Classical machine learning in Python. Use for classification, regression, clustering, dimensionality reduction, model evaluation, hyperparameter tuning, and preprocessing pipelines. Covers linear models, tree ensembles, SVMs, K-Means, PCA, t-SNE. For deep learning use PyTorch/TensorFlow; for gradient boosting at scale use XGBoost/LightGBM.

Survival analysis and time-to-event modeling with scikit-survival. Cox proportional hazards (standard/elastic net), Random Survival Forests, Gradient Boosting, SVMs for censored data. C-index (Harrell/Uno), Brier score, time-dependent AUC evaluation. Kaplan-Meier, Nelson-Aalen, competing risks. scikit-learn Pipeline/GridSearchCV compatible. For frequentist regression use statsmodels; for Bayesian survival use pymc; for simpler parametric models use lifelines.

Parse and create FCS (Flow Cytometry Standard) files v2.0-3.1. Read event data as NumPy arrays, extract channel metadata, handle multi-dataset files, export to CSV/FCS. For advanced gating and compensation use FlowKit.

Query NCI Imaging Data Commons (IDC) for cancer radiology and pathology imaging datasets hosted on Google Cloud. Search DICOM collections by modality, anatomical site, cancer type, or collection name. Download images via Google Cloud Storage or IDAT tool. 50TB+ of publicly accessible DICOM images. Requires Google Cloud account for large downloads; small queries work without billing. For local DICOM processing use pydicom-medical-imaging; for whole-slide pathology use histolab.

OMERO is an open-source platform for biological image data management. Use the omero-py Python client to connect to an OMERO server, search and retrieve images as numpy arrays, annotate images with tags and key-value pairs, manage ROIs, and integrate OMERO image data into downstream analysis pipelines — all programmatically without the OMERO desktop GUI.

PathML is an open-source toolkit for computational pathology. Use it to process whole-slide images (WSIs): load slides, extract tiles, apply stain normalization and nuclear segmentation preprocessing, extract features, and train machine learning models. Supports H&E and multiplex imaging. Ideal for building end-to-end digital pathology pipelines from raw WSI files to quantitative outputs.

Pure Python DICOM library for medical imaging (CT, MRI, X-ray, ultrasound). Read/write DICOM files, extract pixel data as NumPy arrays, access/modify metadata tags, apply windowing (VOI LUT), anonymize PHI, build DICOM from scratch, process series into 3D volumes. For whole-slide pathology images use histolab; for NIfTI neuroimaging use nibabel.

Python library for tracking particles (fluorescent spots, colloids, vesicles, cells) in video microscopy using the Crocker-Grier algorithm. Core modules: locate particles in single frames, batch-process image sequences, link positions into trajectories, filter short-lived tracks, and compute mean squared displacement (MSD) for diffusion analysis. Supports 2D and 3D tracking with subpixel accuracy. Integrates with pims for reading TIF stacks, AVI, and image series. Use when you need quantitative single-particle tracking (SPT) from fluorescence or brightfield video and downstream diffusion coefficient extraction.

Interactive scientific visualization with Plotly. Two-layer API: plotly.express (px) for one-liner DataFrame plots and plotly.graph_objects (go) for full trace-level control. 40+ chart types with hover, zoom, pan, and animation. Exports to interactive HTML or static PNG/SVG/PDF via kaleido. Use for interactive web figures, volcano plots with gene hover info, dose-response dashboards, gene expression heatmaps, and 3D molecular visualizations. Use seaborn for statistical summaries with automatic aggregation; use matplotlib for fine-grained publication figures; use plotly for interactive or web-embedded output.

Interactive visualization with Plotly. 40+ chart types (scatter, line, bar, heatmap, 3D, statistical, geographic) with hover, zoom, and pan. Use for exploratory analysis, dashboards, and presentations. Two APIs: Plotly Express (quick, DataFrame-oriented) and Graph Objects (fine-grained control). For static publication figures use matplotlib; for statistical grammar use seaborn.

Statistical visualization library built on matplotlib with native pandas DataFrame support. Automatic aggregation, confidence intervals, and grouping for distribution plots (histplot, kdeplot), categorical comparisons (boxplot, violinplot, stripplot), relational plots (scatterplot, lineplot), regression plots (regplot, lmplot), matrix plots (heatmap, clustermap), and multi-variable grids (pairplot, jointplot, FacetGrid). Use seaborn for statistical summaries with minimal code; use matplotlib for fine-grained figure control; use plotly for interactive HTML output.

Statistical visualization built on matplotlib with pandas integration. Distribution plots (histplot, kdeplot, violinplot, boxplot), relational plots (scatterplot, lineplot), categorical comparisons, regression, correlation heatmaps. Automatic aggregation and CI. For interactive plots use plotly; for low-level control use matplotlib.

