ALS

The software tool ALS is a deep learning-based approach for classifying amyotrophic lateral sclerosis (ALS) patients versus healthy individuals using genetic data from the Dutch cohort of the Project MinE dataset. The tool employs a two-step approach:

1. Identifying promoter regions likely associated with ALS using a deep convolutional neural network (CNN).

2. A CNN calculates Individuals based on their genotype in the selected genomic regions.

The network architecture accounts for the structure of genome data by applying convolution only to parts of the data where it makes sense from a genomics perspective.

Topic

Genotype and phenotype;Machine learning;Molecular interactions, pathways and networks

Detail

  • Operation: Essential dynamics;Imputation;Genotyping

  • Software interface: Command-line user interface

  • Language: Python

  • License: Not stated

  • Cost: Free of charge

  • Version name: -

  • Credit: Netherlands Organization for Scientific Research (NWO).

  • Input: -

  • Output: -

  • Contact: Alexander Schönhuth a.schoenhuth@cwi.nl

  • Collection: -

  • Maturity: -

Publications

  • Using the structure of genome data in the design of deep neural networks for predicting amyotrophic lateral sclerosis from genotype.
  • Yin B, et al. Using the structure of genome data in the design of deep neural networks for predicting amyotrophic lateral sclerosis from genotype. Using the structure of genome data in the design of deep neural networks for predicting amyotrophic lateral sclerosis from genotype. 2019; 35:i538-i547. doi: 10.1093/bioinformatics/btz369
  • https://doi.org/10.1093/BIOINFORMATICS/BTZ369
  • PMID: 31510706
  • PMC: PMC6612814

Download and documentation

< Back to DB search