Data & Analytics

Fast Python I/O for BigWig (continuous genome signal) and BigBed (interval annotation) files via libBigWig. Use for random-access signal queries at specific genomic coordinates (bw.values, bw.stats), computing per-region summary statistics (mean/max/coverage) over a BED file of regions, writing custom BigWig tracks from numpy arrays, and loading ChIP-seq/ATAC-seq/RNA-seq/methylation coverage tracks (e.g. produced by deeptools bamCoverage) into pandas/numpy for downstream analysis or ML featur...

Mass spectrometry proteomics QC, quantification, comparative analysis, and export for DDA, DIA, and protein-level result tables.

Expert-thinking profile for Proteomics Scientist (bottom-up LC-MS/MS / DDA-DIA-TMT- SILAC / differential abundance / FDR & batch control): Reasons from peptide-to-protein inference, acquisition mode, quantification modality, and missing-value mechanism through MaxQuant, FragPipe/MSFragger, DIA-NN/Spectronaut, Skyline, and MSstats/proDA while treating MNAR missingness, batch confounding, TMT co-isolation ratio compression, and keratin/contaminant signal...

Differential expression analysis for label-free quantitative (LFQ) intensity data with standard MaxQuant and

Query the Precision Medicine Knowledge Graph (PrimeKG) for multiscale biological data including genes, drugs, diseases, phenotypes, and more.

Expert-thinking profile for Precision Agriculture Specialist (site-specific crop management / VRT prescriptions / remote & proximal sensing / RTK-GNSS & ISOBUS / yield-map QA): Reasons from management-zone heterogeneity, the spatial 4R (right input, rate, place, time), and per-zone margin maps through SSURGO/ECa zone delineation, NDVI/NDRE indices, RTK-GNSS georeferencing, and ISOBUS Task Controller as-applied logs while treating planned-versus-applied divergence, NDVI saturation...

Expert-thinking profile for Population Geneticist (dry-lab / computational population genomics): Reasons from Wright–Fisher/coalescent demography, Weir–Cockerham FST, EIGENSOFT PCA, ADMIXTURE ancestry, ADMIXTOOLS f-statistics, and selscan XP-EHH/iHS/PBS selection scans while treating batch confounding, LD pruning choices, cryptic relatedness, and admixture-LD artifacts as first-class failure modes.

Use when creating interactive Python visualizations with Plotly, including pan, zoom, hover charts, dashboard figures, interactive HTML output, or 3D plots. Trigger terms include plotly, interactive chart, interactive plot, dashboard chart, hover, and plotly express. For static publication figures use matplotlib or seaborn; for visualization strategy use scientific-visualization.

Expert-thinking profile for Plasma Physicist (fusion + space plasma / MHD & gyrokinetic / PIC simulation / tokamak-stellarator diagnostics / reconnection): Reasons from collective scales (Debye length, plasma frequency), dimensionless regime parameters (beta, collisionality, Lundquist number), and instability drive-versus- dissipation through Grad-Shafranov equilibria (EFIT, VMEC), gyrokinetic and MHD codes (GENE, NIMROD, XGC), PIC simulation (VPIC, OSIRIS), and...

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

Expert-thinking profile for Photonics Engineer (design / simulation / characterization / optical systems & PIC): Reasons from Maxwell modes, FSR–Q–coupling trade-offs, and optical power/loss budgets; designs PICs and free-space systems with FDTD/INTERCONNECT/Zemax/GDSFactory and certifies links with OLTS/OTDR/M² while treating mesh dispersion errors, TE/TM birefringence, APC/PC connector mismatch, OTDR ghost/gainer events, and...

Full-featured computational pathology toolkit. Use for advanced WSI analysis including multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph construction, and ML model training on pathology data. Supports 160+ slide formats. For simple tile extraction from H&E slides, histolab may be simpler.

DataFrame schema validation using pandera. Schema definitions, column checks, and decorator-based validation.

The workhorse library for in-memory tabular data in Python. Use for loading, cleaning, reshaping, joining, grouping, and analyzing labeled row/column data. Trigger terms include "pandas", "dataframe", "series", "csv", "parquet", "tabular data", "groupby", "pivot", "merge", "data wrangling", "data cleaning". Covers pandas 2.x and the 3.0 changes (Copy-on-Write, default string dtype, PyArrow-backed dtypes).

Hyperparameter optimization (HPO) for ML models using Optuna. Use when tuning learning rate, regularization, architecture choices, or any numeric/categorical hyperparameter. Covers create_study/optimize quickstart, sampler selection (TPE, CMA-ES, grid, random, NSGA-II), pruners for early stopping (MedianPruner, HyperbandPruner), distributed search with RDBStorage, integrations with PyTorch Lightning and scikit-learn, and built-in visualization.

Use this skill when the user wants to build a financial model — 3-statement model, DCF valuation, LBO, SaaS unit economics, sensitivity / scenario analysis, debt schedule, or fundraising projections — in Excel. Trigger on: 'financial model', '3-statement model', 'P&L + BS + CF', 'DCF', 'WACC', 'NPV', 'terminal value', 'LBO', 'debt schedule', 'cash sweep', 'MOIC', 'IRR / XIRR', 'sensitivity table', 'scenario analysis', 'ARR model', 'unit economics', 'CAC / LTV', 'cap table forecast'. Output is...

Use this skill to build a multi-element Excel dashboard — Dashboard sheet on open, multiple formula-driven KPI cards, multiple charts, sparklines, and conditional formatting — from CSV or tabular input. Trigger on: 'dashboard', 'KPI dashboard', 'analytics dashboard', 'executive dashboard', 'metrics dashboard', 'CSV to dashboard', 'data visualization'. Output is a single .xlsx. Scene-layer on officecli-xlsx: inherits every xlsx hard rule. DO NOT invoke for: a single budget tracker / one-sheet ...

Kick off public shotgun metagenomics QC, host-depletion, taxonomic profiling, and functional profiling workflows using nf-core/taxprofiler, Kraken2, Bracken, MetaPhlAn, and HUMAnN.

Dispatch ATAC-seq, ChIP-seq, CUT&RUN, or CUT&Tag requests to assay-specific QC, alignment, signal-track, peak-calling, consensus, and differential peak workflows.

Run or plan ChIP-seq, CUT&RUN, or CUT&Tag QC, control handling, spike-in, peak calling, broad-vs-narrow target selection, replicate, bigWig, and differential binding workflows.

Run or plan bulk RNA-seq differential-expression analysis from count matrices with replicate, design formula, contrast, batch, normalization, QC plot, and result-table checks.

Validate Illumina BCL run folders and sample sheets, plan demultiplexing, review index/UMI/lane choices, run BCL-to-FASTQ conversion, and interpret demux metrics while surfacing license/download boundaries.

Run or plan ATAC-seq QC, alignment, TSS enrichment, fragment-size, blacklist, peak-calling, consensus peak, and differential accessibility workflows.

Kick off public 16S, 18S, ITS, COI, or other marker-gene amplicon microbiome workflows using nf-core/ampliseq, QIIME2, DADA2, and Cutadapt.