install rnaseq on sage

#-- version 2 --
conda install -c conda-forge mamba
mamba create -n rnaseq -c conda-forge -c bioconda -c defaults python fastqc trim-galore star hisat2 picard csvtk preseq rseqc samtools
conda activate rnaseq
pip3 install deeptools
pip3 install multiqc
mamba install -c conda-forge -c bioconda -c defaults -c r stringtie subread gffread r-data.table r-gplots bioconductor-dupradar bioconductor-edger
#(rnaseq) [jhuang@sage ~]$ which nextflow
#/usr/local/bin/nextflow
conda install -c bionconda fq
mamba install -c bioconda ucsc-bedclip ucsc-bedgraphtobigwig
mamba install -c bioconda rsem
mamba install -c bioconda salmon
mamba install -c conda-forge -c bioconda -c defaults -c r r-data.table r-gplots bioconductor-dupradar bioconductor-edger bioconductor-deseq2
mamba install -c conda-forge openjdk=17
conda install -c bioconda bedtools qualimap
#under R
install.packages("BiocManager")
BiocManager::install("tximport")
BiocManager::install("tximeta")        
install.packages("optparse")            
install.packages(“pheatmap”)
(rnaseq2) [jhuang@sage Data_Soeren_RNA-seq_2023]$ nextflow run rnaseq/main.nf --input samplesheet.csv    --outdir results_GRCh38 --genome GRCh38   -profile test_full -resume --max_memory 300.GB --max_time 2400.h --save_reference --aligner star_salmon  --skip_deseq2_qc
(rnaseq) nextflow run rnaseq/main.nf --input samplesheet.csv --outdir results_1585 --fasta 1585.fasta --gtf 1585_m_.gtf -profile test_full -resume --max_memory 200.GB --max_time 2400.h --save_reference --aligner star_salmon   --skip_rseqc --skip_dupradar --skip_preseq --skip_biotype_qc --skip_deseq2_qc --min_mapped_reads 0
#--gtf_extra_attributes gene_name

#-- version 1 --
#conda env create -f ~/Tools/rnaseq/environment.yml
conda create -n rnaseq -c conda-forge -c bioconda -c defaults python=3.6 fastqc trim-galore star=2.6.1d hisat2
conda activate rnaseq
conda install -c conda-forge -c bioconda -c defaults picard csvtk preseq rseqc samtools
pip3 install deeptools
pip3 install multiqc
conda install -c bioconda stringtie subread gffread
conda install -c conda-forge -c bioconda -c defaults -c r r-data.table r-gplots
conda install -c conda-forge -c bioconda -c defaults -c r bioconductor-dupradar bioconductor-edger
conda install nextflow=20.04

install chipseq

conda create -n chipseq -c conda-forge -c bioconda -c defaults -c r python=3.9 fastqc cutadapt trim-galore bwa samtools 
conda activate chipseq
conda install picard bedtools phantompeakqualtools 
conda install -c conda-forge -c bioconda -c defaults -c r r-base 
#ERROR_SINCE_R_NGSPLOT_ONLY_FOR_PYTHON2 conda install -c conda-forge -c bioconda -c defaults -c r r-ngsplot
sudo apt install macs
conda install -c bioconda multiqc
pip3 install deeptools
conda install nextflow=20.04

