ML Model Training overview
Full specification is available
here.
immuneML version: immuneML 1.1.1
Dataset details
General information
| Name |
dataset_GILGFVFTL |
| Type |
Receptor Dataset |
| Example count |
4090 |
Dataset labels
| Label name |
Label values (classes) |
| GILGFVFTL |
'True', 'False' |
Parameters for training ML model
Metrics
| Optimization metric |
auc |
| Other metrics |
balanced_accuracy, precision, recall |
Cross-validation settings
| assessment |
1-fold MC CV (training percentage: 0.7) |
| selection |
5-fold CV |
Optimization results
GILGFVFTL
| Split index |
Optimal settings (preprocessing, encoding, ML) |
Optimization metric (auc) |
Details |
| 1 |
kmer_frequency_logistic_regression |
0.922 |
see details |
Trained models
Trained models are available as zip files which can be directly provided as input for the MLApplication instruction and used to encode
the data and predict the label on a new dataset. These zip files include trained ML model, encoder and preprocessing that were chosen
as optimal for the given label, along with additional files showing the values of each parameter in the model and encoder.