Deep Learning in Virtual Screening: Recent Applications and Developments

Harnessing machine learning potential for personalised drug design and overcoming drug resistance

Drug resistance in cancer treatment presents a significant challenge, necessitating innovative approaches to improve therapeutic efficacy. Integrating machine learning (ML) in cancer research is promising as ML algorithms outrival in analysing complex datasets, identifying patterns, and predicting treatment outcomes. Leveraging diverse data sources such as genomic profiles, clinical records, and drug response assays, ML uncovers molecular mechanisms of drug resistance, enabling personalised treatment, maximising efficacy and minimising adverse effects. Various ML algorithms contribute to the drug discovery process - Random Forest and Decision Trees predict drug-target interactions and aid in virtual screening, and SVM classify leads on bioactivity data. Neural Networks model QSAR to optimise lead compounds and K-means clustering group compounds with similar chemical properties aiding compound selection. Gaussian Processes predict drug responses, Bayesian Networks infer causal relationships, Autoencoders generate novel compounds, and Genetic Algorithms optimise molecular structures. These algorithms collectively enhance efficiency and success rates in drug design endeavours, from lead identification to optimisation and are cost-effective, empowering clinicians with real-time treatment monitoring and improving patient outcomes. This review highlights the immense potential of ML in revolutionising cancer care through effective drug design to reduce drug resistance, and we have also discussed various limitations and research gaps to understand better.

Identification of novel NLRP3 inhibitors as therapeutic options for epilepsy by machine learning-based virtual screening, molecular docking and biomolecular simulation studies

The NOD-Like Receptor Protein-3 (NLRP3) inflammasome is a key therapeutic target for the treatment of epilepsy and has been reported to regulate inflammation in several neurological diseases. In this study, a machine learning-based virtual screening strategy has investigated candidate active compounds that inhibit the NLRP3 inflammasome. As machine learning-based virtual screening has the potential to accurately predict protein-ligand binding and reduce false positives outcomes compared to traditional virtual screening. Briefly, classification models were created using Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbor (KNN) machine learning methods. To determine the most crucial features of a molecule's activity, feature selection was carried out. By utilizing 10-fold cross-validation, the created models were analyzed. Among the generated models, the RF model obtained the best results as compared to others. Therefore, the RF model was used as a screening tool against the large chemical databases. Molecular operating environment (MOE) and PyRx software's were applied for molecular docking. Also, using the Amber Tools program, molecular dynamics (MD) simulation of potent inhibitors was carried out. The results showed that the KNN, SVM, and RF accuracy was 0.911 %, 0.906 %, and 0.946 %, respectively. Moreover, the model has shown sensitivity of 0.82 %, 0.78 %, and 0.86 % and specificity of 0.95 %, 0.96 %, and 0.98 % respectively. By applying the model to the ZINC and South African databases, we identified 98 and 39 compounds, respectively, potentially possessing anti-NLRP3 activity. Also, a molecular docking analysis produced ten ZINC and seven South African compounds that has comparable binding affinities to the reference drug. Moreover, MD analysis of the two complexes revealed that the two compounds (ZINC000009601348 and SANC00225) form stable complexes with varying amounts of binding energy. The in-silico studies indicate that both compounds most likely display their inhibitory effect by inhibiting the NLRP3 protein.

Perspectives on current approaches to virtual screening in drug discovery

INTRODUCTION

For the past two decades, virtual screening (VS) has been an efficient hit finding approach for drug discovery. Today, billions of commercially accessible compounds are routinely screened, and many successful examples of VS have been reported. VS methods continue to evolve, including machine learning and physics-based methods.

AREAS COVERED

The authors examine recent examples of VS in drug discovery and discuss prospective hit finding results from the critical assessment of computational hit-finding experiments (CACHE) challenge. The authors also highlight the cost considerations and open-source options for conducting VS and examine chemical space coverage and library selections for VS.

EXPERT OPINION

The advancement of sophisticated VS approaches, including the use of machine learning techniques and increased computer resources as well as the ease of access to synthetically available chemical spaces, and commercial and open-source VS platforms allow for interrogating ultra-large libraries (ULL) of billions of molecules. An impressive number of prospective ULL VS campaigns have generated potent and structurally novel hits across many target classes. Nonetheless, many successful contemporary VS approaches still use considerably smaller focused libraries. This apparent dichotomy illustrates that VS is best conducted in a fit-for-purpose way choosing an appropriate chemical space. Better methods need to be developed to tackle more challenging targets.

Artificial intelligence for small molecule anticancer drug discovery

INTRODUCTION

The transition from conventional cytotoxic chemotherapy to targeted cancer therapy with small-molecule anticancer drugs has enhanced treatment outcomes. This approach, which now dominates cancer treatment, has its advantages. Despite the regulatory approval of several targeted molecules for clinical use, challenges such as low response rates and drug resistance still persist. Conventional drug discovery methods are costly and time-consuming, necessitating more efficient approaches. The rise of artificial intelligence (AI) and access to large-scale datasets have revolutionized the field of small-molecule cancer drug discovery. Machine learning (ML), particularly deep learning (DL) techniques, enables the rapid identification and development of novel anticancer agents by analyzing vast amounts of genomic, proteomic, and imaging data to uncover hidden patterns and relationships.

AREA COVERED

In this review, the authors explore the important landmarks in the history of AI-driven drug discovery. They also highlight various applications in small-molecule cancer drug discovery, outline the challenges faced, and provide insights for future research.

EXPERT OPINION

The advent of big data has allowed AI to penetrate and enable innovations in almost every stage of medicine discovery, transforming the landscape of oncology research through the development of state-of-the-art algorithms and models. Despite challenges in data quality, model interpretability, and technical limitations, advancements promise breakthroughs in personalized and precision oncology, revolutionizing future cancer management.

Enhancing Chemical Reaction Monitoring with a Deep Learning Model for NMR Spectra Image Matching to Target Compounds

In the synthetic laboratory, researchers typically rely on nuclear magnetic resonance (NMR) spectra to elucidate structures of synthesized products and confirm whether they match the desired target compounds. As chemical synthesis technology evolves toward intelligence and continuity, efficient computer-assisted structure elucidation (CASE) techniques are required to replace time-consuming manual analysis and provide the necessary speed. However, current CASE methods typically aim to derive precise chemical structures from spectroscopic data, yet they suffer from drawbacks such as low accuracy, high computational cost, and reliance on chemical libraries. In meticulously designed chemical synthesis reactions, researchers prioritize confirming the attainment of the target product based on NMR spectra, rather than focusing on identifying the specific product obtained. For this purpose, we innovatively developed a binary classification model, termed as MatCS, to directly predict the relationship between NMR spectra image (including 1H NMR and 13C NMR) and the molecular structure of the target compound. After evaluating various feature extraction methods, MatCS employs a combination of the Graph Attention Networks and Graph Convolutional Networks to learn the structural features of molecular graphs and the pretrained ResNet101 network with a Convolutional Block Attention Module to extract features from NMR spectra images. The results show that on a challenging Testsim data set, which poses difficulty in distinguishing spectra of similar molecular structures, MatCS achieves comprehensive evaluation metrics with an F1-score of 0.81 and an AUC value of 0.87. Simultaneously, it exhibited commendable performance on an external SDBS data set containing experimental NMR spectra, showcasing substantial potential for structural verification tasks in real automated chemical synthesis.

