nf-core/drugresponseeval
Pipeline for testing drug response prediction models in a statistically and biologically sound way.
Define the models and baselines to be tested.
Model to be tested.
string
NaiveDrugMeanPredictor
Baselines to be tested.
string
NaiveMeanEffectsPredictor
Define where the pipeline should find input data and save output data.
Run name for the pipeline. The subdirectory in results will be named like this.
string
my_run
Name of the dataset. Pre-supplied datasets are CTRPv2, CTRPv1, CCLE, GDSC1, GDSC2, TOYv1, TOYv2.
string
CTRPv2
The output directory where the results will be saved. Default is results/
string
results
Email address for completion summary.
string
^([a-zA-Z0-9_\-\.]+)@([a-zA-Z0-9_\-\.]+)\.([a-zA-Z]{2,5})$
Define the mode in which the pipeline will be run.
Run the pipeline in test mode LPO (Leave-random-Pairs-Out), LCO (Leave-Cell-line-Out), or LDO (Leave-Drug-Out).
string
LCO
Options for randomization.
Randomization mode for the pipeline.
string
None
Randomization type for the pipeline.
string
Options for robustness.
Number of trials to run for the robustness test
integer
Options for data input.
Path to the data directory.
string
data
The name of the drug response measure to use.
string
Datasets for cross-study prediction.
string
Link to the latest Zenodo version of the dataset.
string
https://zenodo.org/records/15533857/files/
^https://zenodo.org/records/[0-9]+/files/$
Additional options for the pipeline.
False by default (=refitting). By default, we use measures calculated with CurveCurator instead of original measures reported by the authors for the available datasets, or invoke automatic fitting of custom raw viability data with CurveCurator. Set this flag to disable this option.
boolean
Optimization metric for the pipeline.
string
Number of cross-validation splits.
integer
10
Response transformation
string
Model checkpoint directory
string
TEMPORARY
Disable hyperparameter tuning.
boolean
Train final model on full data.
boolean
Parameters used to describe centralised config profiles. These should not be edited.
Git commit id for Institutional configs.
string
master
Base directory for Institutional configs.
string
https://raw.githubusercontent.com/nf-core/configs/master
Institutional config name.
string
Institutional config description.
string
Institutional config contact information.
string
Institutional config URL link.
string
Less common options for the pipeline, typically set in a config file.
Display version and exit.
boolean
Method used to save pipeline results to output directory.
string
Email address for completion summary, only when pipeline fails.
string
^([a-zA-Z0-9_\-\.]+)@([a-zA-Z0-9_\-\.]+)\.([a-zA-Z]{2,5})$
Send plain-text email instead of HTML.
boolean
Do not use coloured log outputs.
boolean
Incoming hook URL for messaging service
string
Boolean whether to validate parameters against the schema at runtime
boolean
true
Base URL or local path to location of pipeline test dataset files
string
https://raw.githubusercontent.com/nf-core/test-datasets/
Suffix to add to the trace report filename. Default is the date and time in the format yyyy-MM-dd_HH-mm-ss.
string