| name | target-safety |
| description | Assemble the human genetic evidence for and against a target before a programme commits to it — the evidence class that most improves the odds of surviving clinical development. Use this skill to pull gnomAD constraint metrics (LOEUF, pLI, observed/expected) that show whether loss of function is tolerated in people, retrieve GWAS Catalog associations and fine-mapped credible sets for a gene, and read a natural human knockout as a safety readout. Also trigger on gnomAD, LOEUF, pLI, loss-of-function intolerance, mutational constraint, GWAS Catalog, credible set, human knockout, genetic support, or target safety dossier. |
| license | MIT |
| allowed-tools | Read Write Edit Bash |
| compatibility | Requires Python 3.10+ and outbound HTTPS access to gnomad.broadinstitute.org and www.ebi.ac.uk. The bundled clients use only the Python standard library and need no API key. gnomAD is queried through its public GraphQL endpoint; the GWAS Catalog v2 REST service can be slow, so timeouts are generous. |
| metadata | {"version":"1.0","skill-author":"K-Dense Inc.","openclaw":{"emoji":"🧬","homepage":"https://gnomad.broadinstitute.org"},"hermes":{"category":"research"}} |
Target Safety Assessment
Two public datasets answer the question that comes before every programme: what happens to
people who naturally have less of this protein? gnomAD says whether such people exist. The GWAS
Catalog says what else changes when they do. Targets with human genetic support are roughly twice
as likely to survive clinical development, and this is the only evidence class available before a
molecule does.
Services: https://gnomad.broadinstitute.org/api (GraphQL, POST) ·
https://www.ebi.ac.uk/gwas/rest/api/v2 (REST). Both unauthenticated.
Checked against: gnomAD v4.1 and the live GWAS Catalog v2 API, August 2026.
Read references/gnomad-constraint.md before quoting a
constraint number, references/gwas-catalog.md before writing a query
by hand, and
references/interpreting-genetic-evidence.md before
drawing a conclusion — that one is judgement, not syntax.
The three scripts
| Script | Answers |
|---|
gnomad_constraint.py | Do healthy humans exist who have lost this protein? |
gwas_evidence.py | What traits is this gene associated with, and how solidly? |
safety_dossier.py | Both at once, as a verdict with its inputs beside it |
A drug is a chemical phenocopy of a loss-of-function variant
That equivalence is the whole idea. If people carrying LoF variants in a gene are healthy and
common, inhibiting the protein is likely survivable. If those variants have been removed from the
population by selection, that is a warning you can read years before a tox study.
python skills/target-safety/scripts/gnomad_constraint.py compare LRRK2 PCSK9 SCN2A KRAS HTT
symbol loeuf band pLI obs_lof exp_lof
SCN2A 0.154 constrained 1 20 188.7
KRAS 0.2264 constrained 0.9998 1 20.95
HTT 0.3379 constrained 1 104 362.3
LRRK2 0.7537 tolerant 1.317e-43 203 302.6
PCSK9 1.144 unconstrained 2.765e-18 57 62.12
obs_lof against exp_lof is the whole argument. KRAS: one observed loss-of-function variant
where twenty-one were expected. PCSK9: fifty-seven observed against sixty-two expected — no
depletion at all. , which is
exactly why evolocumab and alirocumab exist. The constraint table said so before the drugs did.
