Protein Language Model Predicts Mutation Pathogenicity and Clinical Prognosis

Liu, X., Yang, X., Ouyang, L., Guo, G., Su, J., Xi, R., Yuan, K. and Yuan, F. (2022) Protein Language Model Predicts Mutation Pathogenicity and Clinical Prognosis. NeurIPS 2022 Workshop on Learning Meaningful Representations of Life (LMRL 2022), 12 Sept 2022.

Abstract

Accurately predicting the effects of mutations in cancer has the potential to improve existing treatments and identify novel therapeutic targets. In this paper, we evidence for the first time that the large-scale pre-trained protein language models (PPLMs) are zero-shot predictors for two clinically relevant tasks: identifying disease-causing mutations and predicting patient survival rate. Then we benchmark a series of state-of-the-art (SOTA) PPLMs on 2279 protein variants across 20 cancer-related genes. Our empirical results show that the PPLMs outperform the SOTA baseline, EVE, trained on multiple sequence alignment (MSA) data. We also demonstrate that the evolutionary index score, generated from the PPLM’s softmax layer, is good indicator for both mutation pathogenicity and patient survival rate. Our paper has taken a key step toward the clinical utility of large-scale PPLMs.

• Item Type: Conference or Workshop Item
• Additional Information: This work is supported by the National Natural Science Foundation of China (No. U21A20427, 61972078), the special funding from the Westlake Center of Synthetic Biology and Integrated Bio- engineering (WE-SynBio), and the Research Center for Industries of the Future (No. WU2022C030).
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Yuan, Dr Ke and Yang, Xinyu
• Authors: Liu, X., Yang, X., Ouyang, L., Guo, G., Su, J., Xi, R., Yuan, K., and Yuan, F.
• College/School: College of Science and Engineering; College of Science and Engineering > School of Computing Science

Related URLs

• Organisation
• Organisation