ProSPr: Democratized Implementation of Alphafold Protein Distance Prediction Network

@article{Billings2019ProSPrDI,
  title={ProSPr: Democratized Implementation of Alphafold Protein Distance Prediction Network},
  author={Wendy M Billings and Bryce Hedelius and Todd Millecam and David Wingate and Dennis Della Corte},
  journal={bioRxiv},
  year={2019}
}
Deep neural networks have recently enabled spectacular progress in predicting protein structures, as demonstrated by DeepMin’s winning entry with Alphalfold at the latest Critical Assessment, of Structure Prediction competition (CASP13). The best protein prediction pipeline leverages intermolecular distance predictions to assemble a final protein model, but this distance prediction network has not been published. Here, we make a trained implementation of this network available to the broader… 

Evaluation of Deep Neural Network ProSPr for Accurate Protein Distance Predictions on CASP14 Targets

TLDR
Important updates to the ProSPr network are reported, its performance on the recent Critical Assessment of Structure Prediction (CASP14) competition is reported, and an evaluation of its accuracy dependency on multiple sequence alignment depth is evaluated.

Evaluation of Deep Neural Network ProSPr for Accurate Protein Distance Predictions on CASP14 Targets

TLDR
Important updates to the ProSPr network are reported, its performance in the recent Critical Assessment of Techniques for Protein Structure Prediction (CASP14) competition is reported, and an evaluation of its accuracy dependency on sequence length and multiple sequence alignment depth is evaluated.

Deep Learning-Based Advances in Protein Structure Prediction

TLDR
Important milestones and progresses in the field of protein structure prediction due to DL-based methods as observed in CASP experiments are highlighted and advances in various steps ofprotein structure prediction pipeline viz. protein contact map prediction, protein distogram prediction,protein real-valued distance prediction, and Quality Assessment/refinement are described.

The whole is greater than its parts: ensembling improves protein contact prediction

TLDR
It is shown that ensembling the predictions made by different groups at the recent Critical Assessment of Protein Structure Prediction (CASP13) outperforms all individual groups, and contacts derived from the distance predictions of three additional deep neural networks—AlphaFold, trRosetta, and ProSPr—can be substantially improved by ensembled all three networks.

Deep Learning Approach with Rotate-Shift Invariant Input to Predict Protein Homodimer Structure

TLDR
A two-staged approach which consists of deep convolutional neural network to predict protein contact map for homodimers and optimization procedure based on gradient descent to build the homodimer structure from the contact map.

Protein Structure Prediction Using a Maximum Likelihood Formulation of a Recurrent Geometric Network

TLDR
This work improves upon an existing DL algorithm for protein structure prediction, the Recurrent Geometric Network (RGN), and derives a maximum likelihood loss function that incorporates experimental uncertainty data into model training and results in more accurate structure prediction.

Protein homodimers structure prediction based on deep neural network

TLDR
An algorithm to model the 3D structure of homodimer based on deep learning using the use of the neural network in combination with optimization procedure based on gradient descent method allowed to predict structures for protein homodimers.

Protein sequence‐to‐structure learning: Is this the end(‐to‐end revolution)?

TLDR
An overview and opinion of the novel deep learning approaches developed in the last 2 years and widely used in CASP14 are provided.

DeeplyTough: Learning Structural Comparison of Protein Binding Sites.

TLDR
DeeplyTough is proposed, a convolutional neural network that encodes a three-dimensional representation of protein pockets into descriptor vectors that may be compared efficiently in an alignment-free manner by computing pairwise Euclidean distances.

Structural discrimination analysis for constraint selection in protein modeling

TLDR
This work introduces a constraint evaluation and selection method based on the point-biserial correlation coefficient, which utilizes structural information from an ensemble of models to indirectly measure the power of each constraint in biasing the conformational search towards consensus structures.

References

SHOWING 1-10 OF 14 REFERENCES

Assessment of contact predictions in CASP12: Co‐evolution and deep learning coming of age

TLDR
The analysis of predictions submitted for CASP12 includes predictions of 34 groups for 38 domains classified as free modeling targets which are not accessible to homology‐based modeling due to a lack of structural templates.

Improved contact prediction in proteins: using pseudolikelihoods to infer Potts models.

TLDR
The pseudolikelihood method, applied to 21-state Potts models describing the statistical properties of families of evolutionarily related proteins, significantly outperforms existing approaches to the direct-coupling analysis, the latter being based on standard mean-field techniques.

End-to-end differentiable learning of protein structure

TLDR
The first end‐to‐end differentiable model of protein structure that couples local and global protein structure via geometric units that optimize global geometry without violating local covalent chemistry is reported.

HHblits: lightning-fast iterative protein sequence searching by HMM-HMM alignment

TLDR
An open-source, general-purpose tool that represents both query and database sequences by profile hidden Markov models (HMMs): 'HMM-HMM–based lightning-fast iterative sequence search' (HHblits; http://toolkit.genzentrum.lmu.de/hhblits/).

Gapped BLAST and PSI-BLAST: a new generation of protein database search programs.

TLDR
A new criterion for triggering the extension of word hits, combined with a new heuristic for generating gapped alignments, yields a gapped BLAST program that runs at approximately three times the speed of the original.

SMARCAD1 ATPase activity is required to silence endogenous retroviruses in embryonic stem cells

TLDR
The authors show that the ATPase function of the chromatin remodeler SMARCAD1 facilitates the binding of KAP1 to ERVs and is required for their repression in embryonic stem cells.

An introduction to Docker for reproducible research

TLDR
How the popular emerging technology Docker combines several areas from systems research - such as operating system virtualization, cross-platform portability, modular re-usable elements, versioning, and a 'DevOps' philosophy, to address these challenges is examined.

Hum

The Potts model