Search

Given that wet experimental methods were no longer adequate for the rapid identification of bitter peptides, this paper presented Bitter-Fus, a novel predictive deep learning method incorporating traditional manual features and pre-trained deep features. Firstly, the method automatically extracted deep learning features from peptide sequences using a pre-trained protein sequence language model, then fed the deep learning features into a long short-term memory (LSTM) network for dimensionality reduction to retain the most relevant features. Finally, the reduced-dimensional deep features were fused with the manual features composed of traditional amino acids composition (AAC) method and passed into the feedforward neural network to construct a prediction model. The validation experimental results showed that the prediction method Bitter-Fus obtained an accuracy precision value of 0. 902 and a Mathews correlation coefficient value of 0. 805 in a 10-fold cross-validation, and an accuracy precision value of 0. 930 and a Mathews correlation coefficient value of 0. 862 in the independent dataset test, which significantly outperformed the current state-of-the-art bitter peptide prediction methods BERT4Bitter and iBitter-SCM. [ABSTRACT FROM AUTHOR]

In response to the need for improving prediction accuracy (ACC) in existing models for Antimicrobial Peptides (AMPs), a novel AMP prediction model called DeepGlap was proposed. This model utilized two protein language models for feature extraction from AMP sequences, followed by fusion of feature vectors. These fused vectors were then input into a deep learning network composed of multiple layers of bidirectional long short-term memory networks (mBi-LSTM), one-dimensional convolutional neural networks (1D-CNN), and attention mechanisms. The model underwent performance evaluation and optimization. Results indicated that the model achieved ACC, the Pearson correlation coefficient (MCC), and the area urder the curve (AUC) values of 0.739, 0.489, and 0.81, respectively, demonstrating superior predictive performance compared to existing AMP prediction models. [ABSTRACT FROM AUTHOR]