A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Filters
Non-equilibrium molecular geometries in graph neural networks
[article]
2022
arXiv
pre-print
In this work we investigate the impact of using non-DFT conformations in the training and the testing of existing models and propose a data augmentation method for improving the prediction accuracy of ...
Recently proposed methods have demonstrated that using 3D geometry information of the molecule along with the bonding structure can lead to more accurate prediction on a wide range of properties. ...
Acknowledgments and Disclosure of Funding The authors acknowledge the National Science Foundation for support under grants No. 1920945 and No. 1521687. ...
arXiv:2203.04697v1
fatcat:vtxwrcunc5gd5k5qinntmhr5z4
Conformer generation under restraints
2006
Current Opinion in Structural Biology
NF is supported by the UK Biotechnology and Biological Sciences Research Council. ...
For example, simply generating conformers around a putative model followed by minimization results in a significant improvement in structure prediction [32] and determination [21] . ...
A fruitful direction for Conformer generation under restraints de Bakker et al. 163 Table 1 Applications of restraint-based conformer generation. ...
doi:10.1016/j.sbi.2006.02.001
pmid:16483766
fatcat:5xuwicr2inbvtavt2wml7pcyqi
AlphaFold2 has more to learn about protein energy landscapes
[article]
2023
biorxiv/medrxiv
by the diversity and frequency of different conformations in the folded state. ...
These results indicate that AF2 has more to learn about the underlying energetics of protein ensembles and highlight the need for further developments of methods that readily predict multiple protein conformations ...
This work utilized resources from the NIH HPS Biowulf cluster (http://hpc.nih.gov), and it was supported by the Intramural Research Program of the National Library of Medicine, National Institutes of Health ...
doi:10.1101/2023.12.12.571380
pmid:38168383
pmcid:PMC10760193
fatcat:sgdqveqxojby5hx54js5rf7y6y
Pre-training of Molecular GNNs via Conditional Boltzmann Generator
[article]
2024
arXiv
pre-print
However, this approach is impractical for drug and material discovery tasks because of the computational cost of obtaining multiple conformations. ...
Therefore, it is desirable to generate multiple conformations in advance and extract molecular representations using a 4D-QSAR model that incorporates multiple conformations. ...
These methods use information from multiple conformations but do not explicitly incorporate information on the Boltzmann distribution. ...
arXiv:2312.13110v3
fatcat:zl7dpptgzrepxddhsgydytjutq
Unified 2D and 3D Pre-Training of Molecular Representations
[article]
2022
arXiv
pre-print
The model is pre-trained on three tasks: reconstruction of masked atoms and coordinates, 3D conformation generation conditioned on 2D graph, and 2D graph generation conditioned on 3D conformation. ...
We evaluate our method on 11 downstream molecular property prediction tasks: 7 with 2D information only and 4 with both 2D and 3D information. ...
ACKNOWLEDGMENTS This work was supported in part by the National Natural Science Foundation of China under Contract 61836011 and in part by the Youth Innovation Promotion Association CAS under Grant 2018497 ...
arXiv:2207.08806v1
fatcat:xc6crlzacbbqjlqkf6gmp5ocee
Analysis of the code relating sequence to conformation in globular proteins. Theory and application of expected information
1974
Biochemical Journal
Finally, it is shown how this process of information theory analysis can be reversed to predict the conformation of a protein by using its primary sequence and the above information estimates obtained ...
It is shown how the information transferred was estimated by inspection of proteins of known primary sequence and conformation. 4. ...
Extension of the procedure to the simultaneous prediction of more than two conformations The above theory and procedures apply to the measurement and prediction of two alternative conformations. ...
doi:10.1042/bj1410853
pmid:4463965
pmcid:PMC1168191
fatcat:plc3d5drffb3nniwnmws3kayvm
Convergence and combination of methods in protein–protein docking
2009
Current Opinion in Structural Biology
Although these classes of methods require very different amounts of information in addition to the structures of component proteins, they all share the same four computational steps: (1) simplified and ...
The analysis of results from CAPRI (Critical Assessment of Predicted Interactions), the first communitywide experiment devoted to protein docking, shows that all successful methods consist of multiple ...
Acknowledgments This work has been supported by grant GM061867 from the National Institutes of Health ...
doi:10.1016/j.sbi.2009.02.008
pmid:19327983
pmcid:PMC2763924
fatcat:s7tlxub7arbpzb7o7s3vx5zahy
DynaMine v2, an updated version of the sequence-to-dynamics predictor
2020
Zenodo
-
al states probabilities and our
definition of general dynamics
Sim. ...
the MD data
Data generation
Selection of 100 proteins with
different degree of disorder
MD simulations
Time-dependent phi and psi
angles extraction from each
residue
Calculation of the conformation ...
doi:10.5281/zenodo.4146989
fatcat:g6rh3bgxhzdsjgwo7pvngmweea
Sphinx: merging knowledge-based andab initioapproaches to improve protein loop prediction
2017
Bioinformatics
Results: We show that Sphinx is able to generate high-accuracy predictions and decoy sets enriched with near-native loop conformations, performing better than the ab initio algorithm on which it is based ...
