メニュー
Default scRNA counting route. Turn FASTQ or existing Cell Ranger, STARsolo, SimpleAF / Alevin-fry, or kb-python outputs into a downstream-ready standardized AnnData.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/mdbabumiamssm/LLMs-Universal-Life-Science-and-Clinical-Skills- --skill sc-countコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Operate MedSAM2 for promptable segmentation of 3D medical images and medical videos, including CT lesion propagation, MRI volumes, RECIST-guided prompts, efficient CPU-oriented variants, training, and 3D Slicer integration. Use when generating or validating volumetric masks from sparse prompts or propagating masks through image slices or video frames.
Build reproducible healthcare imaging pipelines with Project MONAI for DICOM, NIfTI, pathology, and multidimensional imaging tasks including preprocessing, augmentation, training, sliding-window inference, evaluation, model bundles, labeling, and deployment. Use when implementing medical image classification, segmentation, registration, detection, generative, or foundation-model workflows in PyTorch.
Operate Google TxGemma prediction and chat models for therapeutic property prediction across small molecules, proteins, nucleic acids, diseases, targets, and cell lines. Use when formatting Therapeutics Data Commons tasks, choosing TxGemma model size or variant, running local or Model Garden inference, fine-tuning on private therapeutic data, or evaluating TxGemma in drug-discovery workflows.
SOC 職業分類に基づく
SKILL.md を表示中
| name | sc-count |
| description | Default scRNA counting route. Turn FASTQ or existing Cell Ranger, STARsolo, SimpleAF / Alevin-fry, or kb-python outputs into a downstream-ready standardized AnnData. |
| version | 0.1.0 |
| author | OmicsClaw |
| license | MIT |
| tags | ["singlecell","scrna","count","cellranger","starsolo","simpleaf","kb-python","fastq"] |
| metadata | {"omicsclaw":{"domain":"singlecell","requires":{"bins":"[Truncated]","env":"[Truncated]","config":"[Truncated]"},"emoji":"🧬","homepage":"https://github.com/TianGzlab/OmicsClaw","os":["macos","linux"],"install":["[Truncated]"],"trigger_keywords":["Cell Ranger count","STARsolo count","fastq to adata","raw single-cell counting","generate count matrix"],"allowed_extra_flags":["--chemistry","--method","--read2","--reference","--sample","--t2g","--threads","--whitelist","--r-enhanced"],"legacy_aliases":["scrna-count","sc-pseudoalign-count","scrna-pseudoalign-count"],"saves_h5ad":true,"requires_preprocessed":false,"param_hints":{"cellranger":"[Truncated]","starsolo":"[Truncated]","simpleaf":"[Truncated]","kb_python":"[Truncated]"}}} |
You are SC Count, a specialized OmicsClaw agent for converting scRNA-seq FASTQ input into standardized count matrices and a downstream-ready AnnData.
h5ad, basic count QC
figures, and preserves backend artifacts.processed.h5ad with
layers['counts'] and OmicsClaw input-contract metadata.README.md, report.md, result.json,
and rerun commands.| Format | Extension | Required Fields / Structure | Example |
|---|---|---|---|
| FASTQ directory | directory | one or more 10x-style FASTQs, optionally multiple samples | fastqs/ |
| FASTQ file | .fastq.gz | one mate file plus --read2 for paired input | PBMC_R1.fastq.gz |
| Cell Ranger output | directory | contains outs/filtered_feature_bc_matrix* | sample_count/ |
| STARsolo output | directory | contains Solo.out/Gene/filtered/ | starsolo_pbmc/ |
| Demo | n/a | --demo flag |
| built-in PBMC example |
| Requirement | Where it should exist | Why it matters |
|---|---|---|
| Raw FASTQs or existing count output | input path | counting requires raw reads or a backend output directory to import |
| Backend reference | --reference | required for real backend runs |
| 10x chemistry contract | --chemistry, --whitelist | required for STARsolo barcode/UMI parsing |
| Transcript-to-gene map | --t2g | required for kb-python runs |
If the user is missing reference assets, guide them to either:
--reference, --whitelist, or --t2gresources/singlecell/references/cellranger/resources/singlecell/references/starsolo/resources/singlecell/references/simpleaf/resources/singlecell/references/kb/resources/singlecell/references/whitelists/Download guidance:
3M-february-2018.txtt2gREADME.md, report.md, result.json, and the reproducibility bundle.oc run sc-count --input fastqs/ --method cellranger --reference /path/to/refdata-gex-GRCh38-2020-A --output results/
oc run sc-count --input fastqs/ --method starsolo --reference /path/to/star_index --chemistry 10xv3 --whitelist /path/to/3M-february-2018.txt --output results/
oc run sc-count --input fastqs/ --method simpleaf --reference /path/to/simpleaf_index --chemistry 10xv3 --output results/
oc run sc-count --input fastqs/ --method kb_python --reference /path/to/kallisto.idx --t2g /path/to/t2g.txt --chemistry 10xv3 --output results/
oc run sc-count --input sample_count/ --method cellranger --output results/
python skills/singlecell/scrna/sc-count/sc_count.py --demo --output /tmp/sc_count_demo
cellranger count with --nosecondary and BAM output kept on.layers['counts'], stabilize names, and record OmicsClaw input-contract metadata.CB_UMI_Simple wrapper with EmptyDrops-style cell calling.Solo.out/Gene/filtered.layers['counts'] and record the same OmicsClaw contract as the Cell Ranger path.simpleaf quant when needed.kb count when needed.Key parameters:
| Parameter | Default | Description |
|---|---|---|
--method | cellranger | choose Cell Ranger, STARsolo, SimpleAF / Alevin-fry, or kb-python |
--reference | none | backend reference directory or index path |
--t2g | none | transcript-to-gene map for kb-python |
--sample | none | choose one sample from a multi-sample FASTQ directory |
--threads | 8 | thread count for backend execution |
--chemistry | auto | Cell Ranger auto-detects; STARsolo requires explicit supported chemistry |
--whitelist | none | STARsolo barcode whitelist file |
Current OmicsClaw behavior: all non-Cell Ranger methods are intentionally scoped to mainstream 10x-style droplet geometry first. Complex custom chemistries remain deferred.
