AMYPred-FRL is a novel approach for accurate prediction of amyloid proteins by using feature representation learning

Abstract

Amyloid proteins have the ability to form insoluble fibril aggregates that have important pathogenic effects in many tissues. Such amyloidoses are prominently associated with common diseases such as type 2 diabetes, Alzheimer's disease, and Parkinson's disease. There are many types of amyloid proteins, and some proteins that form amyloid aggregates when in a misfolded state. It is difficult to identify such amyloid proteins and their pathogenic properties, but a new and effective approach is by developing effective bioinformatics tools. While several machine learning (ML)-based models for in silico identification of amyloid proteins have been proposed, their predictive performance is limited. In this study, we present AMYPred-FRL, a novel meta-predictor that uses a feature representation learning approach to achieve more accurate amyloid protein identification. AMYPred-FRL combined six well-known ML algorithms (extremely randomized tree, extreme gradient boosting, k-nearest neighbor, logistic regression, random forest, and support vector machine) with ten different sequence-based feature descriptors to generate 60 probabilistic features (PFs), as opposed to state-of-the-art methods developed by a single feature-based approach. A logistic regression recursive feature elimination (LR-RFE) method was used to find the optimal m number of 60 PFs in order to improve the predictive performance. Finally, using the meta-predictor approach, the 20 selected PFs were fed into a logistic regression method to create the final hybrid model (AMYPred-FRL). Both cross-validation and independent tests showed that AMYPred-FRL achieved superior predictive performance than its constituent baseline models. In an extensive independent test, AMYPred-FRL outperformed the existing methods by 5.5% and 16.1%, respectively, with accuracy and MCC of 0.873 and 0.710. To expedite high-throughput prediction, a user-friendly web server of AMYPred-FRL is freely available at http://pmlabstack.pythonanywhere.com/AMYPred-FRL. It is anticipated that AMYPred-FRL will be a useful tool in helping researchers to identify new amyloid proteins.

OAF: a new member of the BRICHOS family

“…Other mature polypeptides of the BRICHOS family form amyloid-like structures ( Chen et al , 2022 ; Hedlund et al , 2009 ; Knight et al , 2013 ; Willander et al , 2011 ). To investigate this for OAF, we applied a machine learning approach, AMYPred-FRL, to its wild-type sequence ( Charoenkwan et al. , 2022 ).…”

“…Other mature polypeptides of the BRICHOS family form amyloid-like structures (Chen et al, 2022;Hedlund et al, 2009;Knight et al, 2013;Willander et al, 2011). To investigate this for OAF, we applied a machine learning approach, AMYPred-FRL, to its wild-type sequence (Charoenkwan et al, 2022). This predicted OAF to have the highest probability (97%) of forming amyloid-like structures among all BRICHOS domain mature polypeptides (Supplementary Fig.…”

Prediction of Amyloid Proteins Using Embedded Evolutionary & Ensemble Feature Selection Based Descriptors With eXtreme Gradient Boosting Model

“…To develop an automatic predictor, the selection of a valid training dataset is an essential step. To effectively examine the predictive analysis of our predictor, we used the same training samples that were previously used in PredAmyl-MLP [30], iAMY-SCM [32], RFAmyloid [29], and AMYPred-FRL [33]. Which was initially constructed by Niu et al [29].…”

“…While the negative value drives the predictions toward non-AMY and has a negative effect. To determine the efficacy of the current study, we performed a comparison of the novel predictor with existing predictors such as iAMY-SCM [32], PredAmyl-MLP [30], MetAmyl [25], RFAmyloid [29], and AMYPred-FRL [33] using training and testing datasets. The predictive outcomes of our computational model and its comparison with the existing models are given in Table 5.…”

“…The dipeptides propensity scores and weighted sum functions of the amino acid sequences are computed. In the sequel, Charoenkwan et al proposed an AMYPred-FRL-based metapredictor for AMY proteins [33]. The AMY sequences were formulated using ten different sequential feature engineering methods.…”