% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Mulnaes:893374,
author = {Mulnaes, Daniel and Golchin, Pegah and Koenig, Filip and
Gohlke, Holger},
title = {{T}op{D}omain: {E}xhaustive {P}rotein {D}omain {B}oundary
{M}etaprediction {C}ombining {M}ultisource {I}nformation and
{D}eep {L}earning},
journal = {Journal of chemical theory and computation},
volume = {17},
number = {7},
issn = {1549-9626},
address = {Washington, DC},
reportid = {FZJ-2021-02715},
pages = {4599–4613},
year = {2021},
abstract = {Protein domains are independent, functional, and stable
structural units of proteins. Accurate protein domain
boundary prediction plays an important role in understanding
protein structure and evolution, as well as for protein
structure prediction. Current domain boundary prediction
methods differ in terms of boundary definition, methodology,
and training databases resulting in disparate performance
for different proteins. We developed TopDomain, an
exhaustive metapredictor, that uses deep neural networks to
combine multisource information from sequence- and
homology-based features of over 50 primary predictors. For
this purpose, we developed a new domain boundary data set
termed the TopDomain data set, in which the true annotations
are informed by SCOPe annotations, structural domain
parsers, human inspection, and deep learning. We benchmark
TopDomain against 2484 targets with 3354 boundaries from the
TopDomain test set and achieve F1 scores of $78.4\%$ and
$73.8\%$ for multidomain boundary prediction within ±20
residues and ±10 residues of the true boundary,
respectively. When examined on targets from CASP11-13
competitions, TopDomain achieves F1 scores of $47.5\%$ and
$42.8\%$ for multidomain proteins. TopDomain significantly
outperforms 15 widely used, state-of-the-art ab initio and
homology-based domain boundary predictors. Finally, we
implemented TopDomainTMC, which accurately predicts whether
domain parsing is necessary for the target protein.},
cin = {JSC / NIC / IBI-7 / IBG-4},
ddc = {610},
cid = {I:(DE-Juel1)JSC-20090406 / I:(DE-Juel1)NIC-20090406 /
I:(DE-Juel1)IBI-7-20200312 / I:(DE-Juel1)IBG-4-20200403},
pnm = {5111 - Domain-Specific Simulation Data Life Cycle Labs
(SDLs) and Research Groups (POF4-511) / 2171 - Biological
and environmental resources for sustainable use (POF4-217) /
2172 - Utilization of renewable carbon and energy sources
and engineering of ecosystem functions (POF4-217) /
Forschergruppe Gohlke $(hkf7_20200501)$ / DFG project
267205415 - SFB 1208: Identität und Dynamik von
Membransystemen - von Molekülen bis zu zellulären
Funktionen},
pid = {G:(DE-HGF)POF4-5111 / G:(DE-HGF)POF4-2171 /
G:(DE-HGF)POF4-2172 / $G:(DE-Juel1)hkf7_20200501$ /
G:(GEPRIS)267205415},
typ = {PUB:(DE-HGF)16},
pubmed = {34161735},
UT = {WOS:000674289800059},
doi = {10.1021/acs.jctc.1c00129},
url = {https://juser.fz-juelich.de/record/893374},
}