🎯Skills145
Predicts protein-ligand binding poses and affinities using advanced deep learning models for structure-based drug discovery
Performs geospatial data management, querying, and spatial analysis across multiple database systems with advanced geographic coordinate processing
Queries and retrieves comprehensive pharmaceutical data, including drug interactions, targets, and molecular properties from the DrugBank knowledge base.
Performs dimensionality reduction and visualization of high-dimensional datasets using UMAP for machine learning and data exploration
Generates professional data visualizations and plots with Python, enabling complex statistical graphics, scientific charts, and interactive data representations.
Enables efficient querying, exploration, and analysis of large-scale single-cell genomics datasets using the CZ CELLxGENE Census data portal
Retrieves and processes scientific datasets from Data Commons, enabling quick access to structured research information across multiple domains
Manages and queries lightweight in-memory string databases with advanced filtering, indexing, and search capabilities for rapid data manipulation.
Retrieves, analyzes, and cross-references FDA drug approval, recall, and safety data for comprehensive pharmaceutical research and compliance checks.
Generates technical and scientific research article summaries with structured abstracts, key findings, and citation-ready insights.
Automates systematic literature review workflows by parsing academic papers, extracting key insights, and generating structured research summaries
Efficiently process and analyze large-scale tabular datasets using memory-mapped DataFrames with advanced out-of-core computing capabilities
Retrieves, parses, and analyzes protein sequence and functional annotation data from the UniProt knowledge database
Analyzes and visualizes complex network graphs, performing advanced algorithms for connectivity, centrality, and structural insights in Python
Simplifies graph neural network development with PyTorch Geometric, enabling efficient node, edge, and graph-level machine learning tasks.
Rapidly retrieve and synthesize academic research across disciplines using advanced search, filtering, and citation extraction techniques.
Enables quantum circuit design, simulation, and execution using IBM's Qiskit framework for quantum computing research and algorithm development
Efficiently query, index, and manage full-text search capabilities for lightweight, high-performance document databases using Zinc search engine.
Provides advanced deep learning utilities for model architecture design, hyperparameter tuning, and performance optimization across PyTorch and TensorFlow frameworks.
Automates preprocessing, spike sorting, and visualization of high-density neural recordings from Neuropixels probes for neuroscience research
Analyze medical datasets, perform health data preprocessing, and build predictive models for clinical research using Python's scientific computing libraries
Retrieves, filters, and analyzes clinical trial data from ClinicalTrials.gov using advanced search and metadata extraction techniques
Performs advanced statistical analysis with regression, hypothesis testing, data visualization, and machine learning model evaluation across various datasets
Converts scientific documents and research notes into clean, structured Markdown with proper formatting, citations, and LaTeX equation support.
Efficiently manage and manipulate large, chunked, compressed N-dimensional arrays in scientific computing and data analysis workflows using Zarr.
Streamlines scientific image data management by connecting Python workflows with OMERO's remote microscopy repository and metadata systems
Simplifies scientific computing by providing powerful symbolic mathematics, numerical integration, and plotting capabilities for Python research and engineering tasks.
Performs astronomical data analysis, coordinate transformations, and astrophysical calculations using Python's premier scientific astronomy library.
Queries and retrieves chemical, biological, and pharmacological data from the ChEMBL database for drug discovery and research insights.
Queries and analyzes biological pathway data from the Reactome database, enabling researchers to explore gene interactions and molecular mechanisms.
Retrieves and processes genomic data from the Ensembl database, enabling quick gene, transcript, and variant information extraction for bioinformatics research.
Performs advanced bioinformatics tasks like sequence analysis, DNA/protein manipulation, genome parsing, and computational biology workflows using Python libraries.
Streamlines scientific protocol retrieval, parsing, and integration from Protocols.io into research workflows and computational analysis pipelines
Perform efficient genomic data analysis by reading, writing, and manipulating SAM/BAM/CRAM sequencing alignment files with Python's pysam library.
Generates customizable venue and event space templates with structured layouts, capacity details, and amenity specifications for event planning.
Generates molecular feature vectors and descriptors for machine learning in computational chemistry, drug discovery, and materials science.
