Premium
Neural networks for secondary structure and structural class predictions
Author(s) -
Chandonia JohnMarc,
Karplus Martin
Publication year - 1995
Publication title -
protein science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 3.353
H-Index - 175
eISSN - 1469-896X
pISSN - 0961-8368
DOI - 10.1002/pro.5560040214
Subject(s) - jackknife resampling , artificial neural network , protein secondary structure , overtraining , class (philosophy) , set (abstract data type) , artificial intelligence , computer science , measure (data warehouse) , test set , network structure , filter (signal processing) , machine learning , protein tertiary structure , data mining , pattern recognition (psychology) , mathematics , biology , statistics , medicine , biochemistry , estimator , computer vision , athletes , programming language , physical therapy
A pair of neural network‐based algorithms is presented for predicting the tertiary structural class and the secondary structure of proteins. Each algorithm realizes improvements in accuracy based on information provided by the other. Structural class prediction of proteins nonhomologous to any in the training set is improved significantly, from 62.3% to 73.9%, and secondary structure prediction accuracy improves slightly, from 62.26% to 62.64%. A number of aspects of neural network optimization and testing are examined. They include network overtraining and an output filter based on a rolling average. Secondary structure prediction results vary greatly depending on the particular proteins chosen for the training and test sets; consequently, an appropriate measure of accuracy reflects the more unbiased approach of “jackknife” cross‐validation (testing each protein in the database individually).