RF‐SVM: Identification ofDNA‐binding proteins based on comprehensive feature representation methods and support vector machine

Abstract

Protein-DNA interactions play an important role in biological progress, such as DNA replication, repair, and modification processes. In order to have a better understanding of its functions, the one of the most important steps is the identification of DNAbinding proteins. We propose a DNA-binding protein predictor, namely, RF-SVM, which contains four types features, that is, pseudo amino acid composition (PseAAC), amino acid distribution (AAD), adjacent amino acid composition frequency (ACF) and Local-DPP. Random Forest algorithm is utilized for selecting top 174 features, which are established the predictor model with the support vector machine (SVM) on training dataset UniSwiss-Tr. Finally, RF-SVM method is compared with other existing methods on test dataset UniSwiss-Tst. The experimental results demonstrated that RF-SVM has accuracy of 84.25%. Meanwhile, we discover that the physicochemical properties of amino acids for OOBM770101(H), CIDH920104(H), MIYS990104(H), NISK860101(H), VINM940103(H), and SNEP660101(A) have contribution to predict DNA-binding proteins. The main code and datasets can gain in https://github.com/ NiJianWei996/RF-SVM.

LGC-DBP: the method of DNA-binding protein identification based on PSSM and deep learning

“…In this section, to further illustrate the effectiveness of the proposed LGC-DBP, we will compare it with state-of-the-art methods. On the UniSwissTst test dataset, we compared our model with TargetDBP, iDNAProt-ES Chowdhury et al (2017) , TargetDBP+, MsDBP Du et al (2019) , RF-SVM Zhang et al (2022) , TPSO-DBP Sikander et al (2023) , and DBPboost. All the methods mentioned in this study utilize UniSwiss-Tr as the training dataset and Uniswiss-test as the independent test set.…”

“…, TargetDBP+, MsDBPDu et al (2019), RF-SVMZhang et al (2022),TPSO-DBP Sikander et al (2023), and DBPboost. All the methods mentioned in this study utilize UniSwiss-Tr as the training dataset and Uniswiss-test as the independent test set.…”

HybridDBRpred: improved sequence-based prediction of DNA-binding amino acids using annotations from structured complexes and disordered proteins

“…The protein-level methods predict whether a target protein sequence interacts with DNA. A few examples of recently released tools that predict DNA-binding proteins include StackDPPred ( 17 ), iDRBP_MMC ( 18 ), TargetDBP ( 19 , 20 ), DeepTFactor ( 21 ), RF-SVM ( 22 ), CNN-Pred ( 23 ) and TPSO-DBP ( 24 ). We focus on the residue-level tools that identify DNA binding residues (DBRs) in a given protein sequence since they provide more detailed information compared to the protein-level approaches.…”