technique where molecular docking is applicable.

Computational approaches to predict protein functional families and functional sites

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.

A spatial-temporal gated attention module for molecular property prediction based on molecular geometry

MOTIVATION

Geometry-based properties and characteristics of drug molecules play an important role in drug development for virtual screening in computational chemistry. The 3D characteristics of molecules largely determine the properties of the drug and the binding characteristics of the target. However, most of the previous studies focused on 1D or 2D molecular descriptors while ignoring the 3D topological structure, thereby degrading the performance of molecule-related prediction. Because it is very time-consuming to use dynamics to simulate molecular 3D conformer, we aim to use machine learning to represent 3D molecules by using the generated 3D molecular coordinates from the 2D structure.

RESULTS

We proposed Drug3D-Net, a novel deep neural network architecture based on the spatial geometric structure of molecules for predicting molecular properties. It is grid-based 3D convolutional neural network with spatial-temporal gated attention module, which can extract the geometric features for molecular prediction tasks in the process of convolution. The effectiveness of Drug3D-Net is verified on the public molecular datasets. Compared with other deep learning methods, Drug3D-Net shows superior performance in predicting molecular properties and biochemical activities.

AVAILABILITY AND IMPLEMENTATION

https://github.com/anny0316/Drug3D-Net.

SUPPLEMENTARY DATA

Supplementary data are available online at https://academic.oup.com/bib.

Meta Learning for Low-Resource Molecular Optimization

The goal of molecular optimization (MO) is to discover molecules that acquire improved pharmaceutical properties over a known starting molecule. Despite many recent successes of new approaches for MO, these methods were typically developed for particular properties with rich annotated training examples. Thus, these approaches are difficult to implement in real scenes where only a small amount of pharmaceutical data is usually available due to the expense and significant effort required for the data collection. Here, we propose a new approach, Meta-MO, for molecular optimization with a handful of training samples based on the well-recognized first-order meta-learning algorithms. By using a set of meta tasks with rich training samples, Meta-MO trains a meta model through the meta-learning optimization and adapts the learned model to new low-resource MO tasks. Meta-MO was shown to consistently outperform several pretraining and multitask training procedures, providing an average improvement in the success rate of 4.3% on a large-scale bioactivity data set with diverse target variations. We also observed that Meta-MO resulted in the best performing models across fine-tuning sets with only dozens of samples. To the best of our knowledge, this is the first study to apply meta learning to MO tasks. More importantly, such a strategy could be further extended to many low-resource scenarios in real-world drug design.

OctSurf: Efficient hierarchical voxel-based molecular surface representation for protein-ligand affinity prediction

Voxel-based 3D convolutional neural networks (CNNs) have been applied to predict protein-ligand binding affinity. However, the memory usage and computation cost of these voxel-based approaches increase cubically with respect to spatial resolution and sometimes make volumetric CNNs intractable at higher resolutions. Therefore, it is necessary to develop memory-efficient alternatives that can accelerate the convolutional operation on 3D volumetric representations of the protein-ligand interaction. In this study, we implement a novel volumetric representation, OctSurf, to characterize the 3D molecular surface of protein binding pockets and bound ligands. The OctSurf surface representation is built based on the octree data structure, which has been widely used in computer graphics to efficiently represent and store 3D object data. Vanilla 3D-CNN approaches often divide the 3D space of objects into equal-sized voxels. In contrast, OctSurf recursively partitions the 3D space containing the protein-ligand pocket into eight subspaces called octants. Only those octants containing van der Waals surface points of protein or ligand atoms undergo the recursive subdivision process until they reach the predefined octree depth, whereas unoccupied octants are kept intact to reduce the memory cost. Resulting non-empty leaf octants approximate molecular surfaces of the protein pocket and bound ligands. These surface octants, along with their chemical and geometric features, are used as the input to 3D-CNNs. Two kinds of CNN architectures, VGG and ResNet, are applied to the OctSurf representation to predict binding affinity. The OctSurf representation consumes much less memory than the conventional voxel representation at the same resolution. By restricting the convolution operation to only octants of the smallest size, our method also alleviates the overall computational overhead of CNN. A series of experiments are performed to demonstrate the disk storage and computational efficiency of the proposed learning method. Our code is available at the following GitHub repository: https://github.uconn.edu/mldrugdiscovery/OctSurf.

Bionoi: A Voronoi Diagram-Based Representation of Ligand-Binding Sites in Proteins for Machine Learning Applications

Bionoi is a new software to generate Voronoi representations of ligand-binding sites in proteins for machine learning applications. Unlike many other deep learning models in biomedicine, Bionoi utilizes off-the-shelf convolutional neural network architectures, reducing the development work without sacrificing the performance. When initially generating images of binding sites, users have the option to color the Voronoi cells based on either one of six structural, physicochemical, and evolutionary properties, or a blend of all six individual properties. Encouragingly, after inputting images generated by Bionoi into the convolutional autoencoder, the network was able to effectively learn the most salient features of binding pockets. The accuracy of the generated model is evaluated both visually and numerically through the reconstruction of binding site images from the latent feature space. The generated feature vectors capture well various properties of binding sites and thus can be applied in a multitude of machine learning projects. As a demonstration, we trained the ResNet-18 architecture from Microsoft on Bionoi images to show that it is capable to effectively classify nucleotide- and heme-binding pockets against a large dataset of control pockets binding a variety of small molecules. Bionoi is freely available to the research community at https://github.com/CSBG-LSU/BionoiNet.

Interfering Peptides Targeting Protein-Protein Interactions in the Ethylene Plant Hormone Signaling Pathway as Tools to Delay Plant Senescence

Interfering peptides (iPs) have been recognized as valuable substances to specifically target protein-protein interactions (PPIs) in senescence and disease. Although the concept of iPs has been validated for several PPIs in medical and pharmaceutical research, little attention so far has been paid to the enormous potential iPs that may provide to target and control plant growth and developmental processes or plant environmental responses. However, recent research on PPIs in the ethylene signaling pathway has identified the synthetic peptide NOP-1 derived from the nuclear localization signal of ethylene regulator EIN2 as an efficient inhibitor of typical ethylene responses such as ripening, aging, and senescence. Biophysical and biochemical studies on purified recombinant proteins of the ethylene receptor family from various plant species demonstrate that the synthetic peptide binds in the nM-μM range at the plant target. Here, we describe methods to evaluate and quantify the effect of the NOP-1 peptide on flower senescence as a typical ethylene response in the intact plant system. This approach will help to systematically advance our technological capability to delay plant ethylene responses and to expand shelf-life or vase life of fruits and flowers.