Machine learning classification can reduce false positives in structure-based virtual screening

Integrated ML-Based Strategy Identifies Drug Repurposing for Idiopathic Pulmonary Fibrosis

Idiopathic pulmonary fibrosis (IPF) affects an estimated global population of around 3 million individuals. IPF is a medical condition with an unknown cause characterized by the formation of scar tissue in the lungs, leading to progressive respiratory disease. Currently, there are only two FDA-approved small molecule drugs specifically for the treatment of IPF and this has created a demand for the rapid development of drugs for IPF treatment. Moreover, denovo drug development is time and cost-intensive with less than a 10% success rate. Drug repurposing currently is the most feasible option for rapidly making the drugs to market for a rare and sporadic disease. Normally, the repurposing of drugs begins with a screening of FDA-approved drugs using computational tools, which results in a low hit rate. Here, an integrated machine learning-based drug repurposing strategy is developed to significantly reduce the false positive outcomes by introducing the predock machine-learning-based predictions followed by literature and GSEA-assisted validation and drug pathway prediction. The developed strategy is deployed to 1480 FDA-approved drugs and to drugs currently in a clinical trial for IPF to screen them against "TGFB1", "TGFB2", "PDGFR-a", "SMAD-2/3", "FGF-2", and more proteins resulting in 247 total and 27 potentially repurposable drugs. The literature and GSEA validation suggested that 72 of 247 (29.14%) drugs have been tried for IPF, 13 of 247 (5.2%) drugs have already been used for lung fibrosis, and 20 of 247 (8%) drugs have been tested for other fibrotic conditions such as cystic fibrosis and renal fibrosis. Pathway prediction of the remaining 142 drugs was carried out resulting in 118 distinct pathways. Furthermore, the analysis revealed that 29 of 118 pathways were directly or indirectly involved in IPF and 11 of 29 pathways were directly involved. Moreover, 15 potential drug combinations are suggested for showing a strong synergistic effect in IPF. The drug repurposing strategy reported here will be useful for rapidly developing drugs for treating IPF and other related conditions.

KinomeMETA: a web platform for kinome-wide polypharmacology profiling with meta-learning

Kinase-targeted inhibitors hold promise for new therapeutic options, with multi-target inhibitors offering the potential for broader efficacy while minimizing polypharmacology risks. However, comprehensive experimental profiling of kinome-wide activity is expensive, and existing computational approaches often lack scalability or accuracy for understudied kinases. We introduce KinomeMETA, an artificial intelligence (AI)-powered web platform that significantly expands the predictive range with scalability for predicting the polypharmacological effects of small molecules across the kinome. By leveraging a novel meta-learning algorithm, KinomeMETA efficiently utilizes sparse activity data, enabling rapid generalization to new kinase tasks even with limited information. This significantly expands the repertoire of accurately predictable kinases to 661 wild-type and clinically-relevant mutant kinases, far exceeding existing methods. Additionally, KinomeMETA empowers users to customize models with their proprietary data for specific research needs. Case studies demonstrate its ability to discover new active compounds by quickly adapting to small dataset. Overall, KinomeMETA offers enhanced kinome virtual profiling capabilities and is positioned as a powerful tool for developing new kinase inhibitors and advancing kinase research. The KinomeMETA server is freely accessible without registration at https://kinomemeta.alphama.com.cn/.

An extensive review on lung cancer therapeutics using machine learning techniques: state-of-the-art and perspectives

There are over 100 types of human cancer, accounting for millions of deaths every year. Lung cancer alone claims over 1.8 million lives per year and is expected to surpass 3.2 million by 2050, which underscores the urgent need for rapid drug development and repurposing initiatives. The application of AI emerges as a pivotal solution to developing anti-cancer therapeutics. This state-of-the-art review aims to explore the various applications of AI in lung cancer therapeutics. Predictive models can analyse large datasets, including clinical data, genetic information, and treatment outcomes, for novel drug design and to generate personalised treatment recommendations, potentially optimising therapeutic strategies, enhancing treatment efficacy, and minimising adverse effects. A thorough literature review study was conducted based on articles indexed in PubMed and Scopus. We compiled the use of various machine learning approaches, including CNN, RNN, GAN, VAEs, and other AI techniques, enhancing efficiency with accuracy exceeding 95%, which is validated through a computer-aided drug design process. AI can revolutionise lung cancer therapeutics, streamlining processes and saving biological scientists' time and effort-however, further research is needed to overcome challenges and fully unlock AI's potential in Lung Cancer Therapeutics.

Applying Machine Learning for Antibiotic Development and Prediction of Microbial Resistance

Antimicrobial resistance (AMR) poses a serious threat to human health worldwide. It is now more challenging than ever to introduce a potent antibiotic to the market considering rapid emergence of antimicrobial resistance, surpassing the rate of antibiotic drug discovery. Hence, new approaches need to be developed to accelerate the rate of drug discovery process and meet the demands for new antibiotics, while reducing the cost of their development. Machine learning holds immense promise of becoming a useful tool, especially since in the last two decades, exponential growth has occurred in computational power and biological big data analytics. Recent advancements in machine learning algorithms for drug discovery have provided significant clues for potential antibiotic classes. Apart from discovery of new scaffolds, the machine learning protocols will significantly impact prediction of AMR patterns and drug metabolism. In this review, we outline power of machine learning in antibiotic drug discovery, metabolic fate, and AMR prediction to support researchers engaged and interested in this field.

G Protein-Coupled Receptor-Ligand Pose and Functional Class Prediction

G protein-coupled receptor (GPCR) transmembrane protein family members play essential roles in physiology. Numerous pharmaceuticals target GPCRs, and many drug discovery programs utilize virtual screening (VS) against GPCR targets. Improvements in the accuracy of predicting new molecules that bind to and either activate or inhibit GPCR function would accelerate such drug discovery programs. This work addresses two significant research questions. First, do ligand interaction fingerprints provide a substantial advantage over automated methods of binding site selection for classical docking? Second, can the functional status of prospective screening candidates be predicted from ligand interaction fingerprints using a random forest classifier? Ligand interaction fingerprints were found to offer modest advantages in sampling accurate poses, but no substantial advantage in the final set of top-ranked poses after scoring, and, thus, were not used in the generation of the ligand-receptor complexes used to train and test the random forest classifier. A binary classifier which treated agonists, antagonists, and inverse agonists as active and all other ligands as inactive proved highly effective in ligand function prediction in an external test set of GPR31 and TAAR2 candidate ligands with a hit rate of 82.6% actual actives within the set of predicted actives.

The present state and challenges of active learning in drug discovery

Active learning (AL) is an iterative feedback process that efficiently identifies valuable data within vast chemical space, even with limited labeled data. This characteristic renders it a valuable approach to tackle the ongoing challenges faced in drug discovery, such as the ever-expanding explore space and the limitations of labeled data. Consequently, AL is increasingly gaining prominence in the field of drug development. In this paper, we comprehensively review the application of AL at all stages of drug discovery, including compounds-target interaction prediction, virtual screening, molecular generation and optimization, as well as molecular properties prediction. Additionally, we discuss the challenges and prospects associated with the current applications of AL in drug discovery.

