Coder Social home page Coder Social logo

scmm's Introduction

scMM: Mixture-of-experts multimodal deep generative model for single-cell multiomics analysis

figure

scMM is a novel deep generative model-based framework for the extraction of interpretable joint representations and cross-modal generation for single-cell multiomics data (e.g. transcriptome & chromatin accessibility, transcriptome & surface proteins). It is based on a mixture-of-experts multimodal deep generative model and achieves end-to-end learning by modeling raw count data in each modality based on different probability distributions.

colab_tutorial.ipynb shows how to run scMM using GPU on Google Colab. For the tutorial, we use toy data generated from CITE-seq (single-cell transctiptome & surface protein) data for bone marrow mononuclear cell (BMNC) including randomely subsampled 15,000 cells (Stuart and Butler et. al., 2018). Most varaible 5000 genes were selected for transcriptome data.

RNA and protein count matrix should be stored in folder named RNA-seq and CITE-seq accomapnied with feature information stored in gene.tsv and protein.tsv, respectively. Also, single-cell barcode stored in barcode.tsv should be included. When running on chromatin accessibility data, name folder as ATAC-seq and feature file as peak.tsv. For example, folder structure looks like:

data/BMNC
     |---RNA-seq
     |   |---RNA_count.mtx
     |   |---gene.tsv
     |   |---barcode.tsv
     |---CITE-seq
         |---Protein_count.mtx
         |---protein.tsv
         |---barcode.tsv

Tutorial on downstream analysisfor scMM outputs can be found at R/tutorial.R. Vignette is available here. Codes were adopted from the MMVAE repository.

Check out our preprint for more details on the methods.

scmm's People

Contributors

kodaim1115 avatar

Stargazers

YuanyuanChen avatar Myoung Hoon Lee avatar 任佳旭 avatar Fan Zhang avatar Clayton Rabideau avatar Niklas Binder avatar Chao Gao avatar Kojima Yasuhiro avatar  avatar UniversalNature avatar Wu Xiaokang avatar Hongru Hu avatar Satoshi Nomura avatar Mikhael D. Manurung avatar Hiram Coria avatar Pedro F. Ferreira avatar Kai Cao avatar

Watchers

James Cloos avatar  avatar

scmm's Issues

Error in scRNA+scATAC analysis

Hi,

Thank you for your great tools for single cell multi-omics analysis. I successfully ran the cite-seq demo but failed to ran our scRNA+scATAC data with following error report:

截屏2022-05-23 下午3 08 45

The input files of our scRNA+scATAC data are formatted same as cite-seq demo data. Could you help us solve the error above?

Thanks!
Shaliu

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.