Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →

jimmc414/kosmos

129 skills1.7k installs71.7k starsGitHub

Install

npx skills add https://github.com/jimmc414/kosmos

Skills in this repo

1Scientific SchematicsGenerates publication-quality scientific diagrams and flowcharts using Python plotting libraries. A developer uses it for neural-network architecture diagrams, system diagrams, and flowcharts with quality verification.44installs2Markitdownmarkitdown is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.43installs3Ensembl DatabaseQueries the Ensembl genome database REST API covering genomic data for over 250 species. Developers use it for gene lookups, sequence retrieval, variant effect prediction (VEP), ortholog/paralog finding, and comparative genomics.24installs4PptxA toolkit for programmatically creating, editing, and analyzing PowerPoint (.pptx) presentations. A developer uses it to build slides, layouts, speaker notes, and comments from code.23installs5DocxA tutorial for the docx library to generate .docx Word files with JavaScript/TypeScript. Developers use it to build documents with formatted text, tables, images, headers/footers, and table-of-contents in Node.js or the browser.20installs6Scientific SlidesGuides creation of slide decks for scientific talks in PowerPoint or LaTeX Beamer. A developer or researcher uses it for conference presentations, seminars, and thesis defense slides.19installs7Scientific Visualizationscientific-visualization is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.17installs8Latex PostersProduces conference and academic research posters in LaTeX with beamerposter, tikzposter, or baposter templates. A developer uses it to design multi-column poster layouts, integrate figures, and verify print-ready dimensions and DPI.16installs9ReportlabProvides guidance for programmatic PDF generation with the ReportLab Python toolkit. A developer uses it to automate professional documents like invoices, reports, and certificates.16installs10Research GrantsGuides writing of grant proposals tailored to NSF, NIH, DOE, and DARPA requirements. A developer or researcher uses it to draft compliant, review-ready funding applications.16installs11Citation ManagementProvides citation management for academic research by searching Google Scholar and PubMed, extracting metadata, and validating citations. Developers use it to find papers, verify citation information, convert DOIs to BibTeX, and ensure reference accuracy in scientific writing.15installs12Clinical Decision SupportGenerates clinical decision support (CDS) documents for pharmaceutical and clinical research, including patient cohort analyses and evidence-based treatment recommendation reports. Developers use it to produce publication-ready LaTeX/PDF outputs with GRADE grading, statistical analysis, and biomarker integration.15installs13Literature Reviewliterature-review is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.15installs14Paper 2 WebPaper2All transforms academic papers into websites, presentation videos, and print-ready posters. A developer uses it for paper dissemination and conference preparation from LaTeX or PDF sources.15installs15Treatment PlansGenerates focused 3-4 page medical treatment plans in LaTeX/PDF for various clinical specialties. A developer or clinician uses it for actionable, evidence-based plans across rehab, mental health, and chronic-disease care.15installs16AeonA guide to the scikit-learn-compatible aeon toolkit for time series machine learning across classification, forecasting, clustering, and anomaly detection. A developer uses it when working with temporal or sequential data needing specialized algorithms.14installs17BioservicesThe primary Python tool for accessing 40+ bioinformatics web services through a unified API, including UniProt, KEGG, ChEMBL, PubChem, Reactome, and QuickGO. Developers use it for multi-database workflows involving queries, ID mapping, and pathway analysis.14installs18Clinical ReportsWrites comprehensive clinical reports including CARE-guideline case reports, diagnostic reports, ICH-E3 trial reports, and patient documentation like SOAP and discharge summaries. Developers use it with templates and validation tools that enforce HIPAA, FDA, and ICH-GCP compliance.14installs19PylabrobotPyLabRobot is a hardware-agnostic toolkit for controlling liquid handlers, plate readers, and other lab equipment. A developer uses it to program reproducible protocols and manage deck layouts in simulation or on physical hardware.14installs20Research LookupQueries Perplexity Sonar models through OpenRouter to retrieve current research information with citations. A developer uses it to search academic papers, recent studies, and technical documentation.14installs21Scientific Writingscientific-writing is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.14installs22Statistical Analysisstatistical-analysis is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.14installs23Venue TemplatesProvides venue-specific LaTeX templates and formatting requirements for major