Current loop modelling algorithms can mostly be divided into two categories: knowledge-based, where databases of fragments are searched to find suitable conformations and ab initio, where conformations ...
Our algorithm gives a prediction in every case (unlike some knowledge-based methods) and generates decoy sets that are enriched with near-native conformations. ...
doi:10.1093/bioinformatics/btw823
pmid:28453681
pmcid:PMC5408792
fatcat:cywqk5matbgibg7nyq3z7p7aam
Interpretable Atomistic Prediction and Functional Analysis of Conformational Ensembles and Allosteric States in Protein Kinases Using AlphaFold2 Adaptation with Randomized Sequence Scanning and Local Frustration Profiling
[article]
2024
biorxiv/medrxiv
We show that the proposed AF2 adaptation combined with local frustration mapping of conformational states enable accurate prediction of the ABL active and intermediate structures and conformational ensembles ...
Despite the success of AF2 tools in predicting single protein structures, these methods showed intrinsic limitations in predicting multiple functional conformations of allosteric proteins and fold-switching ...
All authors have read and agreed to the published version of the manuscript.
Conflicts of Interest: The authors declare no conflict of interest. ...
doi:10.1101/2024.02.15.580591
pmid:38496487
pmcid:PMC10942451
fatcat:itkq24fkerel3kwcysqzne4emq
A conformation ensemble approach to protein residue-residue contact
2011
BMC Structural Biology
Protein residue-residue contact prediction is important for protein model generation and model evaluation. ...
Here we develop a conformation ensemble approach to improve residue-residue contact prediction. We collect a number of structural models stemming from a variety of methods and implementations. ...
Acknowledgements The work was partially supported by a NIH grant 1R01GM093123 to JC and a NLM fellowship to JE. ...
doi:10.1186/1472-6807-11-38
pmid:21989082
pmcid:PMC3200154
fatcat:amtwzwgg7nccbjvdwvtyskhofu
DockRank: Ranking docked conformations using partner-specific sequence homology-based protein interface prediction
2013
Proteins: Structure, Function, and Bioinformatics
Selecting near-native conformations from the immense number of conformations generated by docking programs remains a major challenge in molecular docking. ...
m conformations) and Hit Rate (the percentage of nearnative conformations that are included among the top m conformations). ...
Any opinion, finding, and conclusions contained in this article are those of the authors and do not necessarily represent the views of the National Science Foundation. ...
doi:10.1002/prot.24370
pmid:23873600
pmcid:PMC4417613
fatcat:a7l7jshtznaurd7zsuoi2gtzbm
Guiding conformation space search with an all-atom energy potential
2008
Proteins: Structure, Function, and Bioinformatics
Key words: Protein structure prediction; conformational space search; multiple energy functions; active learning; Rosetta; Monte Carlo. 958 PROTEINS V V C 2008 WILEY-LISS, INC. ...
Finally, we are grateful for many helpful discussions with Lila Gierasch from the University of Massachusetts Amherst and with the members of the Gierasch Lab. ...
ACKNOWLEDGMENTS We would like to thank David Baker from the University of Washington, the Baker Lab, and the many contributors to Rosetta for making the Rosetta source code available. ...
doi:10.1002/prot.22123
pmid:18536015
pmcid:PMC2752431
fatcat:sqbmn5qjgnfbze3a4ibmwfmfmu
A conditional random fields method for RNA sequence–structure relationship modeling and conformation sampling
2011
Computer applications in the biosciences : CABIOS
However, predicting RNA tertiary structures is extremely challenging, because of a large conformation space to be explored and lack of an accurate scoring function differentiating the native structure ...
Our method, named as TreeFolder, generates a much higher percentage of native-like decoys than FARNA and BARNACLE, although we use the same simple energy function as BARNACLE. ...
Funding: National Institutes of Health (grant R01GM089753, to J.X.); National Science Foundation (grant DBI-0960390, to J.X.); Open Science Grid and TeraGrid (grants TG-MCB100062 and TGCCR100005, to J.X ...
doi:10.1093/bioinformatics/btr232
pmid:21685058
pmcid:PMC3117333
fatcat:xsrqicxc4jckderkwgin5phqdi
Optimal Conformal Prediction for Small Areas
[article]
2022
arXiv
pre-print
The proposed method takes a conformal prediction approach in which the conformity measure is the posterior predictive density of a working model that incorporates indirect information. ...
Existing inferential methods for small area data involve a trade-off between maintaining area-level frequentist coverage rates and improving inferential precision via the incorporation of indirect information ...
As made clear by the representation of a generic conformal prediction region given in Equation 2 , this information fully classifies the conformal prediction region for a given error rate α. ...
arXiv:2204.08122v1
fatcat:asofhzor6jevhktn4aqg4cwahi
« Previous
Showing results 1 — 15 out of 770,949 results