Consensus holistic virtual screening for drug discovery: a novel machine learning model approach

In drug discovery, virtual screening is crucial for identifying potential hit compounds. This study aims to present a novel pipeline that employs machine learning models that amalgamates various conventional screening methods. A diverse array of protein targets was selected, and their corresponding datasets were subjected to active/decoy distribution analysis prior to scoring using four distinct methods: QSAR, Pharmacophore, docking, and 2D shape similarity, which were ultimately integrated into a single consensus score. The fine-tuned machine learning models were ranked using the novel formula "w_new", consensus scores were calculated, and an enrichment study was performed for each target. Distinctively, consensus scoring outperformed other methods in specific protein targets such as PPARG and DPP4, achieving AUC values of 0.90 and 0.84, respectively. Remarkably, this approach consistently prioritized compounds with higher experimental PIC50 values compared to all other screening methodologies. Moreover, the models demonstrated a range of moderate to high performance in terms of R2 values during external validation. In conclusion, this novel workflow consistently delivered superior results, emphasizing the significance of a holistic approach in drug discovery, where both quantitative metrics and active enrichment play pivotal roles in identifying the best virtual screening methodology.Scientific contributionWe presented a novel consensus scoring workflow in virtual screening, merging diverse methods for enhanced compound selection. We also introduced 'w_new', a groundbreaking metric that intricately refines machine learning model rankings by weighing various model-specific parameters, revolutionizing their efficacy in drug discovery in addition to other domains.

Emerging Strategies in Mesenchymal Stem Cell-Based Cardiovascular Therapeutics

Cardiovascular diseases continue to challenge global health, demanding innovative therapeutic solutions. This review delves into the transformative role of mesenchymal stem cells (MSCs) in advancing cardiovascular therapeutics. Beginning with a historical perspective, we trace the development of stem cell research related to cardiovascular diseases, highlighting foundational therapeutic approaches and the evolution of cell-based treatments. Recognizing the inherent challenges of MSC-based cardiovascular therapeutics, which range from understanding the pro-reparative activity of MSCs to tailoring patient-specific treatments, we emphasize the need to refine the pro-regenerative capacity of these cells. Crucially, our focus then shifts to the strategies of the fourth generation of cell-based therapies: leveraging the secretomic prowess of MSCs, particularly the role of extracellular vesicles; integrating biocompatible scaffolds and artificial sheets to amplify MSCs' potential; adopting three-dimensional ex vivo propagation tailored to specific tissue niches; harnessing the promise of genetic modifications for targeted tissue repair; and institutionalizing good manufacturing practice protocols to ensure therapeutic safety and efficacy. We conclude with reflections on these advancements, envisaging a future landscape redefined by MSCs in cardiovascular regeneration. This review offers both a consolidation of our current understanding and a view toward imminent therapeutic horizons.

Advances in machine intelligence-driven virtual screening approaches for big-data

Virtual screening (VS) is an integral and ever-evolving domain of drug discovery framework. The VS is traditionally classified into ligand-based (LB) and structure-based (SB) approaches. Machine intelligence or artificial intelligence has wide applications in the drug discovery domain to reduce time and resource consumption. In combination with machine intelligence algorithms, VS has emerged into revolutionarily progressive technology that learns within robust decision orders for data curation and hit molecule screening from large VS libraries in minutes or hours. The exponential growth of chemical and biological data has evolved as "big-data" in the public domain demands modern and advanced machine intelligence-driven VS approaches to screen hit molecules from ultra-large VS libraries. VS has evolved from an individual approach (LB and SB) to integrated LB and SB techniques to explore various ligand and target protein aspects for the enhanced rate of appropriate hit molecule prediction. Current trends demand advanced and intelligent solutions to handle enormous data in drug discovery domain for screening and optimizing hits or lead with fewer or no false positive hits. Following the big-data drift and tremendous growth in computational architecture, we presented this review. Here, the article categorized and emphasized individual VS techniques, detailed literature presented for machine learning implementation, modern machine intelligence approaches, and limitations and deliberated the future prospects.

PPIscreenML: Structure-based screening for protein-protein interactions using AlphaFold

Protein-protein interactions underlie nearly all cellular processes. With the advent of protein structure prediction methods such as AlphaFold2 (AF2), models of specific protein pairs can be built extremely accurately in most cases. However, determining the relevance of a given protein pair remains an open question. It is presently unclear how to use best structure-based tools to infer whether a pair of candidate proteins indeed interact with one another: ideally, one might even use such information to screen amongst candidate pairings to build up protein interaction networks. Whereas methods for evaluating quality of modeled protein complexes have been co-opted for determining which pairings interact (e.g., pDockQ and iPTM), there have been no rigorously benchmarked methods for this task. Here we introduce PPIscreenML, a classification model trained to distinguish AF2 models of interacting protein pairs from AF2 models of compelling decoy pairings. We find that PPIscreenML out-performs methods such as pDockQ and iPTM for this task, and further that PPIscreenML exhibits impressive performance when identifying which ligand/receptor pairings engage one another across the structurally conserved tumor necrosis factor superfamily (TNFSF). Analysis of benchmark results using complexes not seen in PPIscreenML development strongly suggest that the model generalizes beyond training data, making it broadly applicable for identifying new protein complexes based on structural models built with AF2.

Machine Learning-Driven Classification of Urease Inhibitors Leveraging Physicochemical Properties as Effective Filter Criteria

Urease, a pivotal enzyme in nitrogen metabolism, plays a crucial role in various microorganisms, including the pathogenic Helicobacter pylori. Inhibiting urease activity offers a promising approach to combating infections and associated ailments, such as chronic kidney diseases and gastric cancer. However, identifying potent urease inhibitors remains challenging due to resistance issues that hinder traditional approaches. Recently, machine learning (ML)-based models have demonstrated the ability to predict the bioactivity of molecules rapidly and effectively. In this study, we present ML models designed to predict urease inhibitors by leveraging essential physicochemical properties. The methodological approach involved constructing a dataset of urease inhibitors through an extensive literature search. Subsequently, these inhibitors were characterized based on physicochemical properties calculations. An exploratory data analysis was then conducted to identify and analyze critical features. Ultimately, 252 classification models were trained, utilizing a combination of seven ML algorithms, three attribute selection methods, and six different strategies for categorizing inhibitory activity. The investigation unveiled discernible trends distinguishing urease inhibitors from non-inhibitors. This differentiation enabled the identification of essential features that are crucial for precise classification. Through a comprehensive comparison of ML algorithms, tree-based methods like random forest, decision tree, and XGBoost exhibited superior performance. Additionally, incorporating the "chemical family type" attribute significantly enhanced model accuracy. Strategies involving a gray-zone categorization demonstrated marked improvements in predictive precision. This research underscores the transformative potential of ML in predicting urease inhibitors. The meticulous methodology outlined herein offers actionable insights for developing robust predictive models within biochemical systems.

Machine Learning for Sequence and Structure-Based Protein-Ligand Interaction Prediction

Developing new drugs is too expensive and time -consuming. Accurately predicting the interaction between drugs and targets will likely change how the drug is discovered. Machine learning-based protein-ligand interaction prediction has demonstrated significant potential. In this paper, computational methods, focusing on sequence and structure to study protein-ligand interactions, are examined. Therefore, this paper starts by presenting an overview of the data sets applied in this area, as well as the various approaches applied for representing proteins and ligands. Then, sequence-based and structure-based classification criteria are subsequently utilized to categorize and summarize both the classical machine learning models and deep learning models employed in protein-ligand interaction studies. Moreover, the evaluation methods and interpretability of these models are proposed. Furthermore, delving into the diverse applications of protein-ligand interaction models in drug research is presented. Lastly, the current challenges and future directions in this field are addressed.

