Computational Drug Discovery Methods

In Silico Identification of Potential Inhibitors of Mycobacterium tuberculosis DNA Gyrase from Phytoconstituents of Indian Medicinal Plants

This study identifies two potential inhibitors of Mycobacterium tuberculosis DNA gyrase from Indian medicinal plants through virtual screening, ADMET prediction, and molecular dynamics simulations.

Identifying compounds to treat opiate use disorder by leveraging multi-omic data integration and multiple drug repurposing databases.

The paper identifies FDA-approved drugs targeting genes associated with opioid use disorder by integrating multi-omic data and drug databases.

Quantum and Classical Graph Convolutional Neural Networks for Protein Ligand Dissociation Constant Prediction

The paper introduces a hybrid quantum-classical graph neural network to predict protein-ligand dissociation constants, showing improved accuracy and parameter efficiency.

The Human-In-the-Loop Drug Design Framework with Equivariant Rectified Flow

The paper introduces HIL-DD, a human-in-the-loop drug design framework that uses an Equivariant Rectified Flow Model to enable efficient collaboration between human experts and AI for generating drug-like molecules.

Semantic-Aware Graph Embedding Approach Uncovers LC-61, a Potent Anti-Leishmania infantum Compound

The paper introduces a semantic-aware graph neural network framework for drug discovery, identifying LC-61 as a potent antileishmanial compound with nanomolar activity.

Comparative Molecular Docking and Toxicity Profiling of Buspirone and Tandospirone Targeting the HTR1A Receptor

This study compares Buspirone and Tandospirone's binding and toxicity profiles at the HTR1A receptor using in silico methods, finding differences in binding affinity and toxicity risks.

Mechanistically Interpretable Toxicity Prediction Through Multimodal Integration of Structure and Transcriptomics

The paper develops a multimodal model integrating chemical structure and transcriptomics to predict toxicity, achieving robust performance across multiple assays and providing mechanistic insights.

Using Large Language Models to Assemble, Audit, and Prioritize the Therapeutic Landscape

The paper presents an AI pipeline that assembles and prioritizes therapeutic landscapes for diseases using structured and unstructured data, with case studies in Alzheimer's, pancreatic cancer, and cystic fibrosis.

UniGEN-DDI: Computing drug-drug interactions using a unified graph embedding network

UniGEN-DDI computes drug-drug interactions using a unified graph embedding network, identifying 12 unknown interactions validated in DrugBank 6.0.

Critical Assessment of a Structure-Based Pipeline for Targeting the Long Non-Coding RNA MALAT1

The paper evaluates a structure-based drug discovery pipeline for targeting MALAT1 using 21 ligands, identifying a binding mode that aligns with experimental affinity trends.

A unified language model bridging de novo and fragment-based 3D molecule design delivers potent CBL-B inhibitors for cancer treatment

Off-target mapping enhances selectivity of machine learning-predicted CK2 inhibitors

The paper develops an ML-powered drug discovery pipeline to design selective CK2 inhibitors with favorable off-target profiles, achieving a 90% hit-rate.

Lessons learned during the journey of data: from experiment to model for predicting kinase affinity, selectivity, polypharmacology, and resistance

This paper describes the development of KinoML, a framework for structure-enabled machine learning in drug discovery, focusing on kinases, and highlights key lessons in data management and model reproducibility.

Chemical Dice Integrator (CDI): A Scalable Framework for Multimodal Molecular Representation Learning

The paper introduces CDI, a framework that unifies multiple molecular representations into a single embedding, achieving better predictive performance than individual methods.

AstraBIND: Graph Attention Network for Predicting Ligand Binding Sites

AstraBIND predicts ligand binding sites using a graph attention network, achieving high accuracy across multiple ligand classes while maintaining efficiency.

PyrMol: A Knowledge-Structured Pyramid Graph Framework forGeneralizable Molecular Property Prediction

PyrMol improves molecular property prediction by integrating expert knowledge into a hierarchical graph framework, outperforming existing methods on benchmark datasets.

MetaboliteChat: A Unified Multimodal Large Language Model for Interactive Metabolite Analysis and Functional Insights

MetaboliteChat is a multimodal LLM that integrates molecular graphs and images with natural language to provide interactive metabolite analysis and functional insights.

SpecLig: Energy-Guided Hierarchical Model for Target-Specific 3D Ligand Design

SpecLig generates target-specific ligands with high affinity and specificity by integrating hierarchical modeling and energy guidance, improving therapeutic potential and reducing off-target risks.

RNA-Focused DNA-Encoded Library Construction, Screening, and Integration of Docking Identify Bioactive Ligands of Pathogenic r(G4C2)exp RNA

The paper identifies bioactive ligands for the toxic r(G4C2)exp RNA using DNA-encoded libraries combined with docking and SAR analysis.

ECLIPSE: Exploration of Complex Ligand-Protein Interactions through Learning from Systems-level Heterogeneous Biomedical Knowledge Graphs

ECLIPSE predicts compound-protein interactions using heterogeneous biomedical knowledge graphs and graph neural networks, achieving strong performance on benchmark tasks.

Uncertainty-Aware Deep Learning for Multi-Metric and Dose-Specific Prediction of Drug Synergy

AlgoraeOS predicts drug synergy with dose-specific inhibition profiles and uncertainty estimates, achieving strong performance across diverse tissues and drug mechanisms.

Machine Learning-Driven Discovery of Synergistic Protein Interactions Identifies ATL3 as a Putative Biomarker for Cancer Drug Response

The paper introduces synerOmics, a machine learning framework to identify synergistic protein interactions, finding ATL3 as a biomarker for lapatinib resistance in breast cancer.

Low rank adaptation of chemical foundation models generate effective odorant representations

The paper shows that fine-tuning chemical foundation models improves odorant-receptor binding prediction, introducing LORAX which outperforms existing models.

MolUNet++: Adaptive-grained Explicit Substructure and Interaction Aware Molecular Representation Learning

MolUNet++ improves molecular representation learning by explicitly analyzing substructures and interactions, outperforming traditional GNN models in prediction tasks and offering interpretable insights.

Benchmarking Real-World Applicability of Molecular Generative Models from De novo Design to Lead Optimization with MolGenBench

This paper introduces MolGenBench, a benchmark for evaluating molecular generative models in drug discovery, highlighting gaps between current models and real-world pharmaceutical workflows.

Physics-Diffusion-Driven Multiscale Aggregation for Drug-Target Interaction Prediction

PDDMA-DTI improves drug-target interaction prediction by combining physics-inspired diffusion with multiscale aggregation and interaction enhancement, achieving better accuracy and robustness than existing methods.

Strategies for robust, accurate, and generalizable benchmarking of drug discovery platforms

The paper benchmarks a drug discovery platform, finding that performance correlates with chemical similarity and dataset source.

DCBK: A Fragment-Based Hybrid Simulation and Machine Learning Framework for Predicting Ligand Dissociation Kinetics

DCBK predicts ligand dissociation kinetics by combining simulation and machine learning, achieving strong agreement with experiments and offering mechanistic insights.

Virtual Screening-Guided Discovery of Small Molecule CHI3L1 Inhibitors with Functional Activity in Glioblastoma Spheroids

This study identifies two small molecule CHI3L1 inhibitors using virtual screening and validates their activity in glioblastoma spheroids.

Data-driven strategies for drug repurposing: insights, recommendations, and case studies

This paper compares drug-target interaction databases to identify repurposing opportunities and presents a pathway-based pipeline for predicting drug repositioning in cancer.