SPINE X: Improving protein secondary structure prediction by multi-step learning coupled with prediction of solvent accessible surface area and backbone torsion angles

By Eshel Faraggi, Tuo Zhang, Yuedong Yang, Lukasz Kurgan, Yaoqi Zhou. 2011

258 citations recorded by the source corpus.

Accurate prediction of protein secondary structure is essential for accurate sequence alignment, three‐dimensional structure modeling, and function prediction. The accuracy of ab initio secondary structure prediction from sequence, however, has only increased from around 77 to 80% over the past decade. Here, we developed a multistep neural‐network algorithm by coupling secondary structure prediction with prediction of solvent accessibility and backbone torsion angles in an iterative manner. Our method called SPINE X was applied to a dataset of 2640 proteins (25% sequence identity cutoff) previously built for the first version of SPINE and achieved a 82.0% accuracy based on 10‐fold cross validation (Q3). Surpassing 81% accuracy by SPINE X is further confirmed by employing an independently built test dataset of 1833 protein chains, a recently built dataset of 1975 proteins and 117 CASP 9 targets (critical assessment of structure prediction techniques) with an accuracy of 81.3%, 82.3% and 81.8%, respectively. The prediction accuracy is further improved to 83.8% for the dataset of 2640 proteins if the DSSP assignment used above is replaced by a more consistent consensus secondary structure assignment method. Comparison to the popular PSIPRED and CASP‐winning structure‐prediction techniques is made. SPINE X predicts number of helices and sheets correctly for 21.0% of 1833 proteins, compared to 17.6% by PSIPRED. It further shows that SPINE X consistently makes more accurate prediction in helical residues (6%) without over prediction while PSIPRED makes more accurate prediction in coil residues (3–5%) and over predicts them by 7%. SPINE X Server and its training/test datasets are available at http://sparks.informatics.iupui.edu/ © 2011 Wiley Periodicals, Inc. J Comput Chem, 2012

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

RaptorX-Property: a web server for protein structure property prediction (2016, methodology): “Since SOLVPRED, SPINE-X and ACCpro predict real-valued relative solvent accessibility, we use the same 10% / 40% threshold as our ACC definition to re-label their output.”
Predicting backbone Cα angles and dihedrals from protein sequences by stacked sparse auto‐encoder deep neural network (2014, methodology): “The lowest accuracy at 90-100% solvent accessibility is likely due to the smallest number of residues at 90-100% solvent-accessible and 20% more coil residues in fully exposed residues [3].”
Protein Secondary Structure Prediction Using Cascaded Convolutional and Recurrent Neural Networks (2016, methodology): “In order to further improve accuracy and robustness, we also compute an ensemble model by averaging 10 weak mod-Table SPINE-X [ Faraggi et al. , 2012 ] , PSIPRED [ Jones, 1999 ] , RaptorX-SS 8 , JPRED [ Drozdetskiy et al. , 2015 ] and DeepCNF.”
Sixty-five years of the long march in protein secondary structure prediction: the final stretch? (2016, methodology): “The angle accuracy has been substantially improved over the years [94, 125, 126] with the highest accuracy reported by SPIDER2 (MAE 1⁄4 19 for / and 30 for w using an independent test of 1199 high-resolution non-redundant proteins) [57].”
Energy functions in de novo protein design: current challenges and future prospects. (2013, methodology): “We employed SPINE-X for secondary structure prediction, which achieves 81–82% accuracy for large benchmark tests (32).”
RaptorX-Angle: real-value prediction of protein backbone dihedral angles through a hybrid method of clustering and deep learning (2018, background): “Firstly, dihedral angle prediction may act as substitute or supplement for secondary structure prediction [4–6].”
Intrinsically Semi-disordered State and Its Role in Induced Folding and Protein Aggregation (2013, background): “To characterize a semi-disordered state, we compare fractions of secondary structures (helical and strand residues) predicted by SPINE-X [16] and fractions of exposed residues predicted by Real-SPINE 3 [17] for long ordered, semi-disordered, and fully disordered regions ([30 residues) of the protein”
Large-scale model quality assessment for improving protein tertiary structure prediction (2015, methodology): “During CASP11, each predictor submitted up to five predicted model with the first one (TS1) designated as the best model.”