syang11 / ProbeRating

ProbeRating: A recommender system to infer binding profiles for nucleic acid-binding proteins

ProbeRating: A recommender system to infer binding profiles for nucleic acid-binding proteins

Welcome!

This repo stores codes and data for the paper:

Shu Yang, Xiaoxi Liu, Raymond Ng. ProbeRating: A recommender system to infer binding profiles for nucleic acid-binding proteins. Bioinformatics. 2020.

It contains:

1. Codes and instructions for the biological sequence embedding package FastBioseq.

2. Codes and instructions for the neural network based recommender system used in ProbeRating

• The data used in the paper were downloaded from public databases and published papers shown below. The supplements folder here contains the protein IDs of the two datasets RRM162 and Homeo215 in this study.
  • CISBP database http://cisbp.ccbr.utoronto.ca/: for Homeo8k dataset
  • CISBP-RNA database http://cisbp-rna.ccbr.utoronto.ca/, and its associated paper http://hugheslab.ccbr.utoronto.ca/supplementary-data/RNAcompete_eukarya/: for RRM162 and RRM3k dataset
  • Affinity Regression paper https://www.nature.com/articles/nbt.3343: for RRM162 and Homeo215 datasets
  • Uniprot database https://www.uniprot.org/: for Uniprot400k dataset