Critical assessment of protein intrinsic disorder prediction
Аутори
Necci, MarcoPiovesan, Damiano
Tosatto, Silvio C. E.
Davidović, Radoslav S.
Veljković, Nevena V.
Остала ауторства
CAID PredictorsDisProt Curators
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
Intrinsically disordered proteins, defying the traditional protein structure–function paradigm, are a challenge to study experimentally. Because a large part of our knowledge rests on computational predictions, it is crucial that their accuracy is high. The Critical Assessment of protein Intrinsic Disorder prediction (CAID) experiment was established as a community-based blind test to determine the state of the art in prediction of intrinsically disordered regions and the subset of residues involved in binding. A total of 43 methods were evaluated on a dataset of 646 proteins from DisProt. The best methods use deep learning techniques and notably outperform physicochemical methods. The top disorder predictor has F max = 0.483 on the full dataset and F max = 0.792 following filtering out of bona fide structured regions. Disordered binding regions remain hard to predict, with F max = 0.231. Interestingly, computing times among methods can vary by up to four orders of magnitude.
Извор:
Nature Methods, 2021, 18, 5, 472-481Финансирање / пројекти:
- National Science Foundation (NSF) [1617369]
- Natural Sciences and Engineering Research Council of Canada [298328]
- Tianjin Municipal Science and Technology Commission [13ZCZDGX01099]
- National Natural Science Foundation of China [31970649]
- National Natural Science Foundation of China [11701296]
- Natural Science Foundation of Tianjin [18JCYBJC24900]
- Japan Agency for Medical Research and Development [16cm0106320h0001]
- Australian Research Council [DP180102060]
- Research Foundation Flanders [G.0328.16 N]
- Agence Nationale de la Recherche [ANR-14-CE10-0021]
- Agence Nationale de la Recherche [ANR-17-CE12-0016]
- Hungarian Ministry for Innovation and Technology ELTE Thematic Excellence Programme [ED-18-1-2019-0030]
- Hungarian Academy of Sciences 'Lendulet' grant [LP2014-18]
- Hungarian Scientific Research Fund [K124670]
- Hungarian Scientific Research Fund [K131702]
- European Union's Horizon 2020 research and innovation programme [778247]. Funding for open access charge: European Union's Horizon 2020 research and innovation programme [778247]
- Italian Ministry of University and Research - PRIN 2017 [2017483NH8]
- ELIXIR
DOI: 10.1038/s41592-021-01117-3
ISSN: 1548-7091
PubMed: 33875885
WoS: 000641237500004
Scopus: 2-s2.0-85104988931
Институција/група
VinčaTY - JOUR AU - Necci, Marco AU - Piovesan, Damiano AU - Tosatto, Silvio C. E. AU - Davidović, Radoslav S. AU - Veljković, Nevena V. PY - 2021 UR - https://vinar.vin.bg.ac.rs/handle/123456789/9698 AB - Intrinsically disordered proteins, defying the traditional protein structure–function paradigm, are a challenge to study experimentally. Because a large part of our knowledge rests on computational predictions, it is crucial that their accuracy is high. The Critical Assessment of protein Intrinsic Disorder prediction (CAID) experiment was established as a community-based blind test to determine the state of the art in prediction of intrinsically disordered regions and the subset of residues involved in binding. A total of 43 methods were evaluated on a dataset of 646 proteins from DisProt. The best methods use deep learning techniques and notably outperform physicochemical methods. The top disorder predictor has F max = 0.483 on the full dataset and F max = 0.792 following filtering out of bona fide structured regions. Disordered binding regions remain hard to predict, with F max = 0.231. Interestingly, computing times among methods can vary by up to four orders of magnitude. T2 - Nature Methods T1 - Critical assessment of protein intrinsic disorder prediction VL - 18 IS - 5 SP - 472 EP - 481 DO - 10.1038/s41592-021-01117-3 ER -
@article{ author = "Necci, Marco and Piovesan, Damiano and Tosatto, Silvio C. E. and Davidović, Radoslav S. and Veljković, Nevena V.", year = "2021", abstract = "Intrinsically disordered proteins, defying the traditional protein structure–function paradigm, are a challenge to study experimentally. Because a large part of our knowledge rests on computational predictions, it is crucial that their accuracy is high. The Critical Assessment of protein Intrinsic Disorder prediction (CAID) experiment was established as a community-based blind test to determine the state of the art in prediction of intrinsically disordered regions and the subset of residues involved in binding. A total of 43 methods were evaluated on a dataset of 646 proteins from DisProt. The best methods use deep learning techniques and notably outperform physicochemical methods. The top disorder predictor has F max = 0.483 on the full dataset and F max = 0.792 following filtering out of bona fide structured regions. Disordered binding regions remain hard to predict, with F max = 0.231. Interestingly, computing times among methods can vary by up to four orders of magnitude.", journal = "Nature Methods", title = "Critical assessment of protein intrinsic disorder prediction", volume = "18", number = "5", pages = "472-481", doi = "10.1038/s41592-021-01117-3" }
Necci, M., Piovesan, D., Tosatto, S. C. E., Davidović, R. S.,& Veljković, N. V.. (2021). Critical assessment of protein intrinsic disorder prediction. in Nature Methods, 18(5), 472-481. https://doi.org/10.1038/s41592-021-01117-3
Necci M, Piovesan D, Tosatto SCE, Davidović RS, Veljković NV. Critical assessment of protein intrinsic disorder prediction. in Nature Methods. 2021;18(5):472-481. doi:10.1038/s41592-021-01117-3 .
Necci, Marco, Piovesan, Damiano, Tosatto, Silvio C. E., Davidović, Radoslav S., Veljković, Nevena V., "Critical assessment of protein intrinsic disorder prediction" in Nature Methods, 18, no. 5 (2021):472-481, https://doi.org/10.1038/s41592-021-01117-3 . .