Computational Drug Discovery Methods

Ability of a Structural World Model to Detect Cryptic Pockets from Apo Structure

This paper introduces a method to detect cryptic pockets from apo protein structures using a structural world model, achieving high accuracy and outperforming existing approaches.

Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction

This paper introduces PLABench, a benchmarking framework for protein-ligand binding affinity prediction, revealing that structural input and training scale alone do not ensure cross-target generalization.

MIRCID: Inferred Hub-miRNAs Drive Cross-Task Improvements in Drug Mechanistic Modeling

MIRCID improves drug mechanism modeling by integrating inferred hub miRNAs with gene expression and TF activity, showing better performance than TF activity alone.

Generative Access to Make-on-Demand Chemical Space Enables Ultra-Large Virtual Screening

The paper introduces REAL-SWIT, a generative framework for ultra-large virtual screening that efficiently explores chemical space by generating molecules with favorable docking scores.

Characterizing Compounds Targeting Colorectal Cancer Derived From Monastrol Using High-Through Screening of an Extensive Combinatorial Library

This paper identifies two fascin-binding compounds using a virtual screening approach combined with experimental validation, showing they inhibit CRC cell proliferation and migration.

Benchmarking Uncertainty and Improving Risk Ranking in Multi-task Bioactivity Prediction

The paper benchmarks uncertainty estimation and risk ranking in multi-task bioactivity prediction, introducing ICSR to improve reliability of kernel-based predictions.

Targeting the CDK4-Cyclin D Complex: A New Generation of Selective Kinase Inhibitors for Cancer Therapy

This paper identifies a novel CDK4 inhibitor, diophenic, that selectively targets the CDK4-Cyclin D1 interaction, showing improved selectivity and reduced off-target effects compared to ATP-competitive inhibitors in GBM models.

GO-Term Enrichment of Proteome-Scale Docking Profiles as a Biological Search-Space Reduction Layer for Protein Target Discovery

GO enrichment of proteome-scale docking profiles shrinks the candidate target list: a held-out GO gate kept 11.32% of known targets in 1.26% of candidates; additive reranking was mixed.

Discovery of Selective Small-Molecule Ligands of SV2C by AI-Enhanced Virtual Screening and Experimental Validation

This paper identifies selective SV2C ligands using AI-enhanced virtual screening and experimental validation, finding 22 active molecules with high selectivity over SV2A and SV2B.

A Graph-based QSAR Modeling Pipeline for Predicting In vitro PubChem Assays and In vivo Human Hepatotoxicity: Mechanistic Analysis of Caspase-3/7 Activation

This paper develops a graph-based QSAR pipeline to predict in vitro Caspase-3/7 activation and in vivo hepatotoxicity, showing improved performance over classical models.

Scaling Network Medicine with LLMs for Combinatorial Drug Repurposing in ER+ Breast Cancer

The paper develops an LLM-driven framework for drug repurposing in ER+ breast cancer, identifying 166 significant drug combinations using pathway analysis and consensus networks.

A Unified 3D Generative Model for Synthesizable Structure-Based Drug Design

This paper introduces LDDM, a generative model for drug design that produces synthetically accessible compounds validated experimentally for five protein targets.

Machine Learning for Toxicity Prediction in Low-Sample Molecular Classes

The paper proposes a framework to improve toxicity prediction for small molecular classes by fine-tuning a general model on class-specific data, outperforming classical methods and the EPA TEST tool.

LLMsFold: Integrating Large Language Models and Biophysical Simulations for De Novo Drug Design

LLMsFold designs and validates new small molecules targeting pathogenic proteins using LLMs and biophysical simulations, showing strong in silico binding and drug-like profiles.

TRACEDD: A Tool-grounded Reasoning and Agentic Coordination for Explainable Drug Design

TRACEDD provides a framework for explainable drug design by integrating multiple agents and tools to coordinate drug discovery tasks from target validation to synthesis planning.

Physical priors improve performance of structure-based binding affinity models

The paper shows that incorporating physics-based priors improves structure-based binding affinity models, achieving performance comparable to ligand-only models on a drug discovery dataset.

Interrogating contrastive learning embeddings for structure-based virtual screening: a case study on DrugCLIP

This paper evaluates DrugCLIP's contrastive learning embeddings for virtual screening, showing strong performance but limitations under realistic conditions.

Assessing the Generalizability of Machine Learning and Physics-Based Methods with DNA-Encoded Libraries

The paper evaluates ML and physics-based methods for predicting protein-ligand binding using DNA-encoded libraries, finding that no single method consistently generalizes to out-of-distribution chemical space.

Lacuna: Cryptic Binding Pocket Discovery via Conformational Ensemble Analysis

Lacuna identifies cryptic binding pockets in proteins by analyzing conformational ensembles, achieving high recovery rates on benchmark datasets.

The Virtual Biotech: A Multi-Agent AI Framework for Therapeutic Discovery and Development

The Virtual Biotech uses AI agents to integrate multi-omic and clinical data for drug discovery, identifying genomic features linked to trial success and proposing therapeutic strategies.

Structure based discovery of antipsychotic-like TAAR1 agonists

The paper identifies TAAR1 agonists with antipsychotic-like effects through computational screening and experimental validation, showing improved potency and reduced side effects in a schizophrenia model.

Interaction Profiles as a Universal Language for Generative Molecular Design with ShEPhERD-2

This paper introduces ShEPhERD-2, a 3D generative model that creates drug-like molecules based on interaction profiles, demonstrating its versatility across multiple design tasks.

Genome-scale perturbation signatures from primary human CD4+ T cells improve genetics-based prioritization of immune drug targets

The paper introduces IGNITE, a framework that combines genetic data with functional genomics to prioritize immune drug targets, showing improved performance over genetic methods alone.

From in silico prediction to experimental validation: Identification of drugs and novel synergistic combinations that inhibit growth of inflammatory breast cancer cells

This study validates computational drug repurposing predictions for inflammatory breast cancer using experimental assays, identifying synergistic combinations that inhibit cancer cell growth and signaling pathways.

G-screen: Scalable Protein-Aware Virtual Screening through Flexible Ligand Alignment

G-screen provides a scalable virtual screening method that combines flexible ligand alignment with protein-aware pharmacophore analysis to efficiently filter large chemical libraries.

Discovery of Bavachin as a Dual Trk-A/Trk-B Agonist via Integrated Computational Screening and Experimental Validation

This study identifies Bavachin as a dual Trk-A/Trk-B agonist using computational screening and experimental validation for neurodegenerative disease therapeutics.

The construction and operation of type IV pili impose a variable energetic burden across phylogenetically distant bacteria

The paper quantifies the energetic cost of type IV pili (T4P) construction and operation across bacterial species, finding significant variation in energy investment.

Joint Learning of Drug-Drug Combination and Drug-DrugInteraction via Coupled Tensor-Tensor Factorization with SideInformation

This paper proposes a joint learning framework for predicting drug combinations and drug-drug interactions using coupled tensor-tensor factorization with side information, achieving strong performance on new-drug prediction.

Deep reinforcement learning-driven discovery of a MsbA-targeted small-molecule antibiotic for the treatment of Acinetobacter baumannii infection

This study uses AI-driven drug design to discover a new MsbA-targeted antibiotic, Y-11, effective against carbapenem-resistant Acinetobacter baumannii with reduced toxicity and resistance.

ReverseScreen.ai: Pharmacophore-Guided Reverse Screening Across the Growing Co-Complex Proteome

ReverseScreen.ai uses pharmacophore fingerprints to efficiently reverse screen molecules against a large protein database, reducing docking time from 40.5 hours to 108 seconds per query.