# #### BioDiscML config file #### #

# See https://github.com/mickaelleclercq/BioDiscML/tree/master/release/Test_datasets 

# for examples.

# IMPORTANT: for classification, do not use classes with numeric attributes. Else,

# they will be interpreted as a regression problem.

#####################

### BASIC OPTIONS ###

#####################

## Working directory. If local execution, don't set it.

# wd must be defined if another classifiers.conf is provided

# Default: wd=*empty* (local directory)

#wd=working_directory

## Project name, used as prefix for outfiles.

# Default: project=myProject

project=myProject

## Type of classification: Classification

# Set to true if we perform a classification (nominal class). 

# Default: doClassification=false

doClassification=false

# If true, set the column class name to classify.

# Default: classificationClassName=class

classificationClassName=class

## Type of classification: Regression

# Set to true if we perform a regression (numeric class). 

# Default:doRegression=false

doRegression=false

# If true, set the column class name to classify.

# Default: regressionClassName=class

regressionClassName=class

## Training input files

# Set infiles here if you have several dataset with a common ID column that will

# be used for merging (see mergingID). Only IDs existing in all files will be kept 

# for training, those missing in one of the file will be ignored.

# All decimal separated values commas (,) will be changed to dots (.).

# You also must remove special symbols within your data (e.g.: %/\*"':éèà).

# Usage: trainFile=filename_in_working_directory,description 

# The description will be used as a prefix for features of the file to avoid  

# duplicated names. It can be left empty if there is no risk of duplicated names.

# (ex:  trainFile=myproteinsfile, protein

#       trainFile=mygenesfile, genes

#       trainFile=mymetadatafile).

# Default: trainFile=*empty*

#trainFile=trainFile1.csv, description

#trainFile=trainFile2.csv

## Predict new data input files

# If you have you own blind test dataset or new data, you can run biodiscml using 

# the -predict option (java -jar biodiscml.jar -config config.conf -predict).

# This function will need two defined input files: 

#  - A newData file (same format and structure as the training input files.

#   This file must contain at least all elements of the retained signature of the 

#   selected best model features. Features present in the newData file, but absent from 

#   the signature of the model will simply be ignored during the prediction)

#  - A model file (produced during a previous execution of biodiscml where a best

#    model have been identified) 

# Usage: newDataFile=filename_in_working_directory,description 

# The description will be used as a prefix for features of the file to avoid  

# duplicated names. It can be left empty if there is no risk of duplicated names.

# (ex:  newDataFile=myproteinsfile, protein

#       newDataFile=mygenesfile, genes

#       newDataFile=mymetadatafile).

# Default: newDataFile=*empty*

# Default: modelFile=*empty*

#newDataFile=newDataFile1.csv, description

#newDataFile=newDataFile2.csv

#modelFile=model.model

## Merging 

# Merging identifier, used if you have many files to merge. It is expected to be

# found in the first column of every files.

# Only rows containing identifiers that exist in all files will be considered in 

# the analysis.

# Default: mergingID=*empty*

#mergingID=identifier

## Sampling

# Perform sampling to create a random validation set not used during training and

# used for further evaluation. 

# Default: sampling=true

sampling=true

# The samplingFold option separate the set in x parts, keep 1 for validation, others 

# for training.

# e.g. samplingFold=3 means that the validation set will be composed of 1/3 of the 

# input data.

# Ignored if sampling=false

# Default: samplingFold=3

samplingFold=3

# Instead of random sampling, you can provide a validation file on which the models 

# will be tested. 

# Note that the validation file must contain the same structure and features as the 

# train file.

# You can also provide several validation files, they will be merged.

# If set, samplingFold options will be ignored. 

# Ignored if sampling=false

# Default: validationFile=*empty*

#validationFile=validationFile1.csv

## Feature exclusion

# Features to exclude from the dataset (separated by commas(,)).

# Do not exclude the identifier (usually the first column).

# Default: excluded=*empty*

#excluded=columnA,columnB

## Best model auto-selection 

# A specified number of models will be generated here, along with various performance 

# metrics and correlated features for each one. Choose how many best models to 

# generate and the metric on which the models will be sorted.

# Instead of a specific number of models, a threshold can also be set.

# Models will be selected based on both numberOfBestModels and 

# numberOfBestModelsSortingMetricThreshold conditions

# Metrics can be any column of the results file: 

#   We prefer those for classification: TEST_MCC, TEST_BER, TRAIN_TEST_BS_MCC, 

#                                           TRAIN_TEST_BS_BER, AVG_BER, AVG_MCC 

#   We prefer those for regression: TEST_CC, TEST_RMSE, TRAIN_TEST_BS_CC, 

#                                       TRAIN_TEST_BS_RMSE, AVG_RMSE, AVG_CC 

# Examples: AVG_MCC at 0.6, AVG_RMSE at 0.3, AVG_CC at 0.8

# See commands in readme.txt to extract specific models

# Default: computeBestModel=true

#    numberOfBestModels=1 

#    numberOfBestModelsSortingMetric=AVG_MCC

#    numberOfBestModelsSortingMetricThreshold=0.1

computeBestModel=true

