RF-Phos: A Novel General Phosphorylation Site Prediction Tool Based on Random Forest

Ismail, Hamid D.; Jones, Ahoi; Kim, Jung Ho; Newman, Robert H.; Kc, Dukka B.

doi:10.1155/2016/3281590

Cited by 36 publications

(35 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To this end, this paper introduces a non-kinase specific phosphorylation site prediction model based on random forests on top of a continuous distributed representaion of amino acids. Experimental results demonstrate that our model compares favorably to three recent state-of-the-art methods, namely PhosphoSVM [11], iPhos-PseEn [27] and RFPhos [19]. Our method out-performs PhosphoSVM, RF-Phos and iPhos-PseEn in predictions for S, Y and T residues in terms of overall scoring metrics.…”

Section: Introductionmentioning

confidence: 71%

“…In this paper we present SKIPHOS, a novel computational model for nonkinase specific prediction of phosphorylation sites using random forests and amino acid skip-gram embeddings. Experimental results from rigorous validation schemes demonstrate the favorable [11], iPhos-PseEn [27] and RFPhos [19]. The SKIPHOS performance cross-validated on the benchmark dataset is better than that of iPhos-PseEn, RF-Phos and PhosphoSVM for all cases, except for S residue when Table 6: Performance of SKIPHOS with the use of different feature types.…”

Section: Resultsmentioning

confidence: 96%

“…Experimental results show that our proposed model yields favorable performance on non-kinase specific prediction of S, Y and T phosphorylation sites, when compared to iPhos-PseEn [27], RF-Phos [19] and PhosphoSVM [11], three recent state-of-the-art corresponding models.…”

Section: Model Evaluationmentioning

confidence: 95%

“…The tree construction is guided with the Gini impurity index calculated for each of such selected features. Various recent bioinformatics studies have employed random forests, demonstrating its benefit and robustness for high dimensional datasets [19,27].…”

Section: Random Forests Based Predictionmentioning

confidence: 99%

“…As a consequence, the number of kinases known to phosphorylate a large amount residues is still limited. To give an example, Phospho.ELM version 9.0 (Dinkel et al, 2010), the benchmark dataset for most phosphorylation prediction studies to date (Trost and Kusalik, 2011;Dou et al, 2014;Ismail et al, 2016;Song et al, 2017), has only 9 kinases each catalyzes more than 100 phosphorylation sites. The total residues phosphorylated by such 9 are 1,616, out of 42,500.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

SKIPHOS: non-kinase specific phosphorylation site prediction with random forests and amino acid skip-gram embeddings

Trac

Phan

Nguyen

et al. 2019

Preprint

View full text Add to dashboard Cite

Phosphorylation, which is catalyzed by kinase proteins, is in the top two most common and widely studied types of known essential post-translation protein modification (PTM). Phosphorylation is known to regulate most cellular processes such as protein synthesis, cell division, signal transduction, cell growth, development and aging. Various phosphorylation site prediction models have been developed, which can be broadly categorized as being kinasespecific or non-kinase specific (general). Unlike the latter, the former requires a large enough number of experimentally known phosphorylation sites annotated with a given kinase for training the model, which is not the case in reality: less than 3% of the phosphorylation sites known to date have been annotated with a responsible kinase. To date, there are a few nonkinase specific phosphorylation site prediction models proposed. This study introduces a non-kinase specific phosphorylation site prediction model based on random forests on top of a continuous distributed representation of amino acids. In the experiments, our method is compared to three recent methods including PhosphoSVM, iPhos-PreEn and RFPhos.

show abstract

Section: Introductionmentioning

confidence: 71%

Section: Resultsmentioning

confidence: 96%

Section: Model Evaluationmentioning

confidence: 95%

Section: Random Forests Based Predictionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

SKIPHOS: non-kinase specific phosphorylation site prediction with random forests and amino acid skip-gram embeddings

Trac

Phan

Nguyen

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

PhosBoost: Improved phosphorylation prediction recall using gradient boosting and protein language models

Poretsky,

Andorf,

Sen

2023

Plant Direct

View full text Add to dashboard Cite

Protein phosphorylation is a dynamic and reversible post‐translational modification that regulates a variety of essential biological processes. The regulatory role of phosphorylation in cellular signaling pathways, protein–protein interactions, and enzymatic activities has motivated extensive research efforts to understand its functional implications. Experimental protein phosphorylation data in plants remains limited to a few species, necessitating a scalable and accurate prediction method. Here, we present PhosBoost, a machine‐learning approach that leverages protein language models and gradient‐boosting trees to predict protein phosphorylation from experimentally derived data. Trained on data obtained from a comprehensive plant phosphorylation database, qPTMplants, we compared the performance of PhosBoost to existing protein phosphorylation prediction methods, PhosphoLingo and DeepPhos. For serine and threonine prediction, PhosBoost achieved higher recall than PhosphoLingo and DeepPhos (.78, .56, and .14, respectively) while maintaining a competitive area under the precision‐recall curve (.54, .56, and .42, respectively). PhosphoLingo and DeepPhos failed to predict any tyrosine phosphorylation sites, while PhosBoost achieved a recall score of .6. Despite the precision‐recall tradeoff, PhosBoost offers improved performance when recall is prioritized while consistently providing more confident probability scores. A sequence‐based pairwise alignment step improved prediction results for all classifiers by effectively increasing the number of inferred positive phosphosites. We provide evidence to show that PhosBoost models are transferable across species and scalable for genome‐wide protein phosphorylation predictions. PhosBoost is freely and publicly available on GitHub.

show abstract

Prediction of phosphorylation sites based on Krawtchouk image moments

Wang

et al. 2017

Proteins

View full text Add to dashboard Cite

Protein phosphorylation is one of the most pervasive post-translational modifications and regulates diverse cellular processes in organisms. Under the catalysis of protein kinases, protein phosphorylation usually occurred in the residues serine (S), threonine (T), or tyrosine (Y). In this contribution, we proposed a novel scheme (named KMPhos) for the theoretical prediction of protein phosphorylation sites. First, the numerical matrix was obtained from a protein sequence fragment by replacing the characters of the residues with the chemical descriptors of amino acid molecules to approximately describe the chemical environment of the protein fragment, which was turned to the grayscale image. Then the Krawtchouk image moments were calculated and used to establish the support vector machine models. The accuracies of 10-fold cross validation for the obtained models on the training set are up to 89.7%, 88.6%, and 90.1% for the residues S, Y, and T, respectively. For the independent test set, the prediction accuracies are up to 90.7% (S), 87.8% (T), and 89.3% (Y). The results of ROC and other evaluations are also satisfactory. Compared with several specialized prediction tools, KMPhos provided the higher accuracy and reliability. An available KMPhos package is provided and can be used directly for phosphorylation sites prediction.

show abstract

RF-Phos: A Novel General Phosphorylation Site Prediction Tool Based on Random Forest

Cited by 36 publications

References 50 publications

SKIPHOS: non-kinase specific phosphorylation site prediction with random forests and amino acid skip-gram embeddings

SKIPHOS: non-kinase specific phosphorylation site prediction with random forests and amino acid skip-gram embeddings

PhosBoost: Improved phosphorylation prediction recall using gradient boosting and protein language models

Prediction of phosphorylation sites based on Krawtchouk image moments

Contact Info

Product

Resources

About