Sasanka Jana

Developed a comprehensive Python toolkit, "Galen-Kit," integrating modules for ETL, EDA, ML, and reporting, streamlining genomic workflows and data analysis.

Engineered and deployed "Galen-CLI," a command-line interface, significantly enhancing the efficiency of bioinformatic pipeline execution for research teams.

Analyzed large-scale transcriptomic and clinical datasets (TCGA, CGGA, Exsegen) using differential expression, PCA, and pathway enrichment to classify Oligodendroglioma subgroups.

Built and validated machine learning models that accurately predict unknown sample subgroups, advancing precision in cancer classification and diagnostic capabilities.

Processed 763 clinical samples and over 18,000 methylation probes to identify four distinct Medulloblastoma molecular subtypes, facilitating targeted therapeutic strategies.

Constructed robust ML models utilizing methylation profiles, ensuring high performance and reliability through rigorous validation techniques for molecular variant identification.

Built robust data pipelines that optimized operational workflows, enhancing efficiency and generating actionable analytics for business improvements.

Conducted in-depth investigations into boiler tube leakages at the Muri plant, leveraging coal quality and water chemistry reports to identify critical root causes.

Utilized Oracle Cloud Infrastructure (OCI) for scalable data analysis, processing large datasets to derive insights and support decision-making.

Collaborated effectively with cross-functional teams to integrate data solutions and presented key findings to senior stakeholders, influencing strategic decisions.