journals, conferences, posters, and grant agencies. A developer or researcher uses it when preparing manuscripts to meet submission guidelines.14installs24Xlsxxlsx is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.14installs25Cellxgene CensusQueries the CZ CELLxGENE Census, a repository of 61M+ single cells, filtering by cell type, tissue, or disease and retrieving expression data. Developers use it for population-scale single-cell analysis, integrating with scanpy or PyTorch.13installs26Exploratory Data Analysisexploratory-data-analysis is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.13installs27Hypothesis GenerationA methodology skill for generating testable scientific hypotheses from observations and designing experiments to evaluate them. A developer uses it to structure hypothesis formulation, competing explanations, and predictions for scientific inquiry.13installs28Kegg DatabaseProvides direct REST API access to the KEGG database for pathways, genes, compounds, and drug interactions. A developer uses it for pathway analysis, gene-pathway mapping, and ID conversion in bioinformatics workflows.13installs29MatplotlibMatplotlib is a foundational Python plotting library for scientific visualization and publication-quality figures. A developer uses it to build a wide range of plot types with subplots and export to PNG, PDF, or SVG.13installs30Modalmodal is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.13installs31Neurokit2NeuroKit2 is a biosignal processing toolkit for physiological data such as ECG, EEG, EDA, and PPG. A developer uses it for HRV analysis, event-related processing, and psychophysiology research.13installs32Peer ReviewA systematic peer-review toolkit for evaluating scientific manuscripts and grants across methodology, statistics, and reproducibility. A developer or researcher uses it to structure critical evaluation and reporting-standards checks.13installs33Perplexity SearchPerforms AI-powered web searches with real-time, source-cited answers via Perplexity models through LiteLLM and OpenRouter. A developer uses it to get grounded answers and recent literature beyond the model's knowledge cutoff.13installs34PymooPymoo is a framework for multi-objective optimization in Python with algorithms like NSGA-II and MOEA/D. A developer uses it for engineering design and optimization problems with constraint handling and Pareto-front analysis.13installs35PytdcPyTDC provides AI-ready datasets and benchmarks from the Therapeutics Data Commons for drug discovery. A developer uses it for therapeutic ML with ADME/toxicity/DTI datasets, scaffold splits, and molecular oracles.13installs36Reactome DatabaseWraps the Reactome REST API for biological pathway analysis, enrichment, and gene-pathway mapping. A developer uses it for systems-biology research involving disease pathways and expression analysis.13installs37Scikit BioProvides guidance for biological data analysis with scikit-bio. A developer uses it for sequence alignments, phylogenetics, and microbiome diversity metrics.13installs38Scikit LearnProvides reference documentation for machine learning in Python with scikit-learn. A developer uses it for supervised/unsupervised learning, model evaluation, hyperparameter tuning, and ML pipelines.13installs39SeabornProvides guidance for statistical visualization with Seaborn. A developer uses it for exploratory analysis and publication figures.13installs40Stable Baselines3Provides guidance for reinforcement learning with Stable Baselines3. A developer uses it to train RL agents, design custom Gym environments, and run vectorized parallel training.13installs41StatsmodelsProvides a statistical modeling toolkit built on statsmodels. A developer uses it for rigorous statistical inference and econometric analysis.13installs42SympyProvides guidance for symbolic computation with SymPy. A developer uses it for exact algebraic results, calculus, and formula manipulation rather than numerical approximation.13installs43TooluniverseProvides access to 600+ scientific tools, datasets, and APIs across bioinformatics, cheminformatics, and drug discovery. A developer uses it for tool discovery and composing computational-biology pipelines in LLM workflows.13installs44TransformersProvides guidance for working with pre-trained transformer models via the Transformers library. A developer uses it for text generation, classification, translation, image tasks, speech recognition, and fine-tuning.13installs45Uspto Databaseuspto-database is a Claude Code skill for databases. It helps solo builders move faster with AI-assisted coding.13installs46Alphafold DatabaseGuides retrieving and analyzing AlphaFold DB protein structure predictions, including coordinate downloads, confidence metrics, and bulk proteome datasets. A developer uses it for structural biology, drug discovery, or protein engineering workflows.12installs47AnndataA guide to the AnnData package for handling annotated data matrices with observation/variable metadata, sparse matrices, and backed mode. A developer uses it for single-cell genomics or any annotated dataset