PredPRBA: Prediction of Protein-RNA Binding Affinity Using Gradient Boosted Regression Trees

Abstract

Protein-RNA interactions play essential roles in many biological aspects. Quantifying the binding affinity of protein-RNA complexes is helpful to the understanding of protein-RNA recognition mechanisms and identification of strong binding partners. Due to experimentally measured protein-RNA binding affinity data available is still limited to date, there is a pressing demand for accurate and reliable computational approaches. In this paper, we propose a computational approach, PredPRBA, which can effectively predict protein-RNA binding affinity using gradient boosted regression trees. We build a dataset of protein-RNA binding affinity that includes 103 protein-RNA complex structures manually collected from related literature. Then, we generate 37 kinds of sequence and structural features and explore the relationship between the features and protein-RNA binding affinity. We find that the binding affinity mainly depends on the structure of RNA molecules. According to the type of RNA associated with proteins composed of the protein-RNA complex, we split the 103 protein-RNA complexes into six categories. For each category, we build a gradient boosted regression tree (GBRT) model based on the generated features. We perform a comprehensive evaluation for the proposed method on the binding affinity dataset using leave-one-out cross-validation. We show that PredPRBA achieves correlations ranging from 0.723 to 0.897 among six categories, which is significantly better than other typical regression methods and the pioneer protein-RNA binding affinity predictor SPOT-Seq-RNA. In addition, a user-friendly web server has been developed to predict the binding affinity of protein-RNA complexes. The PredPRBA webserver is freely available at .

LPI-deepGBDT: a multiple-layer deep framework based on gradient boosting decision trees for lncRNA–protein interaction identification

“…GBDT can generate highly robust, interpretable and competitive classification procedures, especially for exploiting less than clean data [ 29 , 40 , 41 ]. For an lncRNA–protein pair , an estimator denotes an approximate function response to the label , the GBDT model iteratively builds K different individual decision tree using the training data .…”

“…Fan and Zhang [ 28 ] explored a stacked ensemble-based LPI classification model via logistical regression (LPI-BLS). Deng et al [ 29 ] proposed a gradient boosted regression tree for finding possible LPIs. Wekesa et al [ 30 ] designed a categorical boosting-based LPI discovery framework (LPI-CatBoost).…”

Identification of Biomarkers for Cervical Cancer Radiotherapy Resistance Based on RNA Sequencing Data

“…Random forest is a generally acknowledged ensemble classifier for machine learning and can exploit large data repositories for the analysis of risk predictors and their intimate interactions and advancement risk prediction capability ( Yang et al, 2021 ). It was used in evaluating cervical cancer candidate genes as the main objects of our research ( Nunn et al, 2012 ; Wang et al, 2018 ; Deng et al, 2019b ; Ru et al, 2019 ; Lv et al, 2020 ; Yang et al, 2020 ). In the random forest setting, we divided the expression profile data of 103 genes according to the properties of the samples and considered the samples before radiotherapy as “good” and the samples during radiotherapy “poor,” respectively.…”

iPhoPred: A Predictor for Identifying Phosphorylation Sites in Human Protein

“…In this study, we incorporated ANOVA with incremental feature selection (IFS) [54]- [56] to pick out the optimal feature subset. The principle of ANOVA is to calculate the score (F value) of each feature in feature subset, which indicates the contribution of each feature to classification.…”