AG
数据与复现
agent-browser
Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots, extr…
FreedomIntelligence/OpenClaw-Medical-Skills查看
数据与复现
BI
bio-research-tools-biomarker-signature-studio
维护者 FreedomIntelligence · 最近更新 2026年4月1日
Build, validate, and visualize multi-omic biomarker signatures.
原始来源
FreedomIntelligence/OpenClaw-Medical-Skills
https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills/tree/main/skills/bio-research-tools-biomarker-signature-studio
- 维护者
- FreedomIntelligence
- 许可
- MIT
- 最近更新
- 2026年4月1日
技能摘要
来自 SKILL.md 的关键信息
核心说明
- Design validated biomarker panels that are explainable，stable，、 ready ，用于 translational follow-up. This skill stitches together existing biomarker pipeline tooling，adds configurable feature-selection ensembles，small survival-analysis hook，、 artifact export so downstream lab teams can review QC outputs。
- 1. QC + Harmonization：Align expression matrices (samples x features) ，支持 metadata，check label balance，、 compute summary stats. 2. Feature Selection Ensemble：Supports Boruta，elastic-net stability，mutual-information top-K，、 mRMR ，支持 optional intersection voting. 3. Model Factory：Trains multiple estimators (Logistic L1，RandomForest，XGBoost if present) under nested CV，picks champion by AUC. 4. Explainability + Export：Produces SHAP tables/plots when packages are available，exports feature rankings 、 model weights. 5. Survival Hook：If metadata contains time_to_event 、 event skill computes concordance ，用于 selected features ，通过 Cox model。
- All logic lives in scripts/biomarker_signature_studio.py。
原始文档
SKILL.md 摘录
Inputs
- Expression matrix (
--expression): CSV/TSV genes x samples or samples x genes (auto-detected by metadata match). - Metadata (
--metadata): Must contain--label-column. Optional--id-column(defaultsample_id),time_to_event,event. - Optional gene list for filtering (
--feature-list). - Output directory (
--output-dir), created if missing.
Quick CLI Usage
Key flags:
| Flag | Description |
|---|---|
--selectors | Comma list of selection strategies (boruta, lasso, mrmr, mi_topk). |
--models | Models to evaluate (logit, rf, xgb). |
--k-features | Target number of features for mrmr/mi_topk. |
--survival | Enable Cox evaluation when survival columns exist. |
--random-state | Reproducibility. |
--nested-folds | Outer CV folds (default 5). |
Workflow
- Load + align inputs, infer orientation, impute missing values.
- Standardize features (fit on train set only).
- Run requested selectors; create intersection + union candidate lists.
- For each selector output run nested CV training across requested models.
- Export champion metrics (
metrics.json), feature table (selected_features.csv), SHAP summary (shap_summary.csvwhen available), and survival stats (survival.json).
适用场景
- Use bio-research-tools-biomarker-signature-studio ，用于 genomics 、 bioinformatics workflows。
- Apply bio-research-tools-biomarker-signature-studio to sequencing，variant，或 omics analysis tasks。
不适用场景
- Do not rely on this catalog entry alone ，用于 installation 或 maintenance details。
相关技能
相关技能
AL
数据与复现
alpha-vantage
Access 20+ years of global financial data: equities, options, forex, crypto, commodities, economic indicators, and 50+ t…
K-Dense-AI/claude-scientific-skills查看
BI
Filter alignments by flag, quality, region, or paired status.
FreedomIntelligence/OpenClaw-Medical-Skills查看
BI
Index BAM/CRAM files with samtools index for random access.
FreedomIntelligence/OpenClaw-Medical-Skills查看