Identification of SH2 domain-containing proteins and motifs prediction by a deep learning method

Wu, Dong; Fang, Xing; Luan, Kuan; Xu, Qijin; Lin, Shiqi; Sun, Songlin; Yang, Jing; Dong, Bowen; Manavalan, Balachandran; Liao, Zhining

doi:10.1016/j.compbiomed.2023.107065

Cited by 3 publications

(1 citation statement)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, several feature vector-based approaches have been reported, including APPEL, AllerTOP, AllergenFP, AllerCatPro, ProAll-D (Cui et al, 2007;Dimitrov et al, 2013;Dimitrov et al, 2014;Nguyen et al, 2022;Shanthappa and Kumar, 2022). In general, they take sequence-derived compositional, evolutionary, structural and physicochemical information into consideration and achieve allergenic protein classification by using machine learning or deep learning models (Wang et al, 2021;Ao et al, 2022;Wu et al, 2023). For example, random forest (RF), support vector machine (SVM), decision tree (DT), k-nearest neighbors (KNN) and multilayer perceptron (MLP) were employed to establish AlgPred 2.0 on the basis of composition/evolutionary information-based features (Zhang et al, 2007).…”

Section: Introductionmentioning

confidence: 99%

Computational prediction of allergenic proteins based on multi-feature fusion

Liu,

Yang,

Liu

et al. 2023

Front. Genet.

View full text Add to dashboard Cite

Allergy is an autoimmune disorder described as an undesirable response of the immune system to typically innocuous substance in the environment. Studies have shown that the ability of proteins to trigger allergic reactions in susceptible individuals can be evaluated by bioinformatics tools. However, developing computational methods to accurately identify new allergenic proteins remains a vital challenge. This work aims to propose a machine learning model based on multi-feature fusion for predicting allergenic proteins efficiently. Firstly, we prepared a benchmark dataset of allergenic and non-allergenic protein sequences and pretested on it with a machine-learning platform. Then, three preferable feature extraction methods, including amino acid composition (AAC), dipeptide composition (DPC) and composition of k-spaced amino acid pairs (CKSAAP) were chosen to extract protein sequence features. Subsequently, these features were fused and optimized by Pearson correlation coefficient (PCC) and principal component analysis (PCA). Finally, the most representative features were picked out to build the optimal predictor based on random forest (RF) algorithm. Performance evaluation results via 5-fold cross-validation showed that the final model, called iAller (https://github.com/laihongyan/iAller), could precisely distinguish allergenic proteins from non-allergenic proteins. The prediction accuracy and AUC value for validation dataset achieved 91.4% and 0.97%, respectively. This model will provide guide for users to identify more allergenic proteins.

show abstract