Back

Prediction of protein functions using Semantic Based Regularization

Dimitri, G. M.

2024-06-25 bioinformatics
10.1101/2024.06.20.599881 bioRxiv
Show abstract

In this work, done in collaboration with Prof. Michelangelo Diligenti (department of Engineering and Mathematics, University of Siena) we present the use of Semantic Based Regularization Kernel based machine learning method to predict protein function. We initially build the protein functions ontology, given an initial list of proteins. We subsequently performed predictions, both at individual and at joint levels of functions, introducing and adding to the learning procedure ad-hoc first order logic rules. Experiments showed promising performances in using logic rules within the learning process for the sake of bioinformatics applications.

Matching journals

The top 6 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.