• Corpus ID: 234357669

EBM-Fold: Fully-Differentiable Protein Folding Powered by Energy-based Models

  title={EBM-Fold: Fully-Differentiable Protein Folding Powered by Energy-based Models},
  author={Jiaxiang Wu and Shitong Luo and Tao Shen and Haidong Lan and Sheng Wang and Junzhou Huang},
Accurate protein structure prediction from amino-acid sequences is critical to better understanding proteins’ function. Recent advances in this area largely benefit from more precise inter-residue distance and orientation predictions, powered by deep neural networks. However, the structure optimization procedure is still dominated by traditional tools, e.g. Rosetta, where the structure is solved via minimizing a pre-defined statistical energy function (with optional prediction-based restraints… 

SE(3)-Equivariant Energy-based Models for End-to-End Protein Folding

This paper proposes an end-to-end approach for protein structure optimization, powered by SE(3)-equivariant energy-based models, and introduces continuously-annealed Langevin dynamics as a novel sampling algorithm that converges to native protein structures with theoretical guarantees.

Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem

This work proposes to learn a distribution over diverse and longer protein backbone structures via an E(3)equivariant graph neural network and develops SMCDiff to efficiently sample scaffolds from this distribution conditioned on a given motif, and is the first to theoretically guarantee conditional samples from a diffusion model in the largecompute limit.

Differentiable biology: using deep learning for biophysics-based and data-driven modeling of molecular mechanisms.

By distilling differentiable biology into a small set of conceptual primitives and illustrative vignettes, it is shown how it can help to address long-standing challenges in integrating multimodal data from diverse experiments across biological scales.



Improved protein structure prediction using potentials from deep learning

It is shown that a neural network can be trained to make accurate predictions of the distances between pairs of residues, which convey more information about the structure than contact predictions, and the resulting potential can be optimized by a simple gradient descent algorithm to generate structures without complex sampling procedures.

DESTINI: A deep-learning approach to contact-driven protein structure prediction

This work introduces DESTINI (deep structural inference for proteins), a novel computational approach that combines a deep-learning algorithm for protein residue/residue contact prediction with template-based structural modelling, and presents a promising strategy towards solving the protein structure prediction problem.

Improved protein structure prediction using predicted interresidue orientations

A deep residual network for predicting interresidue orientations, in addition to distances, and a Rosetta-constrained energy-minimization protocol for rapidly and accurately generating structure models guided by these restraints are developed.

Generative modeling for protein structures

This work applies Generative Adversarial Networks (GANs) to the task of generating protein structures, and encodes protein structures in terms of pairwise distances between alpha-carbons on the protein backbone, which eliminates the need for the generative model to learn translational and rotational symmetries.

The MULTICOM Protein Structure Prediction Server Empowered by Deep Learning and Contact Distance Prediction.

A practical guide for the latest MULTICOM protein structure prediction system built on top of the latest advances, which was rigorously tested in the 2018 CASP13 experiment.

Energy-based models for atomic-resolution protein conformations

An investigation of the model’s outputs and hidden representations find that it captures physicochemical properties relevant to protein energy.

Analysis of distance-based protein structure prediction by deep learning in CASP13

This CASP13 test confirms the previous findings: (1) predicted distance is more useful than contacts for both template-based and free modeling; and (2) structure modeling may be improved by integrating alignment and co-evolutionary information via deep learning.

Protein structure prediction using multiple deep neural networks in the 13th Critical Assessment of Protein Structure Prediction (CASP13)

AlphaFold, the protein structure prediction system that was entered by the group A7D in CASP13, shows that simple gradient descent on a properly constructed potential is able to perform on par with more expensive traditional search techniques and without requiring domain segmentation.

Protein tertiary structure modeling driven by deep learning and contact distance prediction in CASP13

The success of MULTICOM system in the CASP13 experiment clearly shows that protein contact distance prediction and model selection driven by powerful deep learning holds the key of solving protein structure prediction problem.

CONFOLD2: improved contact-driven ab initio protein structure modeling

An improved contact-driven protein modelling method, CONFOLD2, which allows to quickly generate top five structural models for a protein sequence when its secondary structures and contacts predictions at hand.