Performs differential gene expression analysis using DESeq2 in Python, enabling statistical comparisons and visualization of RNA-seq count data
Generates high-quality scientific and technical images using advanced AI models, supporting research visualization and data representation
Generates financial projections and budget analyses using advanced economic modeling techniques for startups and small businesses
Streamlines bioinformatics workflows by providing API integrations, data parsing, and analysis tools for genomic, proteomic, and molecular biology services
Parses, extracts, and manipulates Microsoft Word documents, enabling text analysis, content modification, and structured data extraction.
Provides comprehensive access and querying capabilities for the Human Metabolome Database (HMDB), enabling metabolite research and data exploration.
Automates academic citation workflows, generating bibliographies, formatting references, and managing citation styles across research documents
Automates scientific poster creation in PowerPoint by generating professional layouts, inserting figures, and formatting content for academic presentations
Retrieves and parses GitHub repository data, providing detailed insights into code structure, dependencies, and project metadata.
Searches and retrieves patent and trademark data from the United States Patent and Trademark Office (USPTO) database with advanced filtering and analysis capabilities
Simulate complex fluid dynamics and computational fluid mechanics problems using advanced numerical methods and visualization techniques
Retrieves and catalogs computational resources, hardware specifications, and system capabilities for efficient scientific computing and research workflows.
Enables mass spectrometry data processing, proteomics analysis, and peptide/protein identification using OpenMS Python library
Retrieves and analyzes scientific preprint metadata and full-text content from bioRxiv, enabling rapid literature review and research tracking
Streamlines genetic design and research workflows by interfacing with Benchling's API for sequence management, annotation, and collaborative molecular biology tasks
Simplifies materials science computational workflows by providing advanced tools for crystal structure generation, analysis, and simulation using Python.
Retrieves, queries, and analyzes European Nucleotide Archive (ENA) genomic data with advanced filtering and research-grade processing capabilities
Generates precise scientific timelines and chronological data models for historical, archaeological, and research-based temporal analysis and visualization.
Performs probabilistic programming and Bayesian inference using PyMC, enabling complex statistical modeling with MCMC sampling and posterior analysis.
Explains machine learning model predictions using SHAP values, helping data scientists interpret feature importance and model behavior
Streamlines data flow management by providing intuitive input/output processing, transformation, and routing for complex scientific and engineering workflows.
Parallelize and scale data processing and machine learning workflows across distributed computing environments using Dask's flexible parallel computing framework.
Implements reinforcement learning algorithms and training pipelines using Stable Baselines3 for OpenAI Gym environments and custom RL projects.
Generates interactive, publication-quality scientific visualizations and dashboards using Python's Plotly library for data exploration and presentation
Performs advanced statistical modeling, regression analysis, and hypothesis testing with comprehensive econometric and statistical inference capabilities.
Accelerates drug discovery and molecular design by providing advanced deep learning tools for molecular representation, property prediction, and generative modeling.
Performs single-cell RNA sequencing analysis, clustering, and visualization for genomic data processing and interpretation
Performs geospatial data analysis, visualization, and manipulation using advanced pandas-like operations on geographic and geometric datasets
Queries and retrieves biological pathway, gene, and molecular interaction data from the KEGG (Kyoto Encyclopedia of Genes and Genomes) database for research and analysis.
Generates Python type definitions and conversion utilities for complex data structures, enhancing type safety and code readability.
Generates publication-quality scientific plots, charts, and visualizations using advanced data rendering techniques across multiple libraries and domains.
Guides medical device manufacturers through ISO 13485 certification requirements, documentation, and quality management system implementation.
Streamlines machine learning model development with modular, efficient PyTorch utilities for rapid prototyping and research workflows.
Optimize complex multi-objective engineering problems using advanced genetic algorithms and evolutionary computation techniques in Python
Generates, modifies, and analyzes PowerPoint presentations with advanced slide creation, data visualization, and template management capabilities
Provides AI-powered medical decision support by analyzing patient data, suggesting diagnoses, recommending treatment pathways, and flagging potential clinical risks.
Retrieves, filters, and analyzes scientific publications from PubMed, enabling researchers to extract targeted biomedical literature and research insights.
