emberwhirl-solo
I built PerturbScope, a dashboard that helps wet-lab biologists, clinician-scientists, and hybrid researchers turn large CRISPR Perturb-seq screens into reviewable target shortlists.
Core trick
Applies evidence gates that check reliability before effect size, exposing missing data, replicate structure, and analysis lineage instead of one opaque ranking.
Description
I built PerturbScope, a dashboard that helps wet-lab biologists, clinician-scientists, and hybrid researchers turn large CRISPR Perturb-seq screens into reviewable target shortlists. The application combines target exploration, configurable evidence gates, matched-condition comparisons, human–mouse translation evidence, custom cell-level phenotypes, immutable provenance, and reproducible exports.
I investigated how prioritization changes when reliability is evaluated before effect size. I found that strong effects can be misleading when knockdown is weak, guides disagree, donor responses fail to reproduce, coverage is limited, or translation evidence is poor. PerturbScope therefore exposes missing data, warnings, replicate structure, and analysis lineage rather than collapsing them into an opaque ranking. This matters because experimental validation is costly: transparent trust gates help researchers allocate scarce resources to candidates supported by stronger, auditable evidence while preserving scientific judgment and enabling independent review.
README excerpt
# PerturbScope **A trust-first decision cockpit for Perturb-seq screens.** PerturbScope helps **wet-lab biologists, physician-scientists, and hybrid researchers** move from a large CRISPR screen to a reviewable target shortlist without hiding weak replication, missing data, or analysis provenance. It combines target exploration, explicit trust gates, matched-condition comparisons, human–mouse model-selection evidence, custom cell readouts, and reproducible exports in one local, no-code web application. > [!IMPORTANT] > **MVP / experimental software:** PerturbScope is an early-stage hackathon prototype intended for exploration, evaluation, and research workflow testing. Features, interfaces, trust thresholds, and analysis methods may change, and results should be independently reviewed and validated before use in consequential research decisions. The repository opens with a fully offline demonstration built from the published CZI Virtual Cells Platform Primary Human CD4+ T Cell Perturb-seq summary tables: **33,983 target-condition records**, **11,526 targets**, **20,509,715 represented perturbed cells**, **26,504 guides**, **four donors**, and **three conditions**.  > PerturbScope is research software. It is not a medical device, does not provide clinical guidance, and does not replace confirmatory statisti