A review of deep learning methods for ligand based drug virtual screening

Drug discovery is costly and time consuming, and modern drug discovery endeavors are progressively reliant on computational methodologies, aiming to mitigate temporal and financial expenditures associated with the process. In particular, the time required for vaccine and drug discovery is prolonged during emergency situations such as the coronavirus 2019 pandemic. Recently, the performance of deep learning methods in drug virtual screening has been particularly prominent. It has become a concern for researchers how to summarize the existing deep learning in drug virtual screening, select different models for different drug screening problems, exploit the advantages of deep learning models, and further improve the capability of deep learning in drug virtual screening. This review first introduces the basic concepts of drug virtual screening, common datasets, and data representation methods. Then, large numbers of common deep learning methods for drug virtual screening are compared and analyzed. In addition, a dataset of different sizes is constructed independently to evaluate the performance of each deep learning model for the difficult problem of large-scale ligand virtual screening. Finally, the existing challenges and future directions in the field of virtual screening are presented.

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.

The Pan-Canadian Chemical Library: A Mechanism to Open Academic Chemistry to High-Throughput Virtual Screening

Computationally screening chemical libraries to discover molecules with desired properties is a common technique used in early-stage drug discovery. Recent progress in the field now enables the efficient exploration of billions of molecules within days or hours, but this exploration remains confined within the boundaries of the accessible chemistry space. While the number of commercially available compounds grows rapidly, it remains a limited subset of all druglike small molecules that could be synthesized. Here, we present a workflow where chemical reactions typically developed in academia and unconventional in drug discovery are exploited to dramatically expand the chemistry space accessible to virtual screening. We use this process to generate a first version of the Pan-Canadian Chemical Library, a collection of nearly 150 billion diverse compounds that does not overlap with other ultra-large libraries such as Enamine REAL or SAVI and could be a resource of choice for protein targets where other libraries have failed to deliver bioactive molecules.

Guided Docking as a Data Generation Approach Facilitates Structure-Based Machine Learning on Kinases

Drug discovery pipelines nowadays rely on machine learning models to explore and evaluate large chemical spaces. While including 3D structural information is considered beneficial, structural models are hindered by the availability of protein-ligand complex structures. Exemplified for kinase drug discovery, we address this issue by generating kinase-ligand complex data using template docking for the kinase compound subset of available ChEMBL assay data. To evaluate the benefit of the created complex data, we use it to train a structure-based E(3)-invariant graph neural network. Our evaluation shows that binding affinities can be predicted with significantly higher precision by models that take synthetic binding poses into account compared to ligand- or drug-target interaction models alone.

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.

Small-Molecule Inhibitors of TIPE3 Protein Identified through Deep Learning Suppress Cancer Cell Growth In Vitro

Tumor necrosis factor-α-induced protein 8-like 3 (TNFAIP8L3 or TIPE3) functions as a transfer protein for lipid second messengers. TIPE3 is highly upregulated in several human cancers and has been established to significantly promote tumor cell proliferation, migration, and invasion and inhibit the apoptosis of cancer cells. Thus, inhibiting the function of TIPE3 is expected to be an effective strategy against cancer. The advancement of artificial intelligence (AI)-driven drug development has recently invigorated research in anti-cancer drug development. In this work, we incorporated DFCNN, Autodock Vina docking, DeepBindBC, MD, and metadynamics to efficiently identify inhibitors of TIPE3 from a ZINC compound dataset. Six potential candidates were selected for further experimental study to validate their anti-tumor activity. Among these, three small-molecule compounds (K784-8160, E745-0011, and 7238-1516) showed significant anti-tumor activity in vitro, leading to reduced tumor cell viability, proliferation, and migration and enhanced apoptotic tumor cell death. Notably, E745-0011 and 7238-1516 exhibited selective cytotoxicity toward tumor cells with high TIPE3 expression while having little or no effect on normal human cells or tumor cells with low TIPE3 expression. A molecular docking analysis further supported their interactions with TIPE3, highlighting hydrophobic interactions and their shared interaction residues and offering insights for designing more effective inhibitors. Taken together, this work demonstrates the feasibility of incorporating deep learning and MD simulations in virtual drug screening and provides inhibitors with significant potential for anti-cancer drug development against TIPE3-.

Drug-Online: an online platform for drug-target interaction, affinity, and binding sites identification using deep learning

BACKGROUND

Accurately identifying drug-target interaction (DTI), affinity (DTA), and binding sites (DTS) is crucial for drug screening, repositioning, and design, as well as for understanding the functions of target. Although there are a few online platforms based on deep learning for drug-target interaction, affinity, and binding sites identification, there is currently no integrated online platforms for all three aspects.

RESULTS

Our solution, the novel integrated online platform Drug-Online, has been developed to facilitate drug screening, target identification, and understanding the functions of target in a progressive manner of "interaction-affinity-binding sites". Drug-Online platform consists of three parts: the first part uses the drug-target interaction identification method MGraphDTA, based on graph neural networks (GNN) and convolutional neural networks (CNN), to identify whether there is a drug-target interaction. If an interaction is identified, the second part employs the drug-target affinity identification method MMDTA, also based on GNN and CNN, to calculate the strength of drug-target interaction, i.e., affinity. Finally, the third part identifies drug-target binding sites, i.e., pockets. The method pt-lm-gnn used in this part is also based on GNN.

CONCLUSIONS

Drug-Online is a reliable online platform that integrates drug-target interaction, affinity, and binding sites identification. It is freely available via the Internet at http://39.106.7.26:8000/Drug-Online/ .

Combining Deep Learning and Structural Modeling to Identify Potential Acetylcholinesterase Inhibitors from Hericium erinaceus

Alzheimer's disease (AD) is the most common type of dementia, affecting over 50 million people worldwide. Currently, most approved medications for AD inhibit the activity of acetylcholinesterase (AChE), but these treatments often come with harmful side effects. There is growing interest in the use of natural compounds for disease prevention, alleviation, and treatment. This trend is driven by the anticipation that these substances may incur fewer side effects than existing medications. This research presents a computational approach combining machine learning with structural modeling to discover compounds from medicinal mushrooms with a high potential to inhibit the activity of AChE. First, we developed a deep neural network capable of rapidly screening a vast number of compounds to indicate their potential to inhibit AChE activity. Subsequently, we applied deep learning models to screen the compounds in the BACMUSHBASE database, which catalogs the bioactive compounds from cultivated and wild mushroom varieties local to Thailand, resulting in the identification of five promising compounds. Next, the five identified compounds underwent molecular docking techniques to calculate the binding energy between the compounds and AChE. This allowed us to refine the selection to two compounds, erinacerin A and hericenone B. Further analysis of the binding energy patterns between these compounds and the target protein revealed that both compounds displayed binding energy profiles similar to the combined characteristics of donepezil and galanthamine, the prescription drugs for AD. We propose that these two compounds, derived from Hericium erinaceus (also known as lion's mane mushroom), are suitable candidates for further research and development into symptom-alleviating AD medications.

