Anika Liu

MAVEN is an R/Shiny app that predicts drug targets and visualizes compound mechanisms of action using transcriptomics and chemical structure data, enabling hypothesis generation for wet-lab scientists.

This study uses scRNA-Seq data to identify drug candidates for repurposing in IPF by matching cell transition signatures to drug perturbation signatures.

This study identifies 33 gene biomarkers for drug-induced vascular injury in rats using gene expression and histopathology data from treated animals.

The paper presents an automated pipeline using NLP and chemical/disease embeddings to classify DILI-related literature, achieving high F1-scores in distinguishing DILI-positive from negative papers.

This paper introduces DILIc, an AI classifier that identifies Drug-Induced Liver Injury literature using NLP and ML, achieving high accuracy in cross-validation and external validation.

The paper develops a framework to identify time-concordant gene expression events in DILI using time-resolved transcriptomics and applies it to rat liver data from TG-GATEs to derive mechanistic hypotheses.

CARNIVAL identifies upstream causal processes from gene expression data by integrating prior knowledge, improving accuracy over existing tools in IgA nephropathy analysis.