Computational Toxicology Methods in Chemical Library Design and High-Throughput Screening Hit Validation.

The discovery of molecular toxicity in a clinical drug candidate can have a significant impact on both the cost and timeline of the drug discovery process. Early identification of potentially toxic compounds during screening library preparation or, alternatively, during the hit validation process is critical to ensure that valuable time and resources are not spent pursuing compounds that may possess a high propensity for human toxicity. This report focuses on the application of computational molecular filters, applied either pre- or post-screening, to identify and remove known reactive and/or potentially toxic compounds from consideration in drug discovery campaigns.

Machine Learning in Early Prediction of Metabolism of Drugs.

Machine learning (ML) has increasingly been applied to predict properties of drugs. Particularly, metabolism can be predicted with ML methods, which can be exploited during drug discovery and development. The prediction of metabolism is a crucial bottleneck in the early identification of toxic metabolites or biotransformation pathways that can affect elimination of the drug and potentially hinder the development of future new drugs. Metabolism prediction can be addressed with the application of ML models trained on large and validated dataset, from early stages of lead optimization to latest stage of drug development. ML methods rely on molecular descriptors that allow to identify and learn chemical and molecular features to predict sites of metabolism (SoMs) or activity associated with mechanism of inhibition (e.g., CYP inhibition). The application of ML methods in the prediction of drug metabolism represents a powerful resource to be exploited during drug discovery and development. ML allows to improve in silico screening and safety assessments of drugs in advance, steering their path to marketing authorization. Prediction of biotransformation reactions and metabolites allows to shorten the time, save the cost, and reduce animal testing. In this context, ML methods represent a technique to fill data gaps and an opportunity to reduce animal testing, calling for the 3R principles within the Big Data era.

PFAS-Biomolecule Interactions: Case Study Using Asclepios Nodes and Automated Workflows in KNIME for Drug Discovery and Toxicology.

The Asclepios suite of KNIME nodes represents an innovative solution for conducting cheminformatics and computational chemistry tasks, specifically tailored for applications in drug discovery and computational toxicology. This suite has been developed using open-source and publicly accessible software. In this chapter, we introduce and explore the Asclepios suite through the lens of a case study. This case study revolves around investigating the interactions between per- and polyfluorinated alkyl substances (PFAS) and biomolecules, such as nuclear receptors. The objective is to characterize the potential toxicity of PFAS and gain insights into their chemical mode of action at the molecular level. The Asclepios KNIME nodes have been designed as versatile tools capable of addressing a wide range of computational toxicology challenges. Furthermore, they can be adapted and customized to accomodate the specific needs of individual users, spanning various domains such as nanoinformatics, biomedical research, and other related applications. This chapter provides an in-depth examination of the technical underpinnings and foundations of these tools. It is accompanied by a practical case study that demonstrates the utilization of Asclepios nodes in a computational toxicology investigation. This showcases the extendable functionalities that can be applied in diverse computational chemistry contexts. By the end of this chapter, we aim for readers to have a comprehensive understanding of the effectiveness of the Asclepios node functions. These functions hold significant potential for enhancing a wide spectrum of cheminformatics applications.

Approaching Pharmacological Space: Events and Components.

The pharmacological space comprises all the dynamic events that determine the bioactivity (and/or the metabolism and toxicity) of a given ligand. The pharmacological space accounts for the structural flexibility and property variability of the two interacting molecules as well as for the mutual adaptability characterizing their molecular recognition process. The dynamic behavior of all these events can be described by a set of possible states (e.g., conformations, binding modes, isomeric forms) that the simulated systems can assume. For each monitored state, a set of state-dependent ligand- and structure-based descriptors can be calculated. Instead of considering only the most probable state (as routinely done), the pharmacological space proposes to consider all the monitored states. For each state-dependent descriptor, the corresponding space can be evaluated by calculating various dynamic parameters such as mean and range values.The reviewed examples emphasize that the pharmacological space can find fruitful applications in structure-based virtual screening as well as in toxicity prediction. In detail, in all reported examples, the inclusion of the pharmacological space parameters enhances the resulting performances. Beneficial effects are obtained by combining both different binding modes to account for ligand mobility and different target structures to account for protein flexibility/adaptability.The proposed computational workflow that combines docking simulations and rescoring analyses to enrich the arsenal of docking-based descriptors revealed a general applicability regardless of the considered target and utilized docking engine. Finally, the EFO approach that generates consensus models by linearly combining various descriptors yielded highly performing models in all discussed virtual screening campaigns.