From Proteins to Ligands: Decoding Deep Learning Methods for Binding Affinity Prediction

Accurate in silico prediction of protein-ligand binding affinity is important in the early stages of drug discovery. Deep learning-based methods exist but have yet to overtake more conventional methods such as giga-docking largely due to their lack of generalizability. To improve generalizability, we need to understand what these models learn from input protein and ligand data. We systematically investigated a sequence-based deep learning framework to assess the impact of protein and ligand encodings on predicting binding affinities for commonly used kinase data sets. The role of proteins is studied using convolutional neural network-based encodings obtained from sequences and graph neural network-based encodings enriched with structural information from contact maps. Ligand-based encodings are generated from graph-neural networks. We test different ligand perturbations by randomizing node and edge properties. For proteins, we make use of 3 different protein contact generation methods (AlphaFold2, Pconsc4, and ESM-1b) and compare these with a random control. Our investigation shows that protein encodings do not substantially impact the binding predictions, with no statistically significant difference in binding affinity for KIBA in the investigated metrics (concordance index, Pearson's R Spearman's Rank, and RMSE). Significant differences are seen for ligand encodings with random ligands and random ligand node properties, suggesting a much bigger reliance on ligand data for the learning tasks. Using different ways to combine protein and ligand encodings did not show a significant change in performance.

Benchmarking ANI potentials as a rescoring function and screening FDA drugs for SARS-CoV-2 Mpro

Here, we introduce the use of ANI-ML potentials as a rescoring function in the host-guest interaction in molecular docking. Our results show that the "docking power" of ANI potentials can compete with the current scoring functions at the same level of computational cost. Benchmarking studies on CASF-2016 dataset showed that ANI is ranked in the top 5 scoring functions among the other 34 tested. In particular, the ANI predicted interaction energies when used in conjunction with GOLD-PLP scoring function can boost the top ranked solution to be the closest to the x-ray structure. Rapid and accurate calculation of interaction energies between ligand and protein also enables screening of millions of drug candidates/docking poses. Using a unique protocol in which docking by GOLD-PLP, rescoring by ANI-ML potentials and extensive MD simulations along with end state free energy methods are combined, we have screened FDA approved drugs against the SARS-CoV-2 main protease (Mpro). The top six drug molecules suggested by the consensus of these free energy methods have already been in clinical trials or proposed as potential drug molecules in previous theoretical and experimental studies, approving the validity and the power of accuracy in our screening method.

Benchmarking Active Learning Protocols for Ligand-Binding Affinity Prediction

Active learning (AL) has become a powerful tool in computational drug discovery, enabling the identification of top binders from vast molecular libraries. To design a robust AL protocol, it is important to understand the influence of AL parameters, as well as the features of the data sets on the outcomes. We use four affinity data sets for different targets (TYK2, USP7, D2R, Mpro) to systematically evaluate the performance of machine learning models [Gaussian process (GP) model and Chemprop model], sample selection protocols, and the batch size based on metrics describing the overall predictive power of the model (R2, Spearman rank, root-mean-square error) as well as the accurate identification of top 2%/5% binders (Recall, F1 score). Both models have a comparable Recall of top binders on large data sets, but the GP model surpasses the Chemprop model when training data are sparse. A larger initial batch size, especially on diverse data sets, increased the Recall of both models as well as overall correlation metrics. However, for subsequent cycles, smaller batch sizes of 20 or 30 compounds proved to be desirable. Furthermore, adding artificial Gaussian noise to the data up to a certain threshold still allowed the model to identify clusters with top-scoring compounds. However, excessive noise (<1σ) did impact the model's predictive and exploitative capabilities.

Learnt representations of proteins can be used for accurate prediction of small molecule binding sites on experimentally determined and predicted protein structures

Protein-ligand binding site prediction is a useful tool for understanding the functional behaviour and potential drug-target interactions of a novel protein of interest. However, most binding site prediction methods are tested by providing crystallised ligand-bound (holo) structures as input. This testing regime is insufficient to understand the performance on novel protein targets where experimental structures are not available. An alternative option is to provide computationally predicted protein structures, but this is not commonly tested. However, due to the training data used, computationally-predicted protein structures tend to be extremely accurate, and are often biased toward a holo conformation. In this study we describe and benchmark IF-SitePred, a protein-ligand binding site prediction method which is based on the labelling of ESM-IF1 protein language model embeddings combined with point cloud annotation and clustering. We show that not only is IF-SitePred competitive with state-of-the-art methods when predicting binding sites on experimental structures, but it performs better on proxies for novel proteins where low accuracy has been simulated by molecular dynamics. Finally, IF-SitePred outperforms other methods if ensembles of predicted protein structures are generated.

Deep reinforcement learning enables better bias control in benchmark for virtual screening

Virtual screening (VS) has been incorporated into the paradigm of modern drug discovery. This field is now undergoing a new wave of revolution driven by artificial intelligence and more specifically, machine learning (ML). In terms of those out-of-the-box datasets for model training or benchmarking, their data volume and applicability domain are limited. They are suffering from the biases constantly reported in the ML application. To address these issues, we present a novel benchmark named MUBDsyn. The utilization of synthetic decoys (i.e., presumed inactives) is the main feature of MUBDsyn, where deep reinforcement learning was leveraged for bias control during decoy generation. Then, we carried out extensive validations on this new benchmark. First, we confirmed that MUBDsyn was superior to the classical benchmarks in control of domain bias, artificial enrichment bias and analogue bias. Moreover, we found that the assessment of ML models based on MUBDsyn was less biased as revealed by the analysis of asymmetric validation embedding bias. In addition, MUBDsyn showed better setting of benchmarking challenge for deep learning models compared with NRLiSt-BDB. Overall, we have proven that MUBDsyn is the close-to-ideal benchmark for VS. The computational tool is publicly available for the easy extension of MUBDsyn.

Docking and other computing tools in drug design against SARS-CoV-2

The use of computer simulation methods has become an indispensable component in identifying drugs against the SARS-CoV-2 coronavirus. There is a huge body of literature on application of molecular modelling to predict inhibitors against target proteins of SARS-CoV-2. To keep our review clear and readable, we limited ourselves primarily to works that use computational methods to find inhibitors and test the predicted compounds experimentally either in target protein assays or in cell culture with live SARS-CoV-2. Some works containing results of experimental discovery of corresponding inhibitors without using computer modelling are included as examples of a success. Also, some computational works without experimental confirmations are also included if they attract our attention either by simulation methods or by databases used. This review collects studies that use various molecular modelling methods: docking, molecular dynamics, quantum mechanics, machine learning, and others. Most of these studies are based on docking, and other methods are used mainly for post-processing to select the best compounds among those found through docking. Simulation methods are presented concisely, information is also provided on databases of organic compounds that can be useful for virtual screening, and the review itself is structured in accordance with coronavirus target proteins.

