PLP_FS: prediction of lysine phosphoglycerylation sites in protein using support vector machine and fusion of multiple F_Score feature selection

Sohrawordi, Md.; Hossain, Md. Ali; Hasan, Md. Al Mehedi

doi:10.1093/bib/bbac306

Cited by 8 publications

(4 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To make a fair and balanced comparison with existing models, the dataset employed in this study was used in the previous study [20], in which the researchers developed a machine learning model PLP FS for phosphoglycerylation site prediction. The dataset made use of the protein synthesis dataset in the Protein Lysine Modifications Database (PLMD) [28].…”

Section: A Preparation Of the Datasetmentioning

confidence: 99%

“…In the past few years, several prediction models for protein phosphoglyceration sites have been developed. We compared the model evaluation results of BERT PLPS on the same dataset to eight other existing models, including PLP FS [20], RAM PGK [59], IDPGK [60], PhoglyPred [61], Bigram-PGK [8], Phogly PseAAC [19], EvolStruct-phogly [62], and predPhogly Site [63]. We also compared the dynamic mask to the static mask using the same dataset.…”

Section: B Comparison and Evaluation With Other Existing Modelsmentioning

confidence: 99%

“…The CKSAAP Phoglysite model [11] utilized the CKSAAP protein feature extraction technique for amino acid feature construction, and the sample feature matrix was used to train a support vector machine (SVM) for the task of predicting amino acid phosphoglycerylation sites. The PLP FS model [20] used three protein feature extraction techniques, including the composition of K-spaced residue pairs (CKSAAP), amino acid composition (AAC), and binary encoding (BE), to construct protein feature vectors. It uses the machine learning algorithm SVM for the prediction of the feature vectors.…”

mentioning

confidence: 99%

See 2 more Smart Citations

BERT_PLPS: A BERT-based Model for Predicting Lysine Phosphoglycerylation Sites

Lai¹,

Wang²,

Ye³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>As one of the most important post-translational modification processes, lysine phosphoglycerylation modifications affect many important biosynthetic processes in the human body. However, traditional experimental methods for the recognization of lysine phosphoglycerylation sites are not only expensive but also time-consuming. Computational techniques may provide an economical and efficient way to predict lysine phosphoglycerylation sites. Therefore, it is extremely necessary and meaningful to study and establish prediction models with high accuracy. In the present study, we propose a BERT-based model, BERT PLPS, which could predict accurately lysine phosphoglycerylation sites. This model extracts amino acid sequence features with three algorithms: CKSAAP, AAC, and BE. Sample equalization is performed using the ADASYN and KNN algorithms. The data are dimensionalized by the ISOMap algorithm, and the features are encoded into feature sequences by an encoder as the input to a BERT-based prediction model. To learn better the intrinsic biological language of lysine, we replaced the original static mask with a dynamic random mask. Compared to other machine learning or deep learning-based models, BERT PLPS exhibits up to 99.53% accuracy and outperforms the most advanced model (PLP FS) with an increase of approximately 0.35% on ACC and approximately 0.93% on MCC.</p>

show abstract

Section: A Preparation Of the Datasetmentioning

confidence: 99%

Section: B Comparison and Evaluation With Other Existing Modelsmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

BERT_PLPS: A BERT-based Model for Predicting Lysine Phosphoglycerylation Sites

Lai¹,

Wang²,

Ye³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In the past few years, several prediction models for protein phosphoglyceration sites have been developed. We compared the model evaluation results of BERT PLPS on the same dataset to eight other existing models, including PLP FS [20], RAM PGK [59], IDPGK [60], PhoglyPred [61], Bigram-PGK [8], Phogly PseAAC [19], EvolStructphogly [62], and predPhogly Site [63]. We also compared the dynamic mask to the static mask using the same dataset.…”

Section: Comparison and Evaluation With Other Existing Modelsmentioning

confidence: 99%

BERT_PLPS: A BERT-based Model for Predicting Lysine Phosphoglycerylation Sites

Lai

Cao

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

As one of the most important post-translational modification processes, lysine phosphoglycerylation modifications affect many important biosynthetic processes in the human body. However, traditional experimental methods for the recognization of lysine phosphoglycerylation sites are not only expensive but also time-consuming. Computational techniques may provide an economical and efficient way to predict lysine phosphoglycerylation sites. Therefore, it is extremely necessary and meaningful to study and establish prediction models with high accuracy. In the present study, we propose a BERT-based model, BERT_PLPS, which could predict accurately lysine phosphoglycerylation sites. This model extracts amino acid sequence features with three algorithms: CKSAAP, AAC, and BE. Sample equalization is performed using the ADASYN and KNN algorithms. The data are dimensionalized by the ISOMap algorithm, and the features are encoded into feature sequences by an encoder as the input to a BERT-based prediction model. To learn better the intrinsic biological language of lysine, we replaced the original static mask with a dynamic random mask. Compared to other machine learning or deep learning-based models, BERT_PLPS exhibits up to 99.53% accuracy and outperforms the most advanced model (PLP_FS) with an increase of approximately 0.35% on ACC and approximately 0.93% on MCC.

show abstract

Feature selection techniques for machine learning: a survey of more than two decades of research

Theng,

Bhoyar

2023

Knowl Inf Syst

View full text Add to dashboard Cite

PLP_FS: prediction of lysine phosphoglycerylation sites in protein using support vector machine and fusion of multiple F_Score feature selection

Cited by 8 publications

References 38 publications

BERT_PLPS: A BERT-based Model for Predicting Lysine Phosphoglycerylation Sites

BERT_PLPS: A BERT-based Model for Predicting Lysine Phosphoglycerylation Sites

BERT_PLPS: A BERT-based Model for Predicting Lysine Phosphoglycerylation Sites

Feature selection techniques for machine learning: a survey of more than two decades of research

Contact Info

Product

Resources

About