Artificial Intelligence in Post-translational Modification Site Prediction: Progress and Future Perspectives.

CLASPP: A unified model for predicting post-translational modifications

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 CLASPP’s 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.

Integrative proteomics and bioinformatics pipelines for PTM profiling.

Post-translational modifications (PTMs) regulate protein function across all life forms and allow plants to respond rapidly to biotic and abiotic stress. Over 450 PTM types have been described across organisms, of which 23-33 have been experimentally confirmed in plants, including phosphorylation, acetylation, methylation, glycosylation, ubiquitination, and sumoylation. These modifications are highly dynamic and often reversible, and frequently act in combination, or "crosstalk," to fine-tune cellular processes. Advances in high-resolution mass spectrometry and large-scale genome sequencing continue to expand the catalogue of known PTM sites, while machine learning and deep learning approaches increasingly support prediction of PTM site localization and function. Unlike broader surveys of plant PTMs, this review focuses specifically on O-phosphorylation and Lys-N(ε)-acetylation, the two best-characterized and most extensively crosstalking PTMs in plants, and integrates four perspectives: the historical development of proteomic and bioinformatics approaches to these modifications; current mass spectrometry-based workflows and enrichment strategies; the bioinformatics tools and databases available for their analysis; and the technical and species-related challenges, particularly in non-model plants, that currently limit their study. We close by outlining priority directions for future research, including multi-omics integration, AI-based prediction, and the translation of PTM knowledge into crop stress resilience and breeding applications.

Learning Shared Residue Backgrounds and Modification-Specific Offsets for PTM Site Prediction

Post-translational modifications (PTMs) are chemical changes added to proteins after translation. These changes affect protein function and regulation, and their disruption is linked to disease-associated mechanisms. Because experimentally validating all possible modification sites is impractical, many computational predictors have been developed for PTM site prediction. In this work, we study whether a shared model can represent common residue-background patterns while learning modification-specific background-to-positive offsets. This framing is especially relevant for residues such as lysine (K), which can be acetylated, ubiquitinated, methylated, or sumoylated depending on the surrounding protein context. We propose an anchor-guided rectified flow matching framework for multi-type PTM site prediction from protein language model embeddings. For each PTM–residue pair, the model builds residue-background anchors from PTM-compatible unannotated residues and positive anchors from experimentally annotated modified residues. Given a candidate residue and target modification type, the model compares the residue embedding with these anchor sets and uses a rectified flow module to estimate a modification-conditioned background-to-positive offset. This offset is combined with anchor-based features and used for site scoring. We evaluate the framework on a dbPTM-derived benchmark covering six commonly studied PTMs: phosphorylation, acetylation, ubiquitination, methylation, sumoylation, and N-linked glycosylation. In the shared-model setting, our approach achieves a macro AUPRC of 0.4195, improving over the gated multi-anchor baseline of 0.4154, while independently trained per-modification models achieve 0.4353. These results suggest that multi-type PTM prediction can be modeled within a single shared framework by combining residue-background anchors with modification-conditioned offset features.

ProtSyntax: a protein large language model for decoding post-translational modification syntax and function

Post-translational modifications (PTMs) expand protein function by encoding context-dependent regulatory states, and their dysregulation contributes to cancer, neurodegeneration and metabolic disease. However, existing methods treat PTMs as independent residue labels, limiting their ability to distinguish contextually permissible sites, model crosstalk and infer functional consequences. Here we introduce ProtSyntax, a PTM-aware foundation protein language model combining protein-aware positional encoding, bidirectional state-space propagation, geometry-constrained attention and adaptive multi-objective learning. This design integrates residue chemistry, motif order, long-range context and three-dimensional microenvironments while coupling PTM recognition to enzyme function. Across 40 PTM-site benchmarks, ProtSyntax exceeded the strongest baselines in mean MCC and AP by 12.66% and 10.67%. ProtSyntax also recovered masked PTM types and sites, rejected structural decoys, generalized to data-scarce modifications, reconstructed crosstalk and linked PTM perturbations to enzyme kinetics. Applications to pathogenic variants, biomolecular condensates and disease-associated PTM landscapes demonstrate its potential to decode the regulatory language of the modified proteome.

PlantPTM: A deep learning framework integrating protein language models with multi-view features for predicting diverse post-translational modification sites in plants.

Post-translational modifications (PTMs) play crucial regulatory roles in plants, orchestrating protein functions to maintain metabolic homeostasis, enable adaptation to dynamic environments, and regulate diverse cellular processes. Thus, the identification of PTM sites is essential for elucidating the mechanisms underlying plant growth, development, and stress responses. However, reliable and cost-effective computational approaches for predicting PTM sites in plants remain lacking. Here, we present PlantPTM, an integrated deep learning framework for predicting nine PTM types in plants. By combining protein language models (PLMs) with evolutionary information, PlantPTM demonstrates robust generalizability across a wide range of PTM types and plant species. Our method achieves state-of-the-art performance, with a mean AUROC of 0.8640 and a peak AUROC of 0.9699 across the nine PTM types. Notably, PlantPTM maintains strong performance even under low-data scenarios and unseen species. Extensive comparative benchmarks demonstrate that PlantPTM outperforms existing PTM prediction tools by an average of 15.46%, with improvements ranging from 2.90% to 19.08% over the best-performing tools for each PTM type. Furthermore, independent in-house MS data confirmed the accuracy of PlantPTM for ubiquitination, acetylation, and N-glycosylation sites, with all AUROC values exceeding 0.8. To facilitate PTM studies in plants, we provide the PlantPTM online service and source code freely available at https://ai4bio.online/PlantPTM and https://github.com/wky0422/PlantPTM, respectively.

TaHL-PTM: Post-Translational Modification Prediction in Proteins via Target-Hooked Discriminative Fine-Tuning of Decoder-only Protein Language Models