2022
DOI: 10.1016/j.csbj.2022.11.012
|View full text |Cite
|
Sign up to set email alerts
|

Deep learning for protein secondary structure prediction: Pre and post-AlphaFold

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
5
0
1

Year Published

2023
2023
2024
2024

Publication Types

Select...
4
3
2

Relationship

0
9

Authors

Journals

citations
Cited by 24 publications
(6 citation statements)
references
References 162 publications
0
5
0
1
Order By: Relevance
“…Overall, the Q3 Protein SS prediction has reached 87-89% accuracy, which is close to its theoretical limit [49], [50]. However, taking current protein structure databases into account, a new study claimed that the theoretical limit of Q3 SS prediction could be extended to 90-92%.…”
Section: Related Workmentioning
confidence: 66%
See 1 more Smart Citation
“…Overall, the Q3 Protein SS prediction has reached 87-89% accuracy, which is close to its theoretical limit [49], [50]. However, taking current protein structure databases into account, a new study claimed that the theoretical limit of Q3 SS prediction could be extended to 90-92%.…”
Section: Related Workmentioning
confidence: 66%
“…However, taking current protein structure databases into account, a new study claimed that the theoretical limit of Q3 SS prediction could be extended to 90-92%. The upper limit of Q8 for eight-state measurements is 84-86% [50], [51]. This indicates that there is still a gap in accuracy to be filled.…”
Section: Related Workmentioning
confidence: 99%
“…This work shows that for the category of therapeutic proteins above 40 amino acids, there is a weak or no correlation between the number of amino acids and their pLDDT or pTM scores. In the case of polypeptides, a reverse observation showed that a smaller number provides more complexity in prediction and less confidence in structure predictability, as applied to polypeptides [90,91]. Both tools correlate significantly positively, representing their orthogonality.…”
Section: Discussionmentioning
confidence: 97%
“…This can be defined in several ways: using a protein's solved structure, a secondary structure predictor, or a tertiary structure predictor that predicts secondary structure. However, tools for predicting secondary structure in those proteins without solved structures (as well as IDPs) have limited accuracy [31][32][33][34]. Tertiary structure predictors such as AlphaFold do predict secondary structure, but this is not their primary function, and any potential biases in detecting secondary structure remain unclear.…”
Section: Introductionmentioning
confidence: 99%