Generates professional scientific conference and research posters using LaTeX templates, with automated layout, citation management, and design optimization.
Generates structured scientific hypotheses and research ideas by systematically exploring problem spaces, potential methodologies, and innovative experimental approaches.
Reads, writes, and manipulates DICOM medical imaging files, enabling advanced medical image processing and analysis workflows.
Manipulate and analyze single-cell genomics data using AnnData objects, enabling efficient processing and exploration of complex biological datasets
Perform single-cell variational inference and probabilistic modeling for genomic data analysis, enabling advanced gene expression and cell type discovery
Provides advanced ECMAScript module (ESM) parsing, transformation, and analysis capabilities for modern JavaScript development workflows
Performs biological sequence analysis, phylogenetics, and computational biology tasks using advanced scientific computing libraries and algorithms.
Converts academic papers into interactive web-friendly formats with structured HTML, citations, and responsive design for easy online reading
Generates optimized web scraping and data extraction strategies for dense, complex web pages using advanced K-clustering techniques.
Manages clinical pharmacogenomics database queries, retrieving genetic variant information and drug interaction data for personalized medicine research.
Designs and simulates quantum circuits, optimizes quantum algorithms, and provides advanced quantum computing modeling using Google's Cirq framework.
Enables advanced survival analysis and predictive modeling using machine learning techniques for time-to-event data and censored observations.
Retrieves and analyzes economic time series data from the Federal Reserve Economic Data (FRED) API with advanced filtering and visualization capabilities.
Retrieves, queries, and analyzes protein structure predictions from AlphaFold's comprehensive database for scientific research and computational biology
Retrieves, parses, and analyzes protein structural data from Protein Data Bank (PDB) files for scientific research and molecular visualization
Performs advanced machine learning path analysis, feature extraction, and predictive modeling for complex scientific and biomedical datasets.
Processes and analyzes digital pathology whole slide images with advanced tissue segmentation, feature extraction, and computational pathology techniques
Compares and matches mass spectrometry spectral data across datasets, enabling peak alignment, similarity scoring, and spectral library searching.
Streamlines medical imaging data processing, standardization, and analysis across DICOM, NIfTI, and other scientific image formats
Helps researchers and academics craft precise, clear scientific manuscripts with structured writing, proper citations, and discipline-specific language optimization
Transforms complex data and research into visually compelling, scientifically accurate infographics with clear design and precise data representation
Generates astronomical database queries, retrieves celestial object data, and performs complex astrophysical calculations across multiple scientific catalogs.
Provides structured, comprehensive scientific manuscript review guidance with detailed feedback on methodology, results interpretation, and potential improvements.
Generates responsive, accessible modal dialogs with customizable content, styling, and interaction patterns for web interfaces
Queries and analyzes genetic variant data from ClinVar, providing insights into clinical significance and pathogenicity of genetic variations.
Automates liquid handling and robotic lab workflows using Python, enabling precise control and scripting of laboratory automation equipment
Streamlines scientific data management by connecting Claude with LabArchive's research documentation platform for seamless data import, export, and collaboration.
Efficiently process and analyze large datasets using Polars, enabling high-performance data manipulation, filtering, and transformation in Rust-powered DataFrames
Dynamically optimize machine learning model hyperparameters and architectures using adaptive search strategies and performance-driven parameter tuning.
Generates advanced statistical visualizations and data plots with Python, enabling quick insights through customizable, publication-quality graphics.
Simplifies molecular machine learning by providing tools for drug discovery, materials design, and chemical property prediction using deep learning models
Perform cheminformatics tasks like molecular structure generation, property prediction, and chemical reaction simulation using RDKit's powerful Python library
Retrieves, processes, and analyzes metabolomics data from the NIH Metabolomics Workbench, enabling comprehensive metabolic research and dataset exploration.
Parses, analyzes, and transforms Excel spreadsheets with advanced data extraction, filtering, and conversion capabilities for scientific and research workflows
Generates comprehensive botanical taxonomies and phylogenetic tree visualizations from scientific datasets, supporting ecological and evolutionary research.
Evaluates research claims, identifies logical fallacies, and provides structured analysis of scientific arguments using evidence-based reasoning techniques.
