Abstract
BackgroundA number of sequence-based methods exist for protein secondary structure prediction. Protein secondary structures can also be determined experimentally from circular dichroism, and infrared spectroscopic data using empirical analysis methods. It has been proposed that comparable accuracy can be obtained from sequence-based predictions as from these biophysical measurements. Here we have examined the secondary structure determination accuracies of sequence prediction methods with the empirically determined values from the spectroscopic data on datasets of proteins for which both crystal structures and spectroscopic data are available.ResultsIn this study we show that the sequence prediction methods have accuracies nearly comparable to those of spectroscopic methods. However, we also demonstrate that combining the spectroscopic and sequences techniques produces significant overall improvements in secondary structure determinations. In addition, combining the extra information content available from synchrotron radiation circular dichroism data with sequence methods also shows improvements.ConclusionCombining sequence prediction with experimentally determined spectroscopic methods for protein secondary structure content significantly enhances the accuracy of the overall results obtained.
Highlights
A number of sequence-based methods exist for protein secondary structure prediction
In this study we have examined the performance of sequence based prediction methods using a neural network methodology, versus the experimentally-determined methods of Circular dichroism (CD) and Fourier transform infrared (FTIR) for assessing secondary structure content
The secondary structure content prediction for sequence prediction methods is generally not reported after publication of the crystal structure
Summary
A number of sequence-based methods exist for protein secondary structure prediction. Protein secondary structures can be determined experimentally from circular dichroism, and infrared spectroscopic data using empirical analysis methods. We have examined the secondary structure determination accuracies of sequence prediction methods with the empirically determined values from the spectroscopic data on datasets of proteins for which both crystal structures and spectroscopic data are available. There has been a growth in the number of crystal structures of proteins as the result of Structural Protemics programmes worldwide, their production has not kept pace with the sequencing effort. Such programmes often produce small amounts of any given protein which are not enough for crystal structure analysis. These quantities are often sufficient for other biophysical studies. Recent years have seen large improvements in the per-residue secondary structure prediction from sequence [1,2],
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
