Calgary, AB  ·  open to bioinformatics & data analysis roles
Canadian Permanent Resident

I turn messy biological
data into decisions.

Data Scientist  //  Clinical Bioinformatician  //  Full-stack Builder

Ph.D. computational biologist building and maintaining production-level genomic pipelines and full-stack apps that make their data usable — from DRAGEN variant calling to FastAPI + SvelteKit dashboards, machine learning, and clear visual analysis.

Toolkit

Built across the whole stack, from sequencer to screen.

Languages & Data

PythonRSQL Shellpandas / NumPyscikit-learn

Web & Apps

FastAPISvelteKitPostgreSQL CeleryRedisCaddy

Genomics

Illumina DRAGENSnakemakehap.py Nanopore/PacBio/IlluminaWGS / WESAlphaFold

Infra & Viz

Linux HPC / SLURMGitCloudflare TableauPlotlymatplotlib / seaborn
Selected work

Engineering and research, mostly where they overlap.

Clinical-grade genomic systems, the software that runs them, and a decade of computational biology and genomics research behind it.

Clinical platform · APL & University of Calgary

Clinical genomics pipelines & the apps around them

Alberta Precision Laboratories · Cumming School of Medicine

Development and maintenance of clinical-grade genome and exome workflows, plus the full-stack software that makes their output usable. I engineer FastAPI + SvelteKit + Celery + Redis applications for exploring sequencing quality metrics, apply statistical process control (Levey–Jennings, outlier detection) for QA, and build automated pipelines such as a DPYD pharmacogenomics workflow that determines diplotypes and generates EPIC-formatted clinical reports.

FastAPISvelteKitPostgreSQLCelery + RedisDRAGENSPC / QC
Rare disease genomics

TIGeR — genomics for rare disease diagnosis

Translational Implementation of Genomics for Rare Diseases

Designed, optimised, and ran production NGS pipelines over 800+ clinical whole-genome and exome datasets on Linux HPC clusters and Illumina DRAGEN — validating CNV and structural-variant callers, evaluating carrier-panel coverage, and assessing mitochondrial variant calling, in support of diagnosing rare genetic disease in Albertans.

DRAGENHPC / SLURMCNV / SV validationCare4Rare
Genome assembly

Genome of an emerging Alberta parasite

Wasmuth Lab · University of Calgary

Led a multi-team project to sequence and assemble the genome of Myxobolus rasmusseni with Oxford Nanopore long reads and its transcriptome with Illumina — producing one of the most repetitive animal genomes described, and new resources for myxozoan biology.

NanoporeLong-read assemblyAnnotationPhylogenomics
Structural bioinformatics

Molecular mimicry in Plasmodium

Wasmuth Lab · University of Calgary

Built and validated a pipeline integrating AlphaFold structure prediction with proteome-wide structural comparison (Foldseek, Dali) to find host–parasite interactions — discovering 41 novel instances of molecular mimicry in the malaria parasite.

AlphaFoldFoldseek / DaliPythonProteomics
Comparative genomics · ML

MitoPredictor & the evolution of mtMutS

Lavrov Lab · Iowa State University

Doctoral and postdoctoral research on animal mitochondrial proteomes: a Random-Forest tool (MitoPredictor) that infers mitochondrial localization, the companion MMPdb database, and a phylogenomic study assembling 94 octocoral mitochondrial genomes to trace MutS-family DNA-repair evolution.

Random ForestR ShinyPhylogeneticsDatabases
Data science · Kaggle & Tableau

Independent analysis, from raw data to a story someone can act on.

Notebooks and dashboards where I clean, validate, and interrogate real datasets, then build the visualization that makes the finding obvious. Full profiles on Kaggle and Tableau Public.

Ecology · citizen science

Feathered Neighbours: three years of Calgary birds

32,422 observations284 species2022–2025

Three years of iNaturalist citizen-science data — 32,422 research-grade observations across 284 species — mapped to find out what drives Calgary's urban bird activity. Seasonal patterns track migration closely, with spring producing the highest species richness and winter the lowest. Geographic analysis found that 4 of the top 10 observation hotspots sit within Inglewood Bird Sanctuary alone, and the top 10 species make up 41% of all sightings — a mix of real abundance and the usual citizen-science bias toward easy-to-identify birds. Built an interactive Tableau dashboard on top of the analysis so the data is explorable, not just reported.

pandasFoliumPlotlyTableaugeospatial
Civic data · spatial equity analysis

Calgary Playground Equity Analysis

5,673 equipment records177 communitiesr = -0.03, p = 0.70

Tested whether Calgary allocates playground equipment unfairly across socioeconomic lines, spatially joining 5,673 equipment records to 177 communities and normalising by population. The result: no significant relationship between single-parent household rates and playground access (Pearson r = -0.03, p = 0.70). The real driver of low per-capita access turns out to be urban density — dense inner-city communities like Beltline and Downtown score lowest not from neglect, but because density mechanically compresses a per-capita metric.

geopandasscipySocrata APIfoliumchoropleth
More

Everything else on Kaggle

Browse the full set of notebooks, datasets, and analysis on my Kaggle profile.

Publications

Peer-reviewed research.

12 papers 8 as first author 2012 – 2025
About

A scientist who also writes poems.

I'm a computational biologist from Mumbai, India, now based in Calgary. I have had the priviledge of learning from amazing scientists in India, USA, and Canada. My current work sits where rigorous genomics meets real software: I build the pipelines that call variants and the applications that let clinicians and scientists actually use the results.

A Ph.D. in Bioinformatics and Computational Biology, roles at Alberta Precision Laboratories, the University of Calgary, and Iowa State University, and a dozen papers along the way — but the thread through all of it is the same: taking something large and tangled and making it clear.

Away from the terminal I'm a poet and visual artist, and the founder of the Creative Science Alliance, a Calgary STEAM community that pays every collaborator. I think the same instinct drives both halves — noticing the pattern, then finding the clearest way to show it to someone else.

Contact

Let's talk.

Open to bioinformatics and data scientist roles (onsite/hybrid/remote). Happy to walk through any of the work above.