ProDCoNN: Protein design using a convolutional neural network

By Yuan Zhang, Yang Chen, Chenran Wang, Chun-chao Lo, Xiuwen Liu, Wei Wu, Jinfeng Zhang. 2019

71 citations recorded by the source corpus.

Designing protein sequences that fold to a given three‐dimensional (3D) structure has long been a challenging problem in computational structural biology with significant theoretical and practical implications. In this study, we first formulated this problem as predicting the residue type given the 3D structural environment around the C α atom of a residue, which is repeated for each residue of a protein. We designed a nine‐layer 3D deep convolutional neural network (CNN) that takes as input a gridded box with the atomic coordinates and types around a residue. Several CNN layers were designed to capture structure information at different scales, such as bond lengths, bond angles, torsion angles, and secondary structures. Trained on a very large number of protein structures, the method, called ProDCoNN (protein design with CNN), achieved state‐of‐the‐art performance when tested on large numbers of test proteins and benchmark datasets.

Subfields: Artificial Intelligence, Molecular Biology, Computational Chemistry & Drug Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

In Computational Chemistry & Drug Discovery

Citations in the corpus

Robust deep learning based protein sequence design using ProteinMPNN (2022, methodology): “Acta Crystallographica Section D: Biological Crystallography, 66(2), 213-221.”
Learning inverse folding from millions of predicted structures (2022, methodology): “…deep learning methods have also been applied to predict amino acid propensities given the surrounding local structural environments (Anand-Achim et al., 2021; Boomsma & Frellsen, 2017; Shroff et al., 2020; Li et al., 2020; Qi & Zhang, 2020; Zhang et al., 2020; Chen et al., 2019; Wang et al., 2018).”
Protein sequence design with a learned potential (2022, methodology): “Structure-based machine learning methods for design thus far have focused on mutation prediction 25 – 30 , rotamer repacking of native sequences 31 , or amino acid sequence design without modeling side-chain conformers 32 – 35 , with some experimental validation including circular dichroism data 33…”
Learning from Protein Structure with Geometric Vector Perceptrons (2020, methodology): “All predictions were obtained from the CASP download center as described by Baldassarre et al. (2020). difference between the two methods is that ProDCoNN has 4 convolutional layers and DenseCPD has 21 layers organized into dense residual blocks.”
DenseCPD: Improving the Accuracy of Neural-Network-Based Computational Protein Sequence Design with DenseNet (2020, background): “Citation information: Qi, Yifei; Zhang, John Z.H. (2020): DenseCPD: Improving the Accuracy of”
Protein sequence design with a learned potential (2020, methodology): “Previous machine learning models for the task of residue prediction conditioned on chemical environment have only been applied to single-shot residue prediction or architecture class, secondary structure, or ∆∆G prediction [60, 89, 62, 63, 61].”