SPPPred: Sequence-Based Protein-Peptide Binding Residue Prediction Using Genetic Programming and Ensemble Learning

Shafiee, Shima; Fathi, Abdolhossein; Taherzadeh, Ghazaleh

doi:10.1109/tcbb.2022.3230540

Cited by 5 publications

(4 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further assess GAPS’s generality in predicting protein–peptide binding sites, we fine-tuned the pre-trained GAPS on another benchmarking dataset called Data_finetuning_BN and then compared it with other models including BiteNet Pp [ 22 ], PepNN-Struct, PepNN-Seq, PepCNN [ 33 ], PepBCL [ 12 ], MTDsite [ 34 ], Visual [ 35 ], P2Rank-Pept [ 36 ], PepBind [ 37 ], Multi-VORFFIP [ 38 ], SPRINT-Str [ 13 ], SPRINT [ 15 ], SPPPred [ 17 ], PeptiMap [ 39 ], and PepSite [ 40 ]. These results are illustrated in Fig.…”

Section: Resultsmentioning

confidence: 99%

“…In addition, SPRINT [ 15 ], which relied on protein sequence data, employed a Support Vector Machine (SVM) [ 16 ] to address this problem. Most recently, an ensemble-based classifier called SPPPred [ 17 ] has been proposed for distinguishing binding residues through a genetic programming algorithm. Nevertheless, these ML algorithms depend on the expertise of professionals and the effectiveness of feature engineering, which could impede their practical implementation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

GAPS: a geometric attention-based network for peptide binding site identification by the transfer learning approach

Zhu,

Zhang,

Shang

et al. 2024

Briefings in Bioinformatics

View full text Add to dashboard Cite

Protein–peptide interactions (PPepIs) are vital to understanding cellular functions, which can facilitate the design of novel drugs. As an essential component in forming a PPepI, protein–peptide binding sites are the basis for understanding the mechanisms involved in PPepIs. Therefore, accurately identifying protein–peptide binding sites becomes a critical task. The traditional experimental methods for researching these binding sites are labor-intensive and time-consuming, and some computational tools have been invented to supplement it. However, these computational tools have limitations in generality or accuracy due to the need for ligand information, complex feature construction, or their reliance on modeling based on amino acid residues. To deal with the drawbacks of these computational algorithms, we describe a geometric attention-based network for peptide binding site identification (GAPS) in this work. The proposed model utilizes geometric feature engineering to construct atom representations and incorporates multiple attention mechanisms to update relevant biological features. In addition, the transfer learning strategy is implemented for leveraging the protein–protein binding sites information to enhance the protein–peptide binding sites recognition capability, taking into account the common structure and biological bias between proteins and peptides. Consequently, GAPS demonstrates the state-of-the-art performance and excellent robustness in this task. Moreover, our model exhibits exceptional performance across several extended experiments including predicting the apo protein–peptide, protein–cyclic peptide and the AlphaFold-predicted protein–peptide binding sites. These results confirm that the GAPS model is a powerful, versatile, stable method suitable for diverse binding site predictions.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

GAPS: a geometric attention-based network for peptide binding site identification by the transfer learning approach

Zhu,

Zhang,

Shang

et al. 2024

Briefings in Bioinformatics

View full text Add to dashboard Cite

show abstract

“…In the pursuit of a more robust predictive model for proteinpeptide binding sites, Shafiee et al adopted an ensemble-based ML classifier named SPPPred. 31 Ensemble learning stands out as an effective strategy for handling imbalanced datasets, as it allows multiple models to collectively contribute to predictions, resulting in enhanced robustness, reduced variance, and improved generalization. 72 In the SPPPred algorithm, the ensemble learning technique of bagging 73 was employed to predict peptide binding residues.…”

Section: Ensemble Learningmentioning

confidence: 99%

Leveraging machine learning models for peptide–protein interaction prediction

Yin,

Mi,

Shukla

2024

RSC Chem. Biol.

View full text Add to dashboard Cite

show abstract

“…In addition, an approach that was grounded in protein sequence data denoted as SPRINT 14 , employed a Support Vector Machine (SVM) 15 to predict protein-peptide binding sites. Most recently, SPPPred 16 has been proposed as an ensemble-based classifier for distinguishing binding residues, through a genetic programming algorithm and related features. However, the major drawbacks of these algorithms are their dependence on expert knowledge and the quality of feature engineering, which have a substantial impact on their predictive performance.…”

Section: Introductionmentioning

confidence: 99%

GAPS: Geometric Attention-based Networks for Peptide Binding Sites Identification by the Transfer Learning Approach

Zhu,

Zhang,

Shang

et al. 2023

Preprint

View full text Add to dashboard Cite

The identification of protein-peptide binding sites significantly advances our understanding of their interaction. Recent advancements in deep learning have profoundly transformed the prediction of protein-peptide binding sites. In this work, we describe the Geometric Attention-based networks for Peptide binding Sites identification (GAPS). The GAPS constructs atom representations using geometric feature engineering and employs various attention mechanisms to update pertinent biological features. In addition, the transfer learning strategy is implemented for leveraging the pre-trained protein-protein binding sites information to enhance training of the protein-peptide binding sites recognition, taking into account the similarity of proteins and peptides. Consequently, GAPS demonstrates state-of-the-art (SOTA) performance in this task. Our model also exhibits exceptional performance across several expanded experiments including predicting the apo protein-peptide, the protein-cyclic peptide, and the predicted protein-peptide binding sites. Overall, the GAPS is a powerful, versatile, stable method suitable for diverse binding site predictions.

show abstract

SPPPred: Sequence-Based Protein-Peptide Binding Residue Prediction Using Genetic Programming and Ensemble Learning

Cited by 5 publications

References 54 publications

GAPS: a geometric attention-based network for peptide binding site identification by the transfer learning approach

GAPS: a geometric attention-based network for peptide binding site identification by the transfer learning approach

Leveraging machine learning models for peptide–protein interaction prediction

GAPS: Geometric Attention-based Networks for Peptide Binding Sites Identification by the Transfer Learning Approach

Contact Info

Product

Resources

About