Sonika Tyagi

This study identifies miRNA-lncRNA interactions and TFs in human labour using machine learning, revealing regulatory networks and a public database for analysis.

The paper identifies transcriptional differences in striatal projecting cortical neurons that distinguish rats susceptible from resistant to activity-based anorexia, linking gene expression patterns to metabolic and neural functions.

This study develops machine learning models to predict co-regulatory modules and gene regulatory networks in the heart using epigenomic data, identifying key transcription factors involved in cardiac development.

The paper introduces linc2function, a deep learning model that identifies and functionally annotates long noncoding RNAs using sequence, structure, and interactome features across species.

This paper introduces genomicBERT, a lightweight genome analysis model that improves efficiency and performance through specialized DNA vocabulary and tokenization, validated across diverse case studies.

The study updates exome matching to account for protein size and expression, finding that differential gene expression between sexes does not improve fecundity, suggesting conserved amino acid proportions across taxa.

The paper provides best practice data life cycle approaches for life sciences researchers focusing on omics datasets and computational data analysis.