Ram Samudrala

This study benchmarks AlphaFold 3's interaction scores against BANDOCK+ for drug discovery, showing AF3's slightly better performance in disease ranking but BANDOCK+'s broader coverage.

The paper introduces the CANDO platform for glioma therapeutic discovery, identifying 23 potential treatments through multiscale analysis and benchmarking.

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

This paper uses the CANDO platform to identify repurposable drugs for schizophrenia, finding 25 high-corroboration candidates with validated targets and biological relevance.

The paper identifies C-to-U RNA editing sites mediated by APOBEC3A/G and links them to disease associations, suggesting RNA editing contributes to protein biodiversity and human health.

The paper integrates heterogeneous biological data to create a human interactome network for drug behavior analysis, enhancing therapeutic candidate generation through multiscale interactomic signatures and machine learning.

The paper validates that osimertinib synergizes with KRAS inhibitors to reduce NSCLC cell proliferation, with MAPK suppression as a key mechanism.

The paper uses machine learning on Tox21 data to identify protein features and pathways linked to compound toxicity, revealing biological mechanisms and cascading interactions.

The paper identifies differentially expressed proteins in COPD patients' bronchoalveolar lavage fluid and uses network analysis to find potential drug targets and repurposable therapies.

This paper introduces a deep learning approach to design drug-like compounds by generating molecules that mimic interaction signatures of existing drugs, showing significant behavioral similarity in 16/20 cases.

This paper reviews and compares performance evaluation measures for drug repurposing technologies using the CANDO platform to improve cross-platform comparability and optimize drug discovery.

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.

The paper introduces a Python package for analyzing drug-proteome and drug-disease relationships to predict potential therapeutics.

The paper upgrades the CANDO platform for drug repurposing by integrating ligand-based and decision tree pipelines, achieving higher accuracy in identifying therapeutic candidates.

The paper improves the CANDO platform's interaction scoring function, increasing benchmarking accuracy for drug repurposing predictions.

The paper evaluates the CANDO platform for drug repurposing by identifying optimal protein subsets that improve accuracy while reducing computational complexity.

The paper develops a substitution matrix-based method to model tooth enamel pellicle peptide interactions with hydroxyapatite, achieving high discrimination accuracy.

The paper generates 10 billion de novo protein models for rice proteins using computational methods, providing centroid models and conformers for benchmarking and functional studies.