Aravind Subramanian

The paper uses a chemical genetic approach with induced pluripotent stem cells to screen for compounds affecting SMA neuronal gene expression, generating a queryable dataset of transcriptional profiles.

The paper compares morphology and gene expression data to determine their complementary roles in mapping cell states across drug perturbations.

The paper presents a LINCS Microenvironment perturbation dataset cataloging transcriptional, proteomic, epigenomic, and phenotypic responses of MCF10A cells to six ligands, enabling integrative analysis of molecular and phenotypic changes.

This study evaluates deconvolution methods for gene expression data using an open innovation competition and finds that random forest regression outperforms other approaches in accuracy and reproducibility.

The paper demonstrates how open innovation competitions improve computational biology methods for antibody clustering, gene expression imputation, and CMap querying.

The paper evaluates module identification methods across disease-relevant networks using GWAS data to identify top-performing algorithms and disease-associated modules.

The paper develops an in-vitro gene expression screening method to predict chemical carcinogenicity and genotoxicity using HepG2 cells and machine learning models.

GeNets provides a platform to compare genomic networks using machine learning and allows analysis of genetic and RNA sequencing data.

The paper creates a proteomic resource profiling 90 drugs in six cell lines, revealing cell-specific responses and enabling integration with transcriptional data to identify therapeutic opportunities.

The paper introduces the GCTx format and associated software packages for efficiently storing and analyzing large dense matrices of perturbation data and annotations.

The paper evaluates RNAi and CRISPR technologies by analyzing gene expression profiles in the Connectivity Map, finding that RNAi has strong off-target effects while CRISPR is more accurate.

The paper introduces the L1000 platform, a high-throughput gene expression profiling method, and reports 1.3 million perturbational profiles expanding the Connectivity Map for drug mechanism discovery and functional annotation.

This paper introduces a deep learning method to infer gene expression from landmark genes, showing significant improvements over linear regression in multiple datasets.