Editing Protein structure prediction (section)

===Background===
Early methods of secondary structure prediction, introduced in the 1960s and early 1970s,<ref>{{cite journal |vauthors=Guzzo AV |title=The influence of amino-acid sequence on protein structure |journal=Biophysical Journal |volume=5 |issue=6 |pages=809–22 |date=November 1965 |pmid=5884309 |pmc=1367904 |doi=10.1016/S0006-3495(65)86753-4 |bibcode=1965BpJ.....5..809G}}</ref><ref>
{{cite journal |vauthors=Prothero JW |title=Correlation between the distribution of amino acids and alpha helices |journal=Biophysical Journal |volume=6 |issue=3 |pages=367–70 |date=May 1966 |pmid=5962284 |pmc=1367951 |doi=10.1016/S0006-3495(66)86662-6 |bibcode=1966BpJ.....6..367P}}</ref><ref>
{{cite journal |vauthors=Schiffer M, Edmundson AB |title=Use of helical wheels to represent the structures of proteins and to identify segments with helical potential |journal=Biophysical Journal |volume=7 |issue=2 |pages=121–35 |date=March 1967 |pmid=6048867 |pmc=1368002 |doi=10.1016/S0006-3495(67)86579-2 |bibcode=1967BpJ.....7..121S}}</ref><ref>
{{cite journal |vauthors=Kotelchuck D, Scheraga HA |title=The influence of short-range interactions on protein onformation. II. A model for predicting the alpha-helical regions of proteins |journal=Proceedings of the National Academy of Sciences of the United States of America |volume=62 |issue=1 |pages=14–21 |date=January 1969 |pmid=5253650 |pmc=285948 |doi=10.1073/pnas.62.1.14 |bibcode=1969PNAS...62...14K |doi-access=free}}</ref><ref>
{{cite journal |vauthors=Lewis PN, Go N, Go M, Kotelchuck D, Scheraga HA |title=Helix probability profiles of denatured proteins and their correlation with native structures |journal=Proceedings of the National Academy of Sciences of the United States of America |volume=65 |issue=4 |pages=810–5 |date=April 1970 |pmid=5266152 |pmc=282987 |doi=10.1073/pnas.65.4.810 |bibcode=1970PNAS...65..810L |doi-access=free}}</ref> focused on identifying likely alpha helices and were based mainly on [[helix-coil transition model]]s.<ref name="Froimowitz">{{cite journal |vauthors=Froimowitz M, Fasman GD |title=Prediction of the secondary structure of proteins using the helix-coil transition theory |journal=Macromolecules |volume=7 |issue=5 |pages=583–9 |year=1974 |pmid=4371089 |doi=10.1021/ma60041a009 |bibcode=1974MaMol...7..583F}}</ref> Significantly more accurate predictions that included beta sheets were introduced in the 1970s and relied on statistical assessments based on probability parameters derived from known solved structures. These methods, applied to a single sequence, are typically at most about 60–65% accurate, and often underpredict beta sheets.<ref name="Mount"/> Since the 1980s, [[artificial neural networks]] have been applied to the prediction of protein structures.<ref>{{cite journal |last1=Qian |first1=Ning |last2=Sejnowski |first2=Terry J. |author2-link=Terry Sejnowski |year=1988 |title=Predicting the secondary structure of globular proteins using neural network models.|url=http://www.columbia.edu/~nq6/publications/protein.pdf|journal=Journal of Molecular Biology|volume=202|issue=4|pages=865–884|doi=10.1016/0022-2836(88)90564-5|pmid=3172241|id=Qian1988}}</ref><ref>{{cite journal|last1=Rost|first1=Burkhard|author-link1=Burkhard Rost|last2=Sander|first2=Chris|year=1993|title=Prediction of protein secondary structure at better than 70% accuracy|url=http://www.cs.albany.edu/~berg/sta650/Assignments/RostSander93.pdf|journal=Journal of Molecular Biology|volume=232|issue=2|pages=584–599|doi=10.1006/jmbi.1993.1413|pmid=8345525|id=Rost1993|access-date=2023-04-20|archive-date=2019-01-31|archive-url=https://web.archive.org/web/20190131040806/http://www.cs.albany.edu/~berg/sta650/Assignments/RostSander93.pdf|url-status=dead}}</ref>
The [[evolution]]ary [[conservation (genetics)|conservation]] of secondary structures can be exploited by simultaneously assessing many [[Sequence homology|homologous sequences]] in a [[multiple sequence alignment]], by calculating the net secondary structure propensity of an aligned column of amino acids. In concert with larger databases of known protein structures and modern [[machine learning]] methods such as [[artificial neural network|neural nets]] and [[support vector machine]]s, these methods can achieve up to 80% overall accuracy in [[globular protein]]s.<ref name="Dor">{{cite journal |vauthors=Dor O, Zhou Y |title=Achieving 80% ten-fold cross-validated accuracy for secondary structure prediction by large-scale training |journal=Proteins |volume=66 |issue=4 |pages=838–45 |date=March 2007 |pmid=17177203 |doi=10.1002/prot.21298 |s2cid=14759081}}</ref> The theoretical upper limit of accuracy is around 90%,<ref name="Dor"/> partly due to idiosyncrasies in DSSP assignment near the ends of secondary structures, where local conformations vary under native conditions but may be forced to assume a single conformation in crystals due to packing constraints. Moreover, the typical secondary structure prediction methods do not account for the influence of [[tertiary structure]] on formation of secondary structure; for example, a sequence predicted as a likely helix may still be able to adopt a beta-strand conformation if it is located within a beta-sheet region of the protein and its side chains pack well with their neighbors. Dramatic conformational changes related to the protein's function or environment can also alter local secondary structure.