Mahesan Niranjan

GAE-Δ uses a graph autoencoder to analyze multi-omics data and predict clinical outcomes while identifying gene network rewiring associated with cancer progression.

sampleclusteR automates clustering of transcriptomics samples using metadata from GEO and ArrayExpress, correctly grouping most samples across multiple datasets.

This paper introduces GARS, a genetic algorithm with rank selection, for parameter estimation in biological models, showing strong accuracy and superiority over existing methods.

The paper develops machine learning models using sequence-derived features to predict protein abundance across multiple cell lines and identifies key features for this task.

This paper uses transfer learning to map biology from mouse to human bone marrow using single-cell RNA-sequencing data, showing improved accuracy with retraining and zero-shot learning.

The paper uses Frac-seq to analyze microRNA effects on gene expression in asthma, identifying six key microRNAs that regulate ~90% of their targets and contribute to disease mechanisms.