Post-translational modifications are important for regulating cellular functions. Although traditional experimental methods accurately identify PTM sites, they are time-consuming. In this study, we propose a novel model capable of predicting 17 types of PTMs through multi-modal integration and AlphaFold predictions. Our model employs an enhanced CNN-transformer architecture to capture local dependencies within the sequence, while incorporating structural features and evolutionary patterns to effectively capture complex spatial relationships and global contextual dependencies. Through rigorous cross-validation and testing, our model demonstrates exceptional performance, achieving area under the curve scores of 96.5%, 91.6%, 91.0%, and 89.5% for the prediction of hydroxylation, malonylation, O-linked glycosylation, and phosphorylation, respectively. Notably, our model accurately identified known phosphorylation sites on tau and two recently identified residues linked to pre-tangle stages and early Alzheimer's disease pathology. This work not only deepens the understanding of PTMs but also holds promise for advancing future research in the prediction of PTM sites and functional annotation.

Abstract Motivation Membrane permeability represents a critical bottleneck in cyclic peptide drug development, limiting the clinical translation of these therapeutically attractive molecules despite their inherent stability and structural diversity. Current computational models for predicting cyclic peptide membrane permeability (CPMP) exhibit insufficient accuracy for early-stage drug screening, hampering the efficiency of lead optimization in pharmaceutical pipelines. Methodology In this study, we introduce a novel multi-source feature fusion model called MSF-CPMP, which aims to increase the accuracy of predicted CPMP. The MSF-CPMP model incorporates three features extracted from SMILES sequences, graph-based molecular structures, and physicochemical properties of cyclic peptides. Results By benchmarking with other machine learning and deep learning-based methods, MSF-CPMP achieved the highest levels of the evaluation metrics such as accuracy of 0.9062 and AUROC of 0.9546, and further validated MSF-CPMP robustness in learning capabilities and efficacy of its multi-source fusion. MSF-CPMP has been validated on FDA-approved cyclic peptide therapeutics, demonstrating strong predictive power for clinical candidates. Our result demonstrates that MSF-CPMP outperforms other methods in predicting CPMP, providing a practical computational tool for accelerating drug screening and reducing attrition rates in cyclic peptide drug discovery, thereby advancing precision-guided pharmaceutical development. Availability Code is available at https://github.com/wanglabhku/MSF-CPMP

MOTIVATION: Peptides and their derivatives hold potential as therapeutic agents. The rising interest in developing peptide drugs is evidenced by increasing approval rates by the FDA of USA. To identify the most potential peptides, study on peptide-protein interactions (PepPIs) presents a very important approach but poses considerable technical challenges. In experimental aspects, the transient nature of PepPIs and the high flexibility of peptides contribute to elevated costs and inefficiency. Traditional docking and molecular dynamics simulation methods require substantial computational resources, and the predictive accuracy of their results remain unsatisfactory. RESULTS: To address this gap, we proposed TPepPro, a Transformer-based model for PepPI prediction. We trained TPepPro on a dataset of 19,187 pairs of peptide-protein complexes with both sequential and structural features. TPepPro utilizes a strategy that combines local protein sequence feature extraction with global protein structure feature extraction. Moreover, TPepPro optimizes the architecture of structural featuring neural network in BN-ReLU arrangement, which notably reduced the amount of computing resources required for PepPIs prediction. According to comparison analysis, the accuracy reached 0.855 in TPepPro, achieving an 8.1% improvement compared to the second-best model TAGPPI. TPepPro achieved an AUC of 0.922, surpassing the second-best model TAGPPI with 0.844. Moreover, the newly developed TPepPro identify certain PepPIs that can be validated according to previous experimental evidence, thus indicating the efficiency of TPepPro to detect high potential PepPIs that would be helpful for amino acid drug applications. AVAILABILITY AND IMPLEMENTATION: The source code of TPepPro is available at https://github.com/wanglabhku/TPepPro.