ChemAP: predicting drug approval with chemical structures before clinical trial phase by leveraging multi-modal embedding space and knowledge distillation.

Recent studies showed that the likelihood of drug approval can be predicted with clinical data and structure information of drug using computational approaches. Predicting the likelihood of drug approval can be innovative and of high impact. However, models that leverage clinical data are applicable only in clinical stages, which is not very practical. Prioritizing drug candidates and early-stage decision-making in the de novo drug development process is crucial in pharmaceutical research to optimize resource allocation. For early-stage decision-making, we need a computational model that uses only chemical structures. This seemingly impossible task may utilize the predictive power with multi-modal features including clinical data. In this work, we introduce ChemAP (Chemical structure-based drug Approval Predictor), a novel deep learning scheme for drug approval prediction in the early-stage drug discovery phase. ChemAP aims to enhance the possibility of early-stage decision-making by enriching semantic knowledge to fill in the gap between multi-modal and single-modal chemical spaces through knowledge distillation techniques. This approach facilitates the effective construction of chemical space solely from chemical structure data, guided by multi-modal knowledge related to efficacy, such as clinical trials and patents of drugs. In this study, ChemAP achieved state-of-the-art performance, outperforming both traditional machine learning and deep learning models in drug approval prediction, with AUROC and AUPRC scores of 0.782 and 0.842 respectively on the drug approval benchmark dataset. Additionally, we demonstrated its generalizability by outperforming baseline models on a recent external dataset, which included drugs from the 2023 FDA-approved list and the 2024 clinical trial failure drug list, achieving AUROC and AUPRC scores of 0.694 and 0.851. These results demonstrate that ChemAP is an effective method in predicting drug approval only with chemical structure information of drug so that decision-making can be done at the early stages of drug development process. To the best of our knowledge, our work is the first of its kind to show that prediction of drug approval is possible only with structure information of drug by defining the chemical space of approved and unapproved drugs using deep learning technology.

MGACL: Prediction Drug-Protein Interaction Based on Meta-Graph Association-Aware Contrastive Learning.

The identification of drug-target interaction (DTI) is crucial for drug discovery. However, how to reduce the graph neural network's false positives due to its bias and negative transfer in the original bipartite graph remains to be clarified. Considering that the impact of heterogeneous auxiliary information on DTI varies depending on the drug and target, we established an adaptive enhanced personalized meta-knowledge transfer network named Meta Graph Association-Aware Contrastive Learning (MGACL), which can transfer personalized heterogeneous auxiliary information from different nodes and reduce data bias. Meanwhile, we propose a novel DTI association-aware contrastive learning strategy that aligns high-frequency drug representations with learned auxiliary graph representations to prevent negative transfer. Our study improves the DTI prediction performance by about 3%, evaluated by analyzing the area under the curve (AUC) and area under the precision-recall curve (AUPRC) compared with existing methods, which is more conducive to accurately identifying drug targets for the development of new drugs.

Future Perspective: Harnessing the Power of Artificial Intelligence in the Generation of New Peptide Drugs.

The expansive field of drug discovery is continually seeking innovative approaches to identify and develop novel peptide-based therapeutics. With the advent of artificial intelligence (AI), there has been a transformative shift in the generation of new peptide drugs. AI offers a range of computational tools and algorithms that enables researchers to accelerate the therapeutic peptide pipeline. This review explores the current landscape of AI applications in peptide drug discovery, highlighting its potential, challenges, and ethical considerations. Additionally, it presents case studies and future prospectives that demonstrate the impact of AI on the generation of new peptide drugs.

A Survey on Computational Methods in Drug Discovery for Neurodegenerative Diseases.

