Added db and updated documentation

README.md

@@ -1,2 +1,66 @@
 # cdiff_fbi
-cdiff pipeline
+Typing of *Clostridioides difficile* isolates using NGS data (reads and contigs) based on tandem repeat loci (TR6, TR10), and toxin genes (cdtA, cdtB, tcdA, tcdB, tcdC).
+
+## Quick start
+```bash
+# Type
+bash cdifftyping.sh -h
+# Process
+bash postcdifftyping.sh -h
+# Summarize
+python3 qc_cdiff_summary.py -h
+```
+
+## Installation
+### Source
+```bash
+# Clone this repo
+git clone https://github.com/ssi-dk/cdiff_fbi.git
+# Create an environment with the required tools with conda
+conda create --name cdiff_pipeline picard gatk4 biopython ruamel.yaml kraken bwa samtools
+# Activate the environment
+conda activate cdiff pipeline
+# Install a custom tool
+git clone https://github.com/ssi-dk/serum_readfilter
+cd serum_readfilter
+pip install .
+```
+
+## Usage
+### Example
+```bash
+# Download data into the test folder
+mkdir -p test
+wget -nc ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR142/ERR142064/ERR142064_2.fastq.gz -P test
+wget -nc ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR142/ERR142064/ERR142064_1.fastq.gz -P test
+touch ERR142064.fasta  # Create an empty file as a fake assembly for testing purposes
+```
+
+### Pipeline
+```bash
+# Build the db
+bash cdifftyping.sh -db db -update yes  # WARNING: Not yet implemented for serumdb or trstdb
+# Type
+bash cdifftyping.sh -i ERR142064 -R1 test/ERR142064_1.fastq.gz -R2 test/ERR142064_2.fastq.gz -c test/ERR142064.fasta -qc pass -o test -db db -update no
+# Process
+bash postcdifftyping.sh -i ERR142064 -d test -stbit "STNA;NA:NA"
+# Summarize
+python3 qc_cdiff_summary.py -i test -o test
+```
+
+## Output
+### .csv
+```
+Name;cdtA/B;tcdA;tcdB;tcdClength;117del;A117T;TRST;TR6;TR10;ST;STalleles;WGS;tcdA:tcdB:tcdC:cdtA:cdtB
+ERR142064;+/+;+;+;0;+;-;Unknown;Unknown;Unknown;STNA;NA:NA;test;8119/8133:6914/7101:700/700:1389/1389:2628/2628
+```
+### .json
+```
+{"Name": "ERR142064", "cdtA": "+", "cdtB": "+", "tcdA": "+", "tcdB": "+", "tcdClength": "0", "117del": "+", "A117T": "-", "TRST": "Unknown", "TR6": "Unknown", "TR10": "Unknown", "ST": "STNA;NA:NA", "WGS": "test", "cov_info": {"tcdA": "8119/8133", "tcdB": "6914/7101", "tcdC": "700/700", "cdtA": "1389/1389", "cdtB": "2628/2628"}}
+```
+
+## Updating the db
+```bash
+# Build the db
+bash cdifftyping.sh -db db -update yes  # WARNING: Not yet implemented for serumdb or trstdb
+```

TRSTfinder3.py

@@ -72,6 +72,7 @@ def revtrans(seq):
 
 
 ## Main
+# Tandem repeat loci TR6 and TR10
 TR6fragments = parse_repeat_sequences(args.trstdb, "TR6_repeat_sequences.ashx")
 TR10fragments = parse_repeat_sequences(args.trstdb, "TR10_repeat_sequences.ashx")
 TR6 = parse_types(args.trstdb, "TR6_types.ashx", TR6fragments)

cdifftyping.sh

@@ -90,9 +90,7 @@ echo "TRSTDB: $trstdb"
 if [[ "$update" == "yes" ]] ; then
 	echo -e "\n# Updating dbs..."
 	## TODO: Find which command was used to make the serumdb, code below is a draft!
-	echo -e "\n# WARNING!: Code not implemented yet!"
-	echo -e "\n# Exiting.."
-	exit 1
+	echo -e "\n# WARNING!: Not yet implemented for serumdb or trstdb!"
 	# # cdiff_serum_readfilter
 	# echo -e "\n# Updating cdiff_serum_readfilter..."
 	# rm -r $serumdb/library $serumdb/taxonomy || true  # Remove old folders

