菜单
SkillsMP 已收集 omicverse/omicverse-skills 中的 39 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 39 / 39 个已收集 Skill。
Two adjacent LC-MS workflows on AnnData — (1) untargeted metabolomics with m/z-based peak annotation, mummichog pathway inference and adduct-ppm matching, and (2) lipidomics with LIPID MAPS shorthand parsing, lipid-class aggregation, and LION term enrichment.…
原文语言：英语
Bulk RNA-seq DEG pipeline: gene ID mapping, DESeq2 normalization, statistical testing, volcano plots, and pathway enrichment in OmicVerse.
原文语言：英语
End-to-end bulk RNA-seq quantification with omicverse's alignment module — SRA download, fastp QC, two interchangeable quantification paths (STAR + featureCount, OR alignment-free kb-python with technology='BULK'), and wiring into `ov.bulk.pyDEG` DESeq2.…
原文语言：英语
CellRank fate maps from RNA velocity. Combine VelocityKernel + ConnectivityKernel into a transition matrix, fit a GPCCA estimator, predict terminal states, and produce per-cell fate probabilities. Visualise with `ov.pl.branch_streamplot` and feed…
原文语言：英语
Run OmicVerse single-cell NMF program discovery as a reusable, triggerable skill — both the classical Python `ov.single.cNMF` (consensus NMF with CPU/GPU factorization, K-selection, RFC labelling) and the Rust-backed `ov.single.NMF` (fast `nmf-rs` backend:…
原文语言：英语
Monocle2-style single-cell trajectory analysis on AnnData via the `ov.single.Monocle` class - DDRTree pseudotime + branch detection + per-gene differential test + BEAM branch-dependent gene discovery, plus the unified `ov.pl.trajectory` /…
原文语言：英语
Run the OmicVerse sctour trajectory branch on raw-count single-cell AnnData. Use when adapting the scTour part of an OmicVerse trajectory notebook, or when you need sctour pseudotime, latent space, or vector-field outputs instead of the diffusion_map,…
原文语言：英语
Run or adapt OmicVerse single-cell trajectory inference on cluster-ready AnnData. Use when converting OmicVerse trajectory notebooks into a reusable skill, or when choosing the diffusion_map, slingshot, palantir, PAGA, or Palantir branch-selection branches…
原文语言：英语
Cell embedding, cell-type annotation, batch integration, and (where supported) perturbation prediction with single-cell foundation models — scGPT, Geneformer, scFoundation, UCE, CellPLM. Driven by the unified `ov.llm.SCLLMManager` interface; one object…
原文语言：英语
OmicVerse plotting: volcano, venn, boxplot, embedding, density, dotplot, convex hull, stacked bar, and Forbidden City color palettes.
原文语言：英语
Convert OmicVerse single-cell preprocessing and marker-discovery notebooks into a reusable, triggerable skill. Use when cleaning AnnData, choosing a preprocessing mode, building PCA and neighborhood graphs, clustering with Leiden, or extracting marker genes…
原文语言：英语
Spatial transcriptomics: Visium/HD, Stereo-seq, Slide-seq preprocessing (crop, rotate, cellpose), deconvolution (Tangram, cell2location, Starfysh), clustering (GraphST, STAGATE), integration, trajectory, communication.
原文语言：英语
Cell-type composition deconvolution of bulk RNA-seq using a single-cell reference. Wraps `ov.bulk.Deconvolution` with four interchangeable backends — TAPE, Scaden, BayesPrism, OmicsTweezer — under one constructor / one `.deconvolution(method=...)` call. Use…
原文语言：英语
Multivariate discrimination and biomarker selection on a preprocessed metabolomics AnnData. Use when running PLS-DA, OPLS-DA, VIP / S-plot inspection, per-metabolite ROC AUC with bootstrap confidence intervals, or building a multi-metabolite biomarker panel…
原文语言：英语
Pathway interpretation, multi-factor designs, differential correlation, MOFA multi-omics, and the MTBLS1 real-data case study on a preprocessed metabolomics AnnData. Use when you need MSEA ORA / GSEA pathway enrichment with KEGG IDs, multi-factor ANOVA-SCA /…
原文语言：英语
Run the canonical metabolomics preprocessing chain on an AnnData peak table — impute, normalize, transform — and apply LC-MS-specific drift / batch / sample QC corrections (drift_correct, SERRF, ComBat, sample_qc). Use when converting `t_metabol_01_intro` or…
原文语言：英语
Paired microbiome × metabolomics integration on sample-aligned AnnDatas. Provides three methods - Spearman correlation (fast pairwise FDR), sklearn CCA (linear canonical mode shared between modalities), and MMvec (PyTorch low-rank co-occurrence model with…
原文语言：英语
16S rRNA amplicon analysis from raw FASTQs to a samples × ASVs AnnData with 7-rank SINTAX taxonomy, plus the canonical alpha / beta / ordination / DA stack. Use when running the vsearch-or-DADA2 amplicon pipeline (`ov.alignment.amplicon_16s_pipeline`), when…
原文语言：英语
Run all three differential-abundance methods (Wilcoxon, pyDESeq2, ANCOM-BC) on the same microbiome AnnData, compare their hit sets via 3-way Venn / overlap counts, and decide which to trust on a given cohort. Use when the user wants to benchmark DA methods on…
原文语言：英语
Combine multiple per-study microbiome AnnDatas into a single cross-cohort table and run inverse-variance / random-effects meta-analysis on differential abundance. Use when you have 16S studies from multiple cohorts that need joint analysis, when you need a…
