Statistics
Datasets are available to download hereEvaluation metrics
AIUPred have been trained and tested in the DisProt database and validated on the first and second rounds of the CAID proposal in comparison to its previous installment.
![...](/static/statistics/evaluation.png)
Benchmarking
AIUPred have also been tested on short disordered regions (less than 30 residues) and fully disordered proteins compared to previous installments
![...](/static/statistics/short_disorder.png)
![...](/static/statistics/fully_diso.png)
Ablation
Ablation analysis of decoder layer architectures on a validation subset
![...](/static/statistics/ablation.png)
Primary citation
AIUPred: combining energy estimation with deep learning for the enhanced prediction of protein disorder
Gábor Erdős, Zsuzsanna Dosztányi
Nucleic Acids Research 2024; gkae385
Gábor Erdős, Zsuzsanna Dosztányi
Nucleic Acids Research 2024; gkae385
v1.2.2