Prediction of Type III Secreted Effectors Based on Word Embeddings for Protein Sequences

Fu, Xiuwei; Xiao, Yiqun; Yang, Yang

doi:10.1007/978-3-319-94968-0_28

Cited by 1 publication

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To avoid the above issue, each sequence can be represented by summing (Equation (9)) or averaging (Equation (10)) all word vectors in the sequence. In our last paper [9], we assess the performance of using both the sum vectors and mean vectors for representing protein sequences.

χ = \sum_{i} V_{ω_{i}}, i \in {1, 2, …, L - k + 1},

χ = \frac{true \sum_{i} V_{ω_{i}}}{L - normal1}, i \in {1, 2, …, L - k + 1},

…”

Section: Methodsmentioning

confidence: 99%

“…However, the identification and analysis of T3SEs are relatively slow due to the restriction of labor-intensive experimental methods, and a large proportion of T3SEs remain uncovered [7]. While computational methods have been demonstrated to be useful for revealing unknown T3SEs [6], a few machine learning-based predictors have been developed for the past decade [7][8][9]. Besides, as the known T3SE sequences accumulated rapidly, several large-scale T3SE databases have emerged, including T3SEdb [10], T3DB [11], etc.…”

Section: Introductionmentioning

confidence: 99%

“…Most of these studies adopted shallow learning methods to perform a binary classification (effector and non-effector). For example, although Fu et al utilized continous distributed features for representing amino acide sequences, they fed the features to support vector machines [9]. Some researchers enhanced the prediction performance by using a hierarchical classifier [13,14], i.e., the combination of homology search and machine learning, while this strategy has little advantage for hard targets, which have no homolog in the database of verified effectors.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

WEDeepT3: predicting type III secreted effectors based on word embedding and deep learning

Yang

2019

Quant. Biol.

Self Cite

View full text Add to dashboard Cite

Background: The type III secreted effectors (T3SEs) are one of the indispensable proteins in the growth and reproduction of Gram-negative bacteria. In particular, the pathogenesis of Gram-negative bacteria depends on the type III secreted effectors, and by injecting T3SEs into a host cell, the host cell's immunity can be destroyed. The high diversity of T3SE sequences and the lack of defined secretion signals make it difficult to identify and predict. Moreover, the related study of the pathological system associated with T3SE remains a hot topic in bioinformatics. Some computational tools have been developed to meet the growing demand for the recognition of T3SEs and the studies of type III secretion systems (T3SS). Although these tools can help biological experiments in certain procedures, there is still room for improvement, even for the current best model, as the existing methods adopt handdesigned feature and traditional machine learning methods. Methods: In this study, we propose a powerful predictor based on deep learning methods, called WEDeepT3. Our work consists mainly of three key steps. First, we train word embedding vectors for protein sequences in a large-scale amino acid sequence database. Second, we combine the word vectors with traditional features extracted from protein sequences, like PSSM, to construct a more comprehensive feature representation. Finally, we construct a deep neural network model in the prediction of type III secreted effectors. Results: The feature representation of WEDeepT3 consists of both word embedding and position-specific features. Working together with convolutional neural networks, the new model achieves superior performance to the state-ofthe-art methods, demonstrating the effectiveness of the new feature representation and the powerful learning ability of deep models. Conclusion: WEDeepT3 exploits both semantic information of k-mer fragments and evolutional information of protein sequences to accurately differentiate between T3SEs and non-T3SEs. WEDeepT3 is available at bcmi.sjtu. edu.cn/~yangyang/WEDeepT3.html.

show abstract