config.yaml

##Data preprocessing
genome :  Yourpath/CharPlant/example/oryza_sativa.fa                 #Genome file in fasta format(Need full path).
bed    :  Yourpath/CharPlant/example/oryza_sativa.bed             #Bed file of Chromatin Accessible Regions for input(Need full path).
out    : ory                                     #Prefix of the output file

##model_parameter(You can use the default parameters,or custom parameters)
epochs : 150 #Number of epochs.(default is 150).
patience : 20 #Number of epochs for early stopping.(default is 20).
learningrate : 0.001 #Learning rate.(default is 0.001).
batch_size : 128 #Batch Size.(default is 128).
dropout : 0.6 #Dropout rate.(default is 0.6).
nb_filter1 : 200 #Number of filters in first layer ofconvolution.(default is 200).
nb_filter2 : 100 #Number of filters in second layer of convolution.(default is 100).
filter_len1 : 19 #Length of filters in first layer of convolution.(default is 19).
filter_len2 : 11 #Length of filters in second layer of convolution.(default is 11).
hidden : 200 #units in the fully connected layer.(default is 200).

##motif
motif_out : Ory #The prefix of motif output folder(example:Ory_motif).

##de_novo_prediction
prediction_out : split_fasta_36_1_ #The Prefix of the output file(example: split_fasta_36_1_`).
split_lines : 20000 #The number of lines in a Sliding window cut genome file splited into smaller files (default is 20,000).
threshold : 0.5 #the threshold adopted to assign positive predictions (default is 0.5)
##batch_submit_job
run_type : local #How the python script runs in batches; 
                 #example:local(run in local); LSF(LSF Cluster management system); PBS(PBS Cluster management system).
batch_submit_jobs_number : 40 #Number of tasks for a job array in one run;
                               #The exact number depends on your server performance;
                               #When you run on a local machine, it is recommended to use 40;
                               #when you run on LSF or PBS, it is recommended to use 100.

##get_positive_sample
speices_name : Rice #The name of the species,used when the final fasta file is generated.

##bowtie2_index
index_name : rice #Your-index-name used in bowtie2.

##bowtie2
sam_prefix : whole_fasta_36_1 #Sam file prefix(example: whole_fasta_36_1).

##macs2
peak_prefix : Oryza_sativa    #Call peak file prefix.