config.yaml

# data input
# file_names_txt is a 2 or 3 column tsv with the following columns
# SAMPLE_NAME     FAST5/FASTQ_READS      SHORT_READS_1,SHORT_READS_2
# sample name in the first column will be used to name ouptut
# the second column can be a directory containing fast5 files (the output of a nanopore run)
#   -OR- a single fastq file containing basecalled data 
# Optionally, a short read sequencing dataset can be provided in the third column, 
#   with pairs separated by a comma. If this option is selected, short read
#   polishing will be turned on. 
file_names_txt: 'sample_reads.txt'
flowcell: 'FLO-MIN106'
kit: 'SQK-LSK109'

#workflow steps to perform
assembler: 'flye' #or canu
min_contig_size: 0 #remove contigs smaller than this from the assembly (can speed up polishing but potentially hurt genome completeness)
skip_circularization: False
skip_polishing: False
polish_both: False #should the input to short read polishing be the output of long read polishing?

#the below options are all related to Canu. genome_size is used by Flye as well.
canu_args: 'cnsThreads=2 cnsMemory=32'
usegrid: True #should Canu use the grid?
grid_options: '--time=80:00:00 --account asbhatt'
genome_size: '100m,250m' #Estimated genome size. The default values work well for typical healthy human gut samples.
                        #A single value can be specified instead, which will perform only one assembly and bypass
                        #merging. This would be suitable for bacterial isolate data, small datasets or very simple
                        #metagenomes.