Navigating the Frontiers of Machine Learning in Neurodegenerative Disease Therapeutics

Recent advances in machine learning hold tremendous potential for enhancing the way we develop new medicines. Over the years, machine learning has been adopted in nearly all facets of drug discovery, including patient stratification, lead discovery, biomarker development, and clinical trial design. In this review, we will discuss the latest developments linking machine learning and CNS drug discovery. While machine learning has aided our understanding of chronic diseases like Alzheimer's disease and Parkinson's disease, only modest effective therapies currently exist. We highlight promising new efforts led by academia and emerging biotech companies to leverage machine learning for exploring new therapies. These approaches aim to not only accelerate drug development but to improve the detection and treatment of neurodegenerative diseases.

Discovery of hematopoietic progenitor kinase 1 inhibitors using machine learning-based screening and free energy perturbation

Hematopoietic progenitor kinase 1 (HPK1) is a key negative regulator of T-cell receptor (TCR) signaling and a promising target for cancer immunotherapy. The development of novel HPK1 inhibitors is challenging yet promising. In this study, we used a combination of machine learning (ML)-based virtual screening and free energy perturbation (FEP) calculations to identify novel HPK1 inhibitors. ML-based screening yielded 10 potent HPK1 inhibitors (IC50 < 1 μM). The FEP-guided modification of the in-house false-positive hit, DW21302, revealed that a single key atom change could trigger activity cliffs. The resulting DW21302-A was a potent HPK1 inhibitor (IC50 = 2.1 nM) and potently inhibited cellular HPK1 signaling and enhanced T-cell function. Molecular dynamics (MD) simulations and ADME predictions confirmed DW21302-A as candidate compound. This study provides new strategies and chemical scaffolds for HPK1 inhibitor development.Communicated by Ramaswamy H. Sarma.

AttentionMGT-DTA: A multi-modal drug-target affinity prediction using graph transformer and attention mechanism

The accurate prediction of drug-target affinity (DTA) is a crucial step in drug discovery and design. Traditional experiments are very expensive and time-consuming. Recently, deep learning methods have achieved notable performance improvements in DTA prediction. However, one challenge for deep learning-based models is appropriate and accurate representations of drugs and targets, especially the lack of effective exploration of target representations. Another challenge is how to comprehensively capture the interaction information between different instances, which is also important for predicting DTA. In this study, we propose AttentionMGT-DTA, a multi-modal attention-based model for DTA prediction. AttentionMGT-DTA represents drugs and targets by a molecular graph and binding pocket graph, respectively. Two attention mechanisms are adopted to integrate and interact information between different protein modalities and drug-target pairs. The experimental results showed that our proposed model outperformed state-of-the-art baselines on two benchmark datasets. In addition, AttentionMGT-DTA also had high interpretability by modeling the interaction strength between drug atoms and protein residues. Our code is available at https://github.com/JK-Liu7/AttentionMGT-DTA.

Fusing Sequence and Structural Knowledge by Heterogeneous Models to Accurately and Interpretively Predict Drug-Target Affinity

Drug-target affinity (DTA) prediction is crucial for understanding molecular interactions and aiding drug discovery and development. While various computational methods have been proposed for DTA prediction, their predictive accuracy remains limited, failing to delve into the structural nuances of interactions. With increasingly accurate and accessible structure prediction of targets, we developed a novel deep learning model, named S2DTA, to accurately predict DTA by fusing sequence features of drug SMILES, targets, and pockets and their corresponding graph structural features using heterogeneous models based on graph and semantic networks. Experimental findings underscored that complex feature representations imparted negligible enhancements to the model's performance. However, the integration of heterogeneous models demonstrably bolstered predictive accuracy. In comparison to three state-of-the-art methodologies, such as DeepDTA, GraphDTA, and DeepDTAF, S2DTA's performance became more evident. It exhibited a 25.2% reduction in mean absolute error (MAE) and a 20.1% decrease in root mean square error (RMSE). Additionally, S2DTA showed some improvements in other crucial metrics, including Pearson Correlation Coefficient (PCC), Spearman, Concordance Index (CI), and R2, with these metrics experiencing increases of 19.6%, 17.5%, 8.1%, and 49.4%, respectively. Finally, we conducted an interpretability analysis on the effectiveness of S2DTA by bidirectional self-attention mechanism. The analysis results supported that S2DTA was an effective and accurate tool for predicting DTA.

Computational methods in glaucoma research: Current status and future outlook

Advancements in computational techniques have transformed glaucoma research, providing a deeper understanding of genetics, disease mechanisms, and potential therapeutic targets. Systems genetics integrates genomic and clinical data, aiding in identifying drug targets, comprehending disease mechanisms, and personalizing treatment strategies for glaucoma. Molecular dynamics simulations offer valuable molecular-level insights into glaucoma-related biomolecule behavior and drug interactions, guiding experimental studies and drug discovery efforts. Artificial intelligence (AI) technologies hold promise in revolutionizing glaucoma research, enhancing disease diagnosis, target identification, and drug candidate selection. The generalized protocols for systems genetics, MD simulations, and AI model development are included as a guide for glaucoma researchers. These computational methods, however, are not separate and work harmoniously together to discover novel ways to combat glaucoma. Ongoing research and progresses in genomics technologies, MD simulations, and AI methodologies project computational methods to become an integral part of glaucoma research in the future.

CODD-Pred: A Web Server for Efficient Target Identification and Bioactivity Prediction of Small Molecules

Target identification and bioactivity prediction are critical steps in the drug discovery process. Here we introduce CODD-Pred (COmprehensive Drug Design Predictor), an online web server with well-curated data sets from the GOSTAR database, which is designed with a dual purpose of predicting potential protein drug targets and computing bioactivity values of small molecules. We first designed a double molecular graph perception (DMGP) framework for target prediction based on a large library of 646 498 small molecules interacting with 640 human targets. The framework achieved a top-5 accuracy of over 80% for hitting at least one target on both external validation sets. Additionally, its performance on the external validation set comprising 200 molecules surpassed that of four existing target prediction servers. Second, we collected 56 targets closely related to the occurrence and development of cancer, metabolic diseases, and inflammatory immune diseases and developed a multi-model self-validation activity prediction (MSAP) framework that enables accurate bioactivity quantification predictions for small-molecule ligands of these 56 targets. CODD-Pred is a handy tool for rapid evaluation and optimization of small molecules with specific target activity. CODD-Pred is freely accessible at http://codd.iddd.group/.

Multi-shelled ECIF: improved extended connectivity interaction features for accurate binding affinity prediction

Motivation

Extended connectivity interaction features (ECIF) is a method developed to predict protein-ligand binding affinity, allowing for detailed atomic representation. It performed very well in terms of Comparative Assessment of Scoring Functions 2016 (CASF-2016) scoring power. However, ECIF has the limitation of not being able to adequately account for interatomic distances.

