ScGPT

Visit Tool

scGPT is an open-source AI tool that provides a foundation model for single-cell multi-omics using generative AI. It enables researchers to analyze single-cell data and develop generative models for biological insights.

Claim this tool

No Views Yet

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is scGPT?

scGPT is an open-source codebase designed to build a foundation model for single-cell multi-omics data using generative AI. It offers pre-trained models for various human cell types and organs, including whole-human, brain, blood, heart, lung, kidney, and pan-cancer. The tool supports zero-shot applications for cell embedding tasks and features efficient reference mapping for millions of cells. Researchers can install scGPT via pip and utilize online apps for reference mapping, cell annotation, and Gene Regulatory Network inference. It is ideal for bioinformaticians and computational biologists working with complex single-cell datasets.

Best used for

Ideal for bioinformaticians and researchers who need to analyze single-cell multi-omics data, develop generative AI models for biological insights, and perform efficient reference mapping. Especially valuable for those working with large-scale human cell datasets and requiring pre-trained models for various applications.

Common actions

analyze single-cell data

develop generative models

map cell references

annotate cell types

infer gene networks

"AI Agents"face swappinggithub copilotopen-sourcedeepfakeautomated workflowlow-code/no-codeworkflowscollaboration

Capabilities

Key features

Single-cell multi-omics foundation model
Generative AI for single-cell data
Pre-trained scGPT checkpoints
Efficient reference mapping
Zero-shot cell embedding tasks
Online interactive apps
Python package installation

Target Audience

professor

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What kind of data can scGPT process?

scGPT is designed to process single-cell multi-omics data. It focuses on building a foundation model for this type of complex biological data, enabling generative AI applications and advanced analysis for researchers in the field.

Are there pre-trained models available with scGPT?

Yes, scGPT provides several pre-trained checkpoints, including a recommended whole-human model and organ-specific models for brain, blood, heart, lung, and kidney cells, as well as a pan-cancer model. These models can be used for various applications.

Can I use scGPT without extensive coding knowledge?

While scGPT is a codebase primarily for developers and researchers, it also offers online interactive apps for tasks like reference mapping, cell annotation, and GRN inference. These apps allow users to get started with a browser, reducing the need for direct coding.

What are the system requirements for installing scGPT?

scGPT works with Python >= 3.7.13 and R >= 3.6.1. It can be installed via pip. For optimal performance, especially with flash-attention, specific GPU and CUDA versions (e.g., CUDA 11.7) might be required, as detailed in the documentation.

Trending

Subcategories trending in Research & Education

Study Assistants Knowledge Management Course Creation Scientific Computing Summarization Language Learning

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce