CLASPP: A unified model for predicting post-translational modifications

Abstract

Post-Translational Modifications (PTMs) are a fundamental mechanism for regulating cellular pathways and increasing the functional diversity of the proteome. Accurately predicting the PTM types that are likely to occur at a given site in the primary sequence is a key challenge in functional proteomics. Existing PTM prediction models predominantly focus on either single PTM types or employ ensemble methods that combine multiple models to predict different PTM types. This fragmentation is largely driven by the vast imbalance in data availability across PTM types, making it difficult to predict multiple PTM types with a single model. To address this limitation, we present the Contrastively Learned Attention-based Stratified PTM Predictor (CLASPP), a unified PTM prediction model. CLASPP addresses imbalance challenges by leveraging unsupervised clustering-based undersampling and a novel contrastive learning framework tailored to PTM data. Additionally, our hierarchical data organization and curation are shown to improve CLASPPs performance by balancing the representation of individual PTM types and provides a standardized dataset to train and validate future model designs. Drawing inspiration from advancements in image and natural language processing, the CLASPP model employs a multi-stage training strategy and a high-quality, curated training dataset to improve PTM prediction performance. To uncover what is learned during the contrastive learning stage, the CLASPP model is shown to distinguish known protein kinase substrate specificity profiles as a form of explainability. Finally, we evaluate the application of CLASPP in predicting PTMs in different model organisms and experimentally validated ubiquitination sites in the understudied DCLK3 kinase. Overall, CLASPP represents a unified model for PTM prediction that addresses key bottlenecks in data imbalance and offers new strategies for biological data curation, thereby improving PTM-type prediction performance across diverse organisms. Author summaryPost-translational modifications (PTMs) are essential changes that proteins undergo, influencing nearly every aspect of cell function, communication, and disease. Accurately predicting where and how these modifications occur is challenging due to the diversity of PTM types and the limitations of existing annotation pipelines. This study introduces a unified deep learning approach, termed CLASPP, leveraging contrastive learning to predict multiple PTM types simultaneously from primary protein sequence alone. By employing advanced data balancing and sampling methods, CLASPP ensures reliable predictions for rare and common modifications. The model utilizes a pre-trained protein language model to capture sequence and structural features encoded in the primary protein sequence. Test results demonstrate that CLASPP consistently surpasses existing tools in predicting 12 major PTM types, and its versatility enables robust predictions across species, not just in human proteins. The final model, data curation, and training datasets are freely accessible for broader use and reproducibility (https://github.com/gravelCompBio/Claspp_forward).