Claude Team plan for research labs

A thinking partner for academic and nonprofit labs to advance scientific discovery and innovation.

Get started

Made for scientific research

A collaborator for your whole lab

Claude writes code, reads the literature, and reasons through experiments alongside your team.

Grounded in science and research

Claude pulls directly from PubMed, Benchling, and other connectors, so answers are grounded in verifiable references.

Verifiable with citations

Claude cites its sources, shows its work, and flags uncertainty. Your research data stays yours.

One plan for your organization

Replace scattered individual subscriptions with a single Team plan. Everyone in your lab gets the same access at an affordable rate to support academic and nonprofit labs.

Video

👁 Image

Play video

Jonah Cool and Eric Kauderer-Abrams share their vision for making Claude the go-to AI research assistant for scientists.

👁 Image

How labs use Claude

Prompt

> use the scRNA-qc skill to perform QC and filtering on the raw_feature_matrix from my experiment

Now let me run the QC analysis on the raw feature matrix:
Bash(python3 scripts/qc_analysis.pypbmc_test_data/raw_feature_bc_matrix.h5)
↳===========================================================
Single-Cell RNA-seq Quality Control AnalysisFollowing scVerse Best Practices
… +60 lines (ctrl+o to expand)

Excellent! The QC analysis completed successfully. Let me update the visualizations:
Read(qc_metrics_before_filtering.png)↳ Read image (732.3KB)
Read(qc_filtering_thresholds.png)↳ Read image (210KB)
Read(qc_metrics_after_filtering.png)↳ Read image (1.1MB)
Perfect! I've successfully completed the QC analysis on your raw feature matrix using the scRNA-qc skill. Here's a summary of the results:QC Analysis SummaryDataset: 2,700 cells × 32,738 genes (raw)Quality Metrics Detected:
- 13 mitochondrial genes
- 106 ribosomal genes
- 13 hemoglobin genes
MAD-Based Filtering Thresholds:
- Total counts: 709 - 6,812
- Genes detected: 367 - 1,821
- Mitochondrial %: MAD threshold 3.65%, Hard threshold 8.0%
Filtering Results:
- 266 cells removed as outliers (9.9%)
- 2,434 cells retained (90.1%)
- Gene filtering reduced from 32,738 to 9,487 genes (29.0%)
Key Observations from Visualizations:
1. Before Filtering: The data shows typical scRNA-seq quality with most cells having 1,000-2,000 counts and detecting 500-1,000 genes. Mitochondrial content is generally low (<5%), which is excellent.
2. Thresholds: The MAD-based thresholds are permissive (5 MADs for counts/genes, 3 MADs for MT%), following scverse best practices to avoid over-filtering.
3. After Filtering: The filtered dataset shows cleaner distributions with tighter clustering, lower mitochondrial content (mostly <3%), and good cell-gene correlation.
Output Files Created:
- raw_feature_bc_matrix_filtered.h5ad - Clean filtered dataset ready for downstream analysis
- raw_feature_bc_matrix_with_qc.h5ad - Original data with QC annotations
- QC visualization PNGs (before/thresholds/after)
The data quality looks excellent! You can now proceed with downstream analysis like normalization, dimensionality reduction, and clustering using the filtered dataset.

Turn ideas into working code

Claude Code writes, debugs, and runs scripts for analysis from your terminal. Build pipelines, prototype methods, and QC data without waiting on the person who knows the repository.

Prompt

Look in this folder and pull together the results CSV and sample metadata. Run treatment vs. control comparisons on every measured endpoint, flag anything significant after multiple-comparison correction, and generate a figure I can drop straight into my slides.

Working folder

~/Data/cytokine_study/

👁 treatment vs control graph

From dataset to figure, on your desktop

Hand Claude Cowork a dataset and a question. Fit models, run stats, generate publication-ready figures locally, with your own files and environment.

Read guide

Prompt

I'm preparing a review on CAR-T cell exhaustion mechanisms. Search PubMed for recent papers on transcriptional regulators of T cell exhaustion in solid tumors. Summarize which transcription factors are consistently implicated, where the field disagrees on their roles, and create a figure I can use in my review draft.

👁 transcriptional regulators chart

Survey an entire field in an afternoon

Pull from PubMed and bioRxiv, find contradictions across papers, and surface testable hypotheses with real citations you can check.

Read guide

Prompt

Benchmark our MC integrator on the 24-dim Genz test function. Sweep sample sizes 10² to 10⁷, 200 replicates each for 95% CIs, compare against the analytical value (μ = 1.5). Publication-ready convergence figure with a summary strip — final estimate, relative error, wall time.

Attachments

mc_integrator

14.2 KB

genz_testfunctions

3.8 MB

NPZ

👁 monte carlo convergence chart

Test hypotheses computationally

Run large-scale numerical experiments, compare results against theoretical predictions, and generate publication-ready figures in a fraction of the time.

👁 logo

Claude connects to your tools

Work across your literature databases, lab platforms, and productivity tools in one place.

