PTPD: Predicting therapeutic peptides by deep learning and word2vec

Research output: Contribution to journalArticle

Standard

PTPD : Predicting therapeutic peptides by deep learning and word2vec. / Wu, Chuanyan; Gao, Rui; Zhang, Yusen; De Marinis, Yang.

In: BMC Bioinformatics, Vol. 20, No. 1, 456, 06.09.2019.

Research output: Contribution to journalArticle

Harvard

APA

CBE

MLA

Vancouver

Author

RIS

TY - JOUR

T1 - PTPD

T2 - Predicting therapeutic peptides by deep learning and word2vec

AU - Wu, Chuanyan

AU - Gao, Rui

AU - Zhang, Yusen

AU - De Marinis, Yang

PY - 2019/9/6

Y1 - 2019/9/6

N2 - 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.

AB - 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.

KW - Deep learning

KW - Therapeutic peptide

KW - Word2vec

U2 - 10.1186/s12859-019-3006-z

DO - 10.1186/s12859-019-3006-z

M3 - Article

C2 - 31492094

AN - SCOPUS:85071896624

VL - 20

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

IS - 1

M1 - 456

ER -