db/cdiff_TRST/TR10_repeat_sequences.ashx

@@ -0,0 +1,144 @@
+>N001
+AAATTAATTATTATATTTCTTT
+>N002
+AAATTAATTTTCTATATTTCTT
+>N003
+AAATTAATGTATTGTATTTCTTT
+>N004
+AAATTAGTTTATTATACTTCTTT
+>N005
+AGATTAATTTTCTATACTTCCT
+>N006
+AGATTAGCTTTCTATACTTCCT
+>N007
+AGATTAGCTTTCTATATTTCTT
+>N008
+AAATTAATTTTCTATACTTCCT
+>N009
+AAATTAGTTTATTACACTTCTTT
+>N010
+AGATTAATTTTCTATACTTTCT
+>N011
+AAATTAATTTTCTATACTTCTT
+>N012
+AAATTAGTTTACTATACTTCTTT
+>N013
+AGATTAGCTTTCTATACTTCTTT
+>N014
+AGATTAATTTTCTACACTTCCT
+>N015
+AAATTAATTTATTATATTTTTT
+>N016
+AAATTAATTTATTGTATTTCTTT
+>N017
+AAATTAATTTTCTATGTTTCTT
+>N018
+AAATTAGCTTATTATACTTTTT
+>N019
+GAATTAGTTTATTATACTTCTTT
+>N020
+AGATTAATTTTCTATATTTCTT
+>N021
+AAATTAGTTTATTATACTTCCT
+>N022
+AAATTAGTTCATTATACTTCTTT
+>N023
+AAATTAATTTTCTACACTTCCT
+>N024
+AAATTAGTTTATTATATTTCTT
+>N025
+AAATTAATATATTGTATTTCTTT
+>N026
+AGATTAATTTTCTATACTTCTTT
+>N027
+AAGTTAATTTATTGTATTTCTTT
+>N028
+AGATTAATTTTCTATATTTCCT 
+>N029
+AAATTAATTTATTATATTTCTTT 
+>N030
+AAGTTAGCTCATTATACTTCTTT
+>N031
+AAATTAGCTTATTATACTTCTT
+>N032
+AGATTAACTTTCTATACTTTCT
+>N033
+AGATTAGTTTTCTATACTTCCT
+>N034
+AAATTAGTTTATTATGCTTCTTT
+>N035
+AAATTAATTTTTTATACTTCCT
+>N036
+AGATTAATTTTCCATACTTCCT
+>N037
+AAATTAGCTCATTATACTTCTTT
+>N038
+AAATTAATTTTCCATATTTCTT
+>N039
+AGATTAATTTTCTATCCTTCCT
+>N040
+AAACTAATTTTCTATACTTCCT
+>N041
+AAATTAGTTTATTATACTTTTT
+>N042
+AAATTAATTTTTTATACTTCTTT
+>N043
+AAATTAGCTTATTATATTTCTT
+>N044
+AGATTAGCTTTCTATACTTTCT
+>N045
+AAATTAGTTTATTATACTTATTT
+>N046
+AAATTAATTTTCTATACTTTCT
+>N047
+AAATTAATTATTGTGTTTCTTT
+>N048
+GAATTAGTTTATTATACTCCTTT
+>N049
+AAATTAATTTTCTATCCTTCCT
+>N050
+AAATTAATGTATTGTGTTTCTTT
+>N051
+AGATTAATTTCCTATACTTCCT
+>N052
+AAATTAGCTTTCTATACTTCCT
+>N053
+AAATCAATTTTCTATATTTCTT
+>N054
+AAATTAATTTTCCATACTTCTT
+>N055
+AGATTAGCTTTTTATACTTCTTT
+>N056
+AGATTAATTTTATATACTTCCT
+>N057
+AAATTAGTTTATTATACTTCTT
+>N058
+AGATTAGCTTTTTATACTTCCT
+>N059
+AAATTAGTTTATTATATTTTTT
+>N060
+AAATTAGTTTATTATATTTCTTT
+>N061
+AAATTAATTTATTATACTTCTTT
+>N062
+AAATTAGTTTATTACACTTCCTT
+>N063
+AAATTAATCTTCTATACTTCCT
+>N064
+AAATTAGTTTATTATACTTCTCT
+>N065
+AAATTAGTTTGTTACACTTCTTT
+>N066
+AAATTAGTTTTCTATATTTCTT
+>N067
+AAATTAAATTTCTATATTTCTT
+>N068
+AGATTAGCTTTCTATACTTCCTT
+>N069
+AAATTAGTTTATTGTACTTCTTT
+>N070
+AAATTAGCTTATTATACTTCTTT
+>N071
+AAATTAATTTTCTATACTTCTTT
+>N072
+AGATTAGCTTTCTATACTTCCTA