Dataset Information

Predicting phosphorylation sites using machine learning by integrating the sequence, structure, and functional information of proteins.

ABSTRACT:

Background

Post-translational modification (PTM) is a biological process that alters proteins and is therefore involved in the regulation of various cellular activities and pathogenesis. Protein phosphorylation is an essential process and one of the most-studied PTMs: it occurs when a phosphate group is added to serine (Ser, S), threonine (Thr, T), or tyrosine (Tyr, Y) residue. Dysregulation of protein phosphorylation can lead to various diseases-most commonly neurological disorders, Alzheimer's disease, and Parkinson's disease-thus necessitating the prediction of S/T/Y residues that can be phosphorylated in an uncharacterized amino acid sequence. Despite a surplus of sequencing data, current experimental methods of PTM prediction are time-consuming, costly, and error-prone, so a number of computational methods have been proposed to replace them. However, phosphorylation prediction remains limited, owing to substrate specificity, performance, and the diversity of its features.

Methods

In the present study we propose machine-learning-based predictors that use the physicochemical, sequence, structural, and functional information of proteins to classify S/T/Y phosphorylation sites. Rigorous feature selection, the minimum redundancy/maximum relevance approach, and the symmetrical uncertainty method were employed to extract the most informative features to train the models.

Results

The RF and SVM models generated using diverse feature types in the present study were highly accurate as is evident from good values for different statistical measures. Moreover, independent test sets and benchmark validations indicated that the proposed method clearly outperformed the existing methods, demonstrating its ability to accurately predict protein phosphorylation.

Conclusions

The results obtained in the present work indicate that the proposed computational methodology can be effectively used for predicting putative phosphorylation sites further facilitating discovery of various biological processes mechanisms.

SUBMITTER: Jamal S

PROVIDER: S-EPMC8142496 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Understanding the molecular details of protein-DNA interactions is critical for deciphering the mechanisms of gene regulation. We present a machine learning approach for the identification of amino acid residues involved in protein-DNA interactions.We start with a Naïve Bayes classifier trained to predict whether a given amino acid residue is a DNA-binding residue based on its identity and the identities of its sequence neighbors. The input to the classifier consists of the identities of the target residue and 4 sequence neighbors on each side of the target residue. The classifier is trained and evaluated (using leave-one-out cross-validation) on a non-redundant set of 171 proteins. Our results indicate the feasibility of identifying interface residues based on local sequence information. The classifier achieves 71% overall accuracy with a correlation coefficient of 0.24, 35% specificity and 53% sensitivity in identifying interface residues as evaluated by leave-one-out cross-validation. We show that the performance of the classifier is improved by using sequence entropy of the target residue (the entropy of the corresponding column in multiple alignment obtained by aligning the target sequence with its sequence homologs) as additional input. The classifier achieves 78% overall accuracy with a correlation coefficient of 0.28, 44% specificity and 41% sensitivity in identifying interface residues. Examination of the predictions in the context of 3-dimensional structures of proteins demonstrates the effectiveness of this method in identifying DNA-binding sites from sequence information. In 33% (56 out of 171) of the proteins, the classifier identifies the interaction sites by correctly recognizing at least half of the interface residues. In 87% (149 out of 171) of the proteins, the classifier correctly identifies at least 20% of the interface residues. This suggests the possibility of using such classifiers to identify potential DNA-binding motifs and to gain potentially useful insights into sequence correlates of protein-DNA interactions.Naïve Bayes classifiers trained to identify DNA-binding residues using sequence information offer a computationally efficient approach to identifying putative DNA-binding sites in DNA-binding proteins and recognizing potential DNA-binding motifs.

Project description:MotivationMicroRNAs (miRNAs) play important roles in general biological processes and diseases pathogenesis. Identifying miRNA target genes is an essential step to fully understand the regulatory effects of miRNAs. Many computational methods based on the sequence complementary rules and the miRNA and mRNA expression profiles have been developed for this purpose. It is noted that there have been many sequence features of miRNA targets available, including the context features of the target sites, the thermodynamic stability and the accessibility energy for miRNA-mRNA interaction. However, most of current computational methods that combine sequence and expression information do not effectively integrate full spectrum of these features; instead, they perceive putative miRNA-mRNA interactions from sequence-based prediction as equally meaningful. Therefore, these sequence features have not been fully utilized for improving miRNA target prediction.ResultsWe propose a novel regularized regression approach that is based on the adaptive Lasso procedure for detecting functional miRNA-mRNA interactions. Our method fully takes into account the gene sequence features and the miRNA and mRNA expression profiles. Given a set of sequence features for each putative miRNA-mRNA interaction and their expression values, our model quantifies the down-regulation effect of each miRNA on its targets while simultaneously estimating the contribution of each sequence feature to predicting functional miRNA-mRNA interactions. By applying our model to the expression datasets from two cancer studies, we have demonstrated our prediction results have achieved better sensitivity and specificity and are more biologically meaningful compared with those based on other methods.Availability and implementationThe source code is available at: http://nba.uth.tmc.edu/homepage/liu/miRNALasso.Supplementary informationSupplementary data are available at Bioinformatics online.ContactYin.Liu@uth.tmc.edu.