PaleAle 5.0: prediction of protein relative solvent accessibility by deep learning

@article{Kaleel2019PaleAle5P,
  title={PaleAle 5.0: prediction of protein relative solvent accessibility by deep learning},
  author={Manaz Kaleel and Mirko Torrisi and Catherine Mooney and Gianluca Pollastri},
  journal={Amino Acids},
  year={2019},
  volume={51},
  pages={1289 - 1296}
}
Predicting the three-dimensional structure of proteins is a long-standing challenge of computational biology, as the structure (or lack of a rigid structure) is well known to determine a protein’s function. Predicting relative solvent accessibility (RSA) of amino acids within a protein is a significant step towards resolving the protein structure prediction challenge especially in cases in which structural information about a protein is not available by homology transfer. Today, arguably the… 
DeepREx-WS: A web server for characterising protein–solvent interaction starting from sequence
Deep learning methods in protein structure prediction
Recent Applications of Deep Learning Methods on Evolution- and Contact-Based Protein Structure Prediction
TLDR
The recent applications of deep learning methods in the protein structure prediction area are explored and the potential opportunities to identify unknown protein structures and functions to be discovered and help guide drug–target interactions are looked at.
Brewery: deep learning and deeper profiles for the prediction of 1D protein structure annotations
TLDR
The proposed Brewery is a suite of ab initio predictors of 1D Protein Structural Annotations that uses multiple sources of evolutionary information to achieve state-of-the-art predictions of Secondary Structure, Structural Motifs, Relative Solvent Accessibility and Contact Density.
End-to-End Deep Learning Model to Predict and Design Secondary Structure Content of Structural Proteins.
TLDR
A deep learning model is reported to predict the secondary structure content of proteins directly from primary sequences, with high computational efficiency and could be widely applied to biomedical industries, including protein biomaterial designs and regenerative medicine applications.
SCLpred‐MEM: Subcellular localization prediction of membrane proteins by deep N‐to‐1 convolutional neural networks
TLDR
SCLpred-MEM, an ab initio protein subcellular localization predictor, powered by an ensemble of Deep N-to-1 Convolutional Neural Networks (N1-NN) trained and tested on strict redundancy reduced datasets, achieves a Matthews correlation coefficient of 0.52, surpassing or matching other state-of-the-art sub cellular localization predictors.
Solvent Accessibility of Residues Undergoing Pathogenic Variations in Humans: From Protein Structures to Protein Sequences
TLDR
The data support the notion that surface accessible area is a distinguished property of residues that undergo variation and that pathogenicity is more frequently associated to the buried property than to the exposed one.
Accurate Estimation of Solvent Accessible Surface Area for Coarse-Grained Biomolecular Structures with Deep Learning.
TLDR
A deep learning-based SASA estimator (DeepCGSA) is developed, which can provide almost perfect SASA estimation based on CG structures of protein and RNA molecules, and will be highly useful in the protein/RNA structure prediction, drug design, and other applications, in which accurate estimations of SASA for CG biomolecular structures are critically important.
...
1
2
...

References

SHOWING 1-10 OF 46 REFERENCES
Accurate prediction of solvent accessibility using neural networks–based regression
TLDR
A novel method for improved prediction of relative solvent accessibilities (RSAs) of amino acid residues in proteins using nonlinear regression, with several feed forward and recurrent neural networks, which are then combined into a consensus predictor.
Linear Regression Models for Solvent Accessibility Prediction in Proteins
TLDR
This work investigates several regression models for RSA prediction using linear L1-support vector regression (SVR) approaches as well as standard linear least squares (LS) regression, and compares the performance of the SVR with that of LS regression and NN-based methods.
Beyond the Twilight Zone: Automated prediction of structural properties of proteins by recursive neural networks and remote homology information
TLDR
It is shown that structural information from homologues improves prediction accuracy well beyond the Twilight Zone of sequence similarity, even below 5% sequence identity, for all four structural properties.
Exploiting the past and the future in protein secondary structure prediction
TLDR
A family of novel architectures which can learn to make predictions based on variable ranges of dependencies are introduced, extending recurrent neural networks and introducing non-causal bidirectional dynamics to capture both upstream and downstream information.
Porter, PaleAle 4.0: high-accuracy prediction of protein secondary structure and relative solvent accessibility
TLDR
It is shown that the increasing training set sizes that come with the continuing growth of the Protein Data Bank keep yielding prediction quality improvements and the impact of protein resolution on prediction performances is examined.
RaptorX-Property: a web server for protein structure property prediction
TLDR
This server employs a powerful in-house deep learning model DeepCNF (Deep Convolutional Neural Fields) to predict secondary structure (SS), solvent accessibility (ACC) and disorder regions (DISO) and it outperforms other servers, especially for proteins without close homologs in PDB or with very sparse sequence profile.
Prediction of protein relative solvent accessibility with a two‐stage SVM approach
TLDR
A two‐stage approach with support vector machines (SVMs) is proposed, where an SVM predictor is introduced to the output of the single‐stage SVM approach to take into account the contextual relationships among solvent accessibilities for the prediction of protein RSA prediction.
SSpro/ACCpro 5: almost perfect prediction of protein secondary structure and relative solvent accessibility using profiles, machine learning and structural similarity
TLDR
These problems of secondary structure and relative solvent accessibility appear now to be essentially solved, as an accuracy of 100% cannot be expected for several well-known reasons.
Combining evolutionary information and neural networks to predict protein secondary structure
TLDR
This work extends the previous three‐level system of neural networks by using additional input information derived from multiple alignments using a position‐specific conservation weight as part of the input to increase performance and greatly increased accuracy.
RSARF: prediction of residue solvent accessibility from protein sequence using random forest method.
TLDR
Comparison of RSARF with other methods using a benchmark dataset containing 20 proteins shows that the approach is useful for prediction of residue solvent accessibility from protein sequence without using structural information.
...
1
2
3
4
5
...