search

compomics / DeepLC

DeepLC: Retention time prediction for (modified) peptides using Deep Learning.
https://iomics.ugent.be/deeplc
Apache License 2.0
52 stars 18 forks source link

Possibility to retrain a model #12

Closed cctsou closed 4 years ago

cctsou commented 4 years ago

Is it possible to retrain a new model? or once it's calibrated could we save the calibrated models for future use?

RobbinBouwmeester commented 4 years ago

Dear Chih-Chiang Tsou, yes it is possible to train new models. The python scripts to retrain are available in "train_eval.zip" here: https://doi.org/10.5281/zenodo.3706875

In that zip file you can use "run_full_mod.py" to retrain. It should be documented, but if things are unclear please do not hesitate to ask.