UMAP-DBP: An Improved DNA-Binding Proteins Prediction Method Based on Uniform Manifold Approximation and Projection

• Published in: The Protein Journal Vol. 40; no. 4; pp. 562 - 575
• Main Authors: Wang, Jinyue, Zhang, Shengli, Qiao, Huijuan, Wang, Jiesheng
• Format: Journal Article
• Language: English
• Published: New York Springer US 01-08-2021; Springer; Springer Nature B.V
• Subjects: Algorithms; Amino acid composition; Amino acid sequence; Amino acids; Animal Anatomy; Approximation; Binding; Biochemistry; Bioorganic Chemistry; Chemistry; Chemistry and Materials Science; Computational Biology; Computer applications; Deep learning; Deoxyribonucleic acid; DNA; DNA binding proteins; DNA-binding protein; DNA-Binding Proteins - chemistry; Feature extraction; Forecasting; Histology; Learning algorithms; Machine learning; Manifolds; Mathematical analysis; Methods; Morphology; Organic Chemistry; Predictive Value of Tests; Protein binding; Protein Conformation; Proteins; Software; Feature importance score; Uniform manifold approximation and projection; DNA-binding proteins; Adaboost
• ISSN: 1572-3887; 1573-4943; 1875-8355
• DOI: 10.1007/s10930-021-10011-y

DNA-binding proteins play a vital role in cellular processes. It is an extremely urgent to develop a high-throughput method for efficiently identifying DNA-binding proteins. According to the current research situation, some methods in machine learning and deep learning show excellent computational speed and accuracy, which are worthy of application. In this work, a novel predictor was proposed to predict DNA binding proteins called UMAP-DBP. Firstly, the feature extraction of primary protein sequence was realized based on physicochemical distance transformation, Profile-based auto-cross covariance and General series correlation pseudo amino acid composition. Secondly, uniform manifold approximation and projection (UMAP) and feature importance score methods were used for feature selection; there is a progressive relationship between them. Finally, the Adaboost operation engine with jackknife test were adopted for predicting DNA-binding proteins. For the jackknife test on the BP1075 and BP594, we obtained an overall accuracy of 82.97% and 82.14%, Cohen's kappa (CK) of 0.66 and 0.64, respectively. The results illustrate that a feasible method has been developed for predicting DNA-binding proteins by UMAP and Adaboost. This is the first study in which UMAP has been successfully applied to identify DNA-binding proteins. All the datasets and codes are accessible at
https://github.com/Wang-Jinyue/UMAP-DBP
.