Skill UI

Gtars is a comprehensive, high-performance toolkit written in Rust, featuring Python bindings for advanced genomic interval analysis. It is designed for computational biology and machine learning applications, providing specialized modules for overlap detection (IGD), coverage track generation (WIG/BigWig), genomic tokenization, and single-cell fragment analysis. Use it for processing BED files, validating reference sequences, and building robust bioinformatic pipelines.

Hypogenic is a powerful framework designed to accelerate scientific discovery by automating the process of hypothesis generation and testing on complex tabular datasets. It supports three advanced modes: HypoGeniC for purely data-driven pattern discovery; HypoRefine for synergistically integrating literature insights with empirical data; and Union methods for comprehensive hypothesis coverage. Ideal for domains like deception detection, content analysis, and advanced predictive modeling where systematic exploration of multiple theories is required.

This skill guides systematic scientific inquiry by helping users develop testable, evidence-based hypotheses from observations and preliminary data. It strictly follows the scientific method, covering literature review, synthesizing evidence, generating multiple competing mechanisms, evaluating hypothesis quality (testability, falsifiability), and designing detailed experimental protocols. Comprehensive reports mandate the use of scientific schematics for visualization.

Automatically generates professional, publication-quality infographics from simple descriptions. This skill integrates advanced AI models (like Gemini 3 Pro and Perplexity Sonar) to perform deep research, ensure data accuracy, and conduct smart, iterative quality reviews against specific document type thresholds (e.g., marketing vs. report). Ideal for visualizing complex data, processes, and statistics for reports, presentations, and social media.

LaminDB is an open-source, unified data framework designed specifically for complex biological datasets. It provides a robust lakehouse architecture that ensures data is queryable, traceable, reproducible, and FAIR (Findable, Accessible, Interoperable, Reusable). Use this skill for managing multi-modal genomic data (scRNA-seq, spatial transcriptomics), tracking computational lineage, curating data using standard biological ontologies, and integrating advanced ML/AI workflows.

Latch is a powerful Python framework designed for building and deploying scalable, serverless bioinformatics pipelines. It allows users to define complex workflows using Python decorators, seamlessly integrate standard tools like Nextflow and Snakemake, and manage cloud data through LatchFile/LatchDir abstractions. Featuring advanced resource configuration, GPU support, and pre-verified pipelines for tasks such as RNA-seq and AlphaFold, it ensures high reproducibility and efficiency in computational biology.

Matchms is a powerful open-source Python library designed for comprehensive mass spectrometry data processing and analytical workflows. It enables users to import spectra from various formats (mzML, MGF, etc.), apply advanced filtering (metadata harmonization, peak selection), and calculate various spectral similarities (e.g., Cosine, Modified Cosine). It is invaluable for metabolite identification, library searching, and building reproducible metabolomics pipelines.

A comprehensive guide to Matplotlib, Python's foundational visualization library. Learn to create diverse visualizations—from simple line plots to complex multi-panel scientific figures. Covers both the convenient pyplot interface and the powerful object-oriented API, ensuring publication-quality results for academic and industrial use cases. Supports various plot types (scatter, heatmap, contour) and advanced customization.

This powerful Python library provides comprehensive medicinal chemistry filters for compound triage in drug discovery. Users can apply established drug-likeness rules (like Lipinski's Rule of Five, Veber, and CNS rules), detect structural alerts (PAINS, NIBR), calculate complexity metrics, and filter molecular libraries using a custom query language. It is essential for prioritizing hit compounds and optimizing lead structures.

NetworkX is a powerful Python library designed for creating, manipulating, and analyzing complex graph and network structures. It supports core graph algorithms such as finding shortest paths, calculating centrality measures (e.g., PageRank, Betweenness), detecting communities, and generating various synthetic network models. It is indispensable for fields like social network analysis, bioinformatics, and transportation system modeling.

PathML is a comprehensive Python toolkit designed for advanced computational pathology workflows. It facilitates the end-to-end analysis of whole-slide pathology images (WSI) from over 160 proprietary formats. Key functionalities include image preprocessing (stain normalization, tissue detection), constructing spatial cell/tissue graphs, and training deep learning models (e.g., HoVer-Net). It is highly specialized for analyzing multiparametric data from technologies like CODEX and Vectra.

This comprehensive toolkit facilitates the entire phylogenetic analysis workflow, from sequence alignment to tree inference. It integrates industry-standard tools like MAFFT for multiple sequence alignment, TrimAl for alignment trimming, and powerful maximum likelihood methods using IQ-TREE 2 or FastTree. Ideal for molecular genomics, tracing viral phylodynamics, studying protein evolution, or conducting molecular clock analysis. Built using Python for seamless integration.