.png){kind=icon}
.png){kind=icon}
Return
Integrating multimodal features with deep learning for protein solubility prediction
.png){kind=icon}
OA
AI
DOI：10.1186/s13321-026-01225-2.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Protein solubility prediction holds significant importance in the fields of biotechnology and medicine. With the continual advancements of computational and experimental techniques such as protein design, enzyme mining, and directed evolution, accurate prediction of native and mutant protein solubility has become a key step in accelerating the development of functional proteins. In this study, we extracted physicochemical properties and co-evolutionary features from protein sequences, and further incorporated graph-based protein representations along with surface features as inputs for solubility prediction. Building upon these features, we developed two models, ProSolNet and ProSolNetMut. ProSolNet predicts whether a protein is soluble, while ProSolNetMut predicts solubility changes induced by mutations. Compared with state-of-the-art models, both models achieved higher accuracy in their respective tasks. In addition, we investigated the underlying mechanisms and application potential of the models through interpretability analysis. In this work, we present ProSolNet and ProSolNetMut to predict protein solubility and mutation-induced solubility changes by leveraging multimodal protein features, including sequence-based global descriptors, structure-based graph representations, and protein surface features. The proposed models achieve improved performance compared with representative existing models.
Keywords:
Protein solubility
Multimodal features
Deep learning
Graph neural network
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
5.7
Papers:
1.5K
Citations:
1.1W