Drugging the entire human proteome: Are we there yet?

Each of the ∼20,000 proteins in the human proteome is a potential target for compounds that bind to it and modify its function. The 3D structures of most of these proteins are now available. Here, we discuss the prospects for using these structures to perform proteome-wide virtual HTS (VHTS). We compare physics-based (docking) and AI VHTS approaches, some of which are now being applied with large databases of compounds to thousands of targets. Although preliminary proteome-wide screens are now within our grasp, further methodological developments are expected to improve the accuracy of the results.

Preparation, Characterization, in-vitro and in-vivo Pharmacokinetic Evaluation of Thermostable Dimethyl Fumarate Cocrystals

Dimethyl fumarate (DMF) is an FDA-approved drug for treating relapsing-remitting multiple sclerosis; but it is susceptible to sublimation leading to its loss during processing. Cocrystals can protect against thermal energy via the interaction of DMF with a coformer via weak forces of interaction. With this hypothesis, we have, for the first time, prepared DMF cocrystals using the solvent evaporation method using coformers like citric acid and succinic acid screened by in-silico predictions and hydrogen bonding properties. Analysis using infra-red (IR), powder x-ray diffraction (PXRD), thermogravimetric analysis (TGA), differential scanning calorimetry (DSC), and sublimation evaluation characterized cocrystals and their thermostability. Comparative analysis of the release profile has been done by dissolution and pharmacokinetic study of DMF and its cocrystals. The cocrystals have improved thermal stability and better pharmacological activities than DMF. In the safety and efficacy evaluation of the formulated cocrystals, they were found to be non-cytotoxic, antioxidant, and inhibiting IL-6 and TNF-α in PBMC induced by lipopolysaccharide (LPS). We have obtained cocrystals of DMF with improved thermal stability and better pharmacological activities than DMF.

Engineering novel scaffolds for specific HDAC11 inhibitors against metabolic diseases exploiting deep learning, virtual screening, and molecular dynamics simulations

The prevalence of metabolic diseases is increasing at a frightening rate year by year. The burgeoning development of deep learning enables drug design to be more efficient, selective, and structurally novel. The critical relevance of Histone deacetylase 11 (HDAC11) to the pathogenesis of several metabolic diseases makes it a promising drug target for curbing metabolic disorders. The present study aims to design new specific HDAC11 inhibitors for the treatment of metabolic diseases. Deep learning was performed to learn the properties of existing HDAC11 inhibitors and yield a novel compound library containing 23,122 molecules. Subsequently, the compound library was screened by ADMET properties, Lipinski & Veber rules, traditional machine classification models, and molecular docking, and 10 compounds were screened as candidate HDAC11 inhibitors. The stability of the 10 new molecules was further evaluated by deploying RMSD, RMSF, MM/GBSA, free energy landscape mapping, and PCA analysis in molecular dynamics simulations. As a result, ten compounds, Cpd_17556, Cpd_2184, Cpd_8907, Cpd_7771, Cpd_14959, Cpd_7108, Cpd_12383, Cpd_13153, Cpd_14500and Cpd_21811, were characterized as good HDAC11 inhibitors and are expected to be promising drug candidates for metabolic disorders, and further in vitro, in vivo and clinical trials to demonstrate in the future.

Secondary metabolites and their bioactivities from Paecilomyces gunnii YMF1.00003

Four new polyketides (1-4) and seven known compounds (5-11) including three polyketides and four sterols were isolated from the fermented extracts of Paecilomyces gunnii YMF1.00003. The new chemical structures were determined through the analysis of the nuclear magnetic resonance and high-resolution electrospray ionization mass spectrometry, and their configurations were subsequently confirmed by nuclear overhauser effect spectroscopy, the calculated electronic circular dichroism (ECD) spectra, and quantum chemical calculations of the NMR data (qcc NMR). Based on the results of pre-activity screening and compound structure target prediction, certain metabolites were assayed to evaluate their cytotoxic and protein kinase Cα inhibitory activities. Results indicated that 3β-hydroxy-7α-methoxy-5α,6α-epoxy-8(14),22E-dien-ergosta (8) exhibited potent cytotoxic activity, with half-maximal inhibitory concentration values of 3.00 ± 0.27 to 15.69 ± 0.61 μM against five tumor cells, respectively. The new compound gunniiol A (1) showed weak cytotoxic activity at a concentration of 40 μM. At a concentration of 20 μg/mL, compounds 1, 6, and 7 exhibited protein kinase Cα inhibition by 43.63, 40.93, and 57.66%, respectively. This study is the first to report steroids demonstrating good cytotoxicity and polyketides exhibiting inhibitory activity against protein kinase Cα from the extracts of P. gunnii.

Inactive-enriched machine-learning models exploiting patent data improve structure-based virtual screening for PDL1 dimerizers

INTRODUCTION

Small-molecule Programmable Cell Death Protein 1/Programmable Death-Ligand 1 (PD1/PDL1) inhibition via PDL1 dimerization has the potential to lead to inexpensive drugs with better cancer patient outcomes and milder side effects. However, this therapeutic approach has proven challenging, with only one PDL1 dimerizer reaching early clinical trials so far. There is hence a need for fast and accurate methods to develop alternative PDL1 dimerizers.

OBJECTIVES

We aim to show that structure-based virtual screening (SBVS) based on PDL1-specific machine-learning (ML) scoring functions (SFs) is a powerful drug design tool for detecting PD1/PDL1 inhibitors via PDL1 dimerization.

METHODS

By incorporating the latest MLSF advances, we generated and evaluated PDL1-specific MLSFs (classifiers and inactive-enriched regressors) on two demanding test sets.

RESULTS

60 PDL1-specific MLSFs (30 classifiers and 30 regressors) were generated. Our large-scale analysis provides highly predictive PDL1-specific MLSFs that benefitted from training with large volumes of docked inactives and enabling inactive-enriched regression.

CONCLUSION

PDL1-specific MLSFs strongly outperformed generic SFs of various types on this target and are released here without restrictions.

T6496 targeting EGFR mediated by T790M or C797S mutant: machine learning, virtual screening and bioactivity evaluation study

Acquired resistance to EGFR is a major impediment in lung cancer treatment, highlighting the urgent need to discover novel compounds to overcome EGFR drug resistance. In this study, we utilized in silico methods and bioactivity evaluation for drug discovery to identify novel active anticancer agents targeting EGFRT790M/L858R and EGFRT790M/C797S/L858R. Firstly, we employed ROC-guided machine learning to retrieve nearly 7,765 compounds from a collection of three libraries (comprising over 220,000 compounds). Next, virtual screening, cluster analysis, and binding model analysis were employed to identify six potential compounds. Additionally, the kinase assay revealed that these six compounds demonstrated higher sensitivity to EGFR than c-Met. Among these compounds, T6496 inhibited both EGFRT790M/L858R and EGFRT790M/C797S/L858R kinases, with an IC50 of 3.30 and 8.72 μM. Furthermore, we evaluated the antitumor effects of the six selected compounds, and compound T6496 exhibited the strongest anticancer activity against H1975 cell lines, with an IC50 value of 2.7 μM. These results suggest that T6496 may mitigate EGFR resistance caused by T790M or C797S mutations. Moreover, the AO staining assay, JC-1 staining, ROS experiment and hemolytic toxicity evaluation revealed that T6496 could induce apoptosis in H1975 cell lines in a time-dependent and concentration-dependent manner, and is a potential compound for further structural optimization.Communicated by Ramaswamy H. Sarma.