原文语言：英语
Build an ASV-level phylogenetic tree (MAFFT alignment + FastTree GTR+Γ), attach it to a 16S AnnData, and run phylogenetically-aware diversity (Faith PD, weighted / unweighted UniFrac). Use when adding tree-aware metrics on top of the basic 16S amplicon…
原文语言：英语
Map free-text cell-type annotations to the Cell Ontology (CL) via NLP-based sentence-transformer matching, with optional LLM-driven abbreviation expansion and Cell Taxonomy taxonomy enrichment. Use when standardising author-shorthand cell-type names to…
原文语言：英语
Multi-annotator consensus for single-cell labels via `ov.single.CellVote`. Combine labels from any subset of SCSA / gpt4celltype / GPTBioInsightor / scMulan / PopV per cluster; resolve disagreement either by LLM arbitration (online) or local-majority voting…
原文语言：英语
LIANA+ ligand-receptor inference on single-cell AnnData via `ov.single.run_liana`, plus the OmicVerse cell-cell communication (CCC) plotting stack with `ov.pl.ccc_heatmap` and `ov.single.to_comm_adata`. Use when computing ligand-receptor scores from a labeled…
原文语言：英语
Tumor microenvironment (TME) cell-state annotation via the pretrained MetaTiME meta-components (Yi et al. 2023). Three-step workflow on a batch-corrected AnnData - over-cluster at high Leiden resolution, score against pretrained MeCs, write MetaTiME /…
原文语言：英语
VIA (Stassen 2021) single-cell trajectory inference via `omicverse.single.pyVIA` - PARC-clustering + lazy-teleporting random-walk + automated terminal-state detection + temporal gene-trend GAMs. Two modes - vanilla (gene-distance only) and RNA-velocity-guided…
原文语言：英语
Transfer cell-type labels from a reference AnnData to a query AnnData with OmicVerse weighted KNN over a shared embedding. Use when converting OmicVerse cross-modal annotation notebooks into a reusable skill, when labeling an ATAC query from an RNA reference,…
原文语言：英语
Transfer cell labels from a reference AnnData to a query AnnData with OmicVerse AnnotationRef. Use when converting OmicVerse reference-annotation notebooks into a reusable, triggerable skill, choosing a label-transfer backend such as harmony, scVI, or…
原文语言：英语
Annotate single-cell AnnData with OmicVerse using the CellTypist, gpt4celltype, or SCSA branches. Use when turning OmicVerse annotation notebooks into a reusable, triggerable skill, selecting a backend, or mapping a clustered AnnData object to cell-type…
原文语言：英语
Run OmicVerse single-cell batch integration as a reusable, triggerable skill after preprocessing is already complete. Use when choosing a batch correction backend such as harmony, combat, scanorama, scVI, CellANOVA, or Concord on a preprocessed AnnData with…
原文语言：英语
Analyze single-cell cell-cell communication with OmicVerse CellPhoneDB and CellChat-style visualization. Use when converting an OmicVerse CellPhoneDB notebook into a reusable skill, when running CellPhoneDB ligand-receptor analysis on annotated AnnData, or…
原文语言：英语
Run and compare OmicVerse single-cell clustering backends as a reusable, triggerable skill. Use when choosing between Leiden, Louvain, scICE, or GMM Gaussian mixture clustering on a prepared AnnData embedding, or when adapting a related OmicVerse clustering…
原文语言：英语
Predict single-cell developmental potency with OmicVerse CytoTRACE2 on AnnData. Use when converting an OmicVerse CytoTRACE2 notebook into a reusable skill, when running the pretrained CytoTRACE2 potency workflow on mouse or human scRNA-seq data, or when…
原文语言：英语
Run OmicVerse single-cell differential abundance or compositional analysis as a reusable, triggerable skill. Use when comparing cell-type abundance between conditions in AnnData, choosing between scCODA, milopy, and milo backends, or adapting a related…
原文语言：英语
Run OmicVerse single-cell differential expression analysis as a reusable, triggerable skill. Use when comparing conditions inside one or more cell types in AnnData, choosing between Wilcoxon, t-test, and memento backends, or adapting a related notebook into a…
原文语言：英语
Build a triggerable kb reference and quantify single-cell FASTQs with OmicVerse alignment.single. Use when converting OmicVerse alignment notebooks into a reusable skill, when creating kallisto|bustools references with ref, or when running count on…
原文语言：英语
Run OmicVerse single-cell LDA topic clustering with the MIRA backend as a reusable, triggerable skill. Use when fitting topic models on count-like AnnData, choosing between in-memory and on-disk execution, or converting topic assignments into hard cluster…
原文语言：英语
Analyze single-cell AnnData for RNA velocity with OmicVerse. Use when converting OmicVerse velocity notebooks into a reusable, triggerable skill, when deciding whether a velocity notebook subset or branch should update an existing skill, or when selecting the…
原文语言：英语
Convert OmicVerse SCENIC notebooks into a reusable, triggerable skill for single-cell AnnData regulon analysis. Use when initializing SCENIC with cisTarget resources, choosing the RegDiffusion, GRNBoost2, or GENIE3 GRN branch, tuning regulon-construction…
原文语言：英语