Computational Drug Discovery Methods

The paper develops a pharmacophore model for SARS-CoV-2 3CLpro inhibitors and validates computationally screened compounds experimentally.

This study screens 384 phytochemicals to identify compounds that inhibit OmpA and OmpW functions in Acinetobacter baumannii, identifying three with strong binding affinity and stability.

The paper benchmarks structure descriptors and similarity coefficients using chemical-genetic interaction data to improve compound function prediction.

DNN-DTIs predicts drug-target interactions using XGBoost feature selection and deep neural networks, achieving high accuracy on multiple datasets.

DTI-Voodoo predicts drug-target interactions using molecular features, phenotypic effects, and protein-protein interaction networks, showing improved performance over existing methods.

This paper provides guidelines for developing machine learning models to predict drug sensitivity using cell line-based pharmacogenomics data, emphasizing proper training and validation practices.

The paper introduces ENNAVIA, a deep learning model for predicting antiviral and anti-coronavirus peptide activity, achieving high accuracy on experimental data.

This paper introduces a Graph Enhanced Transformer model for retrosynthesis prediction, achieving better performance than a vanilla Transformer by incorporating molecular graph information.

The paper introduces bayesynergy, a Bayesian model for analyzing drug combination experiments, providing uncertainty quantification and handling missing data and uneven concentrations.

The paper predicts biological pathways of chemical compounds using a profile-inspired model based on fragment-based vectorial representations, achieving AUC scores between 0.74 and 0.90.

A computational drug repositioning pipeline identifies potential therapeutics for COVID-19 by matching SARS-CoV-2 gene expression signatures to drug profiles.

MatchMaker predicts drug synergy using chemical structures and gene expression, improving performance over existing methods on a large drug combination dataset.

This study identifies 50 drug-like compounds with anti-TB properties that inhibit InhA and EthR, with two compounds passing docking, metabolism, and pharmacokinetics filters.

MGATRx identifies drug repositioning candidates by integrating drug and disease annotations using a multi-view graph attention network, outperforming existing methods and showing translational potential.

The paper develops a deep learning model to screen antiviral drugs against SARS-CoV-2, identifying a novel compound with promising inhibitory activity.

The paper develops a deep learning framework to prioritize novel drug targets and repositionable compounds for Alzheimer's disease using protein-protein interaction networks.

The paper develops a deep learning framework that integrates molecular and interactome data to predict protein-compound interactions, showing improved performance over existing methods.

The paper links genomic defects to chemosensitivity and drug mechanisms using NCI60 data, identifying key defective genes associated with specific drug mechanisms.

This study evaluates multiscale virtual screening pipelines for drug repurposing using the CANDO platform, showing improved performance with hybrid decision tree pipelines over docking-based methods.

TUGDA reduces negative transfer in drug response prediction by adapting in vitro models to in vivo settings through uncertainty-guided domain adaptation.

PharmaNet uses deep RNNs to predict drug-target interactions, achieving high accuracy in ligand prediction and identifying potential antiviral compounds.

The paper introduces comboLTR, a method for predicting drug combination effects using latent tensor reconstruction, outperforming existing methods in speed and accuracy.

This paper designs new ligands using deep learning to convert latent protein descriptors into SMILES strings, resulting in chemically feasible compounds with potential binding affinities to known proteins.

This paper presents a data-driven drug repositioning framework that identifies CVL218, a PARP1 inhibitor, as a potential therapeutic for COVID-19 through in silico and experimental validation.

The paper develops methods to construct disease transcriptional signatures and perform connectivity analysis using scRNA-seq data, identifying mTORC1 and other inhibitors as potential therapies for LAM.

The paper builds predictive models for drug sensitivity using gene expression data from cancer cell lines and applies them to predict drug responses in tumor and normal tissues.

This paper introduces a method to classify protein ligands using structural features derived from binding site atom distributions, showing improved classification performance on benchmark datasets.

This study uses a multipartite network approach to analyze interactions between medicinal plant chemicals and targets, identifying clusters and potential drug candidates.

The paper evaluates an MCSS-based docking approach for predicting binding modes and selectivity of nucleotide ligands, showing improved performance with hybrid solvent models and pose clustering.

The paper identifies related 2D chemical fingerprints that reduce molecular similarity scores and suggests their exclusion for improved virtual screening.