Discovery of Novel Rhizoctonia solani DHFR Inhibitors as Fungicides Using Virtual Screening

Dihydrofolate reductase (DHFR) is an essential enzyme in the folate pathway and has been recognized as a well-known target for antibacterial and antifungal drugs. We discovered eight compounds from the ZINC database using virtual screening to inhibit Rhizoctonia solani (R. solani), a fungal pathogen in crops. These compounds were evaluated with in vitro assays for enzymatic and antifungal activity. Among these, compound Hit8 is the most active R. solani DHFR inhibitor, with the IC50 of 10.2 μM. The selectivity of inhibition is 22.3 against human DHFR with the IC50 of 227.7 μM. Moreover, Hit8 has higher antifungal activity against R. solani (EC50 of 38.2 mg L-1) compared with validamycin A (EC50 of 67.6 mg L-1), a well-documented fungicide. These results suggest that Hit8 may be a potential fungicide. Our study exemplifies a computer-aided method to discover novel inhibitors that could target plant pathogenic fungi.

Integrated Molecular Modeling and Machine Learning for Drug Design

Modern therapeutic development often involves several stages that are interconnected, and multiple iterations are usually required to bring a new drug to the market. Computational approaches have increasingly become an indispensable part of helping reduce the time and cost of the research and development of new drugs. In this Perspective, we summarize our recent efforts on integrating molecular modeling and machine learning to develop computational tools for modulator design, including a pocket-guided rational design approach based on AlphaSpace to target protein-protein interactions, delta machine learning scoring functions for protein-ligand docking as well as virtual screening, and state-of-the-art deep learning models to predict calculated and experimental molecular properties based on molecular mechanics optimized geometries. Meanwhile, we discuss remaining challenges and promising directions for further development and use a retrospective example of FDA approved kinase inhibitor Erlotinib to demonstrate the use of these newly developed computational tools.

Discovery of potent STAT3 inhibitors using structure-based virtual screening, molecular dynamic simulation, and biological evaluation

Introduction

Signal transducer and activator of transcription 3 (STAT3) is ubiquitously hyper-activated in numerous cancers, rendering it an appealing target for therapeutic intervention.

Methods and results

In this study, using structure-based virtual screening complemented by molecular dynamics simulations, we identified ten potential STAT3 inhibitors. The simulations pinpointed compounds 8, 9, and 10 as forming distinct hydrogen bonds with the SH2 domain of STAT3. In vitro cytotoxicity assays highlighted compound 4 as a potent inhibitor of gastric cancer cell proliferation across MGC803, KATO III, and NCI-N87 cell lines. Further cellular assays substantiated the ability of compound 4 to attenuate IL-6-mediated STAT3 phosphorylation at Tyr475. Additionally, oxygen consumption rate assays corroborated compound 4's deleterious effects on mitochondrial function.

Discussion

Collectively, our findings position compound 4 as a promising lead candidate warranting further exploration in the development of anti-gastric cancer therapeutics.

A practical guide to machine-learning scoring for structure-based virtual screening

Structure-based virtual screening (SBVS) via docking has been used to discover active molecules for a range of therapeutic targets. Chemical and protein data sets that contain integrated bioactivity information have increased both in number and in size. Artificial intelligence and, more concretely, its machine-learning (ML) branch, including deep learning, have effectively exploited these data sets to build scoring functions (SFs) for SBVS against targets with an atomic-resolution 3D model (e.g., generated by X-ray crystallography or predicted by AlphaFold2). Often outperforming their generic and non-ML counterparts, target-specific ML-based SFs represent the state of the art for SBVS. Here, we present a comprehensive and user-friendly protocol to build and rigorously evaluate these new SFs for SBVS. This protocol is organized into four sections: (i) using a public benchmark of a given target to evaluate an existing generic SF; (ii) preparing experimental data for a target from public repositories; (iii) partitioning data into a training set and a test set for subsequent target-specific ML modeling; and (iv) generating and evaluating target-specific ML SFs by using the prepared training-test partitions. All necessary code and input/output data related to three example targets (acetylcholinesterase, HMG-CoA reductase, and peroxisome proliferator-activated receptor-α) are available at https://github.com/vktrannguyen/MLSF-protocol , can be run by using a single computer within 1 week and make use of easily accessible software/programs (e.g., Smina, CNN-Score, RF-Score-VS and DeepCoy) and web resources. Our aim is to provide practical guidance on how to augment training data to enhance SBVS performance, how to identify the most suitable supervised learning algorithm for a data set, and how to build an SF with the highest likelihood of discovering target-active molecules within a given compound library.

Network-based drug repurposing for HPV-associated cervical cancer

In women, cervical cancer (CC) is the fourth most common cancer around the world with average cases of 604,000 and 342,000 deaths per year. Approximately 50% of high-grade CC are attributed to human papillomavirus (HPV) types 16 and 18. Chances of CC in HPV-positive patients are 6 times more than HPV-negative patients which demands timely and effective treatment. Repurposing of drugs is considered a viable approach to drug discovery which makes use of existing drugs, thus potentially reducing the time and costs associated with de-novo drug discovery. In this study, we present an integrative drug repurposing framework based on a systems biology-enabled network medicine platform. First, we built an HPV-induced CC protein interaction network named HPV2C following the CC signatures defined by the omics dataset, obtained from GEO database. Second, the drug target interaction (DTI) data obtained from DrugBank, and related databases was used to model the DTI network followed by drug target network proximity analysis of HPV-host associated key targets and DTIs in the human protein interactome. This analysis identified 142 potential anti-HPV repurposable drugs to target HPV induced CC pathways. Third, as per the literature survey 51 of the predicted drugs are already used for CC and 33 of the remaining drugs have anti-viral activity. Gene set enrichment analysis of potential drugs in drug-gene signatures and in HPV-induced CC-specific transcriptomic data in human cell lines additionally validated the predictions. Finally, 13 drug combinations were found using a network based on overlapping exposure. To summarize, the study provides effective network-based technique to quickly identify suitable repurposable drugs and drug combinations that target HPV-associated CC.

Evaluating Scalable Supervised Learning for Synthesize-on-Demand Chemical Libraries

Traditional small-molecule drug discovery is a time-consuming and costly endeavor. High-throughput chemical screening can only assess a tiny fraction of drug-like chemical space. The strong predictive power of modern machine-learning methods for virtual chemical screening enables training models on known active and inactive compounds and extrapolating to much larger chemical libraries. However, there has been limited experimental validation of these methods in practical applications on large commercially available or synthesize-on-demand chemical libraries. Through a prospective evaluation with the bacterial protein-protein interaction PriA-SSB, we demonstrate that ligand-based virtual screening can identify many active compounds in large commercial libraries. We use cross-validation to compare different types of supervised learning models and select a random forest (RF) classifier as the best model for this target. When predicting the activity of more than 8 million compounds from Aldrich Market Select, the RF substantially outperforms a naïve baseline based on chemical structure similarity. 48% of the RF's 701 selected compounds are active. The RF model easily scales to score one billion compounds from the synthesize-on-demand Enamine REAL database. We tested 68 chemically diverse top predictions from Enamine REAL and observed 31 hits (46%), including one with an IC50 value of 1.3 μM.

