2018
DOI: 10.1016/j.procs.2018.07.205
|View full text |Cite
|
Sign up to set email alerts
|

Using unsupervised learning methods for enhancing protein structure insight

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
3
2

Relationship

0
5

Authors

Journals

citations
Cited by 6 publications
(1 citation statement)
references
References 15 publications
0
1
0
Order By: Relevance
“…Because usually there is little or no prior knowledge regarding the number of the representative states, unsupervised learning methods such as clustering are the only types of machine learning tools that can be employed to identify subgroups from a data set . Effective clustering approaches, however, are highly dependent on whether the intention is to study more global structural changes of larger systems or focus more on local shifts such as with IDPs, where the vast array of sampled conformations require more detailed CVs. , Characterizing these disordered or flexible regions, often associated with functional regions, allows for the description of changes to the conformational landscape in different environments or due to ligand binding, which is crucial to understanding enzymatic mechanisms. Accessing these states is a starting point for identifying functionally relevant conformations, determining structures appropriate for docking, or for accelerated simulations to further interrogate the conformational space of the protein of choice .…”
Section: Discussionmentioning
confidence: 99%
“…Because usually there is little or no prior knowledge regarding the number of the representative states, unsupervised learning methods such as clustering are the only types of machine learning tools that can be employed to identify subgroups from a data set . Effective clustering approaches, however, are highly dependent on whether the intention is to study more global structural changes of larger systems or focus more on local shifts such as with IDPs, where the vast array of sampled conformations require more detailed CVs. , Characterizing these disordered or flexible regions, often associated with functional regions, allows for the description of changes to the conformational landscape in different environments or due to ligand binding, which is crucial to understanding enzymatic mechanisms. Accessing these states is a starting point for identifying functionally relevant conformations, determining structures appropriate for docking, or for accelerated simulations to further interrogate the conformational space of the protein of choice .…”
Section: Discussionmentioning
confidence: 99%