01 · Roasts
Zero-to-PyPI in 5 Months
Account created January 2026, already shipping rustscenic on PyPI with a Zenodo DOI and benchmarks. Either you're overclocked or this is a very elaborate fake-it-till-you-make-it arc — either way, the receipts are there.
105 PRs, 0 Issues
You filed 105 pull requests this year and opened exactly zero issues. You apparently never found a bug worth reporting — or you just fix everything silently and move on like a ghost.
Heatmap Says 'I Just Got Here'
Weeks 1–42 of your heatmap are a barren tundra of zeros. All 655 commits are crammed into the last 10 weeks. Consistency is a vibe, not just a volume stat.
98% Solo, 0% Followers
soloPct = 98 and 11 followers: you're shipping Rust bioinformatics tools into the void. The code is real; the audience is theoretical. Consider touching grass on the social layer of GitHub.
Coursework Dilution
Two repos (statistical-power and random-forests-week11) are homework. One is literally a single .qmd file. Submitting coursework to a portfolio GitHub is like padding a CV with 'Microsoft Word: proficient.'
Built using
Zoral
Shadows one worker for a week, then takes over their job with zero extra setup. Behaves exactly like the original.
zoral.ai
02 · Category breakdown
- Impact25% weight68C
- Consistency20% weight65C
- Quality20% weight72B
- Depth15% weight65C
- Breadth10% weight80A
- Community10% weight55D
03 · Stats
365-day commit heatmap
59 active days
Language distribution
- Python57%
- TypeScript16%
- Rust13%
- R8%
- Shell5%
- Nextflow1%
04 · Numbers
Owned repos
non-fork
10
Commits
last 12 months
655
Followers
11
Joined GitHub
Jan 2026
05 · Top repos
Ekin-Kahraman /
rustscenic
Rust-based SCENIC+ replacement achieving 11–52× speedup on regulatory network analysis. Ships as typed Python package with comprehensive GRN, AUCell, topics, and enhancer-linking modules; strong test coverage and CI/CD; documented and validated on real multiome data.
Ekin-Kahraman /
Ekin-Kahraman
Portfolio README of a bioinformatics engineer showcasing multiple published projects (RustScenic on PyPI with Zenodo DOI, Nextflow pipelines, clinical prototypes). Has CI in main project, documented real-data validation and performance benchmarks, but this repo itself is a metadata hub with no substantive code.
Ekin-Kahraman /
safetynett
AI-powered clinical safety netting prototype built for OpenClaw Hackathon. Typed TypeScript/React with full-stack feature set (auth, Supabase backend, red flag detection, auto-escalation), tests, CI/CD, and embedded clinical data covering 39 conditions across 9 specialties. Designed for NHS adoption but undeployed/pre-
Ekin-Kahraman /
single-cell-rnaseq-immune-profiling
Production-grade single-cell RNA-seq pipeline with full CI/test coverage, comprehensive documentation (README + design.md + ARCHITECTURE.md), typed Python 3.10+, multi-resolution clustering, and SHA-256 validated outputs.
Ekin-Kahraman /
rustscenic-airway-case
Validation case study for RustScenic on published airway atlas (58 donors, 32k cells); demonstrates head-to-head parity with pySCENIC (0.984 per-cell Pearson) and 27× AUCell speedup, plus COVID differential regulon biology extending prior deconvolution work.
Ekin-Kahraman /
bulk-rnaseq-differential-expression
Reproducible bulk RNA-seq pipeline for SARS-CoV-2 analysis: typed R code with DESeq2, pathway enrichment, CI/tests, extensive documentation (README, design.md, ARCHITECTURE.md), 12-step workflow with sensitivity/viral-load/sex-interaction analyses on GEO dataset (GSE152075, n=484 → n=60 balanced). 81 MB codebase, 30 co
Ekin-Kahraman /
covid-airway-deconvolution
Research-grade COVID-19 airway cell type deconvolution using PyTorch ensemble on tissue-matched scRNA-seq reference. Well-documented with validation, tests, and CI; achieves r=0.954 on synthetic data but limited external adoption.
Ekin-Kahraman /
rnaseq-nextflow-pipeline
Personal bioinformatics pipeline project: well-documented Nextflow DSL2 RNA-seq workflow with containerised FastQC, fastp, HISAT2, featureCounts, DESeq2, MultiQC steps, full CI, tests, and FastAPI report portal. Very recent (Apr 2026) and experimental.