Exploring chemical space for lead identification by propagating on chemical similarity network

Motivation

Lead identification is a fundamental step to prioritize candidate compounds for downstream drug discovery process. Machine learning (ML) and deep learning (DL) approaches are widely used to identify lead compounds using both chemical property and experimental information. However, ML or DL methods rarely consider compound similarity information directly since ML and DL models use abstract representation of molecules for model construction. Alternatively, data mining approaches are also used to explore chemical space with drug candidates by screening undesirable compounds. A major challenge for data mining approaches is to develop efficient data mining methods that search large chemical space for desirable lead compounds with low false positive rate.

Results

In this work, we developed a network propagation (NP) based data mining method for lead identification that performs search on an ensemble of chemical similarity networks. We compiled 14 fingerprint-based similarity networks. Given a target protein of interest, we use a deep learning-based drug target interaction model to narrow down compound candidates and then we use network propagation to prioritize drug candidates that are highly correlated with drug activity score such as IC50. In an extensive experiment with BindingDB, we showed that our approach successfully discovered intentionally unlabeled compounds for given targets. To further demonstrate the prediction power of our approach, we identified 24 candidate leads for CLK1. Two out of five synthesizable candidates were experimentally validated in binding assays. In conclusion, our framework can be very useful for lead identification from very large compound databases such as ZINC.

Predicting Antibiotic Resistance in ICUs Patients by Applying Machine Learning in Vietnam

Introduction

Artificial Intelligence (AI) and machine learning (ML) are used extensively in HICs to detect and control antibiotic resistance (AMR) in laboratories and clinical institutions. ML is designed to predict outcome variables using an algorithm to enable "machines" to learn the "rules" from the data. ML is increasingly being applied in intensive care units to identify AMR and to assist empiric antibiotic therapy. This study aimed to evaluate the performance of ML models for predicting AMR bacteria and resistance to antibiotics in two Vietnamese hospitals.

Patients and Methods

A cross-sectional study combined with retrospective was conducted from 1st January 2020 to 30th June 2022. Five models were developed to predict antibiotic resistance of bacterial infections of ICU patients. Two datasets were prepared to predict AMR bacteria and antibiotics with ML models. The performance of the prediction models was evaluated by various indicators (sensitivity, specificity, precision, accuracy, F1-score, PRC, AuROC, and NormMCC) to determine the optimal time point for data selection. Python version 3.8 was used for statistical analyses.

Results

The accuracy, F1-score, AuROC, and normMMC of LightGBM, XGBoost, and Random Forest models were higher than those of other models in both datasets. In both datasets 1 and 2, accuracy, F1-score, AuROC and normMCC of the XGBoost model were the highest among five models (from 0.890 to 1.000). Only Random Forest models had specificity scores higher than 0.850. High scores of sensitivity, accuracy, precision, F1-score, and normMCC indicated that the models were making accurate predictions for datasets 1 and 2.

Conclusion

XGBoost, LightGBM, and Random Forest were the best-performed machine learning models to predict antibiotic resistance of bacterial infections of ICUs patients using the patients' EMRs.

Discovering small-molecule senolytics with deep neural networks

The accumulation of senescent cells is associated with aging, inflammation and cellular dysfunction. Senolytic drugs can alleviate age-related comorbidities by selectively killing senescent cells. Here we screened 2,352 compounds for senolytic activity in a model of etoposide-induced senescence and trained graph neural networks to predict the senolytic activities of >800,000 molecules. Our approach enriched for structurally diverse compounds with senolytic activity; of these, three drug-like compounds selectively target senescent cells across different senescence models, with more favorable medicinal chemistry properties than, and selectivity comparable to, those of a known senolytic, ABT-737. Molecular docking simulations of compound binding to several senolytic protein targets, combined with time-resolved fluorescence energy transfer experiments, indicate that these compounds act in part by inhibiting Bcl-2, a regulator of cellular apoptosis. We tested one compound, BRD-K56819078, in aged mice and found that it significantly decreased senescent cell burden and mRNA expression of senescence-associated genes in the kidneys. Our findings underscore the promise of leveraging deep learning to discover senotherapeutics.

Beware of Simple Methods for Structure-Based Virtual Screening: The Critical Importance of Broader Comparisons

We discuss how data unbiasing and simple methods such as protein-ligand Interaction FingerPrint (IFP) can overestimate virtual screening performance. We also show that IFP is strongly outperformed by target-specific machine-learning scoring functions, which were not considered in a recent report concluding that simple methods were better than machine-learning scoring functions at virtual screening.

An artificial neural network model to predict structure-based protein-protein free energy of binding from Rosetta-calculated properties

The prediction of the free energy (ΔG) of binding for protein-protein complexes is of general scientific interest as it has a variety of applications in the fields of molecular and chemical biology, materials science, and biotechnology. Despite its centrality in understanding protein association phenomena and protein engineering, the ΔG of binding is a daunting quantity to obtain theoretically. In this work, we devise a novel Artificial Neural Network (ANN) model to predict the ΔG of binding for a given three-dimensional structure of a protein-protein complex with Rosetta-calculated properties. Our model was tested using two data sets, and it presented a root-mean-square error ranging from 1.67 kcal mol^-1 to 2.45 kcal mol^-1, showing a better performance compared to the available state-of-the-art tools. Validation of the model for a variety of protein-protein complexes is showcased.

Molecular-evaluated and explainable drug repurposing for COVID-19 using ensemble knowledge graph embedding

The search for an effective drug is still urgent for COVID-19 as no drug with proven clinical efficacy is available. Finding the new purpose of an approved or investigational drug, known as drug repurposing, has become increasingly popular in recent years. We propose here a new drug repurposing approach for COVID-19, based on knowledge graph (KG) embeddings. Our approach learns "ensemble embeddings" of entities and relations in a COVID-19 centric KG, in order to get a better latent representation of the graph elements. Ensemble KG-embeddings are subsequently used in a deep neural network trained for discovering potential drugs for COVID-19. Compared to related works, we retrieve more in-trial drugs among our top-ranked predictions, thus giving greater confidence in our prediction for out-of-trial drugs. For the first time to our knowledge, molecular docking is then used to evaluate the predictions obtained from drug repurposing using KG embedding. We show that Fosinopril is a potential ligand for the SARS-CoV-2 nsp13 target. We also provide explanations of our predictions thanks to rules extracted from the KG and instanciated by KG-derived explanatory paths. Molecular evaluation and explanatory paths bring reliability to our results and constitute new complementary and reusable methods for assessing KG-based drug repurposing.

Machine learning-aided scoring of synthesis difficulties for designer chromosomes

Designer chromosomes are artificially synthesized chromosomes. Nowadays, these chromosomes have numerous applications ranging from medical research to the development of biofuels. However, some chromosome fragments can interfere with the chemical synthesis of designer chromosomes and eventually limit the widespread use of this technology. To address this issue, this study aimed to develop an interpretable machine learning framework to predict and quantify the synthesis difficulties of designer chromosomes in advance. Through the use of this framework, six key sequence features leading to synthesis difficulties were identified, and an eXtreme Gradient Boosting model was established to integrate these features. The predictive model achieved high-quality performance with an AUC of 0.895 in cross-validation and an AUC of 0.885 on an independent test set. Based on these results, the synthesis difficulty index (S-index) was proposed as a means of scoring and interpreting synthesis difficulties of chromosomes from prokaryotes to eukaryotes. The findings of this study emphasize the significant variability in synthesis difficulties between chromosomes and demonstrate the potential of the proposed model to predict and mitigate these difficulties through the optimization of the synthesis process and genome rewriting.

