Strange error: bypass_log file not generated #36
Description
Hi, I am not sure why I am running into this error:
MetaPro operating in auto-mode
Forward Reads: /shared5/Simon/emily_beef_trial/Data/MetaT/sequences/105/Raw/105_1_1.fastq
Reverse Reads: /shared5/Simon/emily_beef_trial/Data/MetaT/sequences/105/Raw/105_1_2.fastq
Output filepath: /shared5/Simon/emily_beef_trial/Data/MetaT/processed/105
job path: 105/quality_filter
Traceback (most recent call last):
File "/pipeline/MetaPro.py", line 250, in
main(config_file, pair_1, pair_2, single, contig, output_folder, args_pack, tutorial_mode)
File "/pipeline/MetaPro.py", line 51, in main
metapro_stage_obj.mp_quality_filter()
File "/pipeline/MetaPro_stages.py", line 394, in mp_quality_filter
self.cleanup_quality_start, self.cleanup_quality_end = self.mp_util.launch_stage_simple(self.quality_filter_label, self.quality_path, self.commands, command_list, self.keep_all, self.keep_quality)
File "/pipeline/MetaPro_utilities.py", line 426, in launch_stage_simple
if self.check_bypass_log(self.output_folder_path, job_label):
File "/pipeline/MetaPro_utilities.py", line 132, in check_bypass_log
open(bypass_log_path, "a").close()
FileNotFoundError: [Errno 2] No such file or directory: '105/order_bypass_log_1.txt'
My configuration file is as follows:
[Databases]
database_path: /software/metaPRO/metaPROdb
UniVec_Core: %(database_path)s/univec_core/UniVec_Core.fasta
Adapter: %(database_path)s/Trimmomatic_adapters/TruSeq3-PE-2.fa
Host: %(database_path)s/human_genome/human_genome.fasta
Rfam: %(database_path)s/Rfam/Rfam.cm
DNA_DB: %(database_path)s/choco_mpro_3/family_group
#DNA_DB: %(database_path)s/chocophlan_h3_chunks
#DNA_DB: /home/billy/choco_h3/choco_h3_group
#DNA_DB_Split: %(database_path)s/ChocoPhlAn/ChocoPhlAn_split/
Prot_DB: %(database_path)s/nr/nr
Prot_DB_reads: %(database_path)s/nr/nr
accession2taxid: %(database_path)s/accession2taxid/accession2taxid
nodes: %(database_path)s/WEVOTE_db/nodes_wevote.dmp
names: %(database_path)s/WEVOTE_db/names_wevote.dmp
Kaiju_db: %(database_path)s/kaiju_db/kaiju_db_nr.fmi
Centrifuge_db: %(database_path)s/centrifuge_db/nt
SWISS_PROT: %(database_path)s/swiss_prot_db/swiss_prot_db
SWISS_PROT_map: %(database_path)s/swiss_prot_db/SwissProt_EC_Mapping.tsv
PriamDB: %(database_path)s/PRIAM_db/
DetectDB: %(database_path)s/DETECTv2
WEVOTEDB: %(database_path)s/WEVOTE_db/
EC_pathway: %(database_path)s/EC_pathway/EC_pathway.txt
path_to_superpath: %(database_path)s/path_to_superpath/pathway_to_superpathway.csv
MetaGeneMark_model: /pipeline_tools/mgm/MetaGeneMark_v1.mod
taxid_tree: %(database_path)s/taxid_trees/class_tree.tsv
kraken2_db: %(database_path)s/kraken2
#[code]
#ga_pre_scan_get_libs = /home/billy/human_flu/30785/ga_pre_scan_get_libs.py
[Tools]
Python = python3
Java = java -jar
cdhit_dup = /pipeline_tools/cdhit_dup/cd-hit-dup
Timmomatic = /pipeline_tools/Trimmomatic/trimmomatic-0.36.jar
AdapterRemoval = /pipeline_tools/adapterremoval/AdapterRemoval
vsearch = /pipeline_tools/vsearch/vsearch
Flash = /pipeline_tools/FLASH/flash
BWA = /pipeline_tools/BWA/bwa
SAMTOOLS = /pipeline_tools/samtools/samtools
BLAT = /pipeline_tools/PBLAT/pblat
DIAMOND = /pipeline_tools/DIAMOND/diamond
Blastp = /pipeline_tools/BLAST_p/blastp
Barrnap = /pipeline_tools/Barrnap/bin/barrnap
#note: needle is quite slow. This argument can be swapped for stretcher, but stretcher is not as accurate
Needle = /pipeline_tools/EMBOSS-6.6.0/emboss/needle
Blastdbcmd = /pipeline_tools/BLAST_p/blastdbcmd
Makeblastdb = /pipeline_tools/BLAST_p/makeblastdb
Infernal = /pipeline_tools/infernal/cmscan
Kaiju = /pipeline_tools/kaiju/kaiju
Centrifuge = /pipeline_tools/centrifuge/centrifuge
Priam = /pipeline_tools/PRIAM_search/PRIAM_search.jar
Detect = /pipeline/Scripts/Detect_2.2.9.py
BLAST_dir = /pipeline_tools/BLAST_p
WEVOTE = /pipeline_tools/WEVOTE/WEVOTE
Spades = /pipeline_tools/SPAdes/bin/spades.py
MetaGeneMark = /pipeline_tools/mgm/gmhmmp
#default is 30, to coincide with cdhit_dup's default.
