• Corpus ID: 238407943

Geometric Transformers for Protein Interface Contact Prediction

  title={Geometric Transformers for Protein Interface Contact Prediction},
  author={Alex Morehead and Chen Chen and Jianlin Cheng},
Computational methods for predicting the interface contacts between proteins come highly sought after for drug discovery as they can significantly advance the accuracy of alternative approaches, such as protein-protein docking, protein function analysis tools, and other computational methods for protein bioinformatics. In this work, we present the Geometric Transformer, a novel geometryevolving graph transformer for rotation and translation-invariant protein interface contact prediction… 


DIPS-Plus: The Enhanced Database of Interacting Protein Structures for Interface Prediction
This work expands on a dataset recently introduced for this task, the Database of Interacting Protein Structures (DIPS), to present DIPS-Plus, an enhanced, feature-rich dataset of 42,112 complexes for geometric deep learning of protein interfaces, giving researchers a large, well-curated feature bank for training protein interface prediction methods.
Accurate prediction of inter-protein residue–residue contacts for homo-oligomeric protein complexes
A deep learning model to predict inter-protein residue-residue contacts across homo-oligomeric protein interfaces, named as DeepHomo, which achieved a high precision of >60% for the top predicted contact and outperformed state-of-the-art direct-coupling analysis and machine learning-based approaches.
Predicting protein-protein interface residues using local surface structural similarity
A comparison of PrISEC with PredUs, a recently developed method for predicting interface residues of a query protein based on the known interfaces of its (global) structural homologs, shows that performance superior or comparable to that of PredUs can be obtained using only local surface structural similarity.
Protein interaction interface region prediction by geometric deep learning
A unified Geometric Deep Neural Network, "PInet" (Protein Interface Network), based on joint segmentation of a representation of a protein surfaces, which predicts the interface regions on both interacting proteins, achieving performance equivalent to or much better than the state-of-the-art predictor for each dataset.
ComplexContact: a web server for inter-protein contact prediction using deep learning
A large-scale experimental test shows that ComplexContact greatly outperforms pure co-evolution methods for inter-protein contact prediction, regardless of the species.
BIPSPI: a method for the prediction of partner-specific protein–protein interfaces
The proposed BIPSPI takes into account a pair of interacting proteins rather than a single one in order to predict partner‐specific binding sites, outperforming state‐of‐the‐art methods.
Highly accurate protein structure prediction with AlphaFold
This work validated an entirely redesigned version of the neural network-based model, AlphaFold, in the challenging 14th Critical Assessment of protein Structure Prediction (CASP14)15, demonstrating accuracy competitive with experiment in a majority of cases and greatly outperforming other methods.
Partner-Aware Prediction of Interacting Residues in Protein-Protein Complexes from Sequence Data
It is shown that the models trained on pair-wise contacts outperformed the partner-unaware models in predicting both interacting pairs and interacting single-protein residues.
Deep Learning of High-Order Interactions for Protein Interface Prediction
This work proposes to formulate the protein interface prediction as a 2D dense prediction problem, and proposes a novel deep model to incorporate the sequential information and high-order pairwise interactions to perform interface predictions.
End-to-End Learning on 3D Protein Structure for Interface Prediction
The first end-to-end learning model for protein interface prediction, the Siamese Atomic Surfacelet Network (SASNet), is developed and it is found that SASNet outperforms state-of-the-art methods trained on gold-standard structural data, even when trained on only 3% of the new dataset.