Premium
FRankenstein becomes a cyborg: The automatic recombination and realignment of fold recognition models in CASP6
Author(s) -
Kosinski Jan,
Gajda Michal J.,
Cymerman Iwona A.,
Kurowski Michal A.,
Pawlowski Marcin,
Boniecki Michal,
Obarska Agnieszka,
Papaj Grzegorz,
SroczynskaObuchowicz Paulina,
Tkaczuk Karolina L.,
Sniezynska Paulina,
Sasin Joanna M.,
Augustyn Anna,
Bujnicki Janusz M.,
Feder Marcin
Publication year - 2005
Publication title -
proteins: structure, function, and bioinformatics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.699
H-Index - 191
eISSN - 1097-0134
pISSN - 0887-3585
DOI - 10.1002/prot.20726
Subject(s) - computer science , monster , sequence (biology) , artificial intelligence , model building , superposition principle , construct (python library) , algorithm , pattern recognition (psychology) , programming language , mathematics , biology , genetics , art , physics , art history , mathematical analysis , quantum mechanics
In the course of CASP6, we generated models for all targets using a new version of the “FRankenstein's monster approach.” Previously (in CASP5) we were able to build many very accurate full‐atom models by selection and recombination of well‐folded fragments obtained from crude fold recognition (FR) results, followed by optimization of the sequence–structure fit and assessment of alternative alignments on the structural level. This procedure was however very arduous, as most of the steps required extensive visual and manual input from the human modeler. Now, we have automated the most tedious steps, such as superposition of alternative models, extraction of best‐scoring fragments, and construction of a hybrid “monster” structure, as well as generation of alternative alignments in the regions that remain poorly scored in the refined hybrid model. We have also included the ROSETTA method to construct those parts of the target for which no reasonable structures were generated by FR methods (such as long insertions and terminal extensions). The analysis of successes and failures of the current version of the FRankenstein approach in modeling of CASP6 targets reveals that the considerably streamlined and automated method performs almost as well as the initial, mostly manual version, which suggests that it may be a useful tool for accurate protein structure prediction even in the hands of nonexperts. Proteins 2005;Suppl 7:106–113. © 2005 Wiley‐Liss, Inc.