TY  - 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 . .