[Settings]
AdapterRemoval_minlength = 30
bypass_log_name = order_bypass_log_1.txt
#debug_stop_flag = order_ta_1
taxa_existence_cutoff = 1
DNA_DB_mode = chocophlan
num_threads = 4
Show_unclassified = No
RPKM_cutoff = 0.01
BWA_cigar_cutoff = 90
BLAT_identity_cutoff = 85
BLAT_length_cutoff = 0.65
BLAT_score_cutoff = 60
DIAMOND_identity_cutoff = 85
DIAMOND_length_cutoff = 0.65
DIAMOND_score_cutoff = 60
#determines how much memory should be free for use with each tool. [1-99]
BWA_mem_threshold = 2
BLAT_mem_threshold = 2
DIAMOND_mem_threshold = 2
BWA_pp_mem_threshold = 1
BLAT_pp_mem_threshold = 2
DIAMOND_pp_mem_threshold = 2
DETECT_mem_threshold = 2
Infernal_mem_threshold = 2
Barrnap_mem_threshold = 2
#maximum allowable concurrent instances of the tool [1-number of cores on your machine]
BWA_job_limit = 4
BLAT_job_limit = 4
DIAMOND_job_limit = 4
BWA_pp_job_limit = 4
BLAT_pp_job_limit = 4
DIAMOND_pp_job_limit = 4
DETECT_job_limit = 4
Infernal_job_limit = 4
Barrnap_job_limit = 4
TA_job_limit = 1
#determines how long (seconds) each job should wait before they are launched (imposes delay. for memory-use-detection)
BWA_job_delay = 5
BLAT_job_delay = 5
DIAMOND_job_delay = 5
BWA_pp_job_delay = 5
BLAT_pp_job_delay = 5
DIAMOND_pp_job_delay = 5
#toggle these options to delete the interim data the steps will generate
keep_all = yes
keep_quality = no
keep_host = no
keep_vector = no
keep_rRNA = no
keep_repop = no
keep_assemble_contigs = yes
keep_GA_BWA = no
keep_GA_BLAT = no
keep_GA_DIAMOND = no
keep_GA_final = no
keep_TA = no
keep_EC = no
keep_outputs = no
#Data gets chunked in the pipeline. Control the chunk size to reduece the number of files generated. Increase for speed, and reduced memory load per tool-run [1-99999]
rRNA_chunk_size = 50000
GA_chunk_size = 10000
EC_chunk_size = 1000
#Decides the lossiness of host + vector filtration. For paired-end annotation only. [high/low] high: only if both pairs pass through the filter. low: if either pair passes through filter, both pairs pass
filter_stringency = high
TA_mem_threshold = 5
TA_job_delay = 600
[Labels]
GA_pre_scan = order_1_GA_pre_scan
GA_BWA = order_test_GA_BWA_1
GA_BLAT = order_test_GA_BLAT_1
host_filter = host_read_filter
vector_filter = vector_read_filter
ta = order_ta_1
GA_DIAMOND = order_test_GA_dmd_1