You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Single-cell and spatial omics have unlocked unprecedented insights into cellular diversity, tissue architecture, and drug responses. Despite the remarkable progress in computational tools, the diversity and complexity of analyses can still pose challenges. While the scverse ecosystem provides powerful and interoperable tools such as [Scanpy](https://scanpy.readthedocs.io/en/latest/), [scvi-tools](https://scvi-tools.org/), [Squidpy](https://squidpy.readthedocs.io/), [AnnData](https://anndata.readthedocs.io/en/latest/), [MuData](https://mudata.readthedocs.io/en/latest/), and [SpatialData](https://spatialdata.scverse.org/en/latest/), researchers can sometimes face a steep learning curve, particularly when integrating multiple analytical steps or modalities.
11
+
Single-cell and spatial omics have unlocked unprecedented insights into cellular diversity, tissue architecture, and drug responses.
12
+
Despite the remarkable progress in computational tools, the diversity and complexity of analyses can still pose challenges.
13
+
While the scverse ecosystem provides powerful and interoperable tools such as [Scanpy](https://scanpy.readthedocs.io/en/latest/), [scvi-tools](https://scvi-tools.org/), [Squidpy](https://squidpy.readthedocs.io/), [AnnData](https://anndata.readthedocs.io/en/latest/), [MuData](https://mudata.readthedocs.io/en/latest/), and [SpatialData](https://spatialdata.scverse.org/en/latest/), researchers can sometimes face a steep learning curve, particularly when integrating multiple analytical steps or modalities.
12
14
13
15
**scverse** is a community-driven, open-source initiative behind many of the most widely adopted Python tools in single-cell biology, known for promoting modular, interoperable, and scalable analysis across diverse modalities—from transcriptomics to spatial and immune profiling.
14
16
15
-
We’re excited to announce a collaboration between **scverse** and **Biomni** to further streamline and enhance single-cell and spatial omics analyses. Biomnis intelligent agentic interface is now capable of using scverse tools, enabling researchers to seamlessly integrate, execute, and manage analyses across ten core scverse packages through natural language prompts. Researchers can describe their analysis goals in plain English - e.g., *“cluster cells and identify markers”* or *“analyze perturbation effects between treatment groups”* - and Biomni automatically generates and runs the corresponding scanpy, pertpy, squidpy, or scvi-tools code.
17
+
We’re excited to announce a collaboration between **scverse** and **Biomni** to further streamline and enhance single-cell and spatial omics analyses.
18
+
Biomnis intelligent agentic interface is now capable of using scverse tools, enabling researchers to seamlessly integrate, execute, and manage analyses across ten core scverse packages through natural language prompts.
19
+
Researchers can describe their analysis goals in plain English - e.g., *“cluster cells and identify markers”* or *“analyze perturbation effects between treatment groups”* - and Biomni automatically generates and runs the corresponding scanpy, pertpy, squidpy, or scvi-tools code.
16
20
17
-
The agent understands biological context, handles parameters and dependencies, and returns reproducible results - no coding required. Notably, all codes written by agents are documented and available to users for reproduction or modification as a Jupyter notebook. This is an early-stage capability, and manual review of outputs is encouraged to ensure accuracy, and we invite constructive community feedback to improve.
21
+
The agent understands biological context, handles parameters and dependencies, and returns reproducible results - no coding required.
22
+
Notably, all codes written by agents are documented and available to users for reproduction or modification as a Jupyter notebook.
23
+
This is an early-stage capability, and manual review of outputs is encouraged to ensure accuracy, and we invite constructive community feedback to improve.
18
24
19
25
---
20
26
@@ -38,7 +44,8 @@ To illustrate, here are a few examples of how Biomni equipped with scverse packa
Moving beyond the agentic delegation of individual single-cell tasks, Biomni also enables scientists to run multi-step, cross-tool workflows using natural language. Instead of writing and debugging code across several libraries, you can now execute complex pipelines with a single prompt.
47
+
Moving beyond the agentic delegation of individual single-cell tasks, Biomni also enables scientists to run multi-step, cross-tool workflows using natural language.
48
+
Instead of writing and debugging code across several libraries, you can now execute complex pipelines with a single prompt.
42
49
43
50
**Input**: A Visium spatial transcriptomics dataset in .h5ad format, aligned with histology images and metadata (e.g., treatment condition).
44
51
@@ -59,13 +66,18 @@ Moving beyond the agentic delegation of individual single-cell tasks, Biomni als
Biomni has successfully completed these steps in around 20 minutes. It preprocesses the data, identifies 21 distinct cell types from 17,771 high-quality cells, and maps them across spatial axes with clear anterior-posterior and dorsal-ventral organization. It uncovers major tissue compartments, quantifies gene expression variability (e.g., Slc4a1, T, Mesp2), and performs pathway enrichment, highlighting nervous system and cation channel activity. Biomni also infers cell-cell interactions, such as cardiomyocyte clustering and endothelial co-localization with hematopoietic progenitors. This entire sequence is automatically orchestrated by the agent, enabling reproducible and modular single-cell workflows without writing a single line of code.
