A Method for Identifying Vesicle Transport Proteins Based on LibSVM and MRMD

Abstract

With the development of computer technology, many machine learning algorithms have been applied to the field of biology, forming the discipline of bioinformatics. Protein function prediction is a classic research topic in this subject area. Though many scholars have made achievements in identifying protein by different algorithms, they often extract a large number of feature types and use very complex classification methods to obtain little improvement in the classification effect, and this process is very time-consuming. In this research, we attempt to utilize as few features as possible to classify vesicular transportation proteins and to simultaneously obtain a comparative satisfactory classification result. We adopt CTDC which is a submethod of the method of composition, transition, and distribution (CTD) to extract only 39 features from each sequence, and LibSVM is used as the classification method. We use the SMOTE method to deal with the problem of dataset imbalance. There are 11619 protein sequences in our dataset. We selected 4428 sequences to train our classification model and selected other 1832 sequences from our dataset to test the classification effect and finally achieved an accuracy of 71.77%. After dimension reduction by MRMD, the accuracy is 72.16%.

Identification of cyclin protein using gradient boost decision tree algorithm

“…AAC calculates the frequency of single type of amino acids in a protein sequence [16] , [45] , [46] , [47] , [48] , [49] , [50] . The frequencies of 20 residues can be calculated as where is the number of the p -th residue in a protein sequence with the length of N residues .…”

FSL-Kla: A few-shot learning-based multi-feature hybrid system for lactylation site prediction

“…As the first part of CTD method, CTDC was used to generate 39 features from each protein or peptide referring to the ratio of the number of single amino acid with specific properties [31] , [32] . The formulation is expressed as follows: where N(r) is the number of amino acids of type r in the encoded sequence and N is the length of the sequence.…”

Application of Multilayer Network Models in Bioinformatics

“…Corresponding network structures for different biological data and specific subjects can also be designed to analyse specific biological systems ( Zeng et al, 2016 ; Jiang et al, 2017 ; Liu et al, 2017 ). Currently, at the subcellular level, these networks mainly include gene regulatory networks ( Wang et al, 2010 ; Ding et al, 2011 ; Jiang et al, 2014 ; Cheng et al, 2019 ; Konda et al, 2019 ; Liu L. et al, 2019 ; Mortezaeefar et al, 2019 ; Hong et al, 2020 ), protein functional networks ( Guo et al, 2011 , 2013 , 2014 ; Sikandar et al, 2019 ; Tao et al, 2020 ; Liu et al, 2021 ), metabolic regulatory networks ( Jin et al, 2020 ), and drug targeting networks ( Wei et al, 2014 ; Ding et al, 2017 , 2019 , 2020a , b ; Jin Q. et al, 2019 ; Jin S. et al, 2019 ; Srivastava et al, 2019 ; Zhao et al, 2019 ; Zeng et al, 2020 ).…”