Application of computational methods for class A GPCR Ligand discovery

G protein-coupled receptors (GPCR) are integral membrane proteins of considerable interest as targets for drug development due to their role in transmitting cellular signals in a multitude of biological processes. Of the six classes categorizing GPCR (A, B, C, D, E, and F), class A contains the largest number of therapeutically relevant GPCR. Despite their importance as drug targets, many challenges exist for the discovery of novel class A GPCR ligands serving as drug precursors. Though knowledge of the structural and functional characteristics of GPCR has grown significantly over the past 20 years, a large portion of GPCR lack reported, experimentally determined structures. Furthermore, many GPCR have no known endogenous and/or synthetic ligands, limiting further exploration of their biochemical, cellular, and physiological roles. While many successes in GPCR ligand discovery have resulted from experimental high-throughput screening, computational methods have played an increasingly important role in GPCR ligand identification in the past decade. Here we discuss computational techniques applied to GPCR ligand discovery. This review summarizes class A GPCR structure/function and provides an overview of many obstacles currently faced in GPCR ligand discovery. Furthermore, we discuss applications and recent successes of computational techniques used to predict GPCR structure as well as present a summary of ligand- and structure-based methods used to identify potential GPCR ligands. Finally, we discuss computational hit list generation and refinement and provide comprehensive workflows for GPCR ligand identification.

Validation of Acetylcholinesterase Inhibition Machine Learning Models for Multiple Species

Acetylcholinesterase (AChE) is an important enzyme and target for human therapeutics, environmental safety, and global food supply. Inhibitors of this enzyme are also used for pest elimination and can be misused for suicide or chemical warfare. Adverse effects of AChE pesticides on nontarget organisms, such as fish, amphibians, and humans, have also occurred as a result of biomagnifications of these toxic compounds. We have exhaustively curated the public data for AChE inhibition data and developed machine learning classification models for seven different species. Each set of models were built using up to nine different algorithms for each species and Morgan fingerprints (ECFP6) with an activity cutoff of 1 μM. The human (4075 compounds) and eel (5459 compounds) consensus models predicted AChE inhibition activity using external test sets from literature data with 81% and 82% accuracy, respectively, while the reciprocal cross (76% and 82% percent accuracy) was not species-specific. In addition, we also created machine learning regression models for human and eel AChE inhibition to return a predicted IC₅₀ value for a queried molecule. We did observe an improved species specificity in the regression models, where a human support vector regression model of human AChE inhibition (3652 compounds) predicted the IC₅₀s of the human test set to a better extent than the eel regression model (4930 compounds) on the same test set, based on mean absolute percentage error (MAPE = 9.73% vs 13.4%). The predictive power of these models certainly benefits from increasing the chemical diversity of the training set, as evidenced by expanding our human classification model by incorporating data from the Tox21 library of compounds. Of the 10 compounds we tested that were predicted active by this expanded model, two showed >80% inhibition at 100 μM. This machine learning approach therefore offers the ability to rapidly score massive libraries of molecules against the models for AChE inhibition that can then be selected for future in vitro testing to identify potential toxins. It also enabled us to create a public website, MegaAChE, for single-molecule predictions of AChE inhibition using these models at megaache.collaborationspharma.com.

Computational Chemistry for the Identification of Lead Compounds for Radiotracer Development

The use of computer-aided drug design (CADD) for the identification of lead compounds in radiotracer development is steadily increasing. Traditional CADD methods, such as structure-based and ligand-based virtual screening and optimization, have been successfully utilized in many drug discovery programs and are highlighted throughout this review. First, we discuss the use of virtual screening for hit identification at the beginning of drug discovery programs. This is followed by an analysis of how the hits derived from virtual screening can be filtered and culled to highly probable candidates to test in in vitro assays. We then illustrate how CADD can be used to optimize the potency of experimentally validated hit compounds from virtual screening for use in positron emission tomography (PET). Finally, we conclude with a survey of the newest techniques in CADD employing machine learning (ML).

New avenues in artificial-intelligence-assisted drug discovery

Over the past decade, the amount of biomedical data available has grown at unprecedented rates. Increased automation technology and larger data volumes have encouraged the use of machine learning (ML) or artificial intelligence (AI) techniques for mining such data and extracting useful patterns. Because the identification of chemical entities with desired biological activity is a crucial task in drug discovery, AI technologies have the potential to accelerate this process and support decision making. In addition, the advent of deep learning (DL) has shown great promise in addressing diverse problems in drug discovery, such as de novo molecular design. Herein, we will appraise the current state-of-the-art in AI-assisted drug discovery, discussing the recent applications covering generative models for chemical structure generation, scoring functions to improve binding affinity and pose prediction, and molecular dynamics to assist in the parametrization, featurization and generalization tasks. Finally, we will discuss current hurdles and the strategies to overcome them, as well as potential future directions.

A novel strategy for designing the magic shotguns for distantly related target pairs

Due to its promising capacity in improving drug efficacy, polypharmacology has emerged to be a new theme in the drug discovery of complex disease. In the process of novel multi-target drugs (MTDs) discovery, in silico strategies come to be quite essential for the advantage of high throughput and low cost. However, current researchers mostly aim at typical closely related target pairs. Because of the intricate pathogenesis networks of complex diseases, many distantly related targets are found to play crucial role in synergistic treatment. Therefore, an innovational method to develop drugs which could simultaneously target distantly related target pairs is of utmost importance. At the same time, reducing the false discovery rate in the design of MTDs remains to be the daunting technological difficulty. In this research, effective small molecule clustering in the positive dataset, together with a putative negative dataset generation strategy, was adopted in the process of model constructions. Through comprehensive assessment on 10 target pairs with hierarchical similarity-levels, the proposed strategy turned out to reduce the false discovery rate successfully. Constructed model types with much smaller numbers of inhibitor molecules gained considerable yields and showed better false-hit controllability than before. To further evaluate the generalization ability, an in-depth assessment of high-throughput virtual screening on ChEMBL database was conducted. As a result, this novel strategy could hierarchically improve the enrichment factors for each target pair (especially for those distantly related/unrelated target pairs), corresponding to target pair similarity-levels.

Reducing false positive rate of docking-based virtual screening by active learning

Machine learning-based scoring functions (MLSFs) have become a very favorable alternative to classical scoring functions because of their potential superior screening performance. However, the information of negative data used to construct MLSFs was rarely reported in the literature, and meanwhile the putative inactive molecules recorded in existing databases usually have obvious bias from active molecules. Here we proposed an easy-to-use method named AMLSF that combines active learning using negative molecular selection strategies with MLSF, which can iteratively improve the quality of inactive sets and thus reduce the false positive rate of virtual screening. We chose energy auxiliary terms learning as the MLSF and validated our method on eight targets in the diverse subset of DUD-E. For each target, we screened the IterBioScreen database by AMLSF and compared the screening results with those of the four control models. The results illustrate that the number of active molecules in the top 1000 molecules identified by AMLSF was significantly higher than those identified by the control models. In addition, the free energy calculation results for the top 10 molecules screened out by the AMLSF, null model and control models based on DUD-E also proved that more active molecules can be identified, and the false positive rate can be reduced by AMLSF.

