-
Notifications
You must be signed in to change notification settings - Fork 1
/
configuration
101 lines (79 loc) · 5.15 KB
/
configuration
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
# ============================ Input file configuation ================================
# load seqeunce directory
dir_seq=/work/GoryaninU/golf/data/mfc_real
# ========================== Program running parameter ================================
# number of cpu
cpu_max=24
memory_max=120
num_node=1
# Running step // Please fill Yes or No (Y/N)
step_0_check_quality=Y
step_1_filtering=Y
step_2_taxonomy_assigning=Y
step_3_assembling=Y
step_3_1_coassembling=N
step_4_gene_calling=Y
step_5_annotating=Y
display_result=Y
# ============================ Output file configuration ==============================
# output directory name
dir_out=/work/GoryaninU/golf
dir_out_qc=0_seq_qc
dir_out_fread=1_seq_filtered
dir_out_taxa=2_taxonomy
dir_out_assem=3_assembled
dir_out_co_assem=3_coassembled_2
dir_out_bining=3_1_bining
dir_out_cgene=4_gene_call
dir_out_anno=5_annotation
dir_out_reassembly=3_reassembled
# ================ Program directory and parameters configuration ====================
# Quality checking
dir_fastqc=/apps/unit/GoryaninU/software/FastQC/fastqc
# ---------- Trimming read configuration ---------------------------------------------
dir_trimmomatic=/apps/unit/GoryaninU/software/filter/Trimmomatic-0.36/trimmomatic-0.36.jar
# Config read trimming parameter
p_trimming_LEADING=3 # Remove leading low quality or N bases (below quality 3) (LEADING:3)
p_trimming_TRAILING=3 # Remove trailing low quality or N bases (below quality 3) (TRAILING:3)
p_trimming_SLIDINGWINDOW=4:15 # Scan the read with a 4-base wide sliding window, cutting when the average quality per base drops below 15 (SLIDINGWINDOW:4:15)
p_trimming_MINLEN=36 # Drop reads below the 36 bases long (MINLEN:36)
# ---------- taxonomy assignment configuration ---------------------------------------
dir_metaxa=/apps/unit/GoryaninU/software/taxonomy/Metaxa2_2.1.3/metaxa2
dir_metaxa2_ttt=/apps/unit/GoryaninU/software/taxonomy/Metaxa2_2.1.3/metaxa2_ttt
# config taxonomy parameter
p_taxonomy_identity=0,60,70,75,85,90,97 # Sets the percent identity cutoff to be classified at a certain taxonomic level
# Order of the values is: Kingdom/Domain,Phylum,Class,Order,Family,Genus,Species
# Default values are: 0,60,70,75,85,90,97
p_taxonomy_organism=a,b # {b, bacteria; a, archaea; e, eukaryota; m, mitochondrial; c, chloroplast; A, all; o, other} :
# Profile set to use for the search (comma-separated), default is all
p_taxonomy_match=5 # Number of sequence matches to consider for classification, default = 5
# visualization configuration
dir_krona_vis=/apps/unit/GoryaninU/software/visualization/KronaTools-2.6.1/bin/ktImportText
p_taxonomy_level=7 # Taxonomic level for performing inference, Default is 7 (species level).
# (1 = domain, 2 = phylum, 3 = class, 4 = order, 5 = family, 6 = genus, 7 = species)
dir_MetaPhlAn=/apps/unit/GoryaninU/software/taxonomy/metaphlan2/metaphlan2.py
export mpa_dir=/apps/unit/GoryaninU/software/taxonomy/metaphlan2/
p_MPA_analysis_type=rel_ab # Type of analysis to perform:
# * rel_ab: profiling a metagenomes in terms of relative abundances
# * rel_ab_w_read_stats: profiling a metagenomes in terms of relative abundances and estimate the number of reads comming from each clade.
# * reads_map: mapping from reads to clades (only reads hitting a marker)
# * clade_profiles: normalized marker counts for clades with at least a non-null marker
# * marker_ab_table: normalized marker counts (only when > 0.0 and normalized by metagenome size if --nreads is specified)
# * marker_pres_table: list of markers present in the sample (threshold at 1.0 if not differently specified with --pres_th
# [default 'rel_ab']
# ---------- assembly configuration -------------------------------------------------
dir_SPAdes=/apps/unit/GoryaninU/software/assembler/SPAdes-3.8.2/bin/metaspades.py
dir_metaQuast=/apps/unit/GoryaninU/software/assembler/quast-4.1/metaquast.py
# ---------- bining -----------------------------------------------------------------
# dir_fq2fa=fq2fa.py
# dir_MetaAnnotator=/apps/unit/GoryaninU/software/bining/MetaAnnotator/bin/MetaAnnotator
# dir_MetaAnnotator_bin=/apps/unit/GoryaninU/software/bining/MetaAnnotator/bin/
dir_MaxBin=/apps/unit/GoryaninU/software/bining/MaxBin-2.2/run_MaxBin.pl
# ---------- Gene call tool --------------------------------------------------------
dir_FragGeneScan=/apps/unit/GoryaninU/software/gene_calling/FragGeneScan1.30/FragGeneScan
# ---------- Annotation tool -------------------------------------------------------
dir_split_fasta=src/split_fasta.py
nodes_num=38
dir_InterProScan=/apps/unit/GoryaninU/software/annotation/interproscan-5.18-57.0/interproscan.sh
dir_cognizer=/apps/unit/GoryaninU/software/annotation/cognizer_64bit/
p_cognizer_evalue=-5 #the E-value threshold to be used for the similarity search [default = -5.0]