メニュー
Load when summarising rMATS / SUPPA2 alternative-splicing output and identifying significant differential splicing events. Skip if you only have count-level DE (use bulkrna-de) or for splicing in single-cell or spatial data (currently unsupported).
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。
SOC 職業分類に基づく
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-splicing |
| description | Load when summarising rMATS / SUPPA2 alternative-splicing output and identifying significant differential splicing events. Skip if you only have count-level DE (use bulkrna-de) or for splicing in single-cell or spatial data (currently unsupported). |
| version | 0.3.0 |
| author | OmicsClaw |
| license | MIT |
| tags | ["bulkrna","splicing","alternative-splicing","PSI","rMATS","SUPPA2"] |
Run AFTER rMATS or SUPPA2 has produced its splicing-event table — this skill consumes that output (not raw alignments). Computes per-event ΔPSI (delta percent-spliced-in), flags events crossing significance and ΔPSI thresholds, and groups results by event type (SE / A3SS / A5SS / MXE / RI).
| Input | Format | Required |
|---|---|---|
| Splicing event table | .csv from rMATS or SUPPA2 (event_id, type, ΔPSI, p-value cols) | yes (or --demo) |
--dpsi-cutoff | float | default 0.1 (events with abs ΔPSI ≥ this) |
--padj-cutoff | float | default 0.05 (significance threshold) |
| Output | Path | Notes |
|---|---|---|
| All events | tables/splicing_events.csv | full annotated event table |
| Significant events | tables/significant_events.csv | filtered by --dpsi-cutoff and --padj-cutoff |
| ΔPSI distribution | figures/dpsi_distribution.png | histogram with cutoff lines |
| Event-type breakdown | figures/event_type_distribution.png | SE / A3SS / A5SS / MXE / RI counts |
| Volcano | figures/volcano_splicing.png | ΔPSI vs -log10(padj) |
| Report | report.md + result.json | always |
bulkrna_splicing.py:365,368 on missing or invalid --input.event_type, gene, delta_psi, padj (bulkrna_splicing.py:153-155). No format detection — caller must pre-flatten rMATS / SUPPA2 output to this schema.--dpsi-cutoff AND --padj-cutoff.tables/splicing_events.csv (full) + tables/significant_events.csv (filtered) + report.--dpsi-cutoff is the ABSOLUTE value of ΔPSI. Default 0.1 keeps events with |ΔPSI| ≥ 0.1, including both inclusion-up and inclusion-down. Set to 0 to keep all directionally significant events.event_type, gene, delta_psi, padj (with optional pvalue and event_id). The script does NOT auto-detect rMATS vs SUPPA2 column conventions — if your input uses rMATS's IncLevelDifference/FDR or SUPPA2's dPSI/pval natively, rename columns first or the loader will silently drop your data.event_type column before feeding the skill, or the breakdown bar chart under-counts.python omicsclaw.py run bulkrna-splicing --demo
python omicsclaw.py run bulkrna-splicing \
--input rmats_se.csv --output results/
python omicsclaw.py run bulkrna-splicing \
--input suppa2_events.csv --output results/ \
--dpsi-cutoff 0.2 --padj-cutoff 0.01
references/parameters.md — every CLI flag and tuning hintreferences/methodology.md — rMATS vs SUPPA2 format conventions, event-type taxonomyreferences/output_contract.md — exact output directory layoutbulkrna-de (parallel: gene-level DE, complements exon-level splicing), bulkrna-enrichment (downstream: pathway view of splicing-affected genes via gene-symbol mapping)