An Integrated Machine Learning Model To Spot Peptide Binding Pockets in 3D Protein Screening

The prediction of peptide-protein binding sites is of utmost importance to tackle the onset of severe neurodegenerative diseases and cancer. In this work, we detail a novel machine learning model based on Linear Discriminant Analysis (LDA) demonstrating to be highly predictive in detecting the putative protein binding regions of small peptides. Starting from 439 high-quality pockets derived from peptide-protein crystallographic complexes, three sets of well-established peptide-binding regions were first selected through a Partitioning Around Medoids (PAM) clustering algorithm based on morphological and energetic 3D GRID-MIF molecular descriptors. Next, the best combination between all the putative interacting peptide pockets and related GRID-MIF scores was automatically explored by using the LDA-based protocol implemented in BioGPS. This approach proved successful to recognize the actual interacting peptide regions (that is, AUC = 0.86 and partial ROC enrichment at 5% of 0.48) from all the other pockets of the protein. Validated on two external collections sets, including 445 and 347 crystallographic peptide-protein complexes, our LDA-based model could be effective to further run peptide-protein virtual screening campaigns.

A vending machine for drug-like molecules - automated synthesis of virtual screening hits

As a result of high false positive rates in virtual screening campaigns, prospective hits must be synthesised for validation. When done manually, this is a time consuming and laborious process. Large "on-demand" virtual libraries (>7 × 10¹² members), suitable for preparation using capsule-based automated synthesis and commercial building blocks, were evaluated to determine their structural novelty. One sub-library, constructed from iSnAP capsules, aldehydes and amines, contains unique scaffolds with drug-like physicochemical properties. Virtual screening hits from this iSnAP library were prepared in an automated fashion for evaluation against Aedes aegypti and Phytophthora infestans. In comparison to manual workflows, this approach provided a 10-fold improvement in user efficiency. A streamlined method of relative stereochemical assignment was also devised to augment the rapid synthesis. User efficiency was further improved to 100-fold by downscaling and parallelising capsule-based chemistry on 96-well plates equipped with filter bases. This work demonstrates that automated synthesis consoles can enable the rapid and reliable preparation of attractive virtual screening hits from large virtual libraries.

Discovery of novel anti-tumor compounds targeting PARP-1 with induction of autophagy through in silico and in vitro screening

Poly (ADP-ribose) polymerase 1 (PARP-1) is a critical enzyme involved in DNA damage repair and recombination, and shows great potential for drug development in the treatment of cancers with defective DNA repair. The anti-tumor activities of PARP-1 inhibitors are regulated by both inhibition activities and allosteric mechanisms of PARP-1, and may also be involved in an autophagy-mediated process. Screening PARP-1 inhibitors with potential allosteric mechanisms and induced autophagy process could achieve elevated potency toward cancer cell killing. In this study, we tried to discover novel anti-tumor compounds targeting PARP-1 by computer simulations and in vitro screening. In order to filter PARP-1 inhibitors that could affect the folding state of the helix domain (HD) on PARP-1, the free energy contribution of key residues on HD were systematically analyzed using the ligand-binding crystal structures and integrated into in silico screening workflow for the selection of 20 pick-up compounds. Four compounds (Chemdiv codes: 8012-0567, 8018-6529, 8018-7168, 8018-7603) were proved with above 40% inhibitory ratio targeting PARP-1 under 20 μM, and further performed binding mode prediction and dynamic effect evaluation by molecular dynamics simulation. Further in vitro assays showed that compounds 8018-6529 and 8018-7168 could inhibit the growth of the human colorectal cancer cell (HCT-116) with IC50 values of 4.30 and 9.29 μM and were accompanied with an induced autophagy process. Taken together, we discover two novel anti-tumor compounds that target PARP-1 with an induced autophagy process and provide potential hit compounds for the anti-cancer drug development.

Development of machine learning models for the screening of potential HSP90 inhibitors

Heat shock protein 90 (Hsp90) is a molecular chaperone playing a significant role in the folding of client proteins. This cellular protein is linked to the progression of several cancer types, including breast cancer, lung cancer, and gastrointestinal stromal tumors. Several oncogenic kinases are Hsp90 clients and their activity depends on this molecular chaperone. This makes HSP90 a prominent therapeutic target for cancer treatment. Studies have confirmed the inhibition of HSP90 as a striking therapeutic treatment for cancer management. In this study, we have utilized machine learning and different in silico approaches to screen the KCB database to identify the potential HSP90 inhibitors. Further evaluation of these inhibitors on various cancer cell lines showed favorable inhibitory activity. These inhibitors could serve as a basis for future development of effective HSP90 inhibitors.

Novel Efficient Multistage Lead Optimization Pipeline Experimentally Validated for DYRK1B Selective Inhibitors

In addition to general challenges in drug discovery such as the identification of lead compounds in time- and cost-effective ways, specific challenges also exist. Particularly, it is necessary to develop pharmacological inhibitors that effectively discriminate between closely related molecular targets. DYRK1B kinase is considered a valuable target for cancer-specific mono- or combination chemotherapy; however, the inhibition of its closely related DYRK1A kinase is not beneficial. Existing inhibitors target both kinases with essentially the same efficiency, and the unavailability of the DYRK1B crystal structure makes the discovery of DYRK1B-specific inhibitors even more challenging. Here, we propose a novel multi-stage compound discovery pipeline aimed at in silico identification of both potent and selective small molecules from a large set of initial candidates. The method uses structure-based docking and ligand-based quantitative structure–activity relationship modeling. This approach allowed us to identify lead and runner-up small-molecule compounds targeting DYRK1B with high efficiency and specificity.

Systematic Improvement of the Performance of Machine Learning Scoring Functions by Incorporating Features of Protein-Bound Water Molecules

Water molecules at the ligand-protein interfaces play crucial roles in the binding of the ligands, but the behavior of protein-bound water is largely ignored in many currently used machine learning (ML)-based scoring functions (SFs). In an attempt to improve the prediction performance of existing ML-based SFs, we estimated the water distribution with a HydraMap (HM) method and then incorporated the features extracted from protein-bound waters obtained in this way into three ML-based SFs: RF-Score, ECIF, and PLEC. It was found that a combination of HM-based features can consistently improve the performance of all three SFs, including their scoring, ranking, and docking power. HydraMap-based features show consistently good performance with both crystal structures and docked structures, demonstrating their robustness for SFs. Overall, HM-based features, which are a statistical representation of hydration sites at protein-ligand interfaces, are expected to improve the prediction performance for diverse SFs.

Protein Function Analysis through Machine Learning

Machine learning (ML) has been an important arsenal in computational biology used to elucidate protein function for decades. With the recent burgeoning of novel ML methods and applications, new ML approaches have been incorporated into many areas of computational biology dealing with protein function. We examine how ML has been integrated into a wide range of computational models to improve prediction accuracy and gain a better understanding of protein function. The applications discussed are protein structure prediction, protein engineering using sequence modifications to achieve stability and druggability characteristics, molecular docking in terms of protein–ligand binding, including allosteric effects, protein–protein interactions and protein-centric drug discovery. To quantify the mechanisms underlying protein function, a holistic approach that takes structure, flexibility, stability, and dynamics into account is required, as these aspects become inseparable through their interdependence. Another key component of protein function is conformational dynamics, which often manifest as protein kinetics. Computational methods that use ML to generate representative conformational ensembles and quantify differences in conformational ensembles important for function are included in this review. Future opportunities are highlighted for each of these topics.

