omicverse/omicverse

A python library for multi omics included bulk, single cell and spatial RNA-seq analysis.

What it solves

OmicVerse is a unified Python framework designed to bridge the gap between bulk RNA-seq, single-cell, and spatial transcriptomics. It provides a comprehensive ecosystem for multi-omics analysis, integrating various tools for downstream visualization, model-based analysis, and AI-assisted workflows to deepen biological insights.

How it works

The project is structured as a broad analysis platform rather than a single method. It leverages core data structures like pandas, anndata, numpy, and mudata to implement its infrastructure. The platform is divided into specialized modules:

  • Core Analysis: Integrates a vast array of published transcriptomics tools (e.g., Scanpy, scVI, Geneformer).
  • J.A.R.V.I.S.: An AI-assisted workflow system that includes an ov.Agent for direct interaction with analysis tools, an MCP (Model Context Protocol) server to expose tools to AI assistants like Claude Code, and a Telegram-based chat system.
  • ov.synbio: A synthetic biology stack for genome-scale metabolic modeling, protein/enzyme design (using ESMFold, ProteinMPNN), and DNA design.
  • ov.mol: A molecular dynamics stack that chains docking (AutoDock Vina) and GPU-accelerated molecular dynamics (OpenMM) to calculate binding free energy.

Who it’s for

It is intended for bioinformaticians, computational biologists, and researchers in synthetic biology and molecular dynamics who need a unified toolset for multi-omics data analysis and AI-integrated biological research.

Highlights

  • Unified Multi-Omics: Combines bulk, single-cell, and spatial RNA-seq analysis in one package.
  • AI-Assisted Workflows: Features an agentic system (J.A.R.V.I.S.) and MCP server for AI-driven analysis.
  • AI-Driven Protein Design: Includes tools for structure prediction and inverse design via ESMFold and ProteinMPNN.
  • Integrated Molecular Dynamics: Supports a full pipeline from 3D structure to GPU-based molecular dynamics simulations.

Related

  • Project
    RoboVerseOrg/RoboVerse

    A unified platform, dataset, and benchmark designed to enable scalable and generalizable robot learning by integrating multiple simulation frameworks and datasets.

  • Project
    chainbase-labs/manuscript-core

    A protocol and framework for simplifying omnichain data access and processing, enabling developers to unify blockchain data from multiple sources into a a single pipeline.

  • Project
    scverse/spatialdata

    An open and universal data framework, schema, and serialization format designed for the processing and analysis of uni- and multi-modal spatial omics datasets.

  • Project
    transformerlab/transformerlab-app

    An open-source machine learning platform that unifies training, fine-tuning, inference, and evaluation into a single interface for individuals and research labs.

  • Project
    yakhyo/uniface

    UniFace is a Python library that unifies 15 face‑analysis tasks—detection, landmarks, 3‑D mesh, parsing, matting, gaze, head pose, demographics, emotion, quality, anti‑spoofing, recognition, anonymisation, and FAISS‑based similarity—into a single, easy‑to‑install package (CPU, Apple Silicon, or CUDA). It provides a consistent API, auto‑downloads verified model weights, and includes extensive docs, notebooks, and a community Discord.