iAMY‐DC: Identifying Amyloid Proteins by Using Dynamic Correlation Features

Zou, Hongliang

doi:10.1002/slct.202204629

Cited by 1 publication

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also conduct a comparative evaluation of the proposed model in this study with established models that have demonstrated high performance. Since the Web site provided in the RFAmyloid paper was unavailable, we selected iAmyS cm, BioSeq_SVM, BioSeq_KNN, BioSeq_RF, BioSeq_CD, AmyPred-FRL, and iAmy-DC as the established models for comparison. All the models, including the proposed method and the four established models, are tested on the same data set taken from the CPAD 2.0 database.…”

Section: Resultsmentioning

confidence: 99%

“…Finally, all algorithms concentrate solely on the utilization of features but neglect the interactions between amino acids that originate from their physicochemical differences in real-world scenarios. While iAMY-DC gauges the correlations among features within windows by deploying a sliding window method in conjunction with the Pearson correlation coefficient, it still only considers local information and relies on statistical techniques without accounting for the potential interactions between amino acids.…”

Section: Introductionmentioning

confidence: 99%

“…The iAMY-DC employs the synthetic minority oversampling technique (SMOTE) to address the unbalanced data set collected, characterizing protein sequences based on their physicochemical properties while using the synthetic minority oversampling technique (LASSO) algorithm to select optimal features. The optimal feature set is then used to train support vector machine (SVM) classifiers to achieve highly accurate (accuracy of 0.9104) identification of amyloids …”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

AMYGNN: A Graph Convolutional Neural Network-Based Approach for Predicting Amyloid Formation from Polypeptides

Yang,

Wu,

Liu

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

There has been an increasing interest in the use of amyloids for constructing various functional materials. The design of amyloid-associated functional materials requires the identification of the core peptide sequences as the fundamental building block. The existing computational methods are limited in terms of delineating polypeptides, the typical non-Euclidean structural data, and they fail to capture the dynamic interactions between amino acids due to ignoring the contextual information from surrounding amino acids. Here, we first propose the use of a state-of-the-art graph convolutional neural network for predicting the trends of amyloid formation from specific peptide sequences (AMYGNN) by abstracting each polypeptide as a graph, in which the constituting amino acids are viewed as nodes and edges characterizing the connections between pairs of amino acids are established when they meet a given distance threshold (C α −C α ≤ 5 Å). Our model achieves high performance with accuracy (0.9208), G-mean (0.9203), MCC (0.8417), and F1 (0.9235) in determining the characteristic peptide sequences to form amyloid. 32 of 534 crucial amino acid properties that greatly contribute to the formation of amyloids are ascertained, and the β-folding-like graph structure of a polypeptide is believed to be essential for the formation of amyloid. Our model enables the mapping of polypeptides with underlying interactions between amino acids and provides a quick and precise predictive framework for directing the construction of amyloidassociated functional materials.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation