Computational Drug Discovery Methods

Repurposing Metal-Based Therapeutics for Human Metapneumovirus (HMPV): An Integrative Computational Approach

This study repurposes metal-based drugs as potential inhibitors of HMPV using computational methods, identifying candidates with high binding affinity and favorable stability.

Generation of appropriate protein structures for virtual screening using AlphaFold3 predicted protein-ligand complexes

This study shows that using AlphaFold3 with ligand inputs improves virtual screening performance compared to apo structures, with better results for low molecular weight ligands.

MSF-CPMP: A Novel Multi-Source Feature Fusion Model for Prediction of Cyclic Peptide Membrane Permeability

This paper introduces MSF-CPMP, a multi-source feature fusion model for predicting cyclic peptide membrane permeability, achieving high accuracy and AUROC scores.

Optimizing drug synergy prediction through categorical embeddings in Deep Neural Networks

This study uses categorical embeddings in deep neural networks to improve drug synergy predictions in cancer treatment.

From Library to Landscape: Integrative Annotation Workflows for Compound Libraries in Drug Repurposing

The paper develops two annotation pipelines and dashboards to integrate chemical and bioactivity data for drug repurposing, validated on a compound library with over 5000 compounds.

Graph Network-Based Analysis of Disease-Gene-Drug Associations: Zero-Shot Disease-Drug Prediction and Analysis Strategies

This paper introduces ZS-GNT, a zero-shot drug repurposing method using graph neural networks to predict disease-drug associations without prior knowledge, achieving high accuracy in drug discovery.

The (α, β)-k Boolean Signatures of Molecular Toxicity: Microcystin as a Case Study

The paper applies (α, β)-k feature sets to identify toxicity-related substructures in Microcystin congeners using extended connectivity fingerprints.

NRGSuite-Qt: A PyMOL plugin for high-throughput virtual screening, molecular docking, normal-mode analysis, the study of molecular interactions and the detection of binding-site similarities

NRGSuite-Qt is a PyMOL plugin that integrates multiple tools for protein modeling and analysis, improving workflow efficiency and performance in normal mode analysis.

SynDRep: A Knowledge Graph-Enhanced Tool based on Synergistic Partner Prediction for Drug Repurposing

SynDRep predicts synergistic drug partners for disease repurposing using knowledge graphs and machine learning, achieving 84.58% true predictions with HolE and 0.796 ROC-AUC with random forest.

A Graph-Attention-Based Deep Learning Network for Predicting Biotech-Small-Molecule Drug Interactions

This paper introduces BSI-Net, a graph attention network for predicting interactions between biotech and small-molecule drugs, showing improved performance over existing methods.

DSA-DeepFM: A Dual-Stage Attention-Enhanced DeepFM Model for Predicting Anticancer Synergistic Drug Combinations

DSA-DeepFM improves drug synergy prediction by integrating dual-stage attention with Factorization Machines, outperforming existing models and identifying novel synergistic combinations.

Rethinking cancer drug synergy prediction: a call for standardization in machine learning applications

This study evaluates machine learning approaches for predicting cancer drug synergy and highlights the need for standardized frameworks in the field.

Pharmacophore design and ensemble-docking as approach to screening a large-scale database for identification of potential inhibitors of APH(3')-IIIa of Enterococcus faecalis

This study uses pharmacophore modeling and ensemble-docking to identify potential inhibitors of EfAPH(3')-IIIa from a large-scale database, finding nucleotide analogues as promising candidates.

Interface-aware molecular generative framework for protein-protein interaction modulators

This paper introduces GENiPPI, a molecular generative framework for PPI interfaces, which generates novel compounds targeting PPIs and demonstrates its effectiveness in capturing interface-molecule relationships.

Identification of novel human 15-lipoxygenase-2 (h15-LOX-2) inhibitors using a virtual screening approach

This study identifies six novel h15-LOX-2 inhibitors using virtual screening from a curated ZINC database, with two showing micromolar potency and a mixed-type inhibition mechanism.

HeteroRepur: Efficient Modeling of Heterogeneous Disease Graph for Depression Drug Repurposing using Heterogeneous Graph Neural Networks

HeteroRepur models a heterogeneous disease graph for depression drug repurposing using graph neural networks, identifying new drug candidates and outperforming baseline methods.

Novel artificial intelligence-based identification of drug-gene-disease interaction using protein-protein interaction

This study introduces a novel AI-based method using tensor decomposition to identify drug-gene-disease interactions from protein-protein interactions without prior disease or drug information.

Electron-density informed effective and reliable de novo molecular design and lead optimization with ED2Mol

ED2Mol improves de novo molecular design and lead optimization by incorporating electron density information, achieving high physical reliability and success rates in generating bioactive compounds.

Pharmacophore-guided de novo drug design with diffusion bridge

This paper introduces PharmacoBridge, a diffusion bridge-based method for de novo drug design guided by pharmacophore arrangements, generating molecules with high binding affinity to target proteins.

A Framework for Autonomous AI-Driven Drug Discovery

This paper introduces an AI-driven drug discovery framework that integrates knowledge graphs and large language models to automate and scale drug discovery processes.

CCGM: a Compound Coarse Grain Model representation for enhanced chemotype exploration, annotation and screening

The paper introduces CCGM, a compound representation model that improves chemotype exploration and screening by using a simplified graph structure to capture pharmacophore and chemotype features.

Deep learning-based prediction of chemical accumulation in a pathogenic mycobacterium

The paper uses deep learning to predict drug accumulation in Mycobacterium abscessus, finding that chemical properties alone are insufficient and that models trained on experimental data can accurately predict accumulation for diverse compounds.

In silico Comparison of Novel Proteins from Plasmodium Falciparum as Candidate Drug Targets against Malaria

This study identifies potential drug targets from Plasmodium falciparum by analyzing structural properties and druggability of novel proteins.

A precision oncology-focused deep learning framework for personalized selection of cancer therapy

This paper introduces ScreenDL, a deep learning model that predicts effective cancer therapies using tumor omic and drug screening data, outperforming existing methods in preclinical trials.

In silico exploration of potent flavonoids for dengue therapeutics

This study identifies five flavonoids with potential anti-dengue activity through computational methods, showing better binding affinity than existing ligands.

GEMS: Enhancing Generalizable Binding Affinity Prediction by Removing Data Leakage and Integrating Language Model Embeddings into Graph Neural Networks

The paper introduces GEMS, a graph neural network model that improves binding affinity prediction by removing data leakage and integrating language model embeddings, achieving high performance on independent test datasets.

Chemoenzymatic Synthesis Planning Guided by Reaction Type Score

The paper introduces RTS-CESP, a method using a reaction type score to guide chemoenzymatic synthesis planning, outperforming existing tools and validating new routes for a drug.

Network-based estimation of therapeutic efficacy and adverse reaction potential for prioritisation of anti-cancer drug combinations

This paper introduces a network-based method to estimate therapeutic efficacy and adverse reaction potential of anti-cancer drug combinations using gene set enrichment analysis and network propagation.

Generative AI-assisted Virtual Screening Pipeline for Generalizable and Efficient Drug Repurposing

This paper introduces a Generative AI-assisted Virtual Screening Pipeline for drug repurposing that enables blind screening of protein targets without prior structural knowledge.

DDI-GPT: Explainable Prediction of Drug-Drug Interactions using Large Language Models enhanced with Knowledge Graphs

DDI-GPT predicts drug-drug interactions using a large language model enhanced with knowledge graphs, achieving high accuracy and providing explainable insights into interaction mechanisms.