Cecret Workflow for SARS-CoV-2 Assembly and Lineage Classification V.3

module load Python/3.9.1
module load java/jdk1.8.0_221
module load nextflow/20.04.1
module load singularity/3.5.3

git clone https://github.com/StaPH-B/staphb_toolkit.git
cd staphb_toolkit/packaging/
python3 setup.py install --user
cd ../
export PATH=$PATH:$(pwd)

#Input Sequencing Reads File Path: 
/Full_Path_to_Fastq_File_Directory/INPUT/SRR11953697

#Output Directory:
/Full_Path_to_Cecret_Output_Directory/SRR11953697_cecret_output

mkdir -p cachedir
SINGULARITY_CACHEDIR=/PATH/for/cache
staphb-wf cecret /Full_Path_to_Fastq_File_Directory/INPUT/SRR11953697 --output /Full_Path_to_Cecret_Output_Directory/SRR11953697_cecret_output --profile singularity

staphb-wf cecret --get_config
staphb-wf cecret /Full_Path_to_Fastq_File_Directory/INPUT/SRR11953697 --output /Full_Path_to_Cecret_Output_Directory/SRR11953697_cecret_output --profile singularity -c /Full_Path_to_Config_File_Directory/date_cecret.config

cecret_run_results.txt                # information about the sequencing run that's compatible with legacy workflows
covid_samples.csv                     # only if supplied initially
cecret
|-aligned
| |-pretrimmed.sorted.bam
|-bamsnap
| |-sample
|   |-ivar
|     |-variant.png                   # png of variants identified via ivar
|   |-bcftools
|     |-variant.png                   # png of variants identified via bcftools
|-bedtools_multicov
| |-sample.multicov.txt               # depth per amplicon
|-consensus
| |-sample.consensus.fa               # the likely reason you are running this workflow
|-fastp
| |-sample_clean_PE1.fastq            # clean file: only if params.cleaner=fastp
| |-sample_clean_PE2.fastq            # clean file: only if params.cleaner=fastp
|-fastqc
| |-sample.fastqc.html
| |-sample.fastqc.zip
|-filter                              # optional: turns aligned bams into fastq files
| |-sample_filtered_R1.fastq
| |-sample_filtered_R2.fastq
| |-sample_filtered_unpaired.fastq
|-iqtree                              # optional: relatedness parameter must be set to true
| |-iqtree.treefile
|-ivar_trim
| |-sample.primertrim.bam             # aligned reads after primer trimming. trimmer parameter must be set to 'ivar'
|-ivar_variants
| |-sample.variants.tsv               # list of variants identified via ivar and corresponding scores
|-kraken2
| |-sample_kraken2_report.txt         # kraken2 report of the percentage of reads matching virus and human sequences
|-logs
| |-process_logs                      # for troubleshooting puroses
|-mafft                               # optional: relatedness parameter must be set to true
| |-mafft_aligned.fasta               # multiple sequence alignement generated via mafft
|-nextclade                           # identfication of nextclade clades and variants identified
| |-sample_nextclade_report.csv       # actually a ";" deliminated file
|-pangolin
| |-lineage_report.csv                # identification of pangolin lineages
|-samtools_ampliconstats
| |-sample_ampliconstats.txt          # stats for the amplicons used
|-samtools_coverage
| |-aligned
| | |-sample.cov.hist                 # histogram of coverage for aligned reads
| | |-sample.cov.txt                  # tabular information of coverage for aligned reads
| |-trimmed
|   |-sample.cov.trim.hist            # histogram of coverage for aligned reads after primer trimming
|   |-sample.cov.trim.txt             # tabular information of coverage for aligned reads after primer trimming
|-samtools_depth
| |-aligned
| | |-sample.depth.txt                # read depth for each read position
| |-trimmed
|   |-sample.depth.txt                # read depth for each position
|-samtools_flagstat
| |-aligned
| | |-sample.flagstat.txt             # samtools stats for aligned reads
| |-trimmed
|   |-sample.flagstat.trim.txt        # samtools stats for trimmed reads
|-samtools_plot_ampliconstats
| |-sample.*.png                      # images corresponding to amiplicon performance
|-samtools_stats
| |-aligned
| | |-sample.stats.txt                # samtools stats for aligned reads
| |-trimmed
|   |-sample.stats.trim.txt           # samtools stats for trimmed reads
|-seqyclean
| |-sample_clean_PE1.fastq            # clean file
| |-sample_clean_PE2.fastq            # clean file
|-snp-dists                           # optional: relatedness parameter must be set to true
| |-snp-dists                         # file containing a table of the number of snps that differ between any two samples
|-submission_files                    # optional: is only created if covid_samples.txt exists
| |-sample.genbank.fa                 # fasta file with formatting and header including metadata for genbank
| |-sample.gisaid.fa                  # fasta file with header for gisaid
| |-sample.R1.fastq.gz                # renamed raw fastq.gz file
| |-sample.R2.fastq.gz                # renamed raw fastq.gz file
|-summary
| |-sample.summary.txt                # individual results
|-summary.csv                         # tab-delimited summary of results from the workflow
reads
| |-sample_S1_L001_R1_001.fastq.gz    # initial file
| |-sample_S1_L001_R2_001.fastq.gz    # inital file
work                                  # nextflows work directory. Likely fairly large.
vadr
  |-vadr*                             # vadr output

#Consensus Sequence Path:
/Full_Path_to_Cecret_Output_Directory/SRR11953697_cecret_output/consensus/SRR11953697.consensus.fa

#Summary Report Path:
/Full_Path_to_Cecret_Output_Directory/SRR11953697_cecret_output/summary.txt