ABSTRACT
In this paper, we present peptide-pair encoding (PPE), a general-purpose probabilistic segmentation of protein sequences into commonly occurring variable-length sub-sequences. The idea of PPE segmentation is inspired by the byte-pair encoding (BPE) text compression algorithm, which has recently gained popularity in subword neural machine translation. We modify this algorithm by adding a sampling framework allowing for multiple ways of segmenting a sequence. PPE can be inferred over a large set of protein sequences (Swiss-Prot) and then applied to a set of unseen sequences. This representation can be widely used as the input to any downstream machine learning tasks in protein bioinformatics. In particular, here, we introduce this representation through protein motif mining and protein sequence embedding. (i) DiMotif: we present DiMotif as an alignment-free discriminative motif miner and evaluate the method for finding protein motifs in different settings. The significant motifs extracted could reliably detect the integrins, integrin-binding, and biofilm formation-related proteins on a reserved set of sequences with high F1 scores. In addition, DiMotif could detect experimentally verified motifs related to nuclear localization signals. (ii) ProtVecX: we extend k-mer based protein vector (ProtVec) embedding to variable-length protein embedding using PPE sub-sequences. We show that the new method of embedding can marginally outperform ProtVec in enzyme prediction as well as toxin prediction tasks. In addition, we conclude that the embedding are beneficial in protein classification tasks when they are combined with raw k-mer features.
Availability Implementations of our method will be available under the Apache 2 licence at http://llp.berkeley.edu/dimotif and http://llp.berkeley.edu/protvecx.