PP1

How can sequencing mistakes challenge per-protein predictions?

Sequencing mistakes challenge per-protein predictions because a prediction tool can only be as good as the data on which it was trained on. If those data contains sequencing mistakes then more prediction mistakes will be done by the tool due to misleading training data.

The transformer is a deep learning method to produce a contextual embedding of amino acids in the protein sequence. By using the masked language model objective, it is able to build a context around each position and learns to ‘attend’ or ‘focus’ on amino acids and peptides that are relevant in the given context. These language models have been found to encode contact maps, taxonomy and biophysical characteristics in their distributed representations