Using support vector machine combined with auto covariance to predict protein–protein interactions from protein sequences

By Yanzhi Guo, Lezheng Yu, Z. Wen, Meng-long Li. Nucleic Acids Research, 2008

672 citations recorded by the source corpus.

Compared to the available protein sequences of different organisms, the number of revealed protein–protein interactions (PPIs) is still very limited. So many computational methods have been developed to facilitate the identification of novel PPIs. However, the methods only using the information of protein sequences are more universal than those that depend on some additional information or predictions about the proteins. In this article, a sequence-based method is proposed by combining a new feature representation using auto covariance (AC) and support vector machine (SVM). AC accounts for the interactions between residues a certain distance apart in the sequence, so this method adequately takes the neighbouring effect into account. When performed on the PPI data of yeast Saccharomyces cerevisiae, the method achieved a very promising prediction result. An independent data set of 11 474 yeast PPIs was used to evaluate this prediction model and the prediction accuracy is 88.09%. The performance of this method is superior to those of the existing sequence-based methods, so it can be a useful supplementary tool for future proteomics studies. The prediction software and all data sets used in this article are freely available at http://www.scucic.cn/Predict_PPI/index.htm.

Subfields: Molecular Biology

View Paper: https://www.semanticscholar.org/paper/c96dd175ac5dcccca99c7ef31e2aac4c69f2c925

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

1. Bin Liu
2. Longyun Fang
3. Junjie Chen
4. Xiaolong Wang
5. Fule Liu
6. Jianfeng Pei
7. Luhua Lai
8. Haijun Lv

Citations in the corpus

• Applications of Support Vector Machine (SVM) Learning in Cancer Genomics. (2018, methodology): “In a study conducted by Guo et al. (68), SVM model derived from the primary sequences of proteins was used for predicting PPIs.”
• A Survey on ensemble learning under the era of deep learning (2021, methodology): “For the prediction of protein-protein interactions, You et al. (You et al. 2013) employed auto covariance (AC) (Guo et al. 2008), conjoint triad (CT) (Shen et al. 2007), local descriptor (LD) (Davies et al. 2008) and Moran autocorrelation (MA) (Xia et al. 2009) to extract features from protein…”
• Pse-in-One: a web server for generating various modes of pseudo components of DNA, RNA, and protein sequences (2015, background): “Nucleic acid composition (1) Basic kmer (Kmer) (18) Autocorrelation (2) Dinucleotide-based auto covariance (DAC) (16,21) (3) Dinucleotide-based cross covariance (DCC) (16,21)”
• Sequence-based prediction of protein protein interaction using a deep-learning algorithm (2017, methodology): “Several other methods, such as autocovariance (AC) [7] and amino acid index distribution [8] were developed to extract features such as physical chemical properties, frequencies, and locations of amino acids to represent a protein sequence.”