K-Dense-AI

Access over 800,000 economic time series from the FRED API for comprehensive economic analysis.

Efficiently manage and manipulate spreadsheet files with ease.

Scanpy is a powerful toolkit for single-cell RNA-seq analysis, enabling comprehensive data exploration and visualization.

Access the NIH Metabolomics Workbench via REST API for metabolomics research and biomarker discovery.

Access the European Nucleotide Archive to retrieve DNA/RNA sequences and genome assemblies via API/FTP.

Access NCBI GEO for gene expression and genomics data, enabling comprehensive searches and downloads of datasets.

Vendor-agnostic lab automation framework for controlling diverse laboratory equipment.

A comprehensive collection of 170+ scientific skills for AI agents, enabling advanced research workflows.

Efficiently store and manage large N-dimensional arrays with Zarr in Python.

Perform differential gene expression analysis using Python DESeq2 for RNA-seq data.

Access ZINC's repository of over 230M purchasable compounds for drug discovery and virtual screening.

Create high-quality academic papers and research documents with verifiable citations.

Access USPTO APIs for comprehensive patent and trademark data, enabling detailed IP analysis.

Access the UniProt database via a direct REST API for protein searches and data retrieval.

UMAP is a fast and efficient dimensionality reduction technique for high-dimensional data visualization and clustering.

Powerful statistical modeling library for Python, ideal for econometrics and time series analysis.

Production-ready reinforcement learning algorithms with a scikit-learn-like API for efficient training.

Enhance model interpretability and explainability using SHAP for machine learning predictions.

Create attractive statistical visualizations with ease using Seaborn's pandas integration.

Analyze RNA velocity in single-cell RNA-seq data to infer cell state transitions.

Pymatgen is a powerful Python library for materials science analysis and manipulation.

Comprehensive healthcare AI toolkit for developing and deploying machine learning models with clinical data.

Explore uncertain futures with structured What-If scenario analysis.

Efficiently process and analyze large tabular datasets that exceed available RAM.

Comprehensive toolkit for survival analysis and time-to-event modeling in Python.

Core skill for writing scientific manuscripts with precision and clarity.

Create publication-ready figures with multi-panel layouts and specific journal formatting.

Create high-quality scientific diagrams effortlessly with AI-driven refinement.

Evaluate scientific claims and assess evidence quality using critical thinking frameworks.

Facilitate creative research ideation and exploration through collaborative brainstorming.

Comprehensive Python library for biological data analysis, including sequence manipulation and phylogenetic analysis.

Comprehensive Python library for astronomy and astrophysics.

Access LaTeX templates and guidelines for scientific publications, conferences, and grant proposals.

High-performance reinforcement learning framework optimized for speed and scale.

Access comprehensive U.S. federal financial data through the Treasury Fiscal Data API without an API key.

Access the Precision Medicine Knowledge Graph (PrimeKG) for comprehensive biological data.

Create concise, actionable medical treatment plans in LaTeX/PDF format across all specialties.

TorchDrug provides PyTorch-native graph neural networks for drug discovery and protein modeling.

Zero-shot time series forecasting using Google's TimesFM model for various univariate time series.

Perform symbolic mathematics in Python with SymPy for exact computations.

Python library for reading, writing, and modifying DICOM medical imaging files.

Utilize pre-trained transformer models for diverse tasks in NLP, computer vision, and audio.

A library for developing Graph Neural Networks (GNNs) using PyTorch, enabling advanced graph-based machine learning.

Efficiently store and retrieve genomic variant data using TileDB for scalable population genomics.

Access a vast database of protein-protein interactions for systems biology research.

Scikit-learn is a powerful Python library for machine learning, supporting a wide range of algorithms and techniques.

Create visually engaging slide decks for scientific presentations with structured guidance and design templates.

Systematically evaluate scholarly work using the ScholarEval framework for comprehensive quality assessment.

Efficiently look up current research information using intelligent backend routing.

Access and analyze biological pathways using the Reactome REST API for systems biology research.

Pysam is a powerful Python toolkit for genomic data manipulation, enabling efficient handling of alignment and variant files.

Comprehensive mass spectrometry analysis platform for proteomics and metabolomics.

Rowan is a cloud-based quantum chemistry platform with a Python API for advanced molecular simulations.

Access tissue-specific gene expression and eQTL data from the GTEx project.

Write competitive research proposals for major funding agencies with tailored guidance and compliance support.

Access the world's largest chemical database with 110M+ compounds for cheminformatics.

QuTiP is a powerful library for simulating open quantum systems in Python.

Manage Zotero libraries programmatically with the pyzotero Python client.

Integrate with protocols.io to manage scientific protocols efficiently.

Build and analyze phylogenetic trees using advanced tools for evolutionary analysis.