69
+
Biomni has successfully completed these steps in around 20 minutes.
70
+
It preprocesses the data, identifies 21 distinct cell types from 17,771 high-quality cells, and maps them across spatial axes with clear anterior-posterior and dorsal-ventral organization.
71
+
It uncovers major tissue compartments, quantifies gene expression variability (e.g., Slc4a1, T, Mesp2), and performs pathway enrichment, highlighting nervous system and cation channel activity.
72
+
Biomni also infers cell-cell interactions, such as cardiomyocyte clustering and endothelial co-localization with hematopoietic progenitors.
73
+
This entire sequence is automatically orchestrated by the agent, enabling reproducible and modular single-cell workflows without writing a single line of code.
63
74
64
75
---
65
76
66
77
### **Explore Single-cell Data to Generate New Hypotheses**
67
78
68
-
Biomni also supports curiosity-driven no-code exploratory and hypothesis-driven analyses. By interacting with datasets through natural language prompts, researchers can easily identify biological patterns and generate meaningful hypotheses for experimental validation.
79
+
Biomni also supports curiosity-driven no-code exploratory and hypothesis-driven analyses.
80
+
By interacting with datasets through natural language prompts, researchers can easily identify biological patterns and generate meaningful hypotheses for experimental validation.
69
81
70
82
**Input:**
71
83
@@ -116,4 +128,7 @@ By combining data-driven discovery with biological reasoning, Biomni helps resea
116
128
---
117
129
118
130
### Disclaimer
119
-
This integration between Biomni and scverse highlights a powerful synergy, removing coding barriers while maintaining transparency, reproducibility, and scientific rigor. Although agent-based automation enhances convenience, human expertise remains vital for biological interpretation and validation. We look forward to seeing the innovative discoveries our community achieves with this exciting collaboration.
131
+
132
+
This integration between Biomni and scverse highlights a powerful synergy, removing coding barriers while maintaining transparency, reproducibility, and scientific rigor.
133
+
Although agent-based automation enhances convenience, human expertise remains vital for biological interpretation and validation.
134
+
We look forward to seeing the innovative discoveries our community achieves with this exciting collaboration.
title = "scverse × BioContextAI: Community Infrastructure for Agentic Analysis"
3
+
date = 2025-11-08T00:00:05+01:00
4
+
description = "scverse partners with BioContextAI to build biomedical MCPs."
5
+
author = "Malte Kuehl, Lukas Heumos"
6
+
draft = false
7
+
+++
8
+
9
+
# scverse × BioContextAI: Community Infrastructure for Agentic Analysis
10
+
11
+
We're excited to announce that we are partnering with [BioContextAI][biocontextai], a new open-source initiative for building agentic systems in biomedical research.
12
+
BioContextAI provides a community registry for Model Context Protocol (MCP) servers.
13
+
These are standardized tools that allow AI systems to access specialized databases and software.
14
+
This project was recently published as a [Nature Biotechnology correspondence][Nature Biotechnology correspondence] and we are actively starting to explore and contribute scverse MCP servers.
BioContextAI currently hosts over 40 community-built biomedical MCP servers with hundreds of tools, including the BioContextAI Knowledgebase MCP with access to resources like UniProt, Open Targets, and pathway databases.
21
+
There's a natural synergy here: while scverse packages handle computational analyses, these knowledge resources support the hypothesis generation and interpretation work that happens around those analyses.
22
+
By jointly building best practice scverse MCP servers, we hope to facilitate exploration of omics data and provide improved code generation for scverse ecosystem-enabled analyses, all while maintaining reproducibility and transparency.
23
+
This is early work and we are actively evaluating patterns for building MCP servers that integrate well with existing workflows and best practices.
24
+
25
+
## How to get involved
26
+
27
+
Check out the Registry at [biocontext.ai][biocontextai] to explore community-built MCP servers.
28
+
If you're interested in building new servers, try the [cookiecutter template][biocontextai-cookiecutter] to get started.
29
+
Join the conversation on the [BioContextAI channel][biocontextai-zulip] within the scverse Zulip to connect with other developers and researchers working in this space.
30
+
We're excited to see what the community builds together.
31
+
32
+
## Learn more
33
+
34
+
Learn more about BioContextAI in the [Nature Biotechnology correspondence][Nature Biotechnology correspondence] and on the [BioContextAI website][biocontextai].
0 commit comments