MPMABP: A CNN and Bi-LSTM-Based Method for Predicting Multi-Activities of Bioactive Peptides

Abstract

Bioactive peptides are typically small functional peptides with 2–20 amino acid residues and play versatile roles in metabolic and biological processes. Bioactive peptides are multi-functional, so it is vastly challenging to accurately detect all their functions simultaneously. We proposed a convolution neural network (CNN) and bi-directional long short-term memory (Bi-LSTM)-based deep learning method (called MPMABP) for recognizing multi-activities of bioactive peptides. The MPMABP stacked five CNNs at different scales, and used the residual network to preserve the information from loss. The empirical results showed that the MPMABP is superior to the state-of-the-art methods. Analysis on the distribution of amino acids indicated that the lysine preferred to appear in the anti-cancer peptide, the leucine in the anti-diabetic peptide, and the proline in the anti-hypertensive peptide. The method and analysis are beneficial to recognize multi-activities of bioactive peptides.

Multi-dimensional deep learning drives efficient discovery of novel neuroprotective peptides from walnut protein isolates

“…For the identification of neuroprotective peptides, the accuracy of MiCNN–LSTM was higher than the accuracy of both CNN and LSTM, confirming the validity of the combination of CNN and LSTM. A previous study used the CNN and LSTM based multi-dimensional algorithm to screen for peptides and the values of ACC reached 0.709 46 and 0.722, 51 respectively, which confirmed the high accuracy of the MiCNN–LSTM. This shows that the performance of the MiCNN–LSTM model is still greatly improved over the previous work.…”

Deep learning-based multi-functional therapeutic peptides prediction with a multi-label focal dice loss function

“…To further demonstrate the power of the ETFC model, we compare it with the existing methods. To improve the reproducibility and reliability of MPMABP ( Li et al 2022 ), MLBP ( Tang et al 2022 ), sequential properties-recurrent neural network (SP-RNN) ( Otović et al 2022 ) and PrMFTP ( Yan et al 2022 ), we provide the hyperparameter details of these models in Supplementary Tables S4–S7 , respectively. The comparison of ETFC with MPMABP, MLBP, SP-RNN, and PrMFTP is performed on the test set, and we randomly selected 80% of the set as the subset and repeated this process five times to obtain five subsets.…”

Discovery of novel multi-functional peptides by using protein language models and graph-based deep learning

“…We compared our proposed method iMFP-LG with several state-of-the-art methods, including four conventional machine learning-based methods (CLR [12], RAKEL [34], RBRL [40] and MLDF [43]) and three deep learning-based methods (MPMABP [19], MFBP [31] and PrMFTP [42]). MPMABP and MFBP employed CNNs and RNNs for identifying multi-functional peptides.…”

“…Several works have made a difficult endeavor in discovery of multi-functional peptides. Tang et al [31] and Li et al [19] identified multi-functional peptides by using a multi-label deep learning method, which combines CNN and RNN to extract peptide features and assigns function labels separately. PrMFTP [42] improved the performance of multi-functional therapeutic peptide identification by employing multi-scale CNN, attention-based biLSTM.…”