Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/bowang-lab/schash

https://github.com/bowang-lab/schash

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ✓
    Committers with academic emails
    1 of 3 committers (33.3%) from academic institutions
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (11.3%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: bowang-lab
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 1.46 MB
Statistics
  • Stars: 0
  • Watchers: 3
  • Forks: 2
  • Open Issues: 0
  • Releases: 0
Created over 4 years ago · Last pushed over 3 years ago
Metadata Files
Readme

README.md

scHash

With the increasing availability of large-scale single-cell omics datasets, supervised learning-based cell type annotation tools have positioned their unique advantage in improving annotation accuracy without prior biological information. However, due to the inherent high-dimensionality of single-cell omics data, existing methods lack the capacity or efficiency to handle atlas-level annotation tasks. To address these challenges, we hereby propose scHash, an accurate, efficient, and interpretable deep hashing-based method that can build multi-million reference database and annotate tens of thousands of cells. scHash is robust to batch effects between the query set and the reference database, which is commonly seen in real query tasks. We demonstrate scHash’s accurate and efficient cell type annotation performance as well as its interpretable functionalities on single cell omics datasets across multiple heterogeneous batches and on atlas-level dataset with 1.4M cells. The full paper will be up soon.

:heavyplussign: Method

scHash consists of three sequential steps:

(1) Cell anchor generation.

scHash generates $K$-bit hash code for each unique cell type in the reference database, which is referred as "cell anchors".

(2) Hash function training.

scHash trains a deep hash function that maps raw gene expression to $K$-bit binary hash code subject to weighted cell-anchor loss and quantization loss.

(3) Interpretable cell type annotation.

scHash can efficiently annotate large-scale scRNA-seq dataset and offer interpretability for its annotation through the metadata of most similar reference cells and saliency map.


:triangular_ruler: Requirements and Installation

  • Linux/Unix
  • Python 3.8

Installation.

bash $ pip install scHash

:heavyplussign: Tutorial

We offer the following tutorials for demonstration:

Owner

  • Name: WangLab @ U of T
  • Login: bowang-lab
  • Kind: organization
  • Location: 190 Elizabeth St, Toronto, ON M5G 2C4 Canada

BoWang's Lab at University of Toronto

GitHub Events

Total
Last Year

Committers

Last synced: over 1 year ago

All Time
  • Total Commits: 46
  • Total Committers: 3
  • Avg Commits per committer: 15.333
  • Development Distribution Score (DDS): 0.348
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Chong c****o@m****a 30
Lin Zhang 5****c 9
Rex Ma r****2@g****m 7
Committer Domains (Top 20 + Academic)
mail.utoronto.ca: 1

Issues and Pull Requests

Last synced: 12 months ago

All Time
  • Total issues: 0
  • Total pull requests: 3
  • Average time to close issues: N/A
  • Average time to close pull requests: less than a minute
  • Total issue authors: 0
  • Total pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 3
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
  • shaochon (3)
Top Labels
Issue Labels
Pull Request Labels

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 26 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 0
  • Total versions: 12
  • Total maintainers: 1
pypi.org: schash

scHash package for scRNA-seq data integration

  • Versions: 12
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 26 Last month
Rankings
Dependent packages count: 6.6%
Downloads: 12.7%
Forks count: 19.6%
Average: 21.7%
Dependent repos count: 30.6%
Stargazers count: 39.1%
Maintainers (1)
chong.shao
Last synced: 10 months ago

Dependencies

setup.py pypi
  • anndata >=0.8.0
  • numpy >=1.22.2
  • pandas >=1.1.0
  • pytorch-lightning >=1.6.5
  • scanpy >=1.7
  • scikit-learn >=1.0.2
  • scipy >=1.8.0
  • torch >=1.0.0