Advanced

PTPD : Predicting therapeutic peptides by deep learning and word2vec

Wu, Chuanyan LU ; Gao, Rui ; Zhang, Yusen and De Marinis, Yang LU (2019) In BMC Bioinformatics 20(1).
Abstract

Background In the search for therapeutic peptides for disease treatments, many efforts have been made to identify various functional peptides from large numbers of peptide sequence databases. In this paper, we propose an effective computational model that uses deep learning and word2vec to predict therapeutic peptides (PTPD).∗: Results Representation vectors of all k-mers were obtained through word2vec based on k-mer co-existence information. The original peptide sequences were then divided into k-mers using the windowing method. The peptide sequences were mapped to the input layer by the embedding vector obtained by word2vec. Three types of filters in the convolutional layers, as well as dropout and max-pooling operations, were applied... (More)

Background In the search for therapeutic peptides for disease treatments, many efforts have been made to identify various functional peptides from large numbers of peptide sequence databases. In this paper, we propose an effective computational model that uses deep learning and word2vec to predict therapeutic peptides (PTPD).∗: Results Representation vectors of all k-mers were obtained through word2vec based on k-mer co-existence information. The original peptide sequences were then divided into k-mers using the windowing method. The peptide sequences were mapped to the input layer by the embedding vector obtained by word2vec. Three types of filters in the convolutional layers, as well as dropout and max-pooling operations, were applied to construct feature maps. These feature maps were concatenated into a fully connected dense layer, and rectified linear units (ReLU) and dropout operations were included to avoid over-fitting of PTPD. The classification probabilities were generated by a sigmoid function. PTPD was then validated using two datasets: an independent anticancer peptide dataset and a virulent protein dataset, on which it achieved accuracies of 96% and 94%, respectively.∗: Conclusions PTPD identified novel therapeutic peptides efficiently, and it is suitable for application as a useful tool in therapeutic peptide design.

(Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Deep learning, Therapeutic peptide, Word2vec
in
BMC Bioinformatics
volume
20
issue
1
article number
456
publisher
BioMed Central
external identifiers
  • pmid:31492094
  • scopus:85071896624
ISSN
1471-2105
DOI
10.1186/s12859-019-3006-z
language
English
LU publication?
yes
id
f9daa232-30df-43bf-8ed9-aea3d584f3ba
date added to LUP
2019-09-16 14:34:43
date last changed
2019-11-25 09:34:25
@article{f9daa232-30df-43bf-8ed9-aea3d584f3ba,
  abstract     = {<p>Background In the search for therapeutic peptides for disease treatments, many efforts have been made to identify various functional peptides from large numbers of peptide sequence databases. In this paper, we propose an effective computational model that uses deep learning and word2vec to predict therapeutic peptides (PTPD).∗: Results Representation vectors of all k-mers were obtained through word2vec based on k-mer co-existence information. The original peptide sequences were then divided into k-mers using the windowing method. The peptide sequences were mapped to the input layer by the embedding vector obtained by word2vec. Three types of filters in the convolutional layers, as well as dropout and max-pooling operations, were applied to construct feature maps. These feature maps were concatenated into a fully connected dense layer, and rectified linear units (ReLU) and dropout operations were included to avoid over-fitting of PTPD. The classification probabilities were generated by a sigmoid function. PTPD was then validated using two datasets: an independent anticancer peptide dataset and a virulent protein dataset, on which it achieved accuracies of 96% and 94%, respectively.∗: Conclusions PTPD identified novel therapeutic peptides efficiently, and it is suitable for application as a useful tool in therapeutic peptide design.</p>},
  author       = {Wu, Chuanyan and Gao, Rui and Zhang, Yusen and De Marinis, Yang},
  issn         = {1471-2105},
  language     = {eng},
  month        = {09},
  number       = {1},
  publisher    = {BioMed Central},
  series       = {BMC Bioinformatics},
  title        = {PTPD : Predicting therapeutic peptides by deep learning and word2vec},
  url          = {http://dx.doi.org/10.1186/s12859-019-3006-z},
  doi          = {10.1186/s12859-019-3006-z},
  volume       = {20},
  year         = {2019},
}