Annotated data matrices for single-cell genomics. AnnData stores expression data (X) with observation metadata (obs), variable metadata (var), layers, embeddings (obsm/varm), graphs (obsp/varp), and unstructured data (uns). Use for .h5ad/.zarr file handling, dataset concatenation, and scverse ecosystem integration. For analysis workflows use scanpy; for probabilistic models use scvi-tools.

GATK Best Practices pipeline for germline SNP and indel variant calling from WGS/WES BAM files. Runs HaplotypeCaller in GVCF mode per sample, consolidates with GenomicsDBImport, joint-genotypes with GenotypeGVCFs, and applies VQSR or hard filters. Requires BWA-MEM2-aligned, markdup, and BQSR-processed BAMs. Use DeepVariant instead for a faster deep-learning alternative; GATK is the ENCODE/NIH standard for research and clinical genomics.

Geniml is a Python library for genomic interval machine learning. Train and apply region2vec embeddings to convert BED file regions into numeric vectors, load and index genomic interval datasets for ML pipelines, search embedding spaces with BEDSpace, and evaluate embedding quality. Use for chromatin accessibility clustering, regulatory element classification, cross-sample region comparison, and building ML models on genomic intervals.

NHGRI-EBI GWAS Catalog REST API for SNP-trait associations from published genome-wide association studies. Query studies, associations, variants, traits, genes, and summary statistics. Build polygenic risk score candidates, analyze variant pleiotropy, download summary statistics for Manhattan plots. No authentication required.

Ultra-fast RNA-seq transcript and gene-level quantification using quasi-mapping (no BAM required). Builds a k-mer index from a transcriptome FASTA, then quantifies reads in minutes. Outputs transcript-level TPM/count tables (quant.sf) with optional GC-bias and sequence-bias correction. Integrates directly with tximeta/tximport for DESeq2 or edgeR. Use STAR instead when a genome-aligned BAM is required for variant calling or visualization.

Python API v2 for programming Opentrons OT-2 and Flex liquid handling robots. Write protocols as Python files with metadata and a run() function; control pipettes, labware, and hardware modules (thermocycler, heater-shaker, magnetic, temperature). Simulate locally with opentrons_simulate, then upload to the robot app. Use PyLabRobot instead for hardware-agnostic scripts that run on Hamilton, Tecan, or other vendors.

Guide to quantitative Western blot analysis covering band detection, two-step normalization, fold change calculation, statistical aggregation across biological replicates, and publication-ready visualization. Consult when analyzing blot images with multiple conditions and repetitions, choosing normalization strategies, or preparing densitometry figures for publication.

>-

Pipeline for analyzing Neuropixels extracellular electrophysiology recordings. Covers probe geometry loading (ProbeInterface), spike sorting with Kilosort via SpikeInterface, quality metrics computation, unit curation (ISI violations, firing rate, signal-to-noise), and post-sort analysis (PSTH, tuning curves, population decoding) using pandas and matplotlib. Designed for acute and chronic Neuropixels 1.0/2.0/Ultra recordings from rodent and primate experiments.

PyTorch Geometric (PyG) for graph neural networks. Node classification, graph classification, link prediction with GCN, GAT, GraphSAGE, GIN layers. Message passing framework, mini-batch processing, heterogeneous graphs, neighbor sampling for large-scale learning, model explainability. Supports molecular property prediction (QM9, MoleculeNet), social networks, knowledge graphs, 3D point clouds. For non-graph deep learning use PyTorch directly; for traditional graph algorithms use NetworkX.

>-

Access US Patent and Trademark Office (USPTO) patent data via the PatentsView REST API and Google Patents Public Data (BigQuery). Use it to search patents by inventor, assignee, CPC classification, or keywords; download full patent metadata and claims; analyze patent portfolios; and track technology trends. Ideal for IP landscape analysis, competitor monitoring, prior art searches, and technology forecasting in life sciences and biotech.

Guide for designing and creating scientific schematics, diagrams, and graphical abstracts. Covers tool selection (BioRender, Inkscape, Affinity Designer, PowerPoint), design principles for biological pathway diagrams, molecular mechanism schematics, experimental workflow diagrams, and graphical abstracts for journal submissions. Includes composition rules, icon sourcing, color usage for biological entities, and accessibility considerations. Use when planning or creating a scientific figure that is primarily illustrative rather than data-driven.

Create effective scientific presentations for conferences, seminars, thesis defenses, and grant pitches. Slide design principles, talk structure, timing, data visualization for slides, quality assurance. Works with PowerPoint and LaTeX Beamer. For poster creation use latex-research-posters.

DiffDock is a diffusion-based molecular docking tool that predicts protein-ligand binding poses without requiring a predefined binding site. Use it when the binding site is unknown, when traditional docking fails, or when exploring multiple binding modes. Pipeline: prepare protein (PDB) and ligand (SMILES/SDF) inputs → run DiffDock inference → analyze confidence-ranked poses → visualize in PyMOL or NGLview.

