CONFOLD2: improved contact-driven ab initio protein structure modeling

By Badri Adhikari, Jianlin Cheng. 2017

72 citations recorded by the source corpus.

Contact-guided protein structure prediction methods are becoming more and more successful because of the latest advances in residue-residue contact prediction. To support contact-driven structure prediction, effective tools that can quickly build tertiary structural models of good quality from predicted contacts need to be developed. We develop an improved contact-driven protein modelling method, CONFOLD2, and study how it may be effectively used for ab initio protein structure prediction with predicted contacts as input. It builds models using various subsets of input contacts to explore the fold space under the guidance of a soft square energy function, and then clusters the models to obtain the top five models. CONFOLD2 obtains an average reconstruction accuracy of 0.57 TM-score for the 150 proteins in the PSICOV contact prediction dataset. When benchmarked on the CASP11 contacts predicted using CONSIP2 and CASP12 contacts predicted using Raptor-X, CONFOLD2 achieves a mean TM-score of 0.41 on both datasets. CONFOLD2 allows to quickly generate top five structural models for a protein sequence when its secondary structures and contacts predictions at hand. The source code of CONFOLD2 is publicly available at https://github.com/multicom-toolbox/CONFOLD2/.

Subfields: Materials Chemistry, Molecular Biology

How researchers see this paper

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

In Materials Chemistry

In Molecular Biology

Citations in the corpus

Analysis of several key factors influencing deep learning-based inter-residue contact prediction (2019, background): “Therefore, the contact distance-based ab initio 3D protein structure modeling calls for the development of more precise and sensitive contact prediction (Adhikari and Cheng, 2018; Brunger et al., 1998; Hou et al., 2019; Michel et al., 2017; Pollastri and Baldi, 2002).”
Deep learning extends de novo protein modelling coverage of genomes using iteratively predicted structural constraints (2018, methodology): “For example, CONFOLD2 [9] and EVfold [10] add constraints from predicted contacts to standard inter-atomic distance constraints, then use software such as CNS [11] to generate coordinates from these constraints.”
SE(3)-Equivariant Energy-based Models for End-to-End Protein Folding (2021, background): “In [2, 48, 30, 17], deep networks are introduced to predict inter-residue contacts, distance, and/or orientations, which are then transformed into additional restraints or differentiable energy terms for structure optimization.”
Protein tertiary structure modeling driven by deep learning and contact distance prediction in CASP13 (2019, methodology): “The more detailed distance predictions will be used to more accurately fold proteins by the distance geometry, 42,52 simulated annealing and advanced gradient descent optimization 72,73 as well as to rank protein models.”
Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking (2021, methodology): “Deep neural networks have been used to predict inter-residue contacts, distance and/or orientations (Adhikari and Cheng, 2018; Yang et al., 2020; Senior et al., 2020; Ju et al., 2021), that are subsequently transformed into additional constraints or differentiable energy terms for protein structure…”