Currently, the age structure of the world population is changing due to declining birth rates and increasing life expectancy. As a result, physicians worldwide have to treat an increasing number of age-related diseases, of which neurological disorders represent a significant part. In this context, there is an urgent need to discover new therapeutic approaches to counteract the effects of neurodegeneration on human health, and computational science can be of pivotal importance for more effective neurodrug discovery. The knowledge of the molecular structure of the receptors and other biomolecules involved in neurological pathogenesis facilitates the design of new molecules as potential drugs to be used in the fight against diseases of high social relevance such as dementia, Alzheimer's disease (AD) and Parkinson's disease (PD), to cite only a few. However, the absence of comprehensive guidelines regarding the strengths and weaknesses of alternative approaches creates a fragmented and disconnected field, resulting in missed opportunities to enhance performance and achieve successful applications. This review aims to summarize some of the most innovative strategies based on computational methods used for neurodrug development. In particular, recent applications and the state-of-the-art of molecular docking and artificial intelligence for ligand- and target-based approaches in novel drug design were reviewed, highlighting the crucial role of in silico methods in the context of neurodrug discovery for neurodegenerative diseases.

The future of machine learning for small-molecule drug discovery will be driven by data.

Many studies have prophesied that the integration of machine learning techniques into small-molecule therapeutics development will help to deliver a true leap forward in drug discovery. However, increasingly advanced algorithms and novel architectures have not always yielded substantial improvements in results. In this Perspective, we propose that a greater focus on the data for training and benchmarking these models is more likely to drive future improvement, and explore avenues for future research and strategies to address these data challenges.

Accurate prediction of drug-target interactions in Chinese and western medicine by the CWI-DTI model.

Accurate prediction of drug-target interactions (DTIs) is crucial for advancing drug discovery and repurposing. Computational methods have significantly improved the efficiency of experimental predictions for drug-target interactions in Western medicine. However, accurately predicting the complex relationships between Chinese medicine ingredients and targets remains a formidable challenge due to the vast number and high heterogeneity of these ingredients. In this study, we introduce the CWI-DTI method, which achieves high-accuracy prediction of DTIs using a large dataset of interactive relationships of drug ingredients or candidate targets. Moreover, we present a novel dataset to evaluate the prediction accuracy of both Chinese and Western medicine. Through meticulous collection and preprocessing of data on ingredients and targets, we employ an innovative autoencoder framework to fuse multiple drug (target) topological similarity matrices. Additionally, we employ denoising blocks, sparse blocks, and stacked blocks to extract crucial features from the similarity matrix, reducing noise and enhancing accuracy across diverse datasets. Our results indicate that the CWI-DTI model shows improved performance compared to several existing state-of-the-art methods on the datasets tested in both Western and Chinese medicine databases. The findings of this study hold immense promise for advancing DTI prediction in Chinese and Western medicine, thus fostering more efficient drug discovery and repurposing endeavors. Our model is available at https://github.com/WANG-BIN-LAB/CWIDTI .

PocketDTA: an advanced multimodal architecture for enhanced prediction of drug-target affinity from 3D structural data of target binding pockets.

MOTIVATION: Accurately predicting the drug-target binding affinity (DTA) is crucial to drug discovery and repurposing. Although deep learning has been widely used in this field, it still faces challenges with insufficient generalization performance, inadequate use of 3D information, and poor interpretability. RESULTS: To alleviate these problems, we developed the PocketDTA model. This model enhances the generalization performance by pre-trained models ESM-2 and GraphMVP. It ingeniously handles the first 3 (top-3) target binding pockets and drug 3D information through customized GVP-GNN Layers and GraphMVP-Decoder. In addition, it uses a bilinear attention network to enhance interpretability. Comparative analysis with state-of-the-art (SOTA) methods on the optimized Davis and KIBA datasets reveals that the PocketDTA model exhibits significant performance advantages. Further, ablation studies confirm the effectiveness of the model components, whereas cold-start experiments illustrate its robust generalization capabilities. In particular, the PocketDTA model has shown significant advantages in identifying key drug functional groups and amino acid residues via molecular docking and literature validation, highlighting its strong potential for interpretability. AVAILABILITY AND IMPLEMENTATION: Code and data are available at: https://github.com/zhaolongNCU/PocketDTA.

SMCVdb: a database of experimental cellular toxicity information for drug candidate molecules.