Results

To investigate what kind of distance representation is effective for P-L binding affinity prediction, we have developed two algorithms that improved ECIF's feature extraction method to take distance into account. One is multi-shelled ECIF, which takes into account the distance between atoms by dividing the distance between atoms into multiple layers. The other is weighted ECIF, which weights the importance of interactions according to the distance between atoms. A comparison of these two methods shows that multi-shelled ECIF outperforms weighted ECIF and the original ECIF, achieving a CASF-2016 scoring power Pearson correlation coefficient of 0.877.

Availability and implementation

All the codes and data are available on GitHub (https://github.com/koji11235/MSECIFv2).

Machine learning-based model for accurate identification of druggable proteins using light extreme gradient boosting

The identification of druggable proteins (DPs) is significant for the development of new drugs, personalized medicine, understanding of disease mechanisms, drug repurposing, and economic benefits. By identifying new druggable targets, researchers can develop new therapies for a range of diseases, leading to better patient outcomes. Identification of DPs by machine learning strategies is more efficient and cost-effective than conventional methods. In this study, a computational predictor, namely Drug-LXGB, is introduced to enhance the identification of DPs. Features are discovered by composition, transition, and distribution (CTD), composition of K-spaced amino acid pair (CKSAAP), pseudo-position-specific scoring matrix (PsePSSM), and a novel descriptor, called multi-block pseudo amino acid composition (MB-PseAAC). The dimensions of CTD, CKSAAP, PsePSSM, and MB-PseAAC are integrated and utilized the sequential forward selection as feature selection algorithm. The best characteristics are provided by random forest, extreme gradient boosting, and light eXtreme gradient boosting (LXGB). The predictive analysis of these learning methods is measured via 10-fold cross-validation. The LXGB-based model secures the highest results than other existing predictors. Our novel protocol will perform an active role in designing novel drugs and would be fruitful to explore the potential target. This study will help better to capture a more universal view of a potential target.Communicated by Ramaswamy H. Sarma.

Benchmarking Cross-Docking Strategies for Structure-Informed Machine Learning in Kinase Drug Discovery

In recent years machine learning has transformed many aspects of the drug discovery process including small molecule design for which the prediction of the bioactivity is an integral part. Leveraging structural information about the interactions between a small molecule and its protein target has great potential for downstream machine learning scoring approaches, but is fundamentally limited by the accuracy with which protein:ligand complex structures can be predicted in a reliable and automated fashion. With the goal of finding practical approaches to generating useful kinase:inhibitor complex geometries for downstream machine learning scoring approaches, we present a kinase-centric docking benchmark assessing the performance of different classes of docking and pose selection strategies to assess how well experimentally observed binding modes are recapitulated in a realistic cross-docking scenario. The assembled benchmark data set focuses on the well-studied protein kinase family and comprises a subset of 589 protein structures co-crystallized with 423 ATP-competitive ligands. We find that the docking methods biased by the co-crystallized ligand-utilizing shape overlap with or without maximum common substructure matching-are more successful in recovering binding poses than standard physics-based docking alone. Also, docking into multiple structures significantly increases the chance to generate a low RMSD docking pose. Docking utilizing an approach that combines all three methods (Posit) into structures with the most similar co-crystallized ligands according to shape and electrostatics proofed to be the most efficient way to reproduce binding poses achieving a success rate of 66.9 % across all included systems. The studied docking and pose selection strategies-which utilize the OpenEye Toolkit-were implemented into pipelines of the KinoML framework allowing automated and reliable protein:ligand complex generation for future downstream machine learning tasks. Although focused on protein kinases, we believe the general findings can also be transferred to other protein families.

Discovery of novel JAK1 inhibitors through combining machine learning, structure-based pharmacophore modeling and bio-evaluation

BACKGROUND

Janus kinase 1 (JAK1) plays a critical role in most cytokine-mediated inflammatory, autoimmune responses and various cancers via the JAK/STAT signaling pathway. Inhibition of JAK1 is therefore an attractive therapeutic strategy for several diseases. Recently, high-performance machine learning techniques have been increasingly applied in virtual screening to develop new kinase inhibitors. Our study aimed to develop a novel layered virtual screening method based on machine learning (ML) and pharmacophore models to identify the potential JAK1 inhibitors.

METHODS

Firstly, we constructed a high-quality dataset comprising 3834 JAK1 inhibitors and 12,230 decoys, followed by establishing a series of classification models based on a combination of three molecular descriptors and six ML algorithms. To further screen potential compounds, we constructed several pharmacophore models based on Hiphop and receptor-ligand algorithms. We then used molecular docking to filter the recognized compounds. Finally, the binding stability and enzyme inhibition activity of the identified compounds were assessed by molecular dynamics (MD) simulations and in vitro enzyme activity tests.

RESULTS

The best performance ML model DNN-ECFP4 and two pharmacophore models Hiphop3 and 6TPF 08 were utilized to screen the ZINC database. A total of 13 potentially active compounds were screened and the MD results demonstrated that all of the above molecules could bind with JAK1 stably in dynamic conditions. Among the shortlisted compounds, the four purchasable compounds demonstrated significant kinase inhibition activity, with Z-10 being the most active (IC50 = 194.9 nM).

CONCLUSION

The current study provides an efficient and accurate integrated model. The hit compounds were promising candidates for the further development of novel JAK1 inhibitors.

Open-Source Machine Learning in Computational Chemistry

The field of computational chemistry has seen a significant increase in the integration of machine learning concepts and algorithms. In this Perspective, we surveyed 179 open-source software projects, with corresponding peer-reviewed papers published within the last 5 years, to better understand the topics within the field being investigated by machine learning approaches. For each project, we provide a short description, the link to the code, the accompanying license type, and whether the training data and resulting models are made publicly available. Based on those deposited in GitHub repositories, the most popular employed Python libraries are identified. We hope that this survey will serve as a resource to learn about machine learning or specific architectures thereof by identifying accessible codes with accompanying papers on a topic basis. To this end, we also include computational chemistry open-source software for generating training data and fundamental Python libraries for machine learning. Based on our observations and considering the three pillars of collaborative machine learning work, open data, open source (code), and open models, we provide some suggestions to the community.

Recent Developments in Ultralarge and Structure-Based Virtual Screening Approaches

Drug development is a wide scientific field that faces many challenges these days. Among them are extremely high development costs, long development times, and a small number of new drugs that are approved each year. New and innovative technologies are needed to solve these problems that make the drug discovery process of small molecules more time and cost efficient, and that allow previously undruggable receptor classes to be targeted, such as protein-protein interactions. Structure-based virtual screenings (SBVSs) have become a leading contender in this context. In this review, we give an introduction to the foundations of SBVSs and survey their progress in the past few years with a focus on ultralarge virtual screenings (ULVSs). We outline key principles of SBVSs, recent success stories, new screening techniques, available deep learning-based docking methods, and promising future research directions. ULVSs have an enormous potential for the development of new small-molecule drugs and are already starting to transform early-stage drug discovery.