figure_data/.figures/manifest.json records the standard counting gallery.output_directory/
├── README.md
├── report.md
├── result.json
├── processed.h5ad
├── figures/
│ ├── barcode_rank.png
│ └── count_distributions.png
│ ├── count_complexity_scatter.png
│ └── manifest.json
├── tables/
│ ├── count_summary.csv
│ ├── barcode_metrics.csv
│ └── backend_summary.csv
├── figure_data/
│ ├── manifest.json
│ ├── count_summary.csv
│ └── barcode_metrics.csv
├── artifacts/
│ ├── cellranger/
│ ├── starsolo/
│ ├── simpleaf/
│ └── kb_python/
└── reproducibility/
├── analysis_notebook.ipynb
├── commands.sh
└── requirements.txt
artifacts/ for methods
such as CellBender or RNA-velocity preparation.knowledge_base/knowhows/KH-sc-count-guardrails.md: short execution guardrails for import-vs-run decisions and backend boundaries.knowledge_base/skill-guides/singlecell/sc-count.md: longer operator guide for count-method choice and downstream hand-off.Required:
scanpy, anndata, pandas, numpyOptional but method-specific:
cellrangerSTARsimpleafkbpip install -e ".[singlecell-upstream]"cellrangerSTARsimpleafkbRecommended user guidance:
resources/singlecell/references/... or accept explicit local paths, but should not silently download large references during execution.| Flag | Type | Default | Description | Validation |
|---|---|---|---|---|
--input | str | None | FASTQ path or existing Cell Ranger / STARsolo output directory | Required unless --demo |
--output | str | — | Output directory | Required |
--demo | flag | off | Run with built-in demo data | — |
--method | str | cellranger | Counting backend | Choices: cellranger, starsolo, simpleaf, kb_python |
--reference | str | None | Backend reference path (Cell Ranger transcriptome, STAR genome dir, simpleaf index, or kallisto index) | Required for real backend runs |
--t2g | str | None | Transcript-to-gene map for kb-python runs | Required for kb_python method |
--sample | str | None | Choose one sample from a multi-sample FASTQ directory | — |
--read2 | str | None | Explicit mate FASTQ when --input points to one file | — |
--threads | int | 8 | Backend thread count | — |
--chemistry | str | auto | Chemistry hint; STARsolo supports 10xv2, 10xv3, 10xv4; Cell Ranger auto-detects | — |
--whitelist | str | None | STARsolo barcode whitelist file | Strongly recommended for STARsolo real runs |
--r-enhanced | flag | off | Accepted for CLI consistency; no R Enhanced plots for this skill | No-op |
This skill has no R Enhanced plots. The --r-enhanced flag is accepted for CLI consistency but produces no additional output.
Each backend requires its own reference assets. OmicsClaw does not download references automatically.
| Backend | --reference points to | Also needs |
|---|---|---|
cellranger | Cell Ranger transcriptome dir (e.g., refdata-gex-GRCh38-2020-A) | — |
starsolo | STAR genome directory (built from FASTA + GTF) | --whitelist (10x barcode list), --chemistry |
simpleaf | simpleaf index directory | --chemistry |
kb_python | kallisto index file (.idx) | --t2g (transcript-to-gene map), --chemistry |
Place reference assets under resources/singlecell/references/<backend>/ for auto-detection, or pass explicit paths via --reference.
If a Cell Ranger or STARsolo run has already completed, pass the existing output directory as --input and omit --reference. The wrapper imports the filtered matrix directly without re-running the backend.
# Cell Ranger — run from FASTQ
python omicsclaw.py run sc-count \
--input fastqs/ --method cellranger \
--reference /path/to/refdata-gex-GRCh38-2020-A \
--output results/
# STARsolo — run from FASTQ
python omicsclaw.py run sc-count \
--input fastqs/ --method starsolo \
--reference /path/to/star_index \
--chemistry 10xv3 \
--whitelist /path/to/3M-february-2018.txt \
--output results/
# kb-python — run from FASTQ
python omicsclaw.py run sc-count \
--input fastqs/ --method kb_python \
--reference /path/to/kallisto.idx \
--t2g /path/to/t2g.txt \
--chemistry 10xv3 \
--output results/
# Import existing Cell Ranger output
python omicsclaw.py run sc-count \
--input sample_count/ --method cellranger \
--output results/
sc-fastq-qc for read-level quality assessment before countingsc-qc for quality assessment, or sc-multi-count if merging multiple samples