MADscientist314

# ---
# title: Export QIIME2 OTU table to compatible file for phyloseq
# description: |
#   Three main steps to get to compatible file to import to phyloseq
#
#   Outline:
#   1. Export OTU table
#   2. Export taxonomy table
#   3. Export phylogenetic tree
# ---

MADscientist314

 for n in $(cat list); 
 do 
  echo "converting $n fastq.gz to fasta"; 
  seqtk seq -a $n\_kneaddata_paired_1.fastq.gz >  $n\_kneaddata_paired_1.fasta; 
  seqtk seq -a $n\_kneaddata_paired_2.fastq.gz >  $n\_kneaddata_paired_2.fasta; 
done

MADscientist314

docker run -it -v $PWD:$PWD --name blast_nt ncbi/blast
update_blastdb.pl --showall [*]
#cd /media/jochum00/Aagaard_Raid/reference_datasets/ncbi_db
#mkdir nt
#cd nt
update_blastdb.pl --decompress --source gcp --verbose --verbose nt
export BLASTDB=/media/jochum00/Aagaard_Raid/reference_datasets/ncbi_db/nt


blastn \

MADscientist314

### RScript to go along with the tutorial found here: https://astrobiomike.github.io/amplicon/dada2_workflow_ex


library(dada2)
packageVersion("dada2") # 1.11.5 when this was put together

setwd("~/dada2_amplicon_ex_workflow")

list.files() # make sure what we think is here is actually here

MADscientist314

#!/bin/bash
# Parallel rsync script originally designed for rsyncing 
# large ata transfers from RAID to RAID for the Aagaard Lab. 
# Author: Michael Jochum
# Location: Baylor College of Medicine, Houston, TX, USA
# Contact : [email protected]
# Date : 2 November 2020

##################################
#Step 0: fill this shit out

MADscientist314

for i in *; 
do 
#practice (wont overwrite the file
nawk '{print FILENAME"\t"$0}' $i > $i.bk; mv $i.k $i; 
#will overwrite the file
#nawk '{print FILENAME"\t"$0}' $i > $i.bk; mv $i.bk $i;
done

MADscientist314

threads=48

for n in $(cat manifest_02);
do
nohup fastq_screen
time 
fastq_screen \
--nohits \
--threads $threads  \
--subset 0 \