needing efficient storage and manipulation.12installs48ArboretoA guide to the arboreto library for inferring transcription-factor-to-target gene regulatory networks from expression data, with distributed Dask computation. A developer uses it to analyze transcriptomics data at scale.12installs49AstropyA guide to the astropy library covering celestial coordinates, physical units, FITS files, cosmology, precise time handling, tables, and WCS transformations. A developer uses it for astronomical data analysis and processing.12installs50Benchling IntegrationIntegrates with the Benchling life-sciences R&D platform to access registry entities (DNA, proteins), inventory, electronic lab notebooks, and workflows via Python SDK and REST API. Developers use it to automate lab data operations, build Benchling Apps, or sync Benchling data with external systems.12installs51BiomniAn autonomous biomedical AI agent framework that executes complex, multi-step research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Developers use it for CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, or rare-disease diagnosis via LLM reasoning with code execution.12installs52BiopythonThe primary Python toolkit for molecular biology, handling sequence manipulation, file parsing (FASTA, GenBank, FASTQ, PDB), BLAST workflows, structures, and phylogenetics. Developers use it for Python-based PubMed/NCBI queries via Bio.Entrez and general bioinformatics scripting.12installs53Biorxiv DatabaseA database search tool for the bioRxiv life-sciences preprint server. Developers use it to find preprints by keyword, author, date range, or category, retrieve paper metadata, download PDFs, and conduct literature reviews.12installs54Chembl DatabaseQueries ChEMBL's database of bioactive molecules and drug-discovery data. Developers use it to search compounds by structure or properties, retrieve bioactivity data (IC50, Ki), find inhibitors, and perform SAR studies for medicinal chemistry.12installs55Clinicaltrials DatabaseQueries the ClinicalTrials.gov registry via API v2 to search trials by condition, drug, location, status, or phase. Developers use it for patient matching, research analysis, and exporting clinical trial data with no authentication required.12installs56Clinpgx DatabaseAccesses ClinPGx pharmacogenomics data, the successor to PharmGKB consolidating PharmGKB, CPIC, and PharmCAT. Developers use it to query gene-drug interactions, CPIC guidelines, and allele functions for precision medicine and genotype-guided dosing decisions.12installs57Clinvar DatabaseQueries NCBI ClinVar for the clinical significance of human genetic variants via E-utilities API or FTP. Developers use it to search by gene or position, interpret pathogenicity classifications, and annotate variant call sets for genomic medicine.12installs58CobrapyA Python library for constraint-based reconstruction and analysis (COBRA) of genome-scale metabolic models. Developers use it for flux balance analysis (FBA), flux variability analysis (FVA), gene knockouts, and flux sampling in systems biology and metabolic engineering.12installs59Cosmic DatabaseAccesses COSMIC, the catalogue of somatic mutations in cancer, to query somatic mutations, the Cancer Gene Census, mutational signatures, and gene fusions. Developers use it for cancer research and precision oncology; downloads require authentication.12installs60DaskA Python library for parallel and distributed computing that scales pandas and NumPy operations beyond available RAM. Developers use it to process larger-than-memory datasets, parallelize computations across cores or clusters, and build custom task-graph workflows.12installs61Datacommons ClientProvides programmatic access to Data Commons, a platform aggregating public statistical data from census, health, and environmental sources into a knowledge graph. Developers use it to query demographic, economic, health, and environmental statistics and resolve geographic entities.12installs62DatamolA Pythonic wrapper around RDKit that simplifies molecular cheminformatics with sensible defaults and parallelization. Developers use it for SMILES parsing, standardization, descriptors, fingerprints, clustering, and 3D conformer generation, returning native rdkit.Chem.Mol objects.12installs63DeepchemA Python library for applying machine learning to chemistry, materials science, and biology. Developers use it to predict molecular properties (solubility, toxicity, ADMET), train graph neural networks (GCN, MPNN, AttentiveFP), and apply pretrained models like ChemBERTa on MoleculeNet datasets.12installs64DeeptoolsA suite of command-line tools for processing and analyzing high-throughput sequencing data. Developers use it to convert BAM alignments to normalized coverage tracks, run quality control, and generate heatmaps and profile plots for ChIP-seq, RNA-seq, and ATAC-seq experiments.12installs65DenarioA multiagent AI system built on AG2 and LangGraph that automates scientific research workflows from data analysis to publication. Developers use it to generate research ideas from datasets, develop