PROSTATA: Protein Stability Assessment using Transformers
Umerenkov, D.; Shashkova, T. I.; Strashnov, P. V.; Nikolaev, F.; Sindeeva, M.; Ivanisenko, N. V.; Kardymon, O. L.
Show abstract
Accurate prediction of change in protein stability due to point mutations is an attractive goal that remains unachieved. Despite the high interest in this area, little consideration has been given to the transformer architecture, which is dominant in many fields of machine learning. In this work, we introduce PROSTATA, a predictive model built in knowledge transfer fashion on a new curated dataset. PROSTATA demonstrates superiority over existing solutions based on neural networks. We show that the large margin of improvement is due to both the architecture of the model and the quality of the new training data set. This work opens up opportunities for developing new lightweight and accurate models for protein stability assessment. PROSTATA is available at https://github.com/AIRI-Institute/PROSTATA.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- DDGemb: predicting protein stability change upon single- and multi-point variations with embeddings and deep learning 98%
- DeepAllo: Allosteric Site Prediction using Protein Language Model (pLM) with Multitask Learning 97%
- A Gated Graph Transformer for Protein ComplexStructure Quality Assessment and its Performancein CASP15 97%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.