PlantPTM featured on the cover of Molecular Plant and selected as a Featured Article

The study “PlantPTM: A deep learning framework integrating protein language models with multi-view features for predicting diverse post-translational modification sites in plants,” developed by ZLab led by professor Zhen Chen, appears on the cover of Molecular Plant, Volume 19, Issue 10, published on October 5, 2026, and has been selected as a Featured Article.

The cover artistically envisions the convergence of plant post-translational modification biology and artificial intelligence. A protein structure carrying multiple modification marks merges with an intelligent network, while plant and crop elements connect fundamental discovery with agricultural applications—reflecting PlantPTM's goal of accelerating plant proteomics and PTM discovery with AI.

PlantPTM predicts post-translational modification sites in plant proteins by integrating protein language models, convolutional neural networks, bidirectional gated recurrent units, and multi-view features including PSSMs and one-hot encodings through a self-attention mechanism. Covering six plant species and nine PTM types, it outperforms 25 existing PTM prediction methods and provides a unified, scalable solution across species and modification classes.

The team has also released a free PlantPTM web service supporting batch protein-sequence submission, confidence-ranked candidate sites, and result visualization. The work offers an AI-enabled resource for plant functional proteomics, crop molecular breeding, and plant synthetic biology.