Search Skills

Enables programmatic access, management, and backup of electronic lab notebooks (ELNs) with integrations for scientific workflows including Jupyter and REDCap.

Builds and deploys bioinformatics pipelines using Latch SDK with Nextflow/Snakemake integration for scientific data processing.

Provides machine learning tools for genomic interval data (BED files), including region embeddings and scATAC-seq analysis.

Toolkit for processing, analyzing, and visualizing spreadsheet data with formula support and formatting capabilities.

Generates research posters with responsive HTML/CSS layouts, exportable to PDF or PPTX format for academic presentations.

Applies drug-likeness rules (Lipinski, Veber), PAINS filters, and structural alerts to prioritize compounds and filter chemical libraries.

Enables programmatic access to USPTO databases for patent/trademark research, examination history, citations, and prior art searches.

Provides a hardware-agnostic framework for training quantum machine learning models, supporting variational algorithms and integration with PyTorch, JAX, and TensorFlow.

Queries NHGRI-EBI GWAS Catalog to retrieve SNP-trait associations, p-values, and summary statistics for genetic epidemiology and polygenic risk score analysis.

Provides a toolkit for creating, editing, and processing Microsoft Word documents (.docx) with tracked changes, comments, and formatting preservation.

High-performance toolkit for genomic interval analysis, supporting BED files, coverage tracks, and ML tokenization in computational genomics.

Enables Bayesian inference, hierarchical modeling, and MCMC (NUTS) with PyMC for probabilistic programming and model comparison.

Creates full-paragraph scientific manuscripts in IMRAD structure with citations, figures, and reporting guidelines for journal submissions.

Generates evidence-based clinical decision support documents with statistical analysis, biomarker stratification, and regulatory compliance for pharmaceutical research.

Accesses AlphaFold's 200M+ AI-predicted protein structures via UniProt ID, with PDB/mmCIF downloads and confidence metric analysis for drug discovery research.

Performs UMAP dimensionality reduction for visualizing high-dimensional data in 2D/3D, enabling clustering and ML preprocessing.

Enables open-ended scientific brainstorming to explore interdisciplinary connections, challenge assumptions, and identify research gaps during early planning stages.

Provides a framework for deploying pre-trained transformer models in NLP, computer vision, audio, and multimodal applications for tasks like generation and classification.

Queries NCBI Gene database via E-utilities API to retrieve gene information including RefSeqs, GO terms, locations, and phenotypes for annotation and functional analysis.

Provides simulation tools for open quantum systems, including master equations, Lindblad dynamics, and quantum optics, for physics research and educational purposes.

Queries ChEMBL database for bioactive molecules, enabling drug discovery research through compound searches, bioactivity data retrieval, and structure-activity relationship analysis.

Enables queryable, traceable, and reproducible biological data management with ontologies, workflow tracking, and MLOps integrations for scRNA-seq and other biological datasets.

Programmatic PDF manipulation toolkit for extracting text and tables, creating, merging, splitting, and filling PDFs.

Provides computational tools for materials science, including crystal structure analysis, phase diagrams, and Materials Project integration.