methodologies, execute computational experiments, and produce journal-formatted LaTeX papers.12installs66DiffdockA diffusion-based deep learning tool that predicts 3D binding poses of small-molecule ligands to protein targets. Developers use it for structure-based drug design and virtual screening from PDB files or sequences; it predicts poses and confidence, not binding affinity.12installs67Dnanexus IntegrationIntegrates with the DNAnexus cloud genomics platform to build apps and applets, manage data, and run workflows via the dxpy Python SDK. Developers use it for genomics pipeline development and execution on FASTQ, BAM, and VCF files.12installs68Drugbank DatabaseProvides programmatic access to the DrugBank database of ~9,591 drug entries with 200+ data fields including properties, interactions, targets, and pathways. Developers use it for drug-discovery research, drug-drug interaction analysis, target identification, and ADMET work.12installs69Ena DatabaseAccesses the European Nucleotide Archive (ENA) via REST APIs and FTP for nucleotide sequence data and metadata. Developers use it to retrieve sequences, raw reads (FASTQ), and genome assemblies by accession for genomics and bioinformatics pipelines.12installs70EsmA toolkit for protein language models including ESM3 for generative multimodal protein design and ESM C for efficient embeddings. Developers use it to design proteins, generate representations, perform inverse folding, and run protein-engineering tasks locally or via the Forge API.12installs71EtetoolkitA toolkit (ETE) for phylogenetic and hierarchical tree analysis. Developers use it to manipulate trees (Newick/NHX), detect evolutionary events, analyze orthology/paralogy, integrate NCBI taxonomy, and generate PDF/SVG visualizations for phylogenomics.12installs72FlowioA lightweight Python library for reading and writing Flow Cytometry Standard (FCS) files versions 2.0-3.1. Developers use it to extract event data as NumPy arrays, read metadata and channels, and preprocess cytometry files for pipelines.12installs73Gene DatabaseQueries the NCBI Gene database via E-utilities and the Datasets API for integrated gene information across species. Developers use it to search by symbol or ID and retrieve RefSeqs, GO annotations, chromosomal locations, and phenotypes, including batch lookups.12installs74GenimlA Python package for machine learning on genomic interval data from BED files. Developers use it to train region embeddings (Region2Vec, BEDspace), run single-cell ATAC-seq analysis (scEmbed), and build consensus peak universes for similarity search and clustering.12installs75Geo DatabaseAccesses NCBI's Gene Expression Omnibus (GEO), a repository of 264,000+ studies of high-throughput gene expression data. Developers use it to search and download microarray and RNA-seq datasets (GSE, GSM, GPL) and retrieve SOFT/Matrix files for transcriptomics analysis.12installs76Get Available ResourcesDetects available computational resources (CPU cores, GPUs, memory, disk) at the start of intensive scientific tasks and writes them to a JSON file with strategic recommendations. Developers use it to decide whether to use parallel processing, out-of-core computing (Dask/Zarr), or GPU acceleration.12installs77Ggetgget is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.12installs78GtarsA high-performance Rust toolkit with Python bindings for genomic interval analysis. Developers use it for overlap detection, coverage track generation (WIG/BigWig), ML tokenization, and fragment analysis in computational genomics.12installs79Gwas DatabaseQueries the NHGRI-EBI GWAS Catalog of published genome-wide association studies. Developers use it to search variants by rs ID, disease/trait, or gene and retrieve p-values, effect sizes, and summary statistics for genetic epidemiology and polygenic risk scores.12installs80HistolabA Python library for processing whole slide images (WSI) in digital pathology. Developers use it to detect tissue, extract tiles from gigapixel H&E or IHC slides (SVS, TIFF, NDPI), and segment tissue masks to prepare datasets for computational-pathology deep learning.12installs81Hmdb DatabaseAccesses the Human Metabolome Database (HMDB), which holds 220,945+ metabolite entries with 130+ fields each. Developers use it to search by name, ID, or structure and retrieve chemical properties, biomarker data, NMR/MS spectra, and pathways for metabolomics and metabolite identification.12installs82HypogenicHypogenic is a framework that uses large language models to automatically generate and test scientific hypotheses from datasets and literature. A developer uses it to run data-driven or literature-integrated hypothesis discovery and inference for empirical research tasks.12installs83Labarchive IntegrationIntegrates with the LabArchives electronic lab notebook API to read and manage notebook entries, attachments, and backups. A developer uses it for programmatic ELN workflows and integration with other lab tools.12installs84LamindbLaminDB is an open-source data framework for biology that makes datasets queryable, traceable, and