Conduct AI-powered web searches for real-time information using Perplexity models.

Access AI-ready datasets for drug discovery and therapeutic machine learning.

Access PubMed's extensive database via a REST API for advanced literature searches and citation management.

Lightweight library for whole slide image (WSI) tile extraction and preprocessing.

Comprehensive cheminformatics toolkit for molecular analysis and manipulation.

Qiskit is an open-source quantum computing framework for building and executing quantum circuits on IBM Quantum hardware.

Create research posters in PPTX format using HTML/CSS for modern design and easy visual integration.

High-performance genomic interval operations and bioinformatics file I/O on Polars DataFrames.

Create interactive, publication-quality visualizations with Plotly's extensive charting library.

PennyLane is a hardware-agnostic quantum machine learning framework for training quantum circuits.

Structured peer review process for evaluating scientific manuscripts and grant proposals.

Access RCSB PDB for 3D protein and nucleic acid structures, enabling searches and downloads.

Transform academic papers into engaging promotional formats like websites, videos, and posters.

Pymoo is a powerful Python framework for multi-objective optimization, featuring advanced algorithms and customizable solutions.

Streamline your deep learning projects with PyTorch Lightning, a framework that organizes PyTorch code for efficient training.

Manage and manipulate .pptx files effortlessly, from creation to editing and extraction.

Fast in-memory DataFrame library for efficient data processing and ETL pipelines.

Efficiently manage and manipulate PDF files with a comprehensive set of operations.

Comprehensive computational pathology toolkit for advanced WSI analysis and machine learning.

Conduct comprehensive web searches and deep research using the Parallel Web Systems API.

Official Opentrons Protocol API for OT-2 and Flex robots, enabling precise lab automation.

Access comprehensive data for therapeutic target identification and drug discovery.

Query and analyze scholarly literature using the OpenAlex database for comprehensive research insights.

Integrate with OMERO for managing and analyzing microscopy data using Python.

Access comprehensive hedge fund data through the OFR Hedge Fund Monitor API without any authentication.

Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis.

Comprehensive analysis toolkit for Neuropixels neural recordings.

Molfeat provides over 100 molecular featurizers for machine learning applications in cheminformatics.

Matplotlib is a low-level plotting library for creating highly customizable visualizations.

MATLAB and GNU Octave for numerical computing and scientific analysis.

Matchms enables spectral similarity and compound identification for metabolomics.

Convert various file formats to Markdown efficiently.

Create scientific documents and diagrams using markdown and Mermaid for clear, version-controlled documentation.

Create professional research posters in LaTeX with customizable layouts and designs.

Conduct systematic literature reviews across multiple academic databases with verified citations.

Integrate K-Dense Web for advanced AI-driven research workflows.

AnnData is a data structure for annotated matrices, essential for single-cell analysis.

Access gnomAD for allele frequencies, variant scores, and loss-of-function intolerance metrics.

Comprehensive toolkit for analyzing physiological biosignals including ECG, EEG, and EDA.

Comprehensive toolkit for creating, analyzing, and visualizing complex networks in Python.

Query the Monarch Initiative knowledge graph for disease-gene-phenotype associations across species.

Run and analyze molecular dynamics simulations using OpenMM and MDAnalysis for structural biology and biophysics.

Medchem provides advanced medicinal chemistry filters for drug discovery, enabling efficient compound prioritization and library filtering.

Cloud platform for running Python on GPUs and serverless infrastructure, ideal for AI/ML workloads.

Access KEGG's REST API for pathway analysis and gene mapping in biological research.

Create professional infographics quickly with smart iterative refinement and accurate data integration.

Query the NHGRI-EBI GWAS Catalog for SNP-trait associations and genetic epidemiology insights.

Generate comprehensive market research reports in the style of top consulting firms.

High-performance toolkit for genomic interval analysis in Rust with Python bindings.

Search and retrieve preprints from arXiv using the Atom API for various scientific fields.

Integrate with LabArchives to automate electronic lab notebook workflows.

Access JASPAR for transcription factor binding site profiles and analysis.

Manage and execute lab protocols remotely with Ginkgo Cloud Lab's autonomous infrastructure.

GeoPandas is a Python library for geospatial vector data analysis, enabling spatial operations on geometric types.

Framework for high-performance computational fluid dynamics simulations using Python.

Access comprehensive FDA regulatory data for drugs, devices, and more through the openFDA API.

Access over 200 million AI-predicted protein structures for drug discovery and structural biology.

Integrate and deploy bioinformatics workflows using the Latch platform.

LaminDB is an open-source data framework for biology that ensures data is queryable, traceable, reproducible, and FAIR.

Infer gene regulatory networks from gene expression data using scalable algorithms.

