메뉴
Load when checking a bulk RNA-seq count matrix for library-size outliers, gene detection rates, and sample-sample correlation before DE. Skip if data is raw FASTQ (use bulkrna-read-qc) or aligner logs (use bulkrna-read-alignment), or for single-cell counts (use sc-qc).
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
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.
Evaluate and operate released Profluent OpenCRISPR gene-editing systems, especially OpenCRISPR-1, for controlled research workflows using its published Cas9-like protein, compatible guide RNA designs, protocols, licensing, specificity testing, and experimental validation. Use when comparing OpenCRISPR-1 with SpCas9, planning nonclinical editing studies, or assessing use in nuclease, nickase, deactivated, base, prime, or epigenome-editing contexts.
Operate CZI TranscriptFormer cross-species generative single-cell models to produce cell embeddings, contextual gene embeddings, likelihoods, zero-shot classifiers, disease-state representations, and regulatory analyses from raw-count AnnData files. Use when selecting TF-Sapiens, TF-Exemplar, or TF-Metazoa, processing in- or out-of-distribution species, or scaling embedding extraction across GPUs.
Operate ByteDance Protenix-v2 for open biomolecular structure prediction of proteins, antibodies, nucleic acids, ligands, and complexes using JSON inputs, MSA and template features, constraints, and inference-time sampling. Use when running Protenix locally or through its server, comparing AlphaFold3-style open models, or building reproducible co-folding evaluations.
| name | bulkrna-qc |
| description | Load when checking a bulk RNA-seq count matrix for library-size outliers, gene detection rates, and sample-sample correlation before DE. Skip if data is raw FASTQ (use bulkrna-read-qc) or aligner logs (use bulkrna-read-alignment), or for single-cell counts (use sc-qc). |
| version | 0.3.0 |
| author | OmicsClaw |
| license | MIT |
| tags | ["bulkrna","QC","count-matrix","library-size","gene-detection","sample-correlation","CPM"] |
| requires | ["numpy","pandas","matplotlib","scipy"] |
Run as the first step on a bulk RNA-seq count matrix (genes × samples) before differential expression. Surfaces the four failure modes that silently bias DE results: a sample with a tiny library, a sample with suspiciously few detected genes, a low-correlation outlier vs the rest, and CPM-vs-raw comparison artefacts.
| Input | Format | Required |
|---|---|---|
| Count matrix | .csv (gene id col + sample count cols) | yes (or --demo) |
| Output | Path | Notes |
|---|---|---|
| Library sizes | figures/library_sizes.png | per-sample total counts |
| Gene detection | figures/gene_detection.png | non-zero gene count per sample |
| Sample correlation | figures/sample_correlation.png | log-CPM Pearson heatmap |
| Expression density | figures/expression_density.png | per-sample log-CPM density curves |
| Outlier flag | result.json["outlier_samples"] | sample names flagged below correlation threshold |
| CPM-normalised matrix | tables/cpm_normalized.csv | per-million normalisation, useful for visualisation |
| Report | report.md + result.json | always |
--input or non-existent file per bulkrna_qc.py:428,431).tables/cpm_normalized.csv).report.md + result.json.bulkrna_qc.py:428 raises ValueError("--input is required when not using --demo"); :431 raises FileNotFoundError if the path doesn't exist. No silent demo fallback when --input is given but invalid — fix the path or use --demo.tables/cpm_normalized.csv is emitted as a downstream-friendly artefact, but DE testing must always use raw counts (PyDESeq2's negative-binomial GLM expects integer counts; feeding CPM produces meaningless dispersion estimates). Do not pipe cpm_normalized.csv into bulkrna-de.result.json["outlier_samples"] against the experimental design before excluding samples.report.md's "samples seen" count vs your design before trusting the output.python omicsclaw.py run bulkrna-qc --demo
python omicsclaw.py run bulkrna-qc --input counts.csv --output results/
references/parameters.md — every CLI flag and tuning hintreferences/methodology.md — library-size, gene-detection, correlation-based outlier metricsreferences/output_contract.md — exact output directory layoutbulkrna-read-qc / bulkrna-read-alignment (upstream), bulkrna-de (downstream — raw counts only), bulkrna-batch-correction (downstream if QC reveals batch effects), sc-qc (single-cell sibling)