reproducible with ontology validation. A developer uses it to manage biological data, track workflow lineage, and integrate with Nextflow, Snakemake, and MLOps platforms.12installs85Latchbio IntegrationIntegrates with the LatchBio platform to build and register bioinformatics workflows using the Latch SDK. A developer uses it to author serverless pipelines with task decorators and Nextflow/Snakemake integration.12installs86MatchmsMatchms processes mass spectrometry spectra, harmonizes metadata, and computes spectral similarity scores. A developer uses it for compound identification and MS data processing in metabolomics workflows.12installs87MedchemMedchem applies medicinal-chemistry filters such as drug-likeness rules, PAINS, and structural alerts to compound libraries. A developer uses it to prioritize and filter molecules with parallelized batch screening.12installs88Metabolomics Workbench DatabaseAccesses the NIH Metabolomics Workbench via REST API to query metabolites, studies, and MS/NMR data. A developer uses it for metabolomics and biomarker discovery across thousands of public studies.12installs89MolfeatMolfeat is a molecular featurization hub offering 100+ featurizers to convert SMILES into ML-ready features. A developer uses it for QSAR modeling and molecular machine learning.12installs90NetworkxNetworkX is a Python toolkit for building, analyzing, and visualizing complex networks and graphs. A developer uses it for graph algorithms, centrality, and community detection across social, biological, and citation networks.12installs91Omero IntegrationIntegrates with the OMERO microscopy data management platform to access images, datasets, and annotations via Python. A developer uses it for high-content screening and batch microscopy workflows.12installs92Opentargets DatabaseQueries the Open Targets Platform for target-disease associations and supporting genetics, omics, and safety evidence. A developer uses it for drug-target discovery and therapeutic target identification.12installs93Opentrons IntegrationIntegrates with the Opentrons lab-automation platform to write Protocol API v2 protocols for Flex and OT-2 robots. A developer uses it for automated liquid handling, hardware module control, and labware management.12installs94PathmlPathML is a computational pathology toolkit for whole-slide and multiparametric imaging analysis. A developer uses it for nucleus detection, tissue graph construction, and training ML models on histopathology data.12installs95Pdb DatabaseAccesses the RCSB PDB for 3D protein and nucleic-acid structures via text, sequence, and structure search. A developer uses it for structural biology and drug discovery, downloading coordinates and metadata.12installs96PdfA PDF manipulation toolkit for extracting text and tables, creating, merging, splitting, and filling PDF forms. A developer uses it for programmatic document processing and analysis.12installs97PolarsPolars is a fast Apache Arrow-based DataFrame library with an expression API and lazy evaluation. A developer uses it for high-performance data analysis with joins, group-bys, and CSV/Parquet I/O.12installs98Protocolsio IntegrationIntegrates with the protocols.io API to manage scientific protocols, steps, materials, and workspaces. A developer uses it for protocol discovery, collaborative development, and experiment tracking.12installs99Pubchem DatabaseQueries PubChem via the PUG-REST API and PubChemPy across 110M+ compounds. A developer uses it for cheminformatics tasks including property retrieval and similarity or substructure searches.12installs100Pubmed Databasepubmed-database is a Claude Code skill for databases. It helps solo builders move faster with AI-assisted coding.12installs101PufferlibPufferLib is a high-performance reinforcement-learning library for vectorized training and custom environments. A developer uses it for PPO training, multi-agent systems, and integration with Gymnasium, PettingZoo, Atari, and Procgen.12installs102Pydeseq2PyDESeq2 is a Python implementation of DESeq2 for differential gene expression from bulk RNA-seq counts. A developer uses it to identify DE genes with Wald tests, FDR correction, and diagnostic plots.12installs103PydicomPydicom is a Python library for reading, writing, and modifying DICOM medical imaging files. A developer uses it to extract pixel data, anonymize studies, and process DICOM metadata in radiology and PACS workflows.12installs104PyhealthPyHealth is a healthcare AI toolkit for developing and deploying ML models on clinical data. A developer uses it for EHR prediction tasks, medical coding, and deep-learning models like RETAIN and SafeDrug.12installs105PymatgenPymatgen is a materials-science toolkit for crystal structures, phase diagrams, and electronic-structure analysis. A developer uses it for computational materials science and Materials Project integration.12installs106Pymc Bayesian ModelingPyMC is a probabilistic-programming library for Bayesian modeling and inference. A developer uses it to build hierarchical models, run MCMC or variational inference, and perform