Skill UI

Pysam offers Python bindings to htslib for reading and writing SAM/BAM/CRAM alignments, VCF/BCF variants, and FASTA/FASTQ sequences, enabling coverage stats, pileup analysis, variant queries, and seamless integration into NGS pipelines.

Qiskit is the world's leading open-source framework for building, optimizing, and executing quantum circuits. It provides comprehensive capabilities for quantum error mitigation, running algorithms on diverse hardware backends (including IBM Quantum and simulators), and supporting applications in chemistry and machine learning. Essential for researchers entering the quantum computing field.

Query the Reactome Content and Analysis Services (or the reactome2py client) to fetch pathway hierarchies, map genes, run overrepresentation/expression analyses, and explore disease interactions for systems biology research.

Assess research claims and experimental rigor by evaluating methodology, statistical validity, evidence quality, and biases using GRADE and Cochrane ROB frameworks, plus supporting schematics for complex concepts.

scikit-bio provides a Python-native biological data toolkit for reading/writing FASTA/Newick files, manipulating sequences, building alignments and phylogenies, and calculating diversity metrics for microbiome and ecology workflows.

Probabilistic deep-learning framework built on PyTorch for single-cell omics; handles batch correction, integration, multimodal and spatial data, differential expression, and transfer learning with unified APIs.

Guides using SHAP to explain ML predictions, compute feature importance, generate diagnostic plots, debug models, analyze bias, and compare models across tree, deep, linear, or black-box architectures.

Statsmodels is a comprehensive Python library dedicated to advanced statistical modeling and econometrics. It provides tools for rigorous statistical inference, including Ordinary Least Squares (OLS), Generalized Linear Models (GLM), mixed-effects models, and time series analysis (ARIMA). Use this skill for detailed diagnostics, coefficient estimation, hypothesis testing, and producing publication-ready statistical reports in fields like econometrics and biostatistics.

Query the STRING REST API to retrieve protein-protein interaction networks, map identifiers, visualize evidence-weighted edges, and run GO/KEGG/Pfam enrichment for systems biology analysis.

TileDB-VCF lets you ingest, store, query, and export large genomic VCF/BCF datasets using TileDB’s sparse arrays, supporting incremental sample growth, parallel regions queries, and cloud-local interoperability for population genomics workflows.

This skill provides zero-shot time series forecasting using Google's TimesFM foundation model. It forecasts any univariate time series (like sales, sensor data, or weather) without requiring custom model training. The model delivers point forecasts along with calibrated prediction intervals (quantiles), offering a robust and probabilistic view of future trends. It is ideal for rapid, reliable forecasting across diverse time-based datasets.

TorchDrug is a PyTorch-native toolbox for building graph neural networks tailored to molecules, proteins, and biomedical knowledge graphs, covering property prediction, generation, retrosynthesis, and knowledge graph reasoning with curated datasets and models.