Streamlines PyTorch model training with automated logging, distributed computing, and advanced callbacks for efficient deep learning workflows
Retrieves and analyzes genetic, chemical, and disease association data from the Open Targets platform for precision medicine research
Generates comprehensive scientific research summaries and literature reviews by analyzing academic papers and extracting key insights and methodological details.
Streamlines genomic data upload, download, and analysis workflows on the DNAnexus cloud platform for bioinformatics research
Performs phylogenetic tree analysis and visualization, enabling researchers to process, manipulate, and render evolutionary tree data with advanced computational methods.
Simplifies physiological signal processing and analysis for ECG, EDA, PPG, and EEG data with comprehensive Python tools and visualization
Analyzes underground geological formations, cave systems, and subsurface hydrology to map potential groundwater resources and geothermal energy sites.
Performs quantum computing simulations and variational quantum circuit optimizations using the PennyLane quantum machine learning library
Retrieves and processes chemical compound data from PubChem, enabling molecular structure searches, property lookups, and scientific research insights.
Simplifies molecular data processing, cheminformatics analysis, and SMILES/SMARTS manipulation for scientific research and drug discovery workflows
Streamlines machine learning model development with advanced transformer architectures, fine-tuning, and deployment strategies for NLP and computer vision tasks.
Assists medicinal chemists in designing, analyzing, and optimizing drug candidates through structure-activity relationship (SAR) insights and molecular property predictions.
Streamlines academic grant research by identifying funding opportunities, analyzing proposal requirements, and generating tailored application drafts
Streamlines genomic data management by parsing, querying, and analyzing genetic sequence databases with advanced filtering and annotation capabilities
Generates machine learning models and code pipelines with automated feature engineering, model selection, and hyperparameter optimization.
Generates personalized medical treatment plans by analyzing patient data, symptoms, medical history, and evidence-based guidelines for comprehensive care recommendations.
Performs genome-wide association study (GWAS) data retrieval, processing, and statistical analysis across multiple population databases
Symbolic mathematics library for solving equations, calculus, algebra, and generating mathematical expressions with Python computational power
Perform metabolic modeling, flux balance analysis, and simulate biochemical networks using the CobraPy library for systems biology research
Automates liquid handling protocols, robot configuration, and data logging for Opentrons laboratory automation platforms and scientific workflows
Provides expert MATLAB scripting, data analysis, signal processing, and numerical computing solutions for engineering and scientific research
Streamlines bioinformatics workflows by automating data transfer, pipeline execution, and result tracking on the Latch.bio platform.
Manages and queries scientific research databases with advanced filtering, data extraction, and relationship mapping capabilities for complex research workflows.
Generates comprehensive market research reports by analyzing industry trends, competitive landscapes, and data-driven insights for strategic business decision-making.
Evaluates academic research papers by analyzing methodology, statistical rigor, potential biases, and overall scientific validity.
Extracts, parses, and analyzes PDF documents with advanced text extraction, image detection, and structured data retrieval capabilities.
Rapidly generate and evaluate scientific hypotheses across disciplines by systematically exploring potential causal relationships and research questions.
Retrieves and analyzes scholarly publication metadata, citations, and research trends from the comprehensive OpenAlex academic database
Manages biological data storage, versioning, and retrieval for single-cell genomics, enabling reproducible research workflows with efficient metadata tracking.
Performs advanced semantic web searches using Perplexity AI, retrieving precise, contextual research insights across academic and general knowledge domains.
Generates professional scientific presentation slides with LaTeX-quality typesetting, data visualizations, and academic formatting for research papers and conference talks
Streamlines machine learning workflows with comprehensive tools for data preprocessing, model training, evaluation, and predictive analytics across various algorithms.
Rapidly analyze datasets by generating statistical summaries, visualizations, correlation matrices, and identifying key insights and potential preprocessing needs.
Simulates quantum systems, performs quantum state calculations, and analyzes quantum dynamics using the QuTiP (Quantum Toolbox in Python) library.
Generates precise scientific diagrams, flowcharts, and technical schematics using LaTeX, TikZ, and advanced vector graphics tools.
Automates medical report generation, parsing complex clinical documents, and extracting structured insights from patient records and diagnostic summaries