Claude Science (beta)
Your research partner for rigorous science
The Claude Science app runs analyses, searches databases, and traces every step from data wrangling to publication, so you can spend time on science.
Built for scientific research
Rich scientific artifacts, fully reproducible
View proteins, structures, and molecules natively, with every result reproducible and traced to its code.
Figures, tables, and notebooks include the exact code, environment, and conversation that produced them, so they can be reproduced, edited, or defended months later.
Inspect proteins, alignments, genomic tracks, chemical structures, and PDFs in their native form, with no extra installation required.
A background reviewer flags incorrect citations, untraceable numbers, and figures that don’t match their underlying code.
Annotate a figure to request edits or ask a question. The agent reads the code that produced it and edits directly.
Write up results alongside the analysis that produced them, with rendered Markdown and LaTeX previews.
Manages your compute and scales on demand
Builds environments and manages compute on your laptop, your cluster, or GPUs.
Claude manages the environments each analysis needs, whether on your laptop, a Linux box, or an HPC login node.
Writes batch scripts, then submits and manages jobs over SSH on your own machine or HPC cluster, or through your Modal account.
Variables, dataframes, and loaded models stay in memory across the whole analysis, so iteration is fast.
Domain-ready on day one
Connects to databases and tools your lab needs, so you can start work in your field right away.
Genomics, single-cell, proteomics, structural biology, cheminformatics, and more. Reads literature and can query 60+ scientific databases, so you pull what you need without learning each one.
Save any pipeline as a reusable skill, or connect to your lab’s preferred tool with a connector, and every future session inherits it automatically.
Includes fully sourced indication dossiers available today, and a growing set of skills that build the case behind every program.
How researchers use Claude Science
The app is pre-configured for every major domain in life sciences. When a project spans disciplines, it can help solve hard problems.
Single-cell RNA-seq analysis
Cluster and annotate millions of cells across tissues, surface marker genes, and trace every figure back to the code that made it.
Phylogenetic and evolutionary analysis
Align orthologs, infer maximum-likelihood trees, and map functional residues onto the phylogeny in a single reproducible session.
Protein structure and language model work
Pull predicted structures, layer on domains and clinical variants, and explore the model interactively in 3D.
Cheminformatics and molecular design
Search bioactivity data, compute properties and similarities, and draw or refine structures in a live 2D sketcher.
“Con Claude Science puedo pasar de los datos sin procesar a una figura con calidad de publicación en una sola sesión: ejecutar el análisis, generar gráficos exploratorios y refinarlos, todo dentro de un mismo proyecto. El código y la conversación que hay detrás de cada figura quedan ligados a ella, lo que hace que cada versión sea totalmente reproducible y me permite iterar, revertir y bifurcar tanto como necesite.”
“Claude Science está haciendo posibles análisis que sencillamente no habrían estado a mi alcance como biólogo no computacional. Sinceramente, es realmente transformador. Su capacidad para ejecutar estos análisis, navegar con fluidez por los sitios web existentes y considerar la ciencia con rigor es impresionante… Me he sorprendido pensando en preguntas que llevaba años haciéndome y corriendo a Claude Science para iniciar un proyecto.”
“Claude Science es, sin exagerar, el entorno de computación científica con IA integrada más impresionante que he visto.”
“Las nuevas capacidades agénticas de verificación de datos de Claude Science han ayudado a nuestro equipo a ganar confianza en los resultados biomédicos. Esto hace que Claude resulte especialmente útil para nuestro trabajo de triaje y revisión médica.”
“Xaira está creando capacidades nativas de IA a lo largo de todo el arco del descubrimiento y desarrollo de fármacos, desde modelos predictivos hasta sistemas de IA física que aprenden de la biología a gran escala, impulsadas por flujos de trabajo agénticos diseñados para crear la próxima generación de medicamentos. Claude Code y Claude Science están acelerando ese trabajo: comprimen el camino de la hipótesis a la validación y hacen avanzar nuestra cartera terapéutica, lo que permite a nuestros científicos centrarse en los descubrimientos más importantes y llevar antes medicamentos innovadores a los pacientes.”
“Claude Science encontró de inmediato un virus contaminante de laboratorio en nuestros datos de bulk RNA-seq. Estuvimos atascados con esto durante casi un año, y salió como uno de los primeros hallazgos clave.”
