Assessment of Disordered Linker Predictions in the CAID2 Experiment
Disordered linkers (DLs) are intrinsically disordered regions that facilitate movement between adjacent functional regions/domains, contributing to many key cellular functions. The recently completed second Critical Assessments of protein Intrinsic Disorder prediction (CAID2) experiment evaluated DL...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-02-01
|
Series: | Biomolecules |
Subjects: | |
Online Access: | https://www.mdpi.com/2218-273X/14/3/287 |
_version_ | 1797241901216169984 |
---|---|
author | Kui Wang Gang Hu Zhonghua Wu Vladimir N. Uversky Lukasz Kurgan |
author_facet | Kui Wang Gang Hu Zhonghua Wu Vladimir N. Uversky Lukasz Kurgan |
author_sort | Kui Wang |
collection | DOAJ |
description | Disordered linkers (DLs) are intrinsically disordered regions that facilitate movement between adjacent functional regions/domains, contributing to many key cellular functions. The recently completed second Critical Assessments of protein Intrinsic Disorder prediction (CAID2) experiment evaluated DL predictions by considering a rather narrow scenario when predicting 40 proteins that are already known to have DLs. We expand this evaluation by using a much larger set of nearly 350 test proteins from CAID2 and by investigating three distinct scenarios: (1) prediction residues in DLs vs. in non-DL regions (typical use of DL predictors); (2) prediction of residues in DLs vs. other disordered residues (to evaluate whether predictors can differentiate residues in DLs from other types of intrinsically disordered residues); and (3) prediction of proteins harboring DLs. We find that several methods provide relatively accurate predictions of DLs in the first scenario. However, only one method, APOD, accurately identifies DLs among other types of disordered residues (scenario 2) and predicts proteins harboring DLs (scenario 3). We also find that APOD’s predictive performance is modest, motivating further research into the development of new and more accurate DL predictors. We note that these efforts will benefit from a growing amount of training data and the availability of sophisticated deep network models and emphasize that future methods should provide accurate results across the three scenarios. |
first_indexed | 2024-04-24T18:30:41Z |
format | Article |
id | doaj.art-e6503ee864f74734a2905b993a1c623c |
institution | Directory Open Access Journal |
issn | 2218-273X |
language | English |
last_indexed | 2024-04-24T18:30:41Z |
publishDate | 2024-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Biomolecules |
spelling | doaj.art-e6503ee864f74734a2905b993a1c623c2024-03-27T13:27:52ZengMDPI AGBiomolecules2218-273X2024-02-0114328710.3390/biom14030287Assessment of Disordered Linker Predictions in the CAID2 ExperimentKui Wang0Gang Hu1Zhonghua Wu2Vladimir N. Uversky3Lukasz Kurgan4School of Statistics and Data Science, LPMC and KLMDASR, Nankai University, Tianjin 300071, ChinaSchool of Statistics and Data Science, LPMC and KLMDASR, Nankai University, Tianjin 300071, ChinaSchool of Mathematical Sciences and LPMC, Nankai University, Tianjin 300071, ChinaDepartment of Molecular Medicine, USF Health Byrd Alzheimer’s Research Institute, Morsani College of Medicine, University of South Florida, Tampa, FL 33613, USADepartment of Computer Science, Virginia Commonwealth University, Richmond, VA 23284, USADisordered linkers (DLs) are intrinsically disordered regions that facilitate movement between adjacent functional regions/domains, contributing to many key cellular functions. The recently completed second Critical Assessments of protein Intrinsic Disorder prediction (CAID2) experiment evaluated DL predictions by considering a rather narrow scenario when predicting 40 proteins that are already known to have DLs. We expand this evaluation by using a much larger set of nearly 350 test proteins from CAID2 and by investigating three distinct scenarios: (1) prediction residues in DLs vs. in non-DL regions (typical use of DL predictors); (2) prediction of residues in DLs vs. other disordered residues (to evaluate whether predictors can differentiate residues in DLs from other types of intrinsically disordered residues); and (3) prediction of proteins harboring DLs. We find that several methods provide relatively accurate predictions of DLs in the first scenario. However, only one method, APOD, accurately identifies DLs among other types of disordered residues (scenario 2) and predicts proteins harboring DLs (scenario 3). We also find that APOD’s predictive performance is modest, motivating further research into the development of new and more accurate DL predictors. We note that these efforts will benefit from a growing amount of training data and the availability of sophisticated deep network models and emphasize that future methods should provide accurate results across the three scenarios.https://www.mdpi.com/2218-273X/14/3/287intrinsic disorderdisordered linkersprotein structureprotein functionpredictionassessment |
spellingShingle | Kui Wang Gang Hu Zhonghua Wu Vladimir N. Uversky Lukasz Kurgan Assessment of Disordered Linker Predictions in the CAID2 Experiment Biomolecules intrinsic disorder disordered linkers protein structure protein function prediction assessment |
title | Assessment of Disordered Linker Predictions in the CAID2 Experiment |
title_full | Assessment of Disordered Linker Predictions in the CAID2 Experiment |
title_fullStr | Assessment of Disordered Linker Predictions in the CAID2 Experiment |
title_full_unstemmed | Assessment of Disordered Linker Predictions in the CAID2 Experiment |
title_short | Assessment of Disordered Linker Predictions in the CAID2 Experiment |
title_sort | assessment of disordered linker predictions in the caid2 experiment |
topic | intrinsic disorder disordered linkers protein structure protein function prediction assessment |
url | https://www.mdpi.com/2218-273X/14/3/287 |
work_keys_str_mv | AT kuiwang assessmentofdisorderedlinkerpredictionsinthecaid2experiment AT ganghu assessmentofdisorderedlinkerpredictionsinthecaid2experiment AT zhonghuawu assessmentofdisorderedlinkerpredictionsinthecaid2experiment AT vladimirnuversky assessmentofdisorderedlinkerpredictionsinthecaid2experiment AT lukaszkurgan assessmentofdisorderedlinkerpredictionsinthecaid2experiment |