Query InterPro for comprehensive protein family, domain, and functional site annotations.

Analyze and engineer protein glycosylation for therapeutic applications.

Detect system resources and generate strategic recommendations for computational tasks.

Comprehensive geospatial science skill for remote sensing, GIS, and spatial analysis.

Generate and edit high-quality images using AI models for various visual content needs.

Conduct thorough exploratory data analysis on over 200 scientific file formats.

ETE Toolkit is a comprehensive phylogenetic tree analysis tool for evolutionary research.

Access and download public cancer imaging data from the NCI Imaging Data Commons effortlessly.

Structured hypothesis formulation from observations to create testable predictions.

Toolkit for preparing ISO 13485 certification documentation for medical device Quality Management Systems.

gget is a fast CLI/Python tool for querying over 20 bioinformatics databases for gene and protein information.

Geniml enables machine learning on genomic interval data, specifically BED files, for various genomic analyses.

Access and query NCBI Gene data for gene annotation and functional analysis.

Efficiently parse and manipulate Flow Cytometry Standard (FCS) files with FlowIO.

Query the Ensembl genome database REST API for genomic data across 250+ species.

Comprehensive toolkit for protein language models enabling advanced protein design and analysis.

Automate protein testing and validation with Adaptyv's cloud laboratory platform.

Python library for accessing and analyzing SEC EDGAR filings with structured data extraction.

Access comprehensive drug information from the DrugBank database for research and analysis.

Create, read, edit, and manipulate Word documents (.docx files) effortlessly.

Access real-time and historical financial market data via the Alpha Vantage API.

DiffDock predicts protein-ligand binding poses using diffusion models for drug discovery.

Extract cognitive patterns and thinking fingerprints from any text to analyze reasoning styles.

Automate scientific research workflows from data analysis to publication with Denario's multiagent AI system.

DeepChem enables molecular machine learning with diverse featurizers and pre-built datasets for property prediction.

Access and query public statistical data from Data Commons programmatically.

Facilitate diverse perspectives on decisions and creative challenges with the Consciousness Council.

Dask enables distributed computing for larger-than-RAM pandas and NumPy workflows.

Access and query clinical trial data from ClinicalTrials.gov via API v2.

Efficiently manage citations for academic research with automated tools.

Access and query ChEMBL bioactive molecules and drug discovery data for medicinal chemistry.

Access comprehensive cancer genomics data from cBioPortal for research and analysis.

Integrate with the DNAnexus cloud genomics platform for data management and analysis.

Aeon is a Python toolkit for advanced time series machine learning tasks.

Guided statistical analysis with test selection and reporting. Use when you need help choosing appropriate tests for your data, assumption checking, power analysis, and APA-formatted results. Best for academic research reporting, test selection guidance. For implementing specific models programmatically use statsmodels.

Comprehensive NGS analysis toolkit for processing and visualizing sequencing data.

Datamol is a Pythonic wrapper around RDKit for efficient cheminformatics tasks in drug discovery.

Access the COSMIC cancer mutation database for comprehensive cancer genomics data.

COBRApy is a Python library for constraint-based metabolic modeling, enabling advanced analysis of metabolic networks.

Access and interpret clinical significance of genetic variants using the NCBI ClinVar database.

Access comprehensive pharmacogenomics data for precision medicine decisions.

Create comprehensive clinical reports with templates and regulatory compliance.

Efficiently search and retrieve life sciences preprints from the bioRxiv database.

Generate professional clinical decision support documents for pharmaceutical and clinical research settings.

Programmatically query the CELLxGENE Census with access to over 61 million single-cell data points.

Comprehensive toolkit for computational molecular biology using Python.

Search scientific papers and retrieve structured experimental data from full-text studies.

Cirq is Google's quantum computing framework for designing and simulating quantum circuits.

Access the BRENDA enzyme database via SOAP API for comprehensive enzyme data.

Unified Python interface to 40+ bioinformatics services for seamless data retrieval and analysis.

Access BindingDB to query drug-target binding affinities for drug discovery and analysis.

Integrate with Benchling's R&D platform to automate lab data management.

Query the Cancer Dependency Map for gene dependency scores and drug sensitivity data.

Perform Bayesian modeling and inference with PyMC for probabilistic programming.

Automate hypothesis generation and testing on tabular datasets using LLMs.

Access the Human Metabolome Database with over 220K metabolites for metabolomics research.

Deep generative models for single-cell omics. Use when you need probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, or multi-modal integration (TOTALVI, MultiVI). Best for advanced modeling, batch effects, multimodal data. For standard analysis pipelines use scanpy.

SimPy is a Python framework for discrete-event simulation, ideal for modeling complex systems with processes and resource interactions.