Bioinformatics · Machine Learning · Cancer Genomics
🌐 Website · 📖 About · 🧪 Projects · ✍️ Blog · 📄 Resume · 💼 LinkedIn
I work at the intersection of bioinformatics, machine learning, and cancer genomics — building computational tools to make sense of high-dimensional biological data, from single-cell transcriptomes to gene regulatory networks, in pursuit of a clearer picture of how disease develops.
I'm currently a Computational Biology Researcher at the Ontario Institute for Cancer Research (OICR), where I use single-cell transcriptomics to investigate the developmental origins of medulloblastoma, a pediatric brain cancer.
I recently graduated with a Honours Bachelor of Science at the University of Toronto, specializing in Bioinformatics and Computational Biology, with minors in Computer Science and Immunology.
- Computational Genomics
- Machine Learning for Biology
- Single-Cell & Spatial Omics
- Sequence-to-Function Models
- Cancer Genomics & Brain Tumours
- Precision Medicine
- Tumour & Phenotype Characterization
- Stem Cell Biology
- Antibody Engineering
- Python
- R
- Bash/Shell Scripting
- Java
- C
- JavaScript
- Bulk and single cell RNA-seq analysis
- Supervised/unsupervised machine learning
See the full list on my skills page →
SeedBench-Bio — Python, LLM Evaluation Benchmark testing whether prompt design, not just model choice, changes an LLM's error-detection recall and reasoning quality on seeded bioinformatics review tasks.
EEG Seizure Detection — Python, ML Signal-processing pipeline benchmarking models and engineered EEG features on pediatric seizure data, using leave-one-patient-out cross-validation to test whether performance holds on patients never seen in training.
BMP7 Signaling in Medulloblastoma — R, Bioconductor, Cytoscape Recreated and extended published analysis of BMP7-driven oncogenic signaling: differential expression, GSEA, and pathway enrichment mapping from bulk RNA-seq data.
ExprCompareR — R, Shiny Interactive omics data reporting tool integrating RNA-seq and protein-expression datasets across human tissues for functional genomics and precision oncology research.
Pathogenic SNV Prediction Tool — Python, Bash, ML Machine learning classifier predicting pathogenic vs. benign SNVs using ClinVar labels, annotated across 13,000+ variants with regulatory genomic features.
See the full list on my projects page →
📫 tanayadatar21@gmail.com 💼 linkedin.com/in/tanaya-datar 🌐 tanayadatar.vercel.app