Employing Molecular Conformations for Ligand-Based Virtual Screening with Equivariant Graph Neural Network and Deep Multiple Instance Learning

Ligand-based virtual screening (LBVS) is a promising approach for rapid and low-cost screening of potentially bioactive molecules in the early stage of drug discovery. Compared with traditional similarity-based machine learning methods, deep learning frameworks for LBVS can more effectively extract high-order molecule structure representations from molecular fingerprints or structures. However, the 3D conformation of a molecule largely influences its bioactivity and physical properties, and has rarely been considered in previous deep learning-based LBVS methods. Moreover, the relative bioactivity benchmark dataset is still lacking. To address these issues, we introduce a novel end-to-end deep learning architecture trained from molecular conformers for LBVS. We first extracted molecule conformers from multiple public molecular bioactivity data and consolidated them into a large-scale bioactivity benchmark dataset, which totally includes millions of endpoints and molecules corresponding to 954 targets. Then, we devised a deep learning-based LBVS called EquiVS to learn molecule representations from conformers for bioactivity prediction. Specifically, graph convolutional network (GCN) and equivariant graph neural network (EGNN) are sequentially stacked to learn high-order molecule-level and conformer-level representations, followed with attention-based deep multiple-instance learning (MIL) to aggregate these representations and then predict the potential bioactivity for the query molecule on a given target. We conducted various experiments to validate the data quality of our benchmark dataset, and confirmed EquiVS achieved better performance compared with 10 traditional machine learning or deep learning-based LBVS methods. Further ablation studies demonstrate the significant contribution of molecular conformation for bioactivity prediction, as well as the reasonability and non-redundancy of deep learning architecture in EquiVS. Finally, a model interpretation case study on CDK2 shows the potential of EquiVS in optimal conformer discovery. The overall study shows that our proposed benchmark dataset and EquiVS method have promising prospects in virtual screening applications.

Recent Advances in Computer-Aided Structure-Based Drug Design on Ion Channels

Ion channels play important roles in fundamental biological processes, such as electric signaling in cells, muscle contraction, hormone secretion, and regulation of the immune response. Targeting ion channels with drugs represents a treatment option for neurological and cardiovascular diseases, muscular degradation disorders, and pathologies related to disturbed pain sensation. While there are more than 300 different ion channels in the human organism, drugs have been developed only for some of them and currently available drugs lack selectivity. Computational approaches are an indispensable tool for drug discovery and can speed up, especially, the early development stages of lead identification and optimization. The number of molecular structures of ion channels has considerably increased over the last ten years, providing new opportunities for structure-based drug development. This review summarizes important knowledge about ion channel classification, structure, mechanisms, and pathology with the main focus on recent developments in the field of computer-aided, structure-based drug design on ion channels. We highlight studies that link structural data with modeling and chemoinformatic approaches for the identification and characterization of new molecules targeting ion channels. These approaches hold great potential to advance research on ion channel drugs in the future.

Deep Learning Methods Applied to Drug Concentration Prediction of Olanzapine

Pharmacometrics and the utilization of population pharmacokinetics play an integral role in model-informed drug discovery and development (MIDD). Recently, there has been a growth in the application of deep learning approaches to aid in areas within MIDD. In this study, a deep learning model, LSTM-ANN, was developed to predict olanzapine drug concentrations from the CATIE study. A total of 1527 olanzapine drug concentrations from 523 individuals along with 11 patient-specific covariates were used in model development. The hyperparameters of the LSTM-ANN model were optimized through a Bayesian optimization algorithm. A population pharmacokinetic model using the NONMEM model was constructed as a reference to compare to the performance of the LSTM-ANN model. The RMSE of the LSTM-ANN model was 29.566 in the validation set, while the RMSE of the NONMEM model was 31.129. Permutation importance revealed that age, sex, and smoking were highly influential covariates in the LSTM-ANN model. The LSTM-ANN model showed potential in the application of drug concentration predictions as it was able to capture the relationships within a sparsely sampled pharmacokinetic dataset and perform comparably to the NONMEM model.

A Systematic Review of Deep Learning Methodologies Used in the Drug Discovery Process with Emphasis on In Vivo Validation

The discovery and development of new drugs are extremely long and costly processes. Recent progress in artificial intelligence has made a positive impact on the drug development pipeline. Numerous challenges have been addressed with the growing exploitation of drug-related data and the advancement of deep learning technology. Several model frameworks have been proposed to enhance the performance of deep learning algorithms in molecular design. However, only a few have had an immediate impact on drug development since computational results may not be confirmed experimentally. This systematic review aims to summarize the different deep learning architectures used in the drug discovery process and are validated with further in vivo experiments. For each presented study, the proposed molecule or peptide that has been generated or identified by the deep learning model has been biologically evaluated in animal models. These state-of-the-art studies highlight that even if artificial intelligence in drug discovery is still in its infancy, it has great potential to accelerate the drug discovery cycle, reduce the required costs, and contribute to the integration of the 3R (Replacement, Reduction, Refinement) principles. Out of all the reviewed scientific articles, seven algorithms were identified: recurrent neural networks, specifically, long short-term memory (LSTM-RNNs), Autoencoders (AEs) and their Wasserstein Autoencoders (WAEs) and Variational Autoencoders (VAEs) variants; Convolutional Neural Networks (CNNs); Direct Message Passing Neural Networks (D-MPNNs); and Multitask Deep Neural Networks (MTDNNs). LSTM-RNNs were the most used architectures with molecules or peptide sequences as inputs.

BEAR: A Novel Virtual Screening Method Based on Large-Scale Bioactivity Data

Data-driven drug discovery exploits a comprehensive set of big data to provide an efficient path for the development of new drugs. Currently, publicly available bioassay data sets provide extensive information regarding the bioactivity profiles of millions of compounds. Using these large-scale drug screening data sets, we developed a novel in silico method to virtually screen hit compounds against protein targets, named BEAR (Bioactive compound Enrichment by Assay Repositioning). The underlying idea of BEAR is to reuse bioassay data for predicting hit compounds for targets other than their originally intended purposes, i.e., "assay repositioning". The BEAR approach differs from conventional virtual screening methods in that (1) it relies solely on bioactivity data and requires no physicochemical features of either the target or ligand. (2) Accordingly, structurally diverse candidates are predicted, allowing for scaffold hopping. (3) BEAR shows stable performance across diverse target classes, suggesting its general applicability. Large-scale cross-validation of more than a thousand targets showed that BEAR accurately predicted known ligands (median area under the curve = 0.87), proving that BEAR maintained a robust performance even in the validation set with additional constraints. In addition, a comparative analysis demonstrated that BEAR outperformed other machine learning models, including a recent deep learning model for ABC transporter family targets. We predicted P-gp and BCRP dual inhibitors using the BEAR approach and validated the predicted candidates using in vitro assays. The intracellular accumulation effects of mitoxantrone, a well-known P-gp/BCRP dual substrate for cancer treatment, confirmed nine out of 72 dual inhibitor candidates preselected by primary cytotoxicity screening. Consequently, these nine hits are novel and potent dual inhibitors for both P-gp and BCRP, solely predicted by bioactivity profiles without relying on any structural information of targets or ligands.