numberOfBestModels=1

numberOfBestModelsSortingMetric=AVG_MCC

numberOfBestModelsSortingMetricThreshold=0.1

## Combine models

# If true, only one model will be computed using a combination of all models 

# selected with best models options. 

# Combination rules: 

#   AVG (Average of probabilities)

#   PROD (Product of probabilities)

#   MAJ (Majority voting)

#   MED (Median)

# Default: combineModels=false

#   combinationRule=AVG

combineModels=false

combinationRule=AVG

########################

### ADVANCED OPTIONS ###

########################

## Debug to show more outputs

# 2 levels of verbose, debug and debug2

# Also possibility to print failed models with error explanation

# Default:  debug=false

#           debug2=false

#           printFailedModels=false

debug=false

debug2=false

printFailedModels=false

## Maximum number of cpus to use (enter a value or "max").

# BioDiscML runs in low priority by regularly checking cpus available. So

# you can execute other softwares on your server and it will adapt itself. 

# Just be careful to available memory, limit number of cpus used to avoid out 

# of memory exception. 

# Default: cpus=max

cpus=max

## The separator (delimiter) of infiles will be detected automatically. 

# It is however possible to set it, but it must exist for all files.

# Default: separator=*empty*

#separator=\t

## Leave-One-Out cross validation

# If you have a very large set of samples (more than 2000), it may be better

# to skip Leave-One-Out cross validation by setting loocv to false

# Default: loocv=true

loocv=true

## Criterion (metrics) optimizers

# To test if a model generated with a feature subset is better with another 

# subset, we use various criterions as comparison metrics. 

# You can limit the list of criterions if wanted. 

# Avalaible criterions for classification:AUC, MCC, FDR, BER, ACC, TPR, TNR, 

#   kappa, AUPRC, Fscore, Precision, Recall, TP+FN

# Default: coptimizers=AUC, MCC, FDR, BER, ACC

coptimizers=AUC, MCC, FDR, BER, ACC

## Search modes

# various search modes are implemented, including topX features according to 

# information gain ranking, stepwise search (Forward(F), Forward-Backward(FB), 

# Backward(B) and Backward-Forward(BF)) and all features (all)

searchmodes=F,FB,B,BF,top1,top5,top10,top15,top20,top30,top40,top50,top75,top100

# Regression criterions

# Available criterions for regression: CC, MAE, RMSE, RAE, RRSE 

# Default: roptimizers=CC, RMSE

roptimizers=CC, RMSE 

## Maximum number of features kept after feature selection ranking.

# Higher this number is, longer will be the training.

# Default: maxNumberOfSelectedFeatures = 1000

maxNumberOfSelectedFeatures = 1000

## Maximum number of features models can have.

# Default: maxNumberOfFeaturesInModel = 200

maxNumberOfFeaturesInModel = 200

## Bootstrap and repeated holdout folds

# Default: bootstrapFolds=100

bootstrapFolds=100

# Run without feature selection

# If true, maxNumberOfSelectedFeatures and maxNumberOfFeaturesInModel 

# will be set to maximum (which is the number of features in the dataset).

# Also, if true, available search mode won't be executed

# Default: noFeatureSelection=false

noFeatureSelection=false

## Correlated features

# Thresholds for Spearman and Pearson correlations

# Correlated feature search can be disabled by setting retrieveCorrelatedGenes to 

# false

# Default: retrieveCorrelatedGenes=true

# Default: spearmanCorrelation_lower = -0.99

#   spearmanCorrelation_upper = 0.99

#   pearsonCorrelation_lower = -0.99

#   pearsonCorrelation_upper = 0.99

retrieveCorrelatedGenes=true

spearmanCorrelation_lower = -0.99

spearmanCorrelation_upper = 0.99

pearsonCorrelation_lower = -0.99

pearsonCorrelation_upper = 0.99

# Retrieve features based on equivalent infogain or relieff ranking score

# Default: maxRankingScoreDifference = 0.005

#   retreiveCorrelatedGenesByRankingScore=false

maxRankingScoreDifference = 0.005

retreiveCorrelatedGenesByRankingScore=false

# Create model with correlated genes

# Default: generateModelWithCorrelatedGenes = false

## RUN mode

# BioDiscML will test all available classifier algorithms. If you wish to choose

# specific classifiers, you'll need to use the fast way mode and provide a 

# list of classifiers configurations (classifier name and hyperparameters). 

# Please use Weka GUI to help you choose the configurations

# For each configuration, you'll need to provide what optimizer to use.

# Fast mode classification

# Usage: cfcmd=classifier with options,optimizer.

# Available optimizers: AUC,ACC,SEN,SPE,MCC,TP+FN,kappa and ALLOPT (all optimizers)

# Available search modes: F,FB,B,BF,top1,top5,top10,top15,top20,top30,top40,top50,top75,top100,top200,all and ALLSEARCH (all search modes)

# If no optimizer or search modes are provided, they will all be tested (equivalent to provide ALLOPT and ALLSEARCH)

# Default: classificationFastWay=false

#   ccmd=*empty*    

classificationFastWay=false

ccmd=bayes.NaiveBayes -K, SEN

ccmd=bayes.NaiveBayes -K, AUC

ccmd=misc.VFI -B 0.4, SEN

ccmd=misc.VFI -B 0.4, AUC

ccmd=misc.VFI -B 0.4, AUC, F

ccmd=misc.VFI -B 0.6

ccmd=misc.VFI -B 0.6, ALLOPT, FB

ccmd=trees.J48

# Fast mode regression

# Usage: rfcmd=classifier with options,optimizer.

# Available optimizers: CC, MAE, RMSE, RAE, RRSE. 

# Default: regressionFastWay=false

#   rcmd=*empty* 

regressionFastWay=false

rcmd=functions.GaussianProcesses -L 1.0 -N 1 -K "weka.classifiers.functions.supportVector.PolyKernel -C 250007 -E 1.0", CC

rcmd=functions.GaussianProcesses -L 1.0 -N 1 -K "weka.classifiers.functions.supportVector.PolyKernel -C 250007 -E 1.0", RMSE

# #### End of configuration file #### #