Headline

Data Science @ 4baseCare

About

I’m a data scientist at the intersection of computational biology and precision oncology, working to transform complex genomic and clinical data into actionable insights that improve cancer diagnosis and patient outcomes. At my current role in a cancer diagnostics company, I lead data-driven initiatives that bridge research and real-world applications. I've worked with large-scale cohorts like TCGA, and led comparative studies with Indian pan-cancer datasets, pushing the boundaries of population-specific cancer genomics. I thrive in spaces where data science and innovation directly contribute to lives of people. If you're working in data science, bioinformatics, health tech, or translational research, let's connect— we might have something meaningful to build together.

Location

Bengaluru

AI stack

hugging face

langchain

ollama

openai

Work experience

Data Scientist at 4baseCare, Apr 2024 - Present · 2 yrs 1 mo, Bangalore, Using AI to streamline, simplify, and automate healthcare data: - Building Knowledgebases from raw clinical data(PDFs, Images and Notes) using LLMs - Using AI to automate the extraction, summarization, and structuring of unstructured clinical data from PDFs, images, and handwritten notes. - Developed a patient matching system using clinical and genomic similarity. - Fine-tuning SLMs and LLMs

Research Bioinformatician II at 4baseCare, Apr 2023 - Apr 2024 · 1 yr 1 mo, Bengaluru, Karnataka, India, - Developed key pipelines and modules for making one of the most affordable NGS diagnostic tests for cancer patients using Nextflow, python, and several CLI-based tools. - Developed comprehensive gene fusion detection, visualization and driver prediction/prioritization pipeline using Nextflow and ML (probabilistic classifier) that led to discovery of novel biomarkers.

Associate Research Bioinformatician at 4baseCare, Apr 2022 - Jul 2023 · 1 yr 4 mos, Bengaluru, Karnataka, India, 🌟Awarded Star Player of the Department (Clinical Informatics and Reporting) - Automated custom in-house Python and shell modules/tools of existing data analysis pipelines and reducing the manual intervention by 98% and reducing the failure rate by 96%. - Developed RNA-seq expression data analysis pipelines for cancer data analysis, automated DNA exome and RNA exome data processing, and designed a specialized pipeline to detect gene fusions in cancer using DNA-seq (targeted panel) data using specialized libraries in R and Python

Project Trainee at Bhabha Atomic Research Centre, May 2019 - Jul 2019 · 3 mos, Mumbai, Maharashtra, India, • Tasked with the screening of novel agents for decorporation efficiency of radioactive contamination (Thorium and Thorium compounds) from blood. • Studied and worked on blood cells and liver cells in a BSL-II laboratory.

Summer Intern at Abhinav Steels Pvt. Ltd, May 2018 - Jun 2018 · 2 mos, Jaunpur, Uttar Pradesh, India, • Studied effects of industrial waste on soil and water • Learned water sample analysis techniques • Awarded best Summer Intern of the year

Education

Master of Science - MS, Computer Science: Artificial Intelligence and Machine Learning, Scaler

Master of Technology - MTech, Biotechnology, Kalinga Institute of Industrial Technology, Bhubaneswar

Public links

github: https://github.com/atomikkus