A novel approach to infer protein topology using the state-of-the-art graph neural network (GNN), SchNet, trained on the same dataset used to develop the recent DeepTMHMM model with 5-fold cross-validation.
A novel approach to infer protein topology using the state-of-the-art graph neural network (GNN), SchNet, trained on the same dataset used to develop the recent DeepTMHMM model with 5-fold cross-validation.
DHST is proposed, a deep hybrid structure–topology framework that integrates sequence semantics from a pretrained protein language model with local structural information learned by a residual graph convolutional network and introduces site-specific persistent homology to encode multi-scale topological invariants and a...
Bin Lu, Fujun Xiang, Hai-Long Wang et al.· Applied Sciences· 0 citations
The DeltaFold Classifier (DFC) is introduced, a fast, alignment-free, protein structure classification pipeline based on topological data analysis that achieves performance comparable to that of structure-based comparison methods while substantially improving computational efficiency.
Joseph Nardin-Gennequin, Gabriela Ciuperca, Céline Brochier-Armanet et al.· Proteins: Structure, Functio...· 0 citations
Accurate identification of protein-protein interactions (PPIs) is fundamental for understanding cellular mechanisms and facilitating drug discovery. Although high-throughput experimental methods have expanded the known interactome, they remain resourceintensive and prone to noise. Consequently, computational approaches...
Pantelis Makrygiannis, Nikitas-Rigas Kalogeropoulos, Agorakis Bompotas et al.· International journal on art...· 0 citations
A new deep-learning model for predicting MPIs, which outperformed several existing MPI prediction models and related models adapted to this task and captured higher-order relationships at different scales and expanding the feature-learning space.
Lei Chen, Zhi-Tong Jin, Ying Shao et al.· Briefings in Bioinformatics· 0 citations
MOTIVATION
The identification of compound-protein interactions (CPIs) is crucial in the early stages of drug discovery. However, machine-learning (ML)-based methods based on one- and two-dimensional representations cannot capture important geometric information on the binding sites of CPIs, which limits their predictiv...
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
