※ Advanced Services of GPS-SUMO 2.0 

Please click the check box '' to select your predictor, you can see '' before the selected one.

1. GPS-SUMO 2.0 (PLR):  Prediction based on penalized logistic regression with the group-based prediction system feature (Also available at the HOME page). Speed:

2. GPS-SUMO 2.0 (Transformer):  Prediction based on Transformer with the contextual information. Speed:

3. GPS-SUMO 2.0 (All):  Prediction based on all models with all features. Speed:

4. GPS-SUMO 2.0 (Species-specific):  Species-specific prediction based on all models with all features. Speed:

5. GPS-SUMO 2.0 (Comprehensive):  Prediction based on all models with all features and additional annotations of secondary structure and surface accessibility. Speed:

6. GPS-SUMO 2.0 (Stress conditions):   Prediction based on penalized logistic regression, using 39,938 non-redundant SUMOylation sites identified under various stress conditions, such as SUMO protease inhibition, proteasome inhibition and heat shock. Speed:

According to   Sequence(s) in FASTA format    UniProt Accession Number(s)

     Please enter UniProt accession number(s)


Threshold
SUMOylation: SUMO interaction:
Motif Filter

You could input one UniProt accession number or multiple proteins'  UniProt accession numbers breaking with line breaks.
And please don't input any special characters.

After GPS-SUMO 2.0 predictor model was well-trained, we performed an evaluation on this model. From the evaluation, three thresholds with High, Medium and Low stringency were chosen for GPS-SUMO 2.0. The performance under these three thresholds was presented as follow:

The performance of GPS-SUMO 2.0 in different thresholds
Threshold SUMOylation SUMO interaction
Ac Sn Sp MCC Pr Ac Sn Sp MCC Pr
High 88.63% 57.45% 95.17% 0.5749 71.39% 94.64% 90.06% 95.17% 0.7551 68.08%
Medium 86.60% 68.24% 90.46% 0.5585 60.00% 90.88% 98.14% 90.05% 0.6823 53.02%
Low 84.33% 75.98% 85.01% 0.5293 51.54% 86.80% 99.38% 85.36% 0.6081 43.72%