jungbluth

#!/usr/bin/env Rscript

vd <- venneuler(c(A=5, B=3, C=5, "A&B"=0, "A&C"=0, "B&C"=13 ,"A&B&C"=0))
plot(vd)

jungbluth

#!/usr/bin/env bash


###PREP

##download databases
##located at: http://sourmash.readthedocs.io/en/latest/databases.html

#sbt-database? renameme

jungbluth

#!/usr/bin/env bash

for line in $(cat list); do
  FILE=/global/cfs/cdirs/img/web-data/sandbox.blast.data/${line}/${line}.a.fna
  if [ -f "$FILE" ]; then
    mamba activate sourmash
    sourmash sketch dna -p k=31,scaled=1000 -o ${line}.fna.sig "$FILE"
  fi
done

jungbluth

ID=3300011415

curl -s https://prospero.jgi.doe.gov/ws/lineage/lookup/$ID | jq .

jungbluth

dat1<-read.table("scaffoldCart22861_18-jan-2017.xls", header=T, sep="\t")
dat2<-read.table("scaffolds-to-bins.txt", header=F, sep="\t")
dat3<-merge(dat1, dat2, by.x="Scaffold.ID", by.y="V1")
dat3$genomesum<-0
dat4<-as.data.frame(unique(dat3$V2))
dat4$coverage<-0

for (i in 1:length(levels(dat3$V2))){
dat3[which(dat3$V2==(unique(dat3$V2))[i]),]$genomesum<-sum(dat3[which(dat3$V2==(unique(dat3$V2))[i]),]$Sequence.Length..bp.)
dat4[i,2]<-sum((dat3[which(dat3$V2==(unique(dat3$V2))[i]),]$Sequence.Length..bp./dat3[which(dat3$V2==(unique(dat3$V2))[i]),]$genomesum)*dat3[which(dat3$V2==(unique(dat3$V2))[i]),]$Read.Depth)

jungbluth

#!/usr/bin/env bash

imgid=${1}
listfile=${2}

sqlsample () {     if [ $(echo $(sqlite3 ${1} ".schema") | tr ';' '\n' | grep -c "CREATE TABLE" ) -gt "1" ]; then         echo "Warning: ${1} contains multiple tables - no export here because function written to export single table.";     else         TABLECOLUMNS=$(for line in $(echo $(sqlite3 ${1} ".schema") | sed 's/^[^(]*(//' | tr ',' '\n' | sed 's/^ *//' | sed 's/ .*//'); do printf "$line,"; done | sed 's/,$/\n/');         TABLE=$(echo $(sqlite3 ${1} ".schema") | sed 's/^CREATE TABLE //' | sed 's/ .*//' | sed 's/(.*//');         sqlite3 ${1} "SELECT $(echo $TABLECOLUMNS) FROM $(echo $TABLE)";     fi; }

cd /global/cfs/cdirs/img_web/img_web_data/mer.fs/${imgid}/assembled/fna

# convert sqlite3 database to fasta flat file

jungbluth

anvi-script-reformat-fasta GCA_001899445.1_ASM189944v1_genomic.fna -o GCA_001899445.1_ASM189944v1_genomic_reformatted.fna -l 100 --simplify-names

anvi-gen-contigs-database -f GCA_001899445.1_ASM189944v1_genomic_reformatted.fna -o contigs.db --split-length 10000 --kmer-size 4 -T 2 --prodigal-translation-table 11 -n 'GCA_001899445.1_ASM189944v1_genomic contig database'

anvi-run-hmms -c contigs.db --num-threads 2

anvi-run-ncbi-cogs -c contigs.db -T 2 --sensitive --cog-data-dir /kb/module/work/anviodb/COG

anvi-run-pfams -c contigs.db -T 2 --pfam-data-dir /kb/module/work/anviodb/Pfam

jungbluth

#!/usr/bin/env python3

# this script connects to IMG web backend and pulls together smart, pfam, faa, and gene copy tables
import os
import sys
import pandas

import sqlite3
from glob import glob
from natsort import natsorted

jungbluth

for line in $(cat /global/cfs/cdirs/kbase/ke_prototype/GTDB/Pseudomonas-genus_forManasa/Pseudomonas-IDs_GTDB_v207.list); do
  genomeID=$(echo $line | cut -d "_" -f2-)
  splitA=$(echo $line | cut -d "_" -f2)
  splitB=$(echo $line | cut -d "_" -f3 | sed 's/......\..$//')
  splitC=$(echo $line | cut -d "_" -f3 | sed 's/...\..$//' | sed 's/^...//')
  splitD=$(echo $line | cut -d "_" -f3 | sed 's/\..$//' | sed 's/^......//')
  echo "$splitA $splitB $splitC $splitD"
  wget --recursive -e robots=off --reject "index.html" --timestamping -A "_genomic.fna.gz" ftp://ftp.ncbi.nlm.nih.gov/genomes/all/$splitA/$splitB/$splitC/$splitD/ -P ./
done

jungbluth

#!/usr/bin/env python

import sys
import os

#for x in (os.getenv("PYTHONPATH") if os.getenv("PYTHONPATH") else "").split(":"):
#    if x not in sys.path:
#        sys.path.append(x)
#import qcutils
sys.path.insert(0,"/global/homes/b/bfoster/git/jgi-mt/lib")