The Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) is the largest public repository of gene expression and microarray data available online. Providing good python tooling to build DeepChem style deep learning models on this data would be very useful.
The Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) is the largest public repository of gene expression and microarray data available online. Providing good python tooling to build DeepChem style deep learning models on this data would be very useful.
GEOParse is a good library that provides access to download this data (https://geoparse.readthedocs.io/en/latest/). Looks to be actively maintained.