model comparison and posterior checks.12installs107PyopenmspyOpenMS is a Python interface to OpenMS for mass spectrometry data analysis. A developer uses it for LC-MS/MS proteomics and metabolomics workflows including feature detection, peptide identification, and quantification.12installs108PysamPysam is a toolkit for reading and writing genomic file formats such as SAM/BAM/CRAM and VCF/BCF. A developer uses it in NGS data-processing pipelines to extract regions, iterate alignments, and compute coverage.12installs109Pytorch LightningPyTorch Lightning structures PyTorch code into LightningModules and Trainers for scalable neural-network training. A developer uses it for multi-GPU/TPU and distributed training with callbacks, logging, and data pipelines.12installs110RdkitProvides guidance for cheminformatics work with the RDKit Python library, including molecular I/O, descriptors, fingerprints, substructure search, and reactions. A developer uses it for drug discovery and computational chemistry tasks needing fine-grained molecular control.12installs111ScanpyProvides guidance for single-cell RNA-seq analysis with Scanpy. A developer uses it for QC, dimensionality reduction, clustering, and cell-type annotation of scRNA-seq datasets.12installs112Scholar Evaluationscholar-evaluation is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.12installs113Scientific BrainstormingServes as a research ideation partner for generating hypotheses and exploring interdisciplinary connections. A developer or researcher uses it for creative scientific problem-solving and identifying gaps.12installs114Scientific Critical ThinkingGuides critical assessment of scientific claims and research rigor. A developer or researcher uses it to evaluate methodology, statistical validity, and evidence quality.12installs115Scikit SurvivalProvides a toolkit for survival analysis and time-to-event modeling with scikit-survival. A developer uses it to fit Cox models, survival forests, and evaluate predictions on censored data.12installs116Scvi Toolsscvi-tools is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted coding.12installs117ShapProvides guidance for model interpretability with SHAP (Shapley Additive exPlanations). A developer uses it to explain predictions, compute feature importance, and analyze model bias across tree, deep-learning, and linear models.12installs118SimpyProvides guidance for discrete-event simulation with the SimPy framework. A developer uses it to model manufacturing, service operations, logistics, or network traffic where entities share resources over time.12installs119String DatabaseWraps the STRING API for protein-protein interaction data covering millions of proteins. A developer uses it for network analysis, enrichment, and interaction discovery in systems biology.12installs120TorchdrugProvides a PyTorch-based toolkit for graph machine learning on molecules, proteins, and biomedical graphs. A developer uses it for property prediction, molecular generation, and knowledge-graph reasoning.12installs121Torch GeometricProvides guidance for geometric deep learning with PyTorch Geometric (PyG). A developer uses it for GNN tasks like node classification, link prediction, and molecular property prediction.12installs122Umap LearnProvides guidance for nonlinear dimensionality reduction with UMAP-learn. A developer uses it for visualization and clustering preprocessing on high-dimensional data.12installs123Uniprot DatabaseProvides direct REST API access to UniProt protein data. A developer uses it for protein searches, FASTA retrieval, and ID mapping when UniProt-specific control is needed.12installs124VaexProvides guidance for out-of-core analysis of very large tabular datasets with Vaex. A developer uses it for fast aggregations, visualization, and ML on data that does not fit in memory.12installs125Zarr PythonProvides guidance for chunked N-dimensional array storage with Zarr-Python. A developer uses it for large-scale scientific computing pipelines needing compressed cloud-backed arrays.12installs126Zinc DatabaseWraps the ZINC database of purchasable compounds for drug discovery. A developer uses it for analog discovery, similarity searches, and retrieving docking-ready 3D structures.12installs127Fda DatabaseAccesses FDA regulatory data through the openFDA API covering drugs, devices, foods, and substances. Developers use it to query adverse events, recalls, product labeling, approvals, 510(k)/PMA submissions, and NDC/UNII identifiers.11installs128FluidsimAn object-oriented Python framework for high-performance computational fluid dynamics using pseudospectral FFT methods. Developers use it to run 2D/3D Navier-Stokes, shallow-water, and stratified-flow simulations and analyze turbulence, vortex dynamics, and geophysical flows.11installs129Openalex DatabaseQueries the OpenAlex scholarly database to search papers, authors, institutions, and citations across 240M+ works. A developer uses it for literature search, research-trend analysis, and bibliometrics.11installs

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.