Ekin-Kahraman /
random-forests-week11
Late coursework submission for machine learning week 11; clean R analysis of dog SNP genotypes using logistic regression and random forest with structured pipeline, CI, and validation script. Not portfolio software.
Ekin-Kahraman /
statistical-power-Ekin-Kahraman
Coursework submission for statistical power analysis workshop. Single .qmd file with CI/CD rendering pipeline, minimal scope and explicitly non-portfolio software.
06 · Timeline
- Jan 4, 2026Joined GitHub
- Jan 6, 2026Created Ekin-Kahraman
- Jan 25, 2026Created bulk-rnaseq-differential-expression — Reproducible bulk RNA-seq pipeline for SARS-CoV-2 host response in R (DESeq2, pathway enrichment, viral load and sex-interaction analyses). Zenodo DOI.
- Mar 23, 2026Created single-cell-rnaseq-immune-profiling — End-to-end single-cell RNA-seq immune cell profiling pipeline in Python (scanpy, PBMC 3k)
- Apr 4, 2026Created safetynett — AI-powered clinical safety netting for NHS primary care. Red flag detection, automated patient follow-up, GP escalation.
- Apr 4, 2026Created rnaseq-nextflow-pipeline — Bulk RNA-seq Nextflow pipeline: FastQC, fastp, HISAT2, featureCounts, DESeq2, MultiQC. Dockerised, tested, reproducible.
- Apr 5, 2026Created covid-airway-deconvolution — PyTorch deconvolution of 484 COVID-19 nasopharyngeal samples into 14 airway cell types using a tissue-matched scRNA-seq reference. Validation r = 0.954.
- Apr 19, 2026Created rustscenic — Faster, lower-memory Rust rewrite of the SCENIC and SCENIC+ analysis stack: GRN, AUCell, cisTarget, topics, peak-to-gene links, and eRegulons.
- Apr 19, 2026Created rustscenic-airway-case — RustScenic 0.4.4 validation case: Ziegler 2021 airway atlas, 8/14 canonical TF hits, AUCell Pearson r=0.984 vs pySCENIC-unit
- May 10, 2026Created statistical-power-Ekin-Kahraman — Coursework submission for 5023B Session 3; kept public for assessment, not maintained as portfolio software.
- May 10, 2026Created random-forests-week11 — Coursework submission for 5023B Week 11; kept public for assessment, not maintained as portfolio software.
- May 23, 2026Most recent push to Ekin-Kahraman
07 · Compare
08 · Rubric
How this score was produced
Overall = Σ (category × weight) + gentle top-end curve
Tier thresholds
▸ How the pipeline works
- 01Scrape.Pull every non-fork repo pushed in the last 90 days, plus your contribution calendar, followers, and language byte counts — straight from GitHub's REST & GraphQL APIs.
- 02Triage.A small model reads every repo's file tree + README and picks the 20 files per repo that actually reveal how you code.
- 03Grade each repo. All repos run in parallel through a fast scoring model that reads the picked files and rates each one independently on Impact, Quality, and Depth — with evidence citations.
- 04Aggregate. A larger reasoning model combines the per-repo scores with server-computed stats (heatmap, commit cadence, language entropy, follower count) to produce the 6-dimension profile score + roasts.
- 05Correct.Deterministic server-side checks enforce anchor-scale floors (e.g. a profile with 2,000+ public commits can't score 30 Consistency) and recompute the final verdict.
~90 seconds per profile, ~$0.25 in compute. Total of ~240 files read across your top-12 repos. One rating per GitHub account per day.
▸ Data sources & caveats
- Heatmap & commit totals: GitHub GraphQL
contributionsCollection— covers the last 365 days, includes private repos when the user has opted in (default). - Language %: byte totals across the top 30 owned non-fork repos.
- Curve: a small upward nudge centered on raw score ≈ 70, capping at 100. Prevents specialists from being unfairly penalised for narrow breadth.
- Anchor corrections: when server-measured signals (e.g. privateWorkLikely, multiRepoVolume, follower count) mandate a minimum category score, the aggregation step enforces it. These are signal-conditional, not identity-based floors.