#conda env chipseq2 is still NOT working.
conda create -n chipseq2 -c conda-forge -c bioconda -c defaults python=2.7 fastqc cutadapt trim-galore bwa samtools 
conda activate chipseq2
conda install -c conda-forge -c bioconda -c defaults picard bedtools phantompeakqualtools 
conda install -c conda-forge -c bioconda -c defaults -c r deeptools r-base r-ngsplot macs multiqc
conda install -c conda-forge -c bioconda -c defaults -c r r-ade4 r-assertthat r-base r-bh r-biocmanager r-bit r-bit64 r-bitops r-blob r-catools r-codetools r-crayon r-curl r-dbi r-digest r-domc r-foreach r-formatr r-futile.logger r-futile.options r-glue r-hms r-httr r-hwriter r-idr r-iterators r-jsonlite r-lambda.r r-lattice r-latticeextra r-lazyeval r-magrittr r-mass r-matrix r-matrixstats r-memoise r-mime r-openssl r-pkgconfig r-plogr r-prettyunits r-progress r-r6 r-rcolorbrewer r-rcpp r-rcurl r-rlang r-rsqlite r-segmented r-seqinr r-snow r-spp r-stringi r-stringr r-survival r-venndiagram r-xml
conda install -c conda-forge -c bioconda -c defaults -c r bioconductor-annotationdbi bioconductor-annotationfilter bioconductor-biobase bioconductor-biocgenerics bioconductor-biocparallel bioconductor-biomart bioconductor-biostrings bioconductor-bsgenome bioconductor-chippeakanno bioconductor-delayedarray bioconductor-ensembldb bioconductor-genomeinfodb bioconductor-genomeinfodbdata bioconductor-genomicalignments bioconductor-genomicfeatures bioconductor-genomicranges bioconductor-go.db bioconductor-graph bioconductor-iranges bioconductor-limma bioconductor-multtest bioconductor-protgenerics bioconductor-rbgl bioconductor-regioner bioconductor-rsamtools bioconductor-rsubread bioconductor-rtracklayer bioconductor-s4vectors bioconductor-shortread bioconductor-summarizedexperiment bioconductor-xvector bioconductor-zlibbioc
conda install nextflow=20.04

#first_try
(chipseq) nextflow run NGI-ChIPseq/main.nf --reads '/home/jhuang/DATA/Data_Denise_LT_DNA_Binding/enhancer_analysis/Raw_Data/*.fastq.gz' --genome hg38 --macsconfig macs.config --saveReference --saveAlignedIntermediates --singleEnd --blacklist_filtering -profile standard --project NHDF_enhancer_analysis_hg38 -resume
#--notrim
(chipseq) nextflow run NGI-ChIPseq/main.nf --reads '/home/jhuang/DATA/Data_Denise_LT_DNA_Binding/enhancer_analysis/Raw_Data/*.fastq.gz' --genome hg38 --macsconfig macs.config --saveAlignedIntermediates --notrim --saveTrimmed --singleEnd --blacklist_filtering -profile standard --project NHDF_enhancer_analysis_hg38 -resume
#test
(chipseq) nextflow run NGI-ChIPseq/main.nf --reads '/home/jhuang/DATA/Data_Denise_LT_DNA_Binding/Raw_Data/p783_*.fastq.gz' --genome hg38 --macsconfig macs.config --saveReference --saveAlignedIntermediates --singleEnd --blacklist_filtering -profile standard --project NHDF_enhancer_analysis_hg38 -resume

install spandx

conda create --name spandx2 python=3.8
conda activate spandx2
conda install -c conda-forge -c bioconda -c defaults art trimmomatic bwa bedtools=2.28.0 seqtk pindel mosdepth samtools=1.9 picard gatk4 snpeff=4.3.1t nextflow=22 fasttree
#[genbank copying]
mkdir ~/miniconda3/envs/spandx2/share/snpeff-4.3.1t-5/data/WA_plasmid
cp WA_plasmid.gb ~/miniconda3/envs/spandx2/share/snpeff-4.3.1t-5/data/WA_plasmid/genes.gbk
vim ~/miniconda3/envs/spandx2/share/snpeff-4.3.1t-5/snpEff.config
/home/jhuang/miniconda3/envs/spandx2/bin/snpEff build -genbank WA_plasmid      -d