Predicting molecular properties based on the interpretable graph neural network with multistep focus mechanism

Graph neural networks based on deep learning methods have been extensively applied to the molecular property prediction because of its powerful feature learning ability and good performance. However, most of them are black boxes and cannot give the reasonable explanation about the underlying prediction mechanisms, which seriously reduce people's trust on the neural network-based prediction models. Here we proposed a novel graph neural network named iteratively focused graph network (IFGN), which can gradually identify the key atoms/groups in the molecule that are closely related to the predicted properties by the multistep focus mechanism. At the same time, the combination of the multistep focus mechanism with visualization can also generate multistep interpretations, thus allowing us to gain a deep understanding of the predictive behaviors of the model. For all studied eight datasets, the IFGN model achieved good prediction performance, indicating that the proposed multistep focus mechanism also can improve the performance of the model obviously besides increasing the interpretability of built model. For researchers to use conveniently, the corresponding website (http://graphadmet.cn/works/IFGN) was also developed and can be used free of charge.

Identifying Novel Inhibitors for Hepatic Organic Anion Transporting Polypeptides by Machine Learning-Based Virtual Screening

Integration of statistical learning methods with structure-based modeling approaches is a contemporary strategy to identify novel lead compounds in drug discovery. Hepatic organic anion transporting polypeptides (OATP1B1, OATP1B3, and OATP2B1) are classical off-targets, and it is well recognized that their ability to interfere with a wide range of chemically unrelated drugs, environmental chemicals, or food additives can lead to unwanted adverse effects like liver toxicity and drug-drug or drug-food interactions. Therefore, the identification of novel (tool) compounds for hepatic OATPs by virtual screening approaches and subsequent experimental validation is a major asset for elucidating structure-function relationships of (related) transporters: they enhance our understanding about molecular determinants and structural aspects of hepatic OATPs driving ligand binding and selectivity. In the present study, we performed a consensus virtual screening approach by using different types of machine learning models (proteochemometric models, conformal prediction models, and XGBoost models for hepatic OATPs), followed by molecular docking of preselected hits using previously established structural models for hepatic OATPs. Screening the diverse REAL drug-like set (Enamine) shows a comparable hit rate for OATP1B1 (36% actives) and OATP1B3 (32% actives), while the hit rate for OATP2B1 was even higher (66% actives). Percentage inhibition values for 44 selected compounds were determined using dedicated in vitro assays and guided the prioritization of several highly potent novel hepatic OATP inhibitors: six (strong) OATP2B1 inhibitors (IC₅₀ values ranging from 0.04 to 6 μM), three OATP1B1 inhibitors (2.69 to 10 μM), and five OATP1B3 inhibitors (1.53 to 10 μM) were identified. Strikingly, two novel OATP2B1 inhibitors were uncovered (C7 and H5) which show high affinity (IC₅₀ values: 40 nM and 390 nM) comparable to the recently described estrone-based inhibitor (IC₅₀ = 41 nM). A molecularly detailed explanation for the observed differences in ligand binding to the three transporters is given by means of structural comparison of the detected binding sites and docking poses.

Machine intelligence-driven framework for optimized hit selection in virtual screening

Virtual screening (VS) aids in prioritizing unknown bio-interactions between compounds and protein targets for empirical drug discovery. In standard VS exercise, roughly 10% of top-ranked molecules exhibit activity when examined in biochemical assays, which accounts for many false positive hits, making it an arduous task. Attempts for conquering false-hit rates were developed through either ligand-based or structure-based VS separately; however, nonetheless performed remarkably well. Here, we present an advanced VS framework—automated hit identification and optimization tool (A-HIOT)—comprises chemical space-driven stacked ensemble for identification and protein space-driven deep learning architectures for optimization of an array of specific hits for fixed protein receptors. A-HIOT implements numerous open-source algorithms intending to integrate chemical and protein space leading to a high-quality prediction. The optimized hits are the selective molecules which we retrieve after extreme refinement implying chemical space and protein space modules of A-HIOT. Using CXC chemokine receptor 4, we demonstrated the superior performance of A-HIOT for hit molecule identification and optimization with tenfold cross-validation accuracies of 94.8% and 81.9%, respectively. In comparison with other machine learning algorithms, A-HIOT achieved higher accuracies of 96.2% for hit identification and 89.9% for hit optimization on independent benchmark datasets for CXCR4 and 86.8% for hit identification and 90.2% for hit optimization on independent test dataset for androgen receptor (AR), thus, shows its generalizability and robustness. In conclusion, advantageous features impeded in A-HIOT is making a reliable approach for bridging the long-standing gap between ligand-based and structure-based VS in finding the optimized hits for the desired receptor. The complete resource (framework) code is available at https://gitlab.com/neeraj-24/A-HIOT.

Graphical Abstract

DeepLPI: a novel deep learning-based model for protein-ligand interaction prediction for drug repurposing

The substantial cost of new drug research and development has consistently posed a huge burden for both pharmaceutical companies and patients. In order to lower the expenditure and development failure rate, repurposing existing and approved drugs by identifying interactions between drug molecules and target proteins based on computational methods have gained growing attention. Here, we propose the DeepLPI, a novel deep learning-based model that mainly consists of ResNet-based 1-dimensional convolutional neural network (1D CNN) and bi-directional long short term memory network (biLSTM), to establish an end-to-end framework for protein-ligand interaction prediction. We first encode the raw drug molecular sequences and target protein sequences into dense vector representations, which go through two ResNet-based 1D CNN modules to derive features, respectively. The extracted feature vectors are concatenated and further fed into the biLSTM network, followed by the MLP module to finally predict protein-ligand interaction. We downloaded the well-known BindingDB and Davis dataset for training and testing our DeepLPI model. We also applied DeepLPI on a COVID-19 dataset for externally evaluating the prediction ability of DeepLPI. To benchmark our model, we compared our DeepLPI with the baseline methods of DeepCDA and DeepDTA, and observed that our DeepLPI outperformed these methods, suggesting the high accuracy of the DeepLPI towards protein-ligand interaction prediction. The high prediction performance of DeepLPI on the different datasets displayed its high capability of protein-ligand interaction in generalization, demonstrating that the DeepLPI has the potential to pinpoint new drug-target interactions and to find better destinations for proven drugs.

FNN Based-Virtual Screening Using 2D Pharmacophore Fingerprint for Activity Prediction in Drug Discovery

Drug discovery remains a hard field that faces from the beginning of its process to the end many difficulties and challenges in order to discover a new potential drug. The use of technology has helped a lot in achieving many goals at the lowest cost and in the shortest possible time. Machine learning methods have proven for many years their performance although their limitations in some cases. The use of deep learning for virtual screening in drug discovery allows to process efficiently the huge amount of data and gives more precise results. In this paper, we propose a procedure for virtual screening (VS) based on Feedforward Neural Network in order to predict the biological activity of a set of chemical compounds on a given receptor. we have proposed a distance interval and it divisions to describe the chemical compound by the 2D pharmacophore fingerprint. Our model was trained on a dataset of active and inactive chemical compounds on cyclin A kinase1 receptor (CDK1), a very important protein family which has a role in the regulation of the cell cycle and cancer development. The results have proven that the proposed model is efficient and comparable with some widely used machine learning methods in drug discovery.

