Protein property prediction based on local environment by 3D equivariant convolutional neural networks
Chen, H.; Cheng, Y.; Dong, J.; Mao, J.; Wang, X.; Gao, Y.; Li, Y.; Wang, C.; Wu, Q.
Show abstract
Predicting the properties of proteins is an important procedure in protein engineering. It determines the subspace of mutations for protein modifications, which is critical to the success of the project, but heavily relies on the knowledge and experience of scientists. In this study, we propose a novel deep 3D-CNN model, Eq3DCNN, specifically designed for local environment-related tasks in protein engineering. Eq3DCNN uses basic atom descriptors and their coordinates as inputs, utilizing customized data augmentations to enhance its training efficiency. To make the Eq3DCNN extracted features with more generalization capability, we incorporated a rotation equivariant module to get rotation invariant features. Using cross-validations with different data splitting strategies and under the scenarios of zero-shot predictions, we demonstrate that Eq3DCNN outperformed other 3D-CNN models in stability predictions, and also well-preformed on other prediction tasks, such as the binding pocket and the secondary structure predictions. Our results also identified the key factors that contribute to the models accuracy and the scope of its applications. These findings may help scientists in designing better mutation experiments and increasing the success rate in protein engineering.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Enhanced compound-protein binding affinity prediction by representing protein multimodal information via a coevolutionary strategy 97%
- GraphGPSM: a global scoring model for protein structure using graph neural networks 96%
- GraphCPLMQA: Assessing protein model quality based on deep graph coupled networks using protein language model 96%
Similar papers in this journal
- Membrane contact probability: an essential and predictive character for the structural and functional studies of membrane proteins 96%
- Deducing high-accuracy protein contact-maps from a triplet of coevolutionary matrices through deep residual convolutional networks 96%
- Hybridized distance- and contact-based hierarchical structure modeling for folding soluble and membrane proteins 95%
Similar papers in this journal
- Pretrainable Geometric Graph Neural Network for Antibody Affinity Maturation 97%
- Integration of molecular coarse-grained model into geometric representation learning framework for protein-protein complex property prediction 96%
- Protein folding stability estimation with explicit consideration of unfolded states 96%
Similar papers in this journal
- Accelerating protein engineering with fitness landscape modeling and reinforcement learning 96%
- Improved protein structure prediction by deep learning irrespective of co-evolution information 95%
- PepFlow: direct conformational sampling from peptide energy landscapes through hypernetwork-conditioned diffusion 94%
"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.