Explore connectors

Why scientists choose Claude

"After collaborating with Claude Code for the past 3 months, turning one idea after another into research projects, I am totally hooked. I cannot imagine research anymore without it! Claude's coding and reasoning capabilities are out of this world, and it's dramatically expanded my conception of what's possible."

David Shih, Professor of Physics, Rutgers University

“Claude has helped our lab identify promising research directions to hone in on by enabling rapid preliminary analysis and statistical power prediction for complex, highly specialized experimental designs.”

Silvia Domke, Assistant Professor, University of Zurich

“[Claude] was extraordinarily useful for my research -- both a larger, purely empirical project with a complicated codebase, and some more basic research projects and idea seeds where I needed to prototype something quickly. It definitely changed the game for me, and I re-subscribed!"

Hannah Lawrence, Computer Science Ph.D. student, Massachusetts Institute of Technology

“We have taken data harmonization projects and standards development efforts that would have taken a decade to complete and realized them in months. Claude has fundamentally changed how we interact with domain experts and the content we can deliver, such as for rare disease diagnostics and drug repurposing.”

Melissa Haendel, Director of Precision Health & Translational Informatics at University of North Carolina at Chapel Hill

"Over the last six months, Claude has become a crucial collaborator for our lab, from designing computer processors, to programming languages, to operating systems. As a team of computer systems builders, we can engage in high-risk, engineering-heavy prototyping which would be difficult to justify in the past."

Jonathan Balkind, Assistant Professor of Computer Science, University of California, Santa Barbara

“I use Opus as an intellectual partner to find holes in my ideas before I commit resources to experiments. At the bench, I generate protocols and troubleshoot logistics in real time. With Claude Code, I automate data transformations and build analysis pipelines. As an MD-PhD student juggling course work, lab experiments, analysis, collaborations and scientific writing, having a tool this versatile has been transformative.”

Maia Madison, MD PhD Student, University of California, San Francisco

"Claude has changed the way that I do science, from the way that I explore the literature and brainstorm for a new hypothesis, to our ability to analyze large-scale datasets and integrate diverse information sources at a scale that would be difficult to achieve otherwise. It has accelerated my work, but has also allowed me to generate testable and verifiable ideas and to think about the science in fundamentally new ways. Claude passes the scientific “deletion test” - it has become an essential tool for our work.”

Iain Cheeseman, Herman and Margaret Sokol Professor of Biology; Core Member, Whitehead Institute; Associate Department Head

"I’ve been able to take advantage of Claude’s broad knowledge to connect a research problem in theoretical particle physics to techniques developed for industrial systems engineering and number theory. Claude Code has allowed me to identify and integrate well developed libraries into our niche problem setting and explore bespoke solutions that leverage advanced reasoning capabilities. It has dramatically changed the pace and ambition of this research project."

Kyle Cranmer, Professor and Director of the Data Science Institute, University of Wisconsin, Madison

"'I figured out how to do [insert X] with Claude' has become a frequent refrain in discussions with my team. Claude is enabling my academic research group to acquire new skills and accomplish analysis tasks far more quickly."

Abby Buchwalter, Assistant Professor, University of California, San Francisco

0/5

Get Claude for your lab

Principal investigators from labs with fewer than 75 people can get started by verifying their lab status. For larger labs, reach out to our sales team.

Standard

$15 /user

Per month

Verify your lab

Access to Claude Code & Cowork
Life sciences connectors and skills
Shared projects and file creation
Access to Research
Central billing and administration
Single sign-on (SSO)
Minimum 2 seats

Premium

$75 /user

Per month

Verify your lab

Everything in Standard, plus:

5x more usage*
Higher limits for long-running analyses

*Extra usage limits apply. Prices shown don’t include applicable tax.

Price and plans are subject to change at Anthropic’s discretion.

More resources

Getting started with Claude for life sciences

Tutorial

Advancing Claude in Life Sciences

Blog

Explore the full range of Claude’s capabilities for scientific research

Learn

Learn about the AI for Science program by Anthropic

Learn

FAQ

The discounted Claude Team plan for research labs plan is available to active scientific labs at academic institutions and nonprofit research organizations. Specifically, biomedical and basic science labs are being prioritized in addition to the hard sciences including chemistry, math, computer science, and physics. Eligibility is verified through the lab’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.

The Claude Team plan for research labs includes everything in Claude Team: shared projects, Claude Code, Cowork, file creation, built-in connectors to research databases, single sign-on, and central billing and administration with a minimum purchase of 2 seats.

If you're at a for-profit organization or don't meet the eligibility criteria, Claude Team and Claude Enterprise offer the same capabilities at standard pricing. Visit claude.com/pricing to compare plans, or contact our sales team for help choosing the right fit.

We have tutorials covering common research use cases, including a walkthrough of sample agent skills and MCP connectors. You can also explore life sciences guides and documentation at claude.com/lifesciences, and connect research tools like PubMed, Benchling, and 10X Genomics through built-in connectors.

No. Claude does not train on your conversations, uploaded files, or research data. Your unpublished findings, grant drafts, and proprietary datasets stay private. Admins can configure data retention policies for their team.

URL: https://claude.com/programs/claude-team-plan-for-research-labs