3. Data, Science & AI

Bioinformatics tool for filtering and prioritizing genetic variants by pathogenicity, population frequency, and clinical evidence to identify disease-causing variants in rare disease analysis.

Calculates statistical power and minimum sample sizes for RNA-seq and ATAC-seq experiments to ensure adequate experimental design.

Performs fast miRNA quantification, isomiR detection, and A-to-I RNA editing analysis using miRge3 for small RNA-seq data.

Preprocesses small RNA-seq data with adapter trimming and size selection for miRNA, piRNA, and other small RNAs, preparing reads for downstream analysis.

Detects and quantifies translated ORFs (including uORFs and novel ORFs) from Ribo-seq data using RiboCode and ORFquant for non-canonical translation analysis.

Applies multiple testing correction (FDR, Bonferroni, q-value) to genomics data for accurate differential expression analysis and significance thresholding.

Analyzes spatial proteomics data from CODEX, IMC, and MIBI platforms, performing cell segmentation and protein colocalization for multiplexed imaging integration with transcriptomics.

Exports publication-ready scientific figures in vector formats with proper resolution, sizing, and typography for journal submissions and presentations.

Calculates sequence alignment statistics including identity, conservation scores, and substitution matrices for evolutionary analysis and sequence divergence measurement.

Estimates minimum sample sizes for bioinformatics experiments (e.g., differential expression, ChIP-seq) to achieve statistical significance, supporting grant proposals and experimental design.

Automates standardized quality control report generation for bioinformatics data by aggregating metrics from FastQC and alignment tools via MultiQC.

Provides best practices for building and refining machine learning models, covering tools and techniques for effective model development.

Guides handling unmodelled density blobs in cryo-EM density maps using the Coot molecular graphics software.

Queries PDBe REST and Solr APIs within Coot for protein structure metadata, validation data, and search capabilities.

Provides best practices for protein structure refinement, model building, and validation using Coot, including automated workflows and rotamer fixing.

Guides users in applying Density-Fit Correlations within Coot for validating protein structure models against electron density maps.

Validates molecular structures by comparing models to electron density maps and detecting unmodeled regions, essential for structural biology research.

Enables molecular manipulation, modification, and 2D visualization of chemical structures using RDKit within Coot's Python environment for crystallography workflows.

Comprehensive tool for creating, editing, and analyzing Excel spreadsheets with formulas, formatting, and data visualization capabilities.

Automates context management in LLM agent workflows by delegating to a subagent at 80% context threshold, enabling seamless task continuation without interruption.

Converts natural language descriptions into accurate SQL queries for efficient database interaction without manual syntax writing.

Provides a unified interface for integrating multiple LLM providers including OpenAI, Anthropic, Google, and local models.

Manages conversational context for Clawdbot and Moltbot using AI to maintain session coherence and relevance.

Manages AI agent governance including configuration, policy enforcement, audit logging, and real-time monitoring for AI systems.