Many drug discovery exercises fail because small molecules that are effective inhibitors of target proteins exhibit high cellular toxicity. Early and effective assessment of toxicity and pharmacokinetics is essential to accelerate the drug discovery process. Conventional methods for toxicity profiling, including in vitro and in vivo assays, are laborious and resource-intensive. In response, we introduce the Small Molecule Cell Viability Database (SMCVdb), a comprehensive resource containing toxicity data for over 24 000 compounds obtained through high-content imaging (HCI). SMCVdb seamlessly integrates chemical descriptions and molecular weight data, offering researchers a holistic platform for toxicity data aiding compound prioritization and selection based on biological and economic considerations. Data collection for SMCVdb involved a systematic approach combining HCI toxicity profiling with chemical information and quality control measures ensured data accuracy and consistency. The user-friendly web interface of SMCVdb provides multiple search and filter options, allowing users to query the database based on compound name, molecular weight range, or viability percentage. SMCVdb empowers users to access toxicity profiles, molecular weights, compound names, and chemical descriptions, facilitating the exploration of relationships between compound properties and their effects on cell viability. In summary, the database provides experimentally derived cellular toxicity information for over 24 000 drug candidate molecules to academic researchers, and pharmaceutical companies. The SMCVdb will keep growing and will prove to be a pivotal resource to expedite research in drug discovery and compound evaluation. Database URL: http://smcvdb.rcb.ac.in:4321/.

MetaCGRP is a high-precision meta-model for large-scale identification of CGRP inhibitors using multi-view information.

Migraine is considered one of the debilitating primary headache conditions with an estimated worldwide occurrence of approximately 14-15%, contributing highly to factors responsible for global disability. Calcitonin gene-related peptide (CGRP) is a neuropeptide that plays a crucial role in the pathophysiology of migraines and thus, its inhibition can help relieve migraine symptoms. However, conventional process of CGRP drug development has been laborious and time-consuming with incurred costs exceeding one billion dollars. On the other hand, machine learning (ML)-based approaches that are capable of accurately identifying CGRP inhibitors could greatly facilitate in expediting the discovery of novel CGRP drugs. Therefore, this study proposes a novel and high-accuracy meta-model, namely MetaCGRP, that can precisely identify CGRP inhibitors. To the best of our knowledge, MetaCGRP is the first SMILES-based approach that has been developed to identify CGRP inhibitors without the use of 3D structural information. In brief, we initially employed different molecular representation methods coupled with popular ML algorithms to construct a pool of baseline models. Then, all baseline models were optimized and used to generate multi-view features. Finally, we employed the feature selection method to optimize the multi-view features and determine the best feature subset to enable the construction of the meta-model. Both cross-validation and independent tests indicated that MetaCGRP clearly outperforms several conventional ML classifiers, with accuracies of 0.898 and 0.799 on the training and independent test datasets, respectively. In addition, MetaCGRP in conjunction with molecular docking was utilized to identify five potential natural product candidates from Thai herbal pharmacopoeia and analyze their binding affinity and interactions to CGRP. To facilitate community-wide efforts in expediting the discovery of novel CGRP inhibitors, a user-friendly web server for MetaCGRP is freely available at https://pmlabqsar.pythonanywhere.com/MetaCGRP .

Comparative transcriptomic analysis validates iPSC derived in-vitro progressive fibrosis model as a screening tool for drug discovery and development in systemic sclerosis.

Systemic sclerosis (SSc) is an autoimmune disease characterized by vasculopathy, immune dysregulation, and systemic fibrosis. Research on SSc has been hindered largely by lack of relevant models to study the progressive nature of the disease and to recapitulate the cell plasticity that is observed in this disease context. Generation of models for fibrotic disease using pluripotent stem cells is important for recapitulating the heterogeneity of the fibrotic tissue and are a potential platform for screening anti-fibrotic drugs. We previously reported a novel in-vitro model for fibrosis using induced pluripotent stem cell-derived mesenchymal cells (iSCAR). Here we report the generation of a "scar-like phenotype" when iPSC derived mesenchymal cells are cultured on hydrogel that mimicks a wound healing/scarring response (iSCAR). First, we performed RNA sequencing (RNA-seq) based transcriptome profiling of iSCAR culture at 48 h and 13 days to characterize early and latestage scarring phenotypes. The next generation RNA-seq of these iSCAR culture at different timepoints detected expression 92% of early "scar associated" genes and 85% late "scar associated" genes, respectively. Comparative transcriptomic analysis of a gene level SSc compendium matrix to the iSCAR wound associated model revealed genes common in both data sets. Early scar formation genes showed biological processes of hypoxia (27.5%), vascular development (13.7%) and glycolysis (27.5), while late scar formation showed genes associated with senescence (22.6%). Next we show the effects of two different antifibrotic compounds to validate the utility of the model as a screening tool to study early and late-stagelate-stage fibrosis. An autotaxin inhibitor was used to validate the iSCAR late stage fibrotic model (iSCAR-T) and an antifibrotic tool screening compound of unknown mechanism (EX00015097) was used to study and validate both early (iSCAR-P) and late-stage (iSCAR-T) fibrosis in the iSCAR model.