“Claude Science me ayuda a convertir preguntas biológicas en revisiones bibliográficas preliminares y análisis genómicos bien citados, que generan hipótesis y están listos para la revisión crítica del equipo.”
“LatchBio proporciona una infraestructura de datos nativa para agentes que permite almacenar, procesar y visualizar grandes conjuntos de datos moleculares desde sus interfaces preferidas. Conectar LatchBio a Claude Science mediante MCP permite a los investigadores aprovechar herramientas bioinformáticas verificadas, desplegadas en colaboración con desarrolladores de ensayos como Vizgen, TakaraBio y AtlasXOmics, para completar flujos de trabajo de agentes con una gran precisión científica.”
“Helix® está creando el mayor conjunto de datos clínico-genómicos vinculados del mundo: actualmente supera los 500.000 registros y va camino de alcanzar varios millones. Al poner datos genéticos y fenotípicos detallados a disposición de Claude Science a través de un servidor MCP, permitimos que los investigadores descubran nuestros datos en un único entorno nativo de IA. Muchos de estos investigadores usan Claude como su plataforma de referencia para el descubrimiento, y esto lleva toda la profundidad de nuestros datos allí donde realmente se hace la ciencia.”
“Claude Science está acelerando nuestra forma de diseñar experimentos e identificar nuevos tratamientos. Está acortando drásticamente el tiempo necesario para pasar de una señal genética a una posible terapia.”
Works with your stack
Connectors bring your internal APIs, ELNs, and bespoke pipelines into the workflow, so the Claude Science app works with the tools your lab already runs.
Claude Science resources
FAQ
No. Claude Science is a public beta app, not a model. It uses the same Claude models your plan includes. What’s new is everything around them: the scientific tools, database connections, and compute integrations that let Claude run full analyses on your own infrastructure.
General AI assistants can discuss biology, but they can’t run a pipeline, navigate scientific databases, orchestrate cluster jobs, or keep track of what happened in a previous session. Claude Science manages compute environments per specialist, and saves full provenance on every result. The app ships with analysis specialists for genomics, single-cell, proteomics, structural biology, cheminformatics, and more. It can connect natively to 60+ scientific databases and domain-specific open models. Claude Science uses the skills in NVIDIA’s BioNeMo Agent Toolkit to connect natively to the life sciences models and libraries in BioNeMo, including Evo 2, Boltz-2, and OpenFold3.
The Claude Science app is designed to work with what you’ve already built. Connect your existing tools, ELNs, and internal systems through connectors. Bring your own scripts—it can read, run, and build on existing Python, R, and shell workflows without requiring you to rebuild anything from scratch.
No. The Claude Science app is the workbench where specialized tools work together. Scientific tools, platforms, and domain-specific open models can plug in as skills or connectors. You keep what works and fill in the gaps.
The Claude Science app runs on your infrastructure; raw datasets and compute stay local; content included in prompts and model responses is processed by Anthropic under standard retention. Contact sales to discuss your team's specific needs.
Install the app wherever your data lives: your laptop, a lab Linux box, an HPC login node, or a cloud VM. Connect from your browser. Jobs run on local kernels, your Slurm cluster over SSH, or through your Modal account.
Every artifact the Claude Science app produces includes the exact code that generated it, the environment it ran in, a plain-language description of what was done, and the conversation that led there. Results are reproducible months later, by anyone on your team. A background reviewer also flags any claim it can’t trace to evidence before results surface.
Yes. The Claude Science app is in beta for macOS, Windows, and Linux on Pro, Max, Team, and Enterprise plans. Team and Enterprise users need their admin to enable it first.
Yes. The discounted Claude Team plan for scientists includes access to the Claude Science app, and is available to active scientists at academic and nonprofit research institutions around the world. Eligibility is verified through the group's principal investigator.
If you are a for-profit company, contract research organization, or industry R&D team, please see our Team and Enterprise plans.
Yes. The Claude Science app is available on the Enterprise plan with SSO, SCIM provisioning, custom roles, usage analytics, Compliance API, and control over app features like connectors, skills, remote compute, memory, and more. It’s currently in beta, so admins should review the documentation before rolling out. Contact sales to discuss your team’s requirements.
Start with the documentation. It covers installation, connecting your tools and compute, and admin setup for Team and Enterprise.