% 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{Kryshtafovych:641980,
author = {Kryshtafovych, Andriy and Schwede, Torsten and Topf, Maya
and Fidelis, Krzysztof and Moult, John},
title = {{P}rogress and {B}ottlenecks for {D}eep {L}earning in
{C}omputational {S}tructure {B}iology: {CASP} {R}ound {XVI}},
journal = {Proteins},
volume = {94},
number = {1},
issn = {0887-3585},
address = {New York, NY},
publisher = {Wiley-Liss},
reportid = {PUBDB-2025-05267},
pages = {5 - 14},
year = {2025},
abstract = {CASP16 is the most recent in a series of community
experiments to rigorously assess the state of the art in
areas of computational structural biology. The field has
advanced enormously in recent years: in early CASPs, the
assessments centered around whether the methods were at all
useful. Now they mostly focus on how near we are to not
needing experiments. In most areas, deep learning methods
dominate, particularly AlphaFold variants and associated
technology. In this round, there is no significant change in
overall agreement between calculated monomer protein
structures and their experimental counterparts, not because
of method deficiencies but because, for most proteins,
agreement is likely as high as can be obtained given
experimental uncertainty. For protein complexes, huge gains
in accuracy were made in the previous CASP, but there still
appears to be room for further improvement. In contrast to
these encouraging results, for RNA structures, the deep
learning methods are notably unsuccessful at present and are
not superior to traditional approaches. Both approaches
still produce very poor results in the absence of structural
homology. For macromolecular ensembles, the small CASP
target set limits conclusions, but generally, in the absence
of structural templates, results tend to be poor and
detailed structures of alternative conformations are usually
of relatively low accuracy. For organic ligand–protein
structures and affinities (important for aspects of drug
design), deep learning methods are substantially more
successful than traditional ones on the relatively easy CASP
target set, though the results often fall short of
experimental accuracy. In the less glamorous but essential
area of methods for estimating the accuracy, previous
results found reliable accuracy estimates at the amino acid
level. The present CASP results show that the best methods
are also largely effective in selecting models of protein
complexes with high interface accuracy. Will upcoming method
improvements overcome the remaining barriers to reaching
experimental accuracy in all categories? We will have to
wait until the next CASP to find out, but there are two
promising trends. One is the combination of traditional
physics-inspired methods and deep learning, and the other is
the expected increase in training data, especially for
ligand–protein complexes.},
cin = {CSSB-LIV/UKE-MT},
ddc = {570},
cid = {$I:(DE-H253)CSSB-LIV_UKE-MT-20220525$},
pnm = {899 - ohne Topic (POF4-899)},
pid = {G:(DE-HGF)POF4-899},
experiment = {EXP:(DE-MLZ)NOSPEC-20140101},
typ = {PUB:(DE-HGF)16},
doi = {10.1002/prot.70076},
url = {https://bib-pubdb1.desy.de/record/641980},
}