Skill UI

Provides programmatic and standardized access to massive, versioned datasets of single-cell and spatial transcriptomics from CZ CELLxGENE. This skill allows users to query millions of cells, analyze gene expression, and access pre-calculated embeddings across various tissues, diseases, and species without downloading entire datasets. Essential for large-scale bioinformatics analysis, machine learning model training, and comprehensive cross-dataset comparison.

A specialized toolkit designed for generating and validating research-only artifacts for Clinical Decision Support (CDS) systems. It supports evidence-profile generation, cohort analysis, survival modeling, biomarker evaluation, and governance documentation. IMPORTANT: This skill is strictly for aggregate research and documentation; it must never be used for patient care, diagnosis, or live clinical operations.

This skill generates safety-bounded draft structures and deterministic checks for various clinical, safety, and aggregate research reports (e.g., CSR, aggregate safety tables). It requires verified, de-identified, or synthetic source data, ensuring every generated claim is traceable to a source-fact manifest. IMPORTANT: This skill only creates drafts and checks internal consistency; it cannot diagnose, recommend treatment, or provide medical advice. All outputs are non-clinical and require qualified human review and sign-off.

COBRApy is a comprehensive Python library for Constraint-Based Reconstruction and Analysis (COBRA) of metabolic models. It enables users to simulate complex cellular metabolism, performing crucial analyses such as Flux Balance Analysis (FBA), Flux Variability Analysis (FVA), and virtual gene/reaction knockouts. It is an essential tool for systems biology research and metabolic engineering design.

This tool opens the dedicated Context Mode Insight dashboard in your default browser. Insight serves as the central analytics layer for AI-assisted engineering teams, providing crucial metrics such as per-engineer productive rates, identifying retry waste, detecting blockers, and offering role-narrowed performance views. It is designed to be the single source of truth for comprehensive team performance monitoring and sign-in details.

Dask is a powerful Python library designed for scalable, parallel, and distributed computing. It enables workflows for datasets that exceed available RAM or require processing across multiple machines. Users can scale familiar pandas and NumPy operations (DataFrames, Arrays) and process unstructured data (Bags) efficiently, making it ideal for large-scale ETL, analytics, and distributed machine learning tasks.

Datamol is a high-level, Pythonic abstraction layer built over RDKit, designed for computational chemistry and drug discovery. It simplifies complex molecular operations, offering sensible defaults for tasks like SMILES standardization, descriptor calculation, fingerprint generation (ECFP4), 3D conformer analysis, and molecular clustering. It supports efficient parallel processing and cloud storage I/O, making it ideal for handling large-scale chemical datasets.

An autonomous research agent that plans complex investigations using Directed Acyclic Graphs (DAGs). It executes sub-questions in parallel, performs gap analysis, and iteratively refines findings before synthesizing a comprehensive, structured report. Ideal for deep market analysis, academic literature reviews, or complex problem-solving requiring multiple data sources.

DeepChem is a comprehensive Python library designed to apply machine learning to chemistry, materials science, and biology. It enables sophisticated molecular property prediction (ADMET, solubility, toxicity), drug discovery, and materials design. The library supports diverse featurization methods (fingerprints, graph representations) and advanced model architectures, including GNNs and transfer learning, making it ideal for analyzing complex chemical datasets like MoleculeNet.

deepTools is a comprehensive command-line toolkit designed for processing and analyzing high-throughput sequencing data. It handles core genomics tasks including BAM to bigWig conversion, quality control assessment (PCA, correlation), normalization, and generating publication-quality visualizations (heatmaps, profiles) for ChIP-seq, RNA-seq, and ATAC-seq data. Essential for reproducible genomic research workflows.

This tool provides access to the Cancer Dependency Map (DepMap) data, derived from genome-wide CRISPR screens, RNAi, and compound sensitivity assays. It allows users to query gene dependency scores, identify cancer-specific vulnerabilities, predict synthetic lethal interactions, and validate potential oncology drug targets across various cancer cell lines.

A comprehensive skill for building, operating, and automating complex, reproducible genomics workloads on the DNAnexus platform. It provides deep integration with the `dx` CLI, `dxpy` Python SDK, and workflow languages like Nextflow and WDL. Use it for data transfer, job monitoring, project automation, and ensuring secure, efficient execution of large-scale biological computations.