scDLC

'scDLC' is a deep learning classifier designed for the analysis of large-sample single-cell RNA sequencing (scRNA-seq) data in the context of disease diagnosis. It addresses the limitations of existing statistical methods that often struggle with large sample sizes and violated distribution assumptions.
Key features and findings of scDLC include:
1. Utilizes deep learning technology based on Long Short-Term Memory Recurrent Neural Networks (LSTMs).
2. Doesn't require prior knowledge about the data distribution, making it highly versatile.
3. Accounts for dependencies among prominent feature genes through the LSTM model.
4. LSTMs are well-suited for learning long-term dependencies within sequential data, a characteristic present in gene expression profiles.

Topic

RNA-Seq;Machine learning;RNA;Gene expression;RNA immunoprecipitation

Detail

  • Operation: Standardisation and normalisation;Gene expression profiling;Visualisation

  • Software interface: Command-line user interface

  • Language: Python,R

  • License: Not stated

  • Cost: Free

  • Version name: -

  • Credit: The National Natural Science Foundation of China, Natural Science Foundation of Guangdong Province of China, Project of Educational Commission of Guangdong Province of China, the General Research Fund, the Initiation Grant for Faculty Niche Research Areas of Hong Kong Baptist University.

  • Input: -

  • Output: -

  • Contact: Niansheng Tang nstang@ynu.edu.cn

  • Collection: -

  • Maturity: -

Publications

  • scDLC: a deep learning framework to classify large sample single-cell RNA-seq data.
  • Zhou Y, et al. scDLC: a deep learning framework to classify large sample single-cell RNA-seq data. scDLC: a deep learning framework to classify large sample single-cell RNA-seq data. 2022; 23:504. doi: 10.1186/s12864-022-08715-1
  • https://doi.org/10.1186/S12864-022-08715-1
  • PMID: 35831808
  • PMC: PMC9281153

Download and documentation

< Back to DB search