by-failure-diagnosis
CommunityStatistical failure post-mortem for designs.
Data & Analytics#diagnosis#statistical-analysis#mann-whitney#bh-correction#pass-vs-fail#design-campaign
Author001TMF
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Diagnose failure modes by testing whether PASS designs differ from FAIL designs on key numeric features using Mann-Whitney U tests.
Core Features & Use Cases
- Runs Mann-Whitney U tests between PASS and FAIL groups for canonical metrics (ipsae, ipsae_min, iptm, plddt, rmsd, liabilities, cdr3_length, hydrophobic_fraction, net_charge) with Benjamini-Hochberg correction.
- Produces a structured diagnosis containing discriminating features, effect sizes, and q-values, plus a human-readable table and top recommendations.
- Provides CLI scripts (diagnose_from_csv.py, plot_distributions.py) to generate dashboards, plots, and exportable results for downstream optimization.
Quick Start
Run the diagnosis tool on your campaign's screening output to obtain a feature-discrimination report and recommended next actions.
Dependency Matrix
Required Modules
scipynumpypandasmatplotlib
Components
scriptsreferences
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: by-failure-diagnosis Download link: https://github.com/001TMF/blatant-why/archive/main.zip#by-failure-diagnosis Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.