nextflow run spandx/main.nf --fastq "Raw_Data_RNAseq_K331A_d8_SPANDx/*.fastq.gz" --ref LT_wt.fasta --annotation --database LT_wildtype --pairing SE -resume
(spandx2) nextflow run spandx/main.nf --fastq "raw_data/*_R{1,2}.fastq.gz" --ref WA_chr.fasta --annotation --database WA_chr -resume
(spandx2) nextflow run spandx/main.nf --fastq "raw_data/*_R{1,2}.fastq.gz" --ref WA_plasmid.fasta --annotation --database WA_plasmid -resume
#Note that the files in variants contain only SNPs, but the files in snippy contain SNPs+INDELs which can be used to consensus the results of SPANDx, resulting in the final results of SNPs+INDELs.
~/DATA/Data_Benjamin_Yersinia_SNP/variants_WA_chr$ vim snippy.core.vcf
~/DATA/Data_Benjamin_Yersinia_SNP/snippy_WA_chr/Wacton_S96/Wacton_S96.txt
~/DATA/Data_Benjamin_Yersinia_SNP/snippy_WA_chr/Wacton_S96/Wacton_S96.filt.vcf 

#FOLLOWING INSTALLATION CANNOT FINISH CALCULATION --> MAYBE IT NOW WORKS, BUT NEEDS TO GIVE AT LEAST SAMPLES, AS SAME AS IN SPANDX2
conda create --name spandx python=3.8
#conda install -c conda-forge -c bioconda -c defaults art trimmomatic bwa bedtools seqtk pindel mosdepth samtools picard gatk4 snpeff nextflow fasttree
#-->picard-3.0.0-1, gatk4-4.4.0.0-0, snpeff-5.1-2, trimmomatic-0.39-2 installed!
#DEBUG1: Due to using snpeff-5.1-2 by deleting the option '-t' in all 'snpEff eff -t ...' since '-t' is not a option in the new version.
#DEBUG2: Don't login spandx after login base, since in the case the env uses /home/jhuang/anaconda3/bin/java.
#  - /usr/bin/java: openjdk version "11.0.18" 2023-01-17
#  - /home/jhuang/anaconda3/bin/java: openjdk version "1.8.0_152-release"
#  - /home/jhuang/anaconda3/envs/spandx/bin/java: openjdk version "17.0.3-internal" 2022-04-19
#DEBUG3: using '-' instead of '_'
#  mv V_8_2_4_p600_d8_DonorI.fastq.gz    control-d8-DI.fastq.gz

install bengal3_ac3

conda create -n bengal3_ac3 python=3.6
conda activate bengal3_ac3
conda install -c conda-forge -c bioconda -c defaults  prokka 
conda install -c conda-forge -c bioconda -c defaults  shovill mlst 
conda install -c conda-forge -c bioconda -c defaults  trimmomatic fastqc    
conda install -c conda-forge -c bioconda -c defaults  roary
conda install -c conda-forge -c bioconda -c defaults  snippy
conda install -c conda-forge -c bioconda -c defaults  fasttree raxml-ng  
conda install -c conda-forge -c bioconda -c defaults  gubbins snp-sites
conda install -c conda-forge -c bioconda -c defaults openjdk=11
TODO: snippy is still NOT working in hamm, we have to run the modul  "variants_calling" on hamburg.

install qiime1

conda create -n qiime1 -c bioconda qiime

export environments

#!/bin/bash

# Get a list of conda environments
env_list=$(conda env list | awk '{print $1}' | tail -n +4)

# Iterate through each environment and export it to a YAML file
for env in $env_list; do
    echo "conda activate $env"
    echo "conda env export > \"${env}_exported.yml\""
    echo "conda deactivate"
done

#conda create --name spandx2 --clone spandx
#conda env remove --name spandx

#conda activate spandx
#conda env export > spandx.yml
#rsync -a -P *.yml xxx@xxx:~/xxx/xxx
#conda env create -f spandx.yml

conda activate base
conda env export > "base_exported.yml"
conda deactivate
conda activate HLCA_mapping_env
conda env export > "HLCA_mapping_env_exported.yml"
conda deactivate
conda activate assembly2
conda env export > "assembly2_exported.yml"
conda deactivate
conda activate bac3
conda env export > "bac3_exported.yml"
conda deactivate
conda activate bactopia
conda env export > "bactopia_exported.yml"
conda deactivate