mdbabumiamssm/LLMs-Universal-Life-Science-and-Clinical-Skills- - Page 4

bulkrna-read-qc

FASTQ quality assessment for bulk RNA-seq — Phred scores, GC content, adapter detection, read length distribution, Q20/Q30 rates.

bulkrna-splicing

Alternative splicing analysis — PSI quantification, differential splicing event detection from rMATS/SUPPA2 output.

bulkrna-survival

Survival analysis for bulk RNA-seq — Kaplan-Meier curves, Cox proportional hazards, expression-based patient stratification.

bulkrna-trajblend

Bulk-to-single-cell trajectory interpolation — uses VAE and GNN to bridge bulk RNA-seq with single-cell reference data, generating synthetic single-cell profiles and embedding bulk samples into developmental trajectories.

genomics-alignment

Alignment statistics from SAM/BAM files: mapping rate, MAPQ distribution, insert size, duplicate rate, proper pair rate. Mirrors samtools-flagstat.

genomics-assembly

Genome assembly quality assessment: N50/N90/L50/L90 (QUAST-compatible), GC content, contig length distribution, completeness estimation. Wraps SPAdes, Megahit, Flye, Canu.

genomics-cnv-calling

Copy number variant detection from exome/WGS data using CNVkit, Control-FREEC, or GATK gCNV. Supports tumor-normal pairs, tumor-only, and germline modes.

genomics-epigenomics

Epigenomics analysis including ATAC-seq peak calling with MACS3, ChIP-seq analysis, motif enrichment, and chromatin accessibility.

genomics-phasing

Haplotype phasing analysis: phase block N50, phased fraction, PS (Phase Set) field parsing, pipe-delimited genotype detection. Wraps WhatsHap, SHAPEIT5, Eagle2.

genomics-qc

FASTQ quality control: Phred quality scores, GC/N content, Q20/Q30 rates, per-base quality profiles, read length distribution, and adapter contamination detection.

genomics-sv-detection

Structural variant detection (DEL/DUP/INV/TRA): SV VCF parsing with BND notation, size classification (50bp-10Mb), evidence types. Wraps Manta, Lumpy, Delly, Sniffles.

genomics-variant-annotation

Variant functional impact prediction: VEP consequence types (HIGH/MODERATE/LOW/MODIFIER), SIFT, PolyPhen-2, and CADD scoring. Rule-based annotation engine for demo, wraps VEP/snpEff/ANNOVAR.

genomics-variant-calling

Germline and somatic variant calling (SNVs, Indels) using GATK HaplotypeCaller, Mutect2, DeepVariant, or FreeBayes. Includes GVCF workflow, VQSR, and hard filtering.

genomics-vcf-operations

VCF operations: multi-allelic parsing, variant classification (SNP/MNP/INS/DEL/COMPLEX), Ti/Tv ratio, QUAL/DP filtering, INFO field parsing. Mirrors bcftools stats.

literature

Parse scientific literature (PDFs, URLs, DOIs) to extract GEO accessions, metadata, and datasets. Use when users provide a paper and want to automatically extract data sources for downstream omics analysis.

metabolomics-annotation

Metabolite annotation and structural identification using SIRIUS, CSI:FingerID, GNPS, or MetFrag.

metabolomics-de

Metabolomics differential analysis using univariate tests (t-test, FDR), multivariate methods (PCA, PLS-DA, OPLS-DA, sPLS-DA), Random Forest, and ROC analysis for biomarker discovery.

metabolomics-normalization

Metabolomics data normalization, scaling and transformation.

metabolomics-pathway-enrichment

Metabolomics pathway analysis using MetaboAnalystR (KEGG, Reactome), pathview visualization, MSEA, mummichog, and network-based topology analysis.

metabolomics-peak-detection

Peak picking, feature detection, alignment and grouping using XCMS, MZmine 3, or MS-DIAL.

metabolomics-quantification

Feature quantification, missing value imputation, and normalization for metabolomics data.

metabolomics-statistics

Statistical analysis for metabolomics — PCA, PLS-DA, clustering, and univariate tests.

metabolomics-xcms-preprocessing

XCMS3 workflow for LC-MS/GC-MS metabolomics preprocessing. Peak detection (CentWave/MatchedFilter), RT alignment (Obiwarp), correspondence, gap filling, and CAMERA adduct/isotope annotation.

omics-skill-builder

Create OmicsClaw-native skill scaffolds for new reusable workflows that are not yet represented in the current skill catalog.

orchestrator

Multi-omics query routing and pipeline orchestration across all OmicsClaw domains. Routes natural language queries to the correct analysis skill across spatial transcriptomics, single-cell omics, genomics, proteomics, and metabolomics.

proteomics-data-import

Import and convert proteomics data formats between MaxQuant, DIA-NN, Spectronaut, and standard CSV.

proteomics-de

Differential protein abundance testing using MSstats, limma, proDA, and scipy/statsmodels for Python. Multiple testing correction with BH FDR.

proteomics-enrichment

Pathway, network, and functional enrichment for proteomics using STRING, DAVID, or g:Profiler.

proteomics-identification

Database search for peptide/protein identification using MaxQuant, MS-GF+, Comet, or Mascot.

proteomics-ms-qc

Mass spectrometry raw data quality control using PTXQC, rawTools, or MSstatsQC.

proteomics-ptm

Post-translational modification analysis including phosphorylation, acetylation, and ubiquitination. Site localization, motif analysis, and quantitative PTM analysis with MSstatsPTM.

proteomics-quantification

Protein/peptide quantification (LFQ, TMT, DIA) using MaxQuant LFQ, DIA-NN, or Skyline.

proteomics-structural

Structural proteomics and cross-linking MS analysis using XlinkX, pLink, or xiSEARCH.

scatac-preprocessing

Single-cell ATAC-seq preprocessing with a Signac-style TF-IDF + LSI workflow. Performs cell and peak filtering, top-peak selection, TF-IDF normalization, latent semantic indexing, neighborhood graph construction, UMAP, and Leiden clustering, then exports a…

sc-ambient-removal

Remove ambient RNA contamination from droplet-based single-cell RNA-seq using a simple subtraction path, CellBender, or SoupX. The wrapper exposes only the parameters that are actually wired into the current implementation.

sc-batch-integration

Integrate multi-sample scRNA-seq data with Harmony, scVI, scANVI, BBKNN, Scanorama, or supported R-backed integration methods.

sc-cell-annotation

Annotate cell types from normalized scRNA-seq data using marker scoring, CellTypist, PopV-style reference mapping, lightweight KNNPredict-style mapping, SingleR, or scmap through shared Python/R backends.

sc-cell-communication

Cell-cell communication analysis for annotated scRNA-seq data using a built-in ligand-receptor scorer, LIANA, CellPhoneDB, CellChat, or a NicheNet R path.

sc-clustering

Build the neighbor graph, run a low-dimensional embedding, and cluster single-cell data from a normalized scRNA AnnData object.

sc-count

Default scRNA counting route. Turn FASTQ or existing Cell Ranger, STARsolo, SimpleAF / Alevin-fry, or kb-python outputs into a downstream-ready standardized AnnData.