Computational Drug Discovery Methods

GALILEO Generatively Expands Chemical Space and Achieves One-Shot Identification of a Library of Novel, Specific, Next Generation Broad-Spectrum Antiviral Compounds at High Hit Rates

This study uses GALILEO and ChemPrint to generate novel antiviral compounds targeting the conserved Thumb-1 site, achieving 100% hit rate in vitro against HCV and Coronavirus 229E.

High throughput mutational scanning of a protein via alchemistry on a high-performance computing resource

The paper demonstrates the feasibility of high-throughput mutational scanning of a protein using alchemical free energy calculations on a high-performance computing resource.

The role of induced polarization in drug discovery applications

This study calculates polarizability tensors for drug-like molecules and uses machine learning to predict IC50s, showing induced polarizability's importance in binding.

Exploring FDA-Approved Antiviral Drugs for Human Metapneumovirus Treatment: Integrative Computational Insights

This study identifies Remdesivir and Peramivir as promising FDA-approved antiviral drugs for HMPV treatment using computational methods.

A genetically based computational drug repurposing framework for rapid identification of candidate compounds: application to COVID-19

This paper presents a computational drug repurposing framework that identifies FDA-approved drugs for COVID-19 by integrating genetic expression data and EMR data, finding four compounds with protective effects in validation.

Docking 14 million virtual isoquinuclidines against the mu and kappa opioid receptors reveals dual antagonists-inverse agonists with reduced withdrawal effects

The paper screens 14.6 million virtual isoquinuclidines against opioid receptors to identify dual antagonists-inverse agonists with reduced withdrawal effects compared to naloxone.

Transfer learning applied in predicting small molecule bioactivity

This study compares two transfer learning approaches for predicting small molecule bioactivity, finding similar performance but different strengths in handling smaller assays.

Small molecule machine learning: All models are wrong, some may not even be useful

The paper evaluates coverage bias in small molecule datasets and proposes methods to assess and improve dataset representativeness for machine learning models.

A pilot study on the biological applications of indole alkaloids derived from Nagaland biodiversity

This paper investigates the ADME properties, toxicity, and DNA binding of indole alkaloids from Nagaland plants using computational methods.

Learning a CoNCISE language for small-molecule binding

This paper introduces CoNCISE, a method that accelerates drug-target interaction prediction by compressing small molecule data into 15 bits per compound, achieving high accuracy and enabling rapid screening of large chemical libraries.

Unveiling BPDE Induced Carcinogenic Signaling: Computational Insights into NF-κB, MAPK, and PI3K/Akt Pathway Activation

This study examines BPDE's carcinogenic effects through computational analysis of its binding to NF-κB, MAPK, and PI3K/Akt pathways, revealing its role in inflammation, cell survival, and tumor progression.

Peptide-aware chemical language model successfully predicts membrane diffusion of cyclic peptides

The paper introduces PeptideCLM, a chemical language model that predicts membrane diffusion of cyclic peptides more effectively than existing models.

Harnessing Computational Insights to Identify Potent Inhibitors for Human Metapneumovirus (HMPV): A Synergistic Approach with Natural Compounds

This study identifies natural compounds as potential inhibitors of HMPV matrix protein through computational screening and analysis.

Molecular docking, validation, dynamic simulation and pharmacokinetic prediction of natural compounds against Mycobacterium tuberculosis Beta-lactamase BlaC

This study identifies natural inhibitors against Mycobacterium tuberculosis BlaC using molecular docking and simulations, finding Tryptoquivaline K as a stable and promising inhibitor.

Semi-supervised Contrastive Learning for Bioactivity Prediction using Cell Painting Image Data

This paper introduces a semi-supervised contrastive learning method for bioactivity prediction from Cell Painting image data, improving classification of pharmacological classifications and biological targets.

Fine-tuning molecular mechanics force fields to experimental free energy measurements

This study fine-tunes a GNN-based molecular mechanics force field using experimental hydration free energy data to improve predictions of related free energies.

DTPPI: predicting drug interactions using a weighted drug-protein network

The paper introduces DTPPI, a machine learning method that uses a drug-target-protein-protein interaction network to predict drug-drug interactions with improved accuracy.

NfκBin: A Machine Learning based Method for Screening Nf-κB Inhibitors.

This paper develops a machine learning model and software tool to predict NF-κB inhibitors from chemical libraries, achieving reliable predictions validated against experimental data.

The impact of Library Size and Scale of Testing on Virtual Screening

This paper tests the impact of library size and testing scale on virtual screening by comparing results from 1.7 billion vs. 99 million molecule libraries against AmpC β-lactamase, finding improved hit rates and potency with larger libraries.

Synergizing Network Pharmacology and Pan-Cancer Analysis in TCM Repositioning for Tumor Therapy

This paper develops a method combining network pharmacology and pan-cancer analysis to reposition TCM herbs, identifying potential cancer indications and building a predictive system for ARCR.

A Bayesian active learning platform for scalable combination drug screens

BATCHIE efficiently identifies effective drug combinations through adaptive experimentation, reducing the number of required experiments while accurately predicting synergies.

HerbComb: an integrated database for the discovery of novel combinational therapies from herbal medicines

HerbComb is a database that identifies synergistic herbal medicine combinations by analyzing gene signatures and pharmacological properties, validated using Tongxinluo for Stroke.

DrugDomain 2.0: comprehensive database of protein domains-ligands/drugs interactions across the whole Protein Data Bank

DrugDomain 2.0 maps protein domain-ligand interactions across the Protein Data Bank, integrating experimental and AI-predicted data for over 37,000 ligands and 7,560 drugs.

HMG-DTI: a drug-target interaction prediction framework combining Hierarchical Molecular Graphs and improved Convolutional Block Attention Module

This paper introduces mHGM-DTI, a framework for drug-target interaction prediction that improves feature extraction and molecular encoding, achieving better performance than existing models in 11 out of 16 experiments.

DrugForm-DTA: Towards real-world drug-target binding Affinity Model

DrugForm-DTA predicts drug-target binding affinity using sequence-based inputs, achieving performance comparable to in-vitro experiments and outperforming molecular modeling methods.

Protein-ligand affinity prediction via Jensen-Shannon divergence of molecular dynamics simulation trajectories

This paper improves a method for predicting protein-ligand affinity by replacing deep learning with Jensen-Shannon divergence, reducing computation time and improving correlation sign prediction.

Identification of novel inhibitors targeting serine acetyltransferase from Neisseria gonorrhoeae

The paper identifies a novel inhibitor of serine acetyltransferase from Neisseria gonorrhoeae with an IC50 of 13.9 μM through virtual screening.

Unlocking the Potential of High-Quality Dopamine Transporter Pharmacological Data: Advancing Robust Machine Learning-Based QSAR Modeling

The paper compiles and filters high-quality DAT pharmacological data to build and compare QSAR models, showing improved predictive power with better data quality and size.

Transfer learning enables discovery of sub-micromolar antibacterials for ESKAPE pathogens from ultra-large chemical spaces

This paper uses transfer learning to identify potent antibacterials from large chemical libraries, finding 54% of tested compounds active against E. coli with sub-micromolar potency.

Integrated in silico and experimental screening identifies novel ligands that target precursor microRNA-31 at the Dicer cleavage site

The paper identifies novel ligands that bind to the Dicer cleavage site of pre-miR-31 through in silico screening and experimental validation.