Combining structure-based pharmacophore modeling and machine learning for the identification of novel BTK inhibitors

Bruton's tyrosine kinase (BTK) is a critical enzyme which is involved in multiple signaling pathways that regulate cellular survival, activation, and proliferation, making it a major cancer therapeutic target. We applied the novel integrated structure-based pharmacophore modeling, machine learning, and other in silico studies to screen the Korean chemical database (KCB) to identify the potential BTK inhibitors (BTKi). Further evaluation of these inhibitors on three different human cancer cell lines showed significant cell growth inhibitory activity. Among the 13 compounds shortlisted, four demonstrated consistent cell inhibition activity among breast, gastric, and lung cancer cells (IC50 below 3 μM). The selected compounds also showed significant kinase inhibition activity (IC50 below 5 μM). The current study suggests the potential of these inhibitors for targeting BTK malignant tumors.

A reinforcement learning approach for protein-ligand binding pose prediction

Protein ligand docking is an indispensable tool for computational prediction of protein functions and screening drug candidates. Despite significant progress over the past two decades, it is still a challenging problem, characterized by the still limited understanding of the energetics between proteins and ligands, and the vast conformational space that has to be searched to find a satisfactory solution. In this project, we developed a novel reinforcement learning (RL) approach, the asynchronous advantage actor-critic model (A3C), to address the protein ligand docking problem. The overall framework consists of two models. During the search process, the agent takes an action selected by the actor model based on the current location. The critic model then evaluates this action and predict the distance between the current location and true binding site. Experimental results showed that in both single- and multi-atom cases, our model improves binding site prediction substantially compared to a naïve model. For the single-atom ligand, copper ion (Cu²⁺), the model predicted binding sites have a median root-mean-square-deviation (RMSD) of 2.39 Å to the true binding sites when starting from random starting locations. For the multi-atom ligand, sulfate ion (SO₄^2-), the predicted binding sites have a median RMSD of 3.82 Å to the true binding sites. The ligand-specific models built in this study can be used in solvent mapping studies and the RL framework can be readily scaled up to larger and more diverse sets of ligands.

PLAS-5k: Dataset of Protein-Ligand Affinities from Molecular Dynamics for Machine Learning Applications

Computational methods and recently modern machine learning methods have played a key role in structure-based drug design. Though several benchmarking datasets are available for machine learning applications in virtual screening, accurate prediction of binding affinity for a protein-ligand complex remains a major challenge. New datasets that allow for the development of models for predicting binding affinities better than the state-of-the-art scoring functions are important. For the first time, we have developed a dataset, PLAS-5k comprised of 5000 protein-ligand complexes chosen from PDB database. The dataset consists of binding affinities along with energy components like electrostatic, van der Waals, polar and non-polar solvation energy calculated from molecular dynamics simulations using MMPBSA (Molecular Mechanics Poisson-Boltzmann Surface Area) method. The calculated binding affinities outperformed docking scores and showed a good correlation with the available experimental values. The availability of energy components may enable optimization of desired components during machine learning-based drug design. Further, OnionNet model has been retrained on PLAS-5k dataset and is provided as a baseline for the prediction of binding affinities.

Feasibility and application of machine learning enabled fast screening of poly-beta-amino-esters for cartilage therapies

Despite the large prevalence of diseases affecting cartilage (e.g. knee osteoarthritis affecting 16% of population globally), no curative treatments are available because of the limited capacity of drugs to localise in such tissue caused by low vascularisation and electrostatic repulsion. While an effective delivery system is sought, the only option is using high drug doses that can lead to systemic side effects. We introduced poly-beta-amino-esters (PBAEs) to effectively deliver drugs into cartilage tissues. PBAEs are copolymer of amines and di-acrylates further end-capped with other amine; therefore encompassing a very large research space for the identification of optimal candidates. In order to accelerate the screening of all possible PBAEs, the results of a small pool of polymers (n = 90) were used to train a variety of machine learning (ML) methods using only polymers properties available in public libraries or estimated from the chemical structure. Bagged multivariate adaptive regression splines (MARS) returned the best predictive performance and was used on the remaining (n = 3915) possible PBAEs resulting in the recognition of pivotal features; a further round of screening was carried out on PBAEs (n = 150) with small variations of structure of the main candidates from the first round. The refinements of such characteristics enabled the identification of a leading candidate predicted to improve drug uptake > 20 folds over conventional clinical treatment; this uptake improvement was also experimentally confirmed. This work highlights the potential of ML to accelerate biomaterials development by efficiently extracting information from a limited experimental dataset thus allowing patients to benefit earlier from a new technology and at a lower price. Such roadmap could also be applied for other drug/materials development where optimisation would normally be approached through combinatorial chemistry.

Marine Natural Products in Clinical Use

Marine natural products are potent and promising sources of drugs among other natural products of plant, animal, and microbial origin. To date, 20 drugs from marine sources are in clinical use. Most approved marine compounds are antineoplastic, but some are also used for chronic neuropathic pain, for heparin overdosage, as haptens and vaccine carriers, and for omega-3 fatty-acid supplementation in the diet. Marine drugs have diverse structural characteristics and mechanisms of action. A considerable increase in the number of marine drugs approved for clinical use has occurred in the past few decades, which may be attributed to increasing research on marine compounds in laboratories across the world. In the present manuscript, we comprehensively studied all marine drugs that have been successfully used in the clinic. Researchers and clinicians are hopeful to discover many more drugs, as a large number of marine natural compounds are being investigated in preclinical and clinical studies.

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.

Maximizing the integration of virtual and experimental screening in hit discovery

INTRODUCTION

Experimental and virtual screening contributes to the discovery of more than 50% of clinical candidates. Considering the similar concept and goals, early-phase drug discovery would benefit from the effective integration of these approaches.

AREAS COVERED

After reviewing the recent trends in both experimental and virtual screening, the authors discuss different integration strategies from parallel, focused, sequential, and iterative screening. Strategic considerations are demonstrated in a number of real-life case studies.

EXPERT OPINION

Experimental and virtual screening are complementary approaches that should be integrated in lead discovery settings. Virtual screening can access extremely large synthetically feasible chemical space that can be effectively searched on GPU clusters or cloud architectures. Experimental screening provides reliable datasets by quantitative HTS applications, and DNA-encoded libraries (DEL) have enlarged the chemical space covered by these technologies. These developments, together with the use of artificial intelligence methods, represent new options for their efficient integration. The case studies discussed here demonstrate the benefits of complementary strategies, such as focused and iterative screening.