deep learning applied to sa prediction hai'e gong mar 22ndcasp/temp/20160322.pdf · mat lab...
Post on 25-Mar-2018
218 Views
Preview:
TRANSCRIPT
Deep learning applied to SA prediction
Hai'e GongMar 22nd, 2016
● Improving prediction of secondary structure, local backbone angles, and solvent accessible surface area of proteins by iterative deep learning
● Rhys Heffernan, Kuldip Paliwal, James Lyons, Abdollah Dehzangi, Alok Sharma, Jihua Wang, Abdul Sattar, Yuedong Yang, Yaoqi Zhou
● Scientific Reports
Abstract
Protein structure prediction
Secondary structure
Angles
ASA
The contribution of iteration
Related work
This method: SPIDER2
Datasets
Model
Architechture
Iterative algorithm
Iteration performace
Iteration performace on SS
Iteration performace on prediction accuracy of angles
RMSD of constructed structures by angles
Comparision with other tools
Q3 and its misclassifications
Comparision with models in CASP 11
Contructed structures by angles
The contribution of other structural info except for predicted SS
Applications of the prediction results
Summary
● Use angles as features when predicting strutural information.
● Apply architecture of iterative algorithms to our work.
● Use bigger dataset.● Broaden the window size around the target
residue.
top related