Search and retrieve cryo-EM density maps, fitted atomic models, and metadata from the Electron Microscopy Data Bank (EMDB) REST API. Query by keyword, resolution, method, or organism; fetch entry details, map download URLs, associated PDB models, and publications. No authentication required. For experimental atomic coordinates use pdb-database; for AlphaFold predicted structures use alphafold-database-access.

Python library for analyzing molecular dynamics (MD) trajectories from GROMACS, AMBER, NAMD, CHARMM, and LAMMPS. Reads topology and trajectory files into Universe objects; supports RMSD, RMSF, radius of gyration, contact maps, hydrogen bond analysis, PCA, and custom distance/angle calculations across millions of frames. Use for structural analysis after MD simulations; use OpenMM or GROMACS directly for running simulations.

Molecular featurization hub (100+ featurizers) for ML. Convert SMILES to numerical representations via fingerprints (ECFP, MACCS, MAP4), descriptors (RDKit 2D, Mordred), pretrained models (ChemBERTa, GIN, Graphormer), and pharmacophore features. Scikit-learn compatible transformers with parallelization, caching, and state persistence. For QSAR, virtual screening, similarity search, and deep learning on molecules.

Query Open Targets Platform GraphQL API for target-disease associations, evidence scores, drug-target links, and safety data. Search targets by gene symbol, diseases by EFO ID, retrieve evidence scores from 20+ data sources, drug mechanisms, and tractability assessments. For ChEMBL bioactivity use chembl-database-bioactivity; for clinical trials use clinicaltrials-database-search.

Query RCSB PDB (200K+ experimental structures) via rcsb-api Python SDK. Text, attribute, sequence, and structure similarity search. Fetch metadata via Schema or GraphQL. Download PDB/mmCIF coordinate files. For AlphaFold predicted structures use alphafold-database-access.

Rowan is a cloud-based computational chemistry platform providing quantum chemistry calculations via a Python SDK. Use it to run geometry optimization, conformer generation, torsional scans, and energy minimization with DFT or semiempirical methods, and retrieve molecular properties (dipole moment, partial charges, frontier orbital energies) — without managing local quantum chemistry software or HPC clusters.

Query ZINC15/ZINC22 virtual compound libraries for drug discovery. Search purchasable lead-like, fragment-like, and drug-like compounds by molecular weight, logP, reactivity class, or SMILES similarity. Download 3D compound sets for docking, retrieve SMILES for in-silico screening. ZINC20 contains 1.4B compounds; purchasable subset is 750M. For bioactivity data use chembl-database-bioactivity; for approved drugs use drugbank-database-access.

Infer, analyze, and visualize intercellular communication from scRNA-seq data using CellChat (R). Pipeline: create CellChat object from Seurat or count matrix → subset CellChatDB ligand-receptor database → identify over-expressed genes per cell group → infer communication probabilities → compute pathway-level signaling → analyze network centrality (senders, receivers, influencers) → visualize with chord diagrams, heatmaps, and bubble plots → compare across conditions. Human and mouse supported. Use liana for a pure-Python equivalent.

Constraint-based reconstruction and analysis (COBRA) of genome-scale metabolic models. FBA, FVA, gene/reaction knockouts, flux sampling, production envelopes, gapfilling, and media optimization. Use for metabolic engineering strain design, essential gene identification, and flux distribution analysis. For kinetic modeling use tellurium; for pathway visualization use Escher.

Research profitable products to sell on eBay. Analyze completed listings, sell-through rates, average selling prices, competition density, and seasonal demand patterns.

Product photography for Etsy — composition, lighting, backgrounds, editing, lifestyle shots, 360 views

Etsy pricing — cost calculation, competitor pricing, perceived value, shipping cost integration, sales and coupons

Shop branding — banner design, logo, brand story, cohesive listing photography, packaging

Amazon profit margin calculator for sellers. Calculate cost breakdowns, profit margins, break-even points, and get pricing recommendations. Supports single product analysis and batch calculations. Input product cost, shipping, FBA fees, and get instant profitability analysis. No API key required. Use when: (1) evaluating new product profitability before sourcing, (2) diagnosing existing product margins, (3) adjusting pricing strategy, (4) analyzing multiple SKUs at once.

Master Shopify analytics and reporting. Understand key metrics, build custom reports, track customer behavior, and make data-driven decisions to grow your Shopify store.

DIY product photography — setup, lighting, backgrounds, editing, lifestyle shots, 360 views

Step-by-step Shopify store setup guide. From account creation to first sale — theme selection, product uploads, payment and shipping configuration, domain setup, and launch checklist.

当需要理解或扩展基础设施层（加载器、基类、路径、错误处理）等底层开发时使用。

>

>

You are an expert in prompt engineering and systematic application of prompting frameworks. Help users transform vague or incomplete prompts into well-structured, effective prompts through analysis, d

Manage stacked PR workflows with Graphite CLI in Graphite-enabled repos only; supports autonomous coordinator/workmux execution.

Uploads promo videos and content to Cloudflare R2 or AWS S3. Use when the user wants to host promo content for social media or distribution.