DMV Petri Dish
Synthetic lethality is one of the cleanest routes to targeted cancer therapy, yet it remains understudied, and most cancer-screening data sits siloed behind deep expertise.
Core trick
Serves ten-plus drug-sensitivity datasets through a synthetic-lethality scan that ranks drugs by how much more they kill cells carrying a chosen driver mutation.
Description
Synthetic lethality is one of the cleanest routes to targeted cancer therapy, yet it remains understudied, and most cancer-screening data sits siloed behind deep expertise. We made over 10 datasets (over 20GB of drug data) explorable by anyone, with quick tooling to screen for potential drugs by cancer-type. We grounded our work by replicating our lung synthetic-lethal study (doi.org/10.21203/rs.3.rs-9559070/v1 – preprint) which used RB1/CDKN2A/PTEN/TP53 as driver gene mutations and found relevant synthetic lethal pairs (original dataset was DepMap, but we now have other datasets that show this generalization as well).
The value of this project is that preclinical cancer researchers can massively look at an interpretation of cancer therapeutics using the synthetic lethality model, and get access to new drug targets and mechanism interpretations. Because this mechanism requires two genes, a driver gene and targeted gene – only big datasets are good a finding this non-obvious but very useful class of potential therapeutics.
MoCoMakers/tumor-preclinical-discovery★ 00 forksPythonNOASSERTIONCreated Jul 13, 2026 · last push Jul 13, 2026
README excerpt
# Pan-Cancer Synthetic-Lethality Explorer **Find the drug + mutation pairs where a drug kills cancer cells that carry a specific mutation much harder than otherwise-similar cells that lack it** — synthetic lethality, one of the cleanest routes to a cancer therapy with a built-in target. ## ▶ Try the live demo — no install, no account # **[tumor.mocomakers.com](https://tumor.mocomakers.com/)** Open it, hit **🎯 SL Scan**, type a gene like `TP53`, and watch every drug get ranked by how mutant-selective it is. That's the whole pitch in ~10 seconds. Everything below is just detail. > ⚠️ **Very early & EXPERIMENTAL.** This is an active hackathon build — a working slice of a larger > framework, moving fast. **These reports have not been peer-reviewed and should be considered > experimental.** The pieces described under "What it does well" are live end-to-end on real data; more > lenses and validations are on the roadmap. Best experienced through the live demo above. --- ## What it does well (live, on real warehouse data) - **Genotype-selectivity engine (S′ / ΔpS′).** Every drug–cell-line dose-response curve collapses to a single **S′** score (like AUC, but higher = more killing). Pooled per genotype, the mutant-vs-wild-type gap **ΔpS′** ranks synthetic-lethal leads. The transform reproduces the manuscript exactly. - **SL Scan — one gene, every drug.** Choose a screen and a driver gene; a permutation test ranks every compound by mutant-selective killing with FDR q-valu