Bio Machine Learning Prediction Explanation
Explains ML predictions on omics data with SHAP, LIME, and permutation importance, handling the correlated-feature trap, the conditional-vs-interventional Shapley choice, and the attribution-is-not-causation boundary. Use when interpreting an omics classifier, debugging shortcut/batch learning, or deciding whether an attribution ranking can be trusted as biology. For validated feature selection see machine-learning/biomarker-discovery; explanations are not a selection method.
Install
/plugin marketplace add hackernoon/cuttlefish-agent-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add hackernoon/cuttlefish-agent-skills --skill bio-machine-learning-prediction-explanationgit clone --depth 1 https://github.com/hackernoon/cuttlefish-agent-skills.git /tmp/cuttlefish-agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/cuttlefish-agent-skills/plugins/data-science/skills/bio-machine-learning-prediction-explanation ~/.claude/skills/bio-machine-learning-prediction-explanationPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
## Version Compatibility Reference examples tested with: numpy 1.26+, pandas 2.2+, scikit-learn 1.4+, shap 0.44+, lime 0.2+. Before using code patterns, verify installed versions match. If versions differ: - Python: `pip show <package>` then `help(module.function)` to check signatures Two shap drifts: the Explanation-object plotting API arrived ~0.36 (new-style `shap.plots.*` take an `Explanation`, legacy `shap.summary_plot`/`dependence_plot` take numpy arrays -- mixing them is the most common runtime error); and `TreeExplainer(..., feature_perturbation='auto')` became the default in 0.47 (was `interventional`), so providing or omitting `data=` silently changes the estimand. Always set `feature_perturbation` explicitly. If code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt rather than retrying. # Model Interpretation for Omics Classifiers **"Which genes drive my classifier?"** -> Compute attributions, but treat them as a description of the model (not biology), choose the Shapley conditioning deliberately, and aggregate over correlated gene modules before ranking. - Tree models: `shap.TreeExplainer(model, data=background, feature_perturbation='interventional')` - Model-agnostic local: `lime.lime_tabular.LimeTabularExplainer` - Model-reliance screen: `sklearn.inspection.permutation_importance`
Details
- Skill name
bio-machine-learning-prediction-explanation- Repository
- hackernoon/cuttlefish-agent-skills
- Path
plugins/data-science/skills/bio-machine-learning-prediction-explanation/SKILL.md- License
- MIT
- Repo updated
- 4 November 2026
FAQ
What does the Bio Machine Learning Prediction Explanation skill do?
Explains ML predictions on omics data with SHAP, LIME, and permutation importance, handling the correlated-feature trap, the conditional-vs-interventional Shapley choice, and the attribution-is-not-causation boundary. Use when interpreting an omics classifier, debugging shortcut/batch learning, or deciding whether an attribution ranking can be trusted as biology. For validated feature selection see machine-learning/biomarker-discovery; explanations are not a selection method.
How do I install the Bio Machine Learning Prediction Explanation skill?
Claude Code plugin: /plugin marketplace add hackernoon/cuttlefish-agent-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Bio Machine Learning Prediction Explanation popular?
It lives in hackernoon/cuttlefish-agent-skills, which has 9 GitHub stars and 3 forks.
Related skills
AI Traffic Tracking
9hackernoon/cuttlefish-agent-skills
Compatibility pointer for AI assistant referrals and generative search visibility; maintained in Open Analytics.
Analytics Tracking
9hackernoon/cuttlefish-agent-skills
Compatibility pointer for GA4 event, key-event and User-ID tracking; maintained in Open Analytics.
Bio Admet Prediction
9hackernoon/cuttlefish-agent-skills
Predicts ADMET properties using ADMETlab 3.0 (119 platform features, including 77 prediction models with modeled-endpoint uncertainty), ADMET-AI, DeepChem MolNet, and chemprop D-MPNN with explicit handling of OECD QSAR principles, applicability domain assessment, calibration, hERG/CYP/AMES endpoints, and PAINS / Lipinski / Ro5 / Veber / BBB druglikeness filters. Use when filtering compounds for drug-likeness, prioritizing leads by predicted safety, or building an in-house ADMET QSAR model.
Bio Multi Omics Mixomics Analysis
9hackernoon/cuttlefish-agent-skills
Builds supervised and unsupervised multivariate integration across bulk omics blocks with mixOmics - sPLS for sparse pairwise correlation, DIABLO (block.splsda) for a multi-block discriminant signature, rCCA for regularized canonical correlation, and MINT for multi-study integration. Covers why these projection methods maximize covariance or correlation and not truth, why DIABLO's design matrix is the central correlation-versus-discrimination decision, why cross-validation must wrap keepX selection or the reported error is leaked, why balanced error rate is required under class imbalance, and
Bio Machine Learning Omics Classifiers
9hackernoon/cuttlefish-agent-skills
Builds diagnostic and prognostic classifiers on omics feature matrices with regularized logistic regression, random forest, and gradient-boosted trees, handling the p>>n regime, batch shortcut learning, class imbalance, and probability calibration. Use when building a classifier from expression, methylation, or variant data, choosing an algorithm for high-dimensional small-n data, or diagnosing a suspiciously perfect AUC. For unbiased evaluation see machine-learning/model-validation; for feature selection see machine-learning/biomarker-discovery; for time-to-event outcomes see machine-learning
Public Face Review Builder
5getclera/claude-skills
Turn a supplied people/contact list with names, profile-picture URLs, roles, LinkedIn URLs, and optional owner fields into a mobile-friendly face-memorization web app with grid, quiz, flashcard, shuffle, and filtering modes, then publish it to a shareable public URL when an approved writable hosting destination is available. Use when the user wants to memorize attendees, founders, candidates, customers, investors, or other people before an event or meeting.
Browse the most popular Claude skills, all learning & education skills, or write your own with the skills generator.