Benchmarking AlphaFold-enabled molecular docking predictions for antibiotic discovery

Efficient identification of drug mechanisms of action remains a challenge. Computational docking approaches have been widely used to predict drug binding targets; yet, such approaches depend on existing protein structures, and accurate structural predictions have only recently become available from AlphaFold2. Here, we combine AlphaFold2 with molecular docking simulations to predict protein‐ligand interactions between 296 proteins spanning Escherichia coli's essential proteome, and 218 active antibacterial compounds and 100 inactive compounds, respectively, pointing to widespread compound and protein promiscuity. We benchmark model performance by measuring enzymatic activity for 12 essential proteins treated with each antibacterial compound. We confirm extensive promiscuity, but find that the average area under the receiver operating characteristic curve (auROC) is 0.48, indicating weak model performance. We demonstrate that rescoring of docking poses using machine learning‐based approaches improves model performance, resulting in average auROCs as large as 0.63, and that ensembles of rescoring functions improve prediction accuracy and the ratio of true‐positive rate to false‐positive rate. This work indicates that advances in modeling protein‐ligand interactions, particularly using machine learning‐based approaches, are needed to better harness AlphaFold2 for drug discovery.

Identification of Potential Cytochrome P450 3A5 Inhibitors: An Extensive Virtual Screening through Molecular Docking, Negative Image-Based Screening, Machine Learning and Molecular Dynamics Simulation Studies

Cytochrome P450 3A5 (CYP3A5) is one of the crucial CYP family members and has already proven to be an important drug target for cardiovascular diseases. In the current study, the PubChem database was screened through molecular docking and high-affinity molecules were adopted for further assessment. A negative image-based (NIB) model was used for a similarity search by considering the complementary shape and electrostatics of the target and small molecules. Further, the molecules were segregated into active and inactive groups through six machine learning (ML) matrices. The active molecules found in each ML model were used for in silico pharmacokinetics and toxicity assessments. A total of five molecules followed the acceptable pharmacokinetics and toxicity profiles. Several potential binding interactions between the proposed molecules and CYP3A5 were observed. The dynamic behavior of the selected molecules in the CYP3A5 was explored through a molecular dynamics (MD) simulation study. Several parameters obtained from the MD simulation trajectory explained the stability of the protein–ligand complexes in dynamic states. The high binding affinity of each molecule was revealed by the binding free energy calculation through the MM-GBSA methods. Therefore, it can be concluded that the proposed molecules might be potential CYP3A5 molecules for therapeutic application in cardiovascular diseases subjected to in vitro/in vivo validations.

Boosting Protein-Ligand Binding Pose Prediction and Virtual Screening Based on Residue-Atom Distance Likelihood Potential and Graph Transformer

The past few years have witnessed enormous progress toward applying machine learning approaches to the development of protein-ligand scoring functions. However, the robust performance and wide applicability of scoring functions remain a big challenge for increasing the success rate of docking-based virtual screening. Herein, a novel scoring function named RTMScore was developed by introducing a tailored residue-based graph representation strategy and several graph transformer layers for the learning of protein and ligand representations, followed by a mixture density network to obtain residue-atom distance likelihood potential. Our approach was resolutely validated on the CASF-2016 benchmark, and the results indicate that RTMScore can outperform almost all of the other state-of-the-art methods in terms of both the docking and screening powers. Further evaluation confirms the robustness of our approach that can not only retain its docking power on cross-docked poses but also achieve improved performance as a rescoring tool in larger-scale virtual screening.

Emerging frontiers in virtual drug discovery: From quantum mechanical methods to deep learning approaches

Virtual screening-based approaches to discover initial hit and lead compounds have the potential to reduce both the cost and time of early drug discovery stages, as well as to find inhibitors for even challenging target sites such as protein-protein interfaces. Here in this review, we provide an overview of the progress that has been made in virtual screening methodology and technology on multiple fronts in recent years. The advent of ultra-large virtual screens, in which hundreds of millions to billions of compounds are screened, has proven to be a powerful approach to discover highly potent hit compounds. However, these developments are just the tip of the iceberg, with new technologies and methods emerging to propel the field forward. Examples include novel machine-learning approaches, which can reduce the computational costs of virtual screening dramatically, while progress in quantum-mechanical approaches can increase the accuracy of predictions of various small molecule properties.

SCORCH: Improving structure-based virtual screening with machine learning classifiers, data augmentation, and uncertainty estimation

INTRODUCTION

The discovery of a new drug is a costly and lengthy endeavour. The computational prediction of which small molecules can bind to a protein target can accelerate this process if the predictions are fast and accurate enough. Recent machine-learning scoring functions re-evaluate the output of molecular docking to achieve more accurate predictions. However, previous scoring functions were trained on crystalised protein-ligand complexes and datasets of decoys. The limited availability of crystal structures and biases in the decoy datasets can lower the performance of scoring functions.

OBJECTIVES

To address key limitations of previous scoring functions and thus improve the predictive performance of structure-based virtual screening.

METHODS

A novel machine-learning scoring function was created, named SCORCH (Scoring COnsensus for RMSD-based Classification of Hits). To develop SCORCH, training data is augmented by considering multiple ligand poses and labelling poses based on their RMSD from the native pose. Decoy bias is addressed by generating property-matched decoys for each ligand and using the same methodology for preparing and docking decoys and ligands. A consensus of 3 different machine learning approaches is also used to improve performance.

RESULTS

We find that multi-pose augmentation in SCORCH improves its docking power and screening power on independent benchmark datasets. SCORCH outperforms an equivalent scoring function trained on single poses, with a 1% enrichment factor (EF) of 13.78 vs. 10.86 on 18 DEKOIS 2.0 targets and a mean native pose rank of 5.9 vs 30.4 on CSAR 2014. Additionally, SCORCH outperforms widely used scoring functions in virtual screening and pose prediction on independent benchmark datasets.

CONCLUSION

By rationally addressing key limitations of previous scoring functions, SCORCH improves the performance of virtual screening. SCORCH also provides an estimate of its uncertainty, which can help reduce the cost and time required for drug discovery.

Proteome-Wide Profiling of the Covalent-Druggable Cysteines with a Structure-Based Deep Graph Learning Network

Covalent ligands have attracted increasing attention due to their unique advantages, such as long residence time, high selectivity, and strong binding affinity. They also show promise for targets where previous efforts to identify noncovalent small molecule inhibitors have failed. However, our limited knowledge of covalent binding sites has hindered the discovery of novel ligands. Therefore, developing in silico methods to identify covalent binding sites is highly desirable. Here, we propose DeepCoSI, the first structure-based deep graph learning model to identify ligandable covalent sites in the protein. By integrating the characterization of the binding pocket and the interactions between each cysteine and the surrounding environment, DeepCoSI achieves state-of-the-art predictive performances. The validation on two external test sets which mimic the real application scenarios shows that DeepCoSI has strong ability to distinguish ligandable sites from the others. Finally, we profiled the entire set of protein structures in the RCSB Protein Data Bank (PDB) with DeepCoSI to evaluate the ligandability of each cysteine for covalent ligand design, and made the predicted data publicly available on website.