Predicting transcriptional responses to novel chemical perturbations using deep generative model for drug discovery.

Understanding transcriptional responses to chemical perturbations is central to drug discovery, but exhaustive experimental screening of disease-compound combinations is unfeasible. To overcome this limitation, here we introduce PRnet, a perturbation-conditioned deep generative model that predicts transcriptional responses to novel chemical perturbations that have never experimentally perturbed at bulk and single-cell levels. Evaluations indicate that PRnet outperforms alternative methods in predicting responses across novel compounds, pathways, and cell lines. PRnet enables gene-level response interpretation and in-silico drug screening for diseases based on gene signatures. PRnet further identifies and experimentally validates novel compound candidates against small cell lung cancer and colorectal cancer. Lastly, PRnet generates a large-scale integration atlas of perturbation profiles, covering 88 cell lines, 52 tissues, and various compound libraries. PRnet provides a robust and scalable candidate recommendation workflow and successfully recommends drug candidates for 233 diseases. Overall, PRnet is an effective and valuable tool for gene-based therapeutics screening.

GGAS2SN: Gated Graph and SmilesToSeq Network for Solubility Prediction.

Aqueous solubility is a critical physicochemical property of drug discovery. Solubility is a key issue in pharmaceutical development because it can limit a drug's absorption capacity. Accurate solubility prediction is crucial for pharmacological, environmental, and drug development studies. This research introduces a novel method for solubility prediction by combining gated graph neural networks (GGNNs) and graph attention neural networks (GATs) with Smiles2Seq encoding. Our methodology involves converting chemical compounds into graph structures with nodes representing atoms and edges indicating chemical bonds. These graphs are then processed by using a specialized graph neural network (GNN) architecture. Incorporating attention mechanisms into GNN allows for capturing subtle structural dependencies, fostering improved solubility predictions. Furthermore, we utilized the Smiles2Seq encoding technique to bridge the semantic gap between molecular structures and their textual representations. Smiles2Seq seamlessly converts chemical notations into numeric sequences, facilitating the efficient transfer of information into our model. We demonstrate the efficacy of our approach through comprehensive experiments on benchmark solubility data sets, showcasing superior predictive performance compared to traditional methods. Our model outperforms existing solubility prediction models and provides interpretable insights into the molecular features driving solubility behavior. This research signifies an important advancement in solubility prediction, offering potent tools for drug discovery, formulation development, and environmental assessments. The fusion of GGNN and Smiles2Seq encoding establishes a robust framework for accurately forecasting solubility across various chemical compounds, fostering innovation in various domains reliant on solubility data.

TarKG: a comprehensive biomedical knowledge graph for target discovery.

MOTIVATION: Target discovery is a crucial step in drug development, as it directly affects the success rate of clinical trials. Knowledge graphs (KGs) offer unique advantages in processing complex biological data and inferring new relationships. Existing biomedical KGs primarily focus on tasks such as drug repositioning and drug-target interactions, leaving a gap in the construction of KGs tailored for target discovery. RESULTS: We established a comprehensive biomedical KG focusing on target discovery, termed TarKG, by integrating seven existing biomedical KGs, nine public databases, and traditional Chinese medicine knowledge databases. TarKG consists of 1 143 313 entities and 32 806 467 relations across 15 entity categories and 171 relation types, all centered around 3 core entity types: Disease, Gene, and Compound. TarKG provides specialized knowledges for the core entities including chemical structures, protein sequences, or text descriptions. By using different KG embedding algorithms, we assessed the knowledge completion capabilities of TarKG, particularly for disease-target link prediction. In case studies, we further examined TarKG's ability to predict potential protein targets for Alzheimer's disease (AD) and to identify diseases potentially associated with the metallo-deubiquitinase CSN5, using literature analysis for validation. Furthermore, we provided a user-friendly web server (https://tarkg.ddtmlab.org) that enables users to perform knowledge retrieval and relation inference using TarKG. AVAILABILITY AND IMPLEMENTATION: TarKG is accessible at https://tarkg.ddtmlab.org.

