Updated 3w ago
by sagirimo
BioDSH
The bioinformatics agent desktop for clinicians and wet-lab scientists — built on DeepSeek Harness. One-click installers, a skill store, offline mode.
59 GitHub stars (59)
+9 in 16 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | +2 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | +1 |
| Oct 9 | +1 |
| Oct 10 | +2 |
| Oct 11 | 0 |
| Oct 12 | +1 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | +2 |
| Oct 16 | 0 |
- 13 skills (13 skills found in its SKILL.md files)
- 1 forks (1 forks)
- 3w ago last update (Last updated 3w ago)
Install
Skills CLI
npx skills add sagirimo/BioDSH
Asks which skills and agents to install. Just one: npx skills add sagirimo/BioDSH --skill data-format-bridge — add -g for every project.
Claude Code
git clone https://github.com/sagirimo/BioDSHcp -r "BioDSH/biodsh-core/skills/data-format-bridge" ~/.claude/skills/
Copies the data-format-bridge skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add sagirimo/BioDSH
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
data-format-bridge
Convert analysis tables (csv/tsv/xlsx/parquet/h5ad obs-var/rds/sav/dta) into the formats clinicians and statisticians open directly — SPSS .sav, Stata .dta, R .rds with a ready-to-run .R script, GraphPad Prism .pzfx plus a Prism-ready wide CSV, and tidy Excel workbooks. Never touches the input file.
biodsh-core/skills/data-format-bridge/SKILL.md on GitHub (opens in a new tab) -
desktop-control
See and drive the user's desktop without vision - list and focus windows, read on-screen controls and text as JSON with coordinates (UI Automation on Windows, OCR elsewhere), then click, type, send hotkeys, open apps and paste tables into Excel/SPSS/GraphPad Prism/Zotero.
biodsh-core/skills/desktop-control/SKILL.md on GitHub (opens in a new tab) -
drug-docking
Virtual screening by molecular docking with AutoDock Vina — dock a set of small-molecule ligands (given as SMILES in a .smi/.csv/.txt file, or as an .sdf) into a receptor pocket, rank the hits by predicted binding affinity (kcal/mol) and save the best pose for each ligand. Use for structure-based drug screening / hit finding, not for ligand-based similarity search.
biodsh-core/skills/drug-docking/SKILL.md on GitHub (opens in a new tab) -
image-generate
Generate scientific illustrations (graphical abstracts, mechanism schematics, cover art, poster art) from a text prompt through the image provider configured in the BioDSH app. Not for data plots.
biodsh-core/skills/image-generate/SKILL.md on GitHub (opens in a new tab) -
md-simulation
Run a short molecular dynamics simulation of a protein (optionally a protein-ligand complex) with OpenMM — fix the structure, minimize, equilibrate, run a brief production trajectory, and report backbone RMSD stability over time. Use to relax/equilibrate a structure and check its stability, not for long production MD or free-energy calculations.
biodsh-core/skills/md-simulation/SKILL.md on GitHub (opens in a new tab) -
scanpy-clustering
Run a minimal deterministic Scanpy pipeline (QC, normalization, HVG, PCA, Leiden clustering, UMAP) on an h5ad file and write clusters.csv, umap.png and summary.json.
biodsh-core/skills/scanpy-clustering/SKILL.md on GitHub (opens in a new tab) -
scrna-cellstate-annotation
Assign evidence-backed broad immune cell classes and T-cell states to clustered AnnData data without using clinical outcome labels.
biodsh-core/skills/scrna-cellstate-annotation/SKILL.md on GitHub (opens in a new tab) -
scrna-inspect-qc
Inspect an input AnnData h5ad file and produce auditable single-cell RNA-seq quality-control evidence without modifying or filtering the source data.
biodsh-core/skills/scrna-inspect-qc/SKILL.md on GitHub (opens in a new tab) -
scrna-preprocess-cluster
Preprocess and cluster an AnnData h5ad dataset with state-aware normalization, deterministic Scanpy settings, and machine-readable scientific provenance.
biodsh-core/skills/scrna-preprocess-cluster/SKILL.md on GitHub (opens in a new tab) -
scrna-repro-audit
Read-only reproducibility audit of a completed BioDSH run bundle: verifies input/command/output hashes and result consistency from a result.json.
biodsh-core/skills/scrna-repro-audit/SKILL.md on GitHub (opens in a new tab) -
scrna-treatment-response
Compare immune-cell compositions between response groups using patient-level aggregation, deterministic inference, and explicit longitudinal-label safeguards.
biodsh-core/skills/scrna-treatment-response/SKILL.md on GitHub (opens in a new tab) -
scrna-virtual-knockout
In-silico single-gene knockout on scRNA-seq (scTenifoldKnk-style): build a gene regulatory network, virtually knock out a gene, and rank the genes most affected by its loss.
biodsh-core/skills/scrna-virtual-knockout/SKILL.md on GitHub (opens in a new tab) -
zotero-connect
Read and extend the user's own Zotero 7 library through the local desktop app — search papers, list collections and tags, pull PDF full text for summarising, add references by DOI/PMID, and export BibTeX/RIS/CSL-JSON. Never deletes or edits existing items.
biodsh-core/skills/zotero-connect/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.