Sriram Chandrasekaran

Modeling Microbiome Modulation of Tumor Metabolic Networks to Predict Synergistic Therapies

This paper develops a framework combining machine learning and metabolic modeling to predict synergistic cancer therapies influenced by microbiome composition in colorectal cancer.

Transfer learning predicts species-specific drug interactions in emerging pathogens

The paper develops a transfer learning framework to predict drug interactions for under-studied pathogens and validates synergistic combinations against antibiotic-resistant bacteria.

Multi-Tissue Metabolomic Signatures of Five Longevity Interventions Converge on Ergothioneine and Lipid Remodeling in Male UM-HET3 Mice

This study identifies shared metabolic changes across five longevity interventions in mice, highlighting ergothioneine and lipid remodeling as key features.

Recon8D: A metabolic regulome network from oct-omics and machine learning

The paper uses machine learning to predict metabolomic variation across cancer cell lines using 8 omic layers, identifying key predictors and signaling pathways.

A Modular Machine Learning Framework for Small-Molecule Drug Repurposing Based on Organ Permeability, Target Binding, and Biomarker Modulation

SCOUT is a machine learning framework for drug repurposing that integrates organ permeability, target binding, and biomarker modulation to prioritize candidates with high therapeutic relevance.

A Heterogeneous Graph Framework for Inference of Metabolite-Protein-Drug Interaction Networks

The paper introduces TopoMPI, a graph-based framework for predicting metabolite-protein-drug interactions by integrating multiple biological relationships and achieving AUCs between 0.79 and 0.86 across various datasets.

Discrimination of Normal from Slow-Aging Mice by Plasma Metabolomic and Proteomic Features

The paper uses machine learning to identify plasma metabolomic and proteomic features that distinguish slow-aging mice from controls, finding triglycerides with varying fatty acid chain lengths as key predictors.

Reprogramming SREBP1-dependent lipogenesis and inflammation in high-risk breast with licochalcone A: a novel path to cancer prevention

This study shows licochalcone A suppresses breast cancer growth by targeting SREBP1-dependent lipogenesis and inflammation.

Rapid prediction of thermodynamically destabilizing tyrosine phosphorylations in cancers

The paper predicts destabilizing tyrosine phosphorylations in cancers using machine learning, finding 58% of recurrent phosphorylations are destabilizing and identifying pathway and network patterns associated with these events.

Inferring Metabolic Objectives and Tradeoffs in Single Cells During Embryogenesis

The paper infers metabolic objectives and tradeoffs in single cells during embryogenesis using integrated omics data and a novel framework combining metabolic modeling and machine learning.

Ultra-high-throughput screening of antimicrobial combination therapies using a two-stage transparent machine learning model

This paper introduces M2D2, a two-stage ML model that identifies synergistic antimicrobial drug combinations and validates them experimentally against E. coli.

An Ensemble Metabolome-Epigenome Interaction Network Identifies Metabolite Modulators of Epigenetic Drugs

The paper identifies metabolites that modulate epigenetic drugs by analyzing histone PTM-metabolite interactions across 600 cell lines.

TaxiBGC: a Taxonomy-guided Approach for Profiling Experimentally Characterized Microbial Biosynthetic Gene Clusters and Secondary Metabolite Production Potential in Metagenomes

TaxiBGC improves BGC prediction in metagenomes by using taxonomy-guided methods, showing better performance than read-based approaches and linking BGCs to human diseases.

A flux-based machine learning model to simulate the impact of pathogen metabolic heterogeneity on drug interactions

The paper develops a flux-based machine learning model to predict drug interactions in E. coli, accounting for metabolic heterogeneity and growth conditions, identifying 24 synergistic combinations.

Metabolic signatures of regulation by phosphorylation and acetylation

The paper uses machine learning to classify metabolic regulation by phosphorylation and acetylation across multiple organisms and conditions.

Dynamic metabolic network modeling of a mammalian cell cycle using time-course multi-omics data

The paper uses dynamic metabolic modeling to analyze time-course multi-omics data from murine pro-B cells, revealing key metabolic changes during the cell cycle.

A multi-scale pipeline linking drug transcriptomics with pharmacokinetics predicts in vivo interactions of tuberculosis drugs

This paper links drug transcriptomics with pharmacokinetics to predict in vivo drug interactions for tuberculosis treatments.

Individual differences in honey bee behavior enabled by plasticity in brain gene regulatory networks

The paper identifies brain gene regulatory network plasticity as a mechanism underlying individual differences in honey bee behavior.

Purine metabolism regulates DNA repair and therapy resistance in glioblastoma

This study shows that purine metabolism affects DNA repair and therapy resistance in glioblastoma, suggesting that targeting purine synthesis could improve treatment outcomes.

Transcriptomic signatures predict regulators of drug synergy and clinical regimen efficacy against Tuberculosis

The paper develops a computational model to identify synergistic anti-TB drug combinations using transcriptomic data and validates its predictions with clinical trial data.

Cross-species systems analysis of evolutionary toolkits of neurogenomic response to social challenge

The paper identifies conserved neurogenomic response toolkits across species using multi-species transcriptomic analysis and systems-level functional grouping.