DisorderUnetLM: Validating ProteinUnet for efficient protein intrinsic disorder prediction
This work addresses efficient disorder prediction for drug and enzyme design, but it is incremental as it builds upon ProteinUnet.
The paper tackles protein intrinsic disorder prediction by introducing DisorderUnetLM, which achieves top results in benchmarks, ranking 1st for Disorder-NOX with ROC-AUC 0.844 and 10th for Disorder-PDB with ROC-AUC 0.924.
The prediction of intrinsic disorder regions has significant implications for understanding protein functions and dynamics. It can help to discover novel protein-protein interactions essential for designing new drugs and enzymes. Recently, a new generation of predictors based on protein language models (pLMs) is emerging. These algorithms reach state-of-the-art accuracy with-out calculating time-consuming multiple sequence alignments (MSAs). The article introduces the new DisorderUnetLM disorder predictor, which builds upon the idea of ProteinUnet. It uses the Attention U-Net convolutional neural network and incorporates features from the ProtTrans pLM. DisorderUnetLM achieves top results in the direct comparison with recent predictors exploiting MSAs and pLMs. Moreover, among 43 predictors from the latest CAID-2 benchmark, it ranks 1st for the Disorder-NOX subset (ROC-AUC of 0.844) and 10th for the Disorder-PDB subset (ROC-AUC of 0.924). The code and model are publicly available and fully reproducible at doi.org/10.24433/CO.7350682.v1.