MultiPep: a hierarchical deep learning approach for multi-label classification of peptide bioactivities

Abstract

Peptide-based therapeutics are here to stay and will prosper in the future. A key step in identifying novel peptide-drugs is the determination of their bioactivities. Recent advances in peptidomics screening approaches hold promise as a strategy for identifying novel drug targets. However, these screenings typically generate an immense number of peptides and tools for ranking these peptides prior to planning functional studies are warranted. Whereas a couple of tools in the literature predict multiple classes, these are constructed using multiple binary classifiers. We here aimed to use an innovative deep learning approach to generate an improved peptide bioactivity classifier with capacity of distinguishing between multiple classes. We present MultiPep: a deep learning multi-label classifier that assigns peptides to zero or more of 20 bioactivity classes. We train and test MultiPep on data from several publically available databases. The same data are used for a hierarchical clustering, whose dendrogram shapes the architecture of MultiPep. We test a new loss function that combines a customized version of Matthews correlation coefficient with binary cross entropy (BCE), and show that this is better than using class-weighted BCE as loss function. Further, we show that MultiPep surpasses state-of-the-art peptide bioactivity classifiers and that it predicts known and novel bioactivities of FDA-approved therapeutic peptides. In conclusion, we present innovative machine learning techniques used to produce a peptide prediction tool to aid peptide-based therapy development and hypothesis generation.

Excretory-secretory products from the brown stomach worm, Teladorsagia circumcincta, exert antimicrobial activity in in vitro growth assays

“…A further AMP prediction tool, MultiPep ( https://github.com/scheelelab/MultiPep ), was applied to the identification of T. circumcincta EV and EV-depleted ESP sequences with putative antimicrobial properties. MultiPep assigns each query sequence to one of 20 peptide bioactivity classes, based on intrinsic amino acid patterns [ 33 ]. Then, within each bioactivity class, individual sequences are assigned a probability score of between 0 and 1, where 1 indicates the highest probability of a given query sequence correctly identified as belonging to the corresponding bioactivity class.…”

Identification of Antioxidative Peptides Derived from Arthrospira maxima in the Biorefinery Process after Extraction of C-Phycocyanin and Lipids

“…However, these processes are slow, cumbersome, and costly since they require a lot of laboratory work. A few models based on machine learning or deep learning have been used to predict the activities of peptides [ 37 , 38 , 39 ]. Herein, an online tool named Peptide Ranker (PepRank) was used to predict bioactive peptides resulting from LC-MS/MS [ 37 ].…”

Deep learning-based multi-functional therapeutic peptides prediction with a multi-label focal dice loss function

“…As shown in Table 4 , ETFC is significantly better than MPMABP, MLBP, SP-RNN, and PrMFTP on the metrics of Precision, Coverage, Accuracy, and Absolute true. Since there are eight shared classes of peptides between ETFC (21 classes of peptides) and MultiPep (20 classes of peptides) ( Grønning et al 2021 ). For a fair comparison, we compare ETFC and MultiPep ( https://agbg.shinyapps.io/MultiPep/ ) on another test set.…”

“…The rest 20% is the test set, which is applied for the model evaluation. Note that the evaluation of MultiPep ( Grønning et al 2021 ) is performed on another test set, which consists of the eight shared classes (ABP, ACP, ADP, AFP, AHP, ATP, AVP, and DPPIP) of peptides between ETFC and MultiPep.…”