Back

Regular Architecture (RegArch): A standard expression language for describing protein architectures

Ortega, D. R.; Jensen, G. J.

2019-06-22 bioinformatics
10.1101/679910 bioRxiv
Show abstract

Domain architecture - the arrangement of features in a protein - exhibits syntactic patterns similar to the grammar of a language. This feature enables pattern mining for protein function prediction, comparative genomics, and studies of molecular evolution and complexity. To facilitate such work, here we propose Regular Architecture (RegArch), an expression language to describe syntactic patterns in protein architectures. Like the well-known Regular Expressions for text, RegArchs codify positional and non-positional patterns of elements into nested JSON objects. We describe the standard and provide a reference implementation in JavaScript to parse RegArchs and match annotated proteins.

Matching journals

The top 2 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.