Navigating Ultralarge Virtual Chemical Spaces with Product-of-Experts Chemical Language Models.

Ultralarge virtual chemical spaces have emerged as a valuable resource for drug discovery, providing access to billions of make-on-demand compounds with high synthetic success rates. Chemical language models can potentially accelerate the exploration of these vast spaces through direct compound generation. However, existing models are not designed to navigate specific virtual chemical spaces and often overlook synthetic accessibility. To address this gap, we introduce product-of-experts (PoE) chemical language models, a modular and scalable approach to navigating ultralarge virtual chemical spaces. This method allows for controlled compound generation within a desired chemical space by combining a prior model pretrained on the target space with expert and anti-expert models fine-tuned using external property-specific data sets. We demonstrate that the PoE chemical language model can generate compounds with desirable properties, such as those that favorably dock to dopamine receptor D2 (DRD2) and are predicted to cross the blood-brain barrier (BBB), while ensuring that the majority of generated compounds are present within the target chemical space. Our results highlight the potential of chemical language models for navigating ultralarge virtual chemical spaces, and we anticipate that this study will motivate further research in this direction. The source code and data are freely available at https://github.com/shuyana/poeclm.

Improving docking and virtual screening performance using AlphaFold2 multi-state modeling for kinases.

Structure-based virtual screening (SBVS) is a crucial computational approach in drug discovery, but its performance is sensitive to structural variations. Kinases, which are major drug targets, exemplify this challenge due to active site conformational changes caused by different inhibitor types. Most experimentally determined kinase structures have the DFGin state, potentially biasing SBVS towards type I inhibitors and limiting the discovery of diverse scaffolds. We introduce a multi-state modeling (MSM) protocol for AlphaFold2 (AF2) kinase structures using state-specific templates to address these challenges. Our comprehensive benchmarks evaluate predicted model qualities, binding pose prediction accuracy, and hit compound identification through ensemble SBVS. Results demonstrate that MSM models exhibit comparable or improved structural accuracy compared to standard AF2 models, enhancing pose prediction accuracy and effectively capturing kinase-ligand interactions. In virtual screening experiments, our MSM approach consistently outperforms standard AF2 and AF3 modeling, particularly in identifying diverse hit compounds. This study highlights the potential of MSM in broadening kinase inhibitor discovery by facilitating the identification of chemically diverse inhibitors, offering a promising solution to the structural bias problem in kinase-targeted drug discovery.

Perry Disease: Current Outlook and Advances in Drug Discovery Approach to Symptomatic Treatment.

Perry disease (PeD) is a rare, neurodegenerative, genetic disorder inherited in an autosomal dominant manner. The disease manifests as parkinsonism, with psychiatric symptoms on top, such as depression or sleep disorders, accompanied by unexpected weight loss, central hypoventilation, and aggregation of DNA-binding protein (TDP-43) in the brain. Due to the genetic cause, no causal treatment for PeD is currently available. The only way to improve the quality of life of patients is through symptomatic therapy. This work aims to review the latest data on potential PeD treatment, specifically from the medicinal chemistry and computer-aided drug design (CADD) points of view. We select proteins that might represent therapeutic targets for symptomatic treatment of the disease: monoamine oxidase B (MAO-B), serotonin transporter (SERT), dopamine D2 (D2R), and serotonin 5-HT1A (5-HT1AR) receptors. We report on compounds that may be potential hits to develop symptomatic therapies for PeD and related neurodegenerative diseases and relieve its symptoms. We use Phase pharmacophore modeling software (version 2023.08) implemented in Schrödinger Maestro as a ligand selection tool. For each of the chosen targets, based on the resolved protein-ligand structures deposited in the Protein Data Bank (PDB) database, pharmacophore models are proposed. We review novel, active compounds that might serve as either hits for further optimization or candidates for further phases of studies, leading to potential use in the treatment of PeD.