genomewalker’s gists

genomewalker / hmp_sample_selection

Created January 20, 2020 06:58

	library(tidyverse)

	# Functions for pretty histograms
	nclass.all <- function(x, fun = median)
	{
	fun(c(
	nclass.Sturges(x),
	nclass.scott(x),
	nclass.FD(x)
	))

genomewalker / repair.md

Created November 7, 2019 07:14

../opt/bbmap/repair.sh in=../DBs/fastq_clean/samples/tm3_1.2.gz out=r1.fq out2=r2.fq outs=sr.fq overwrite

Set INTERLEAVED to false
Started output stream.

Input:                          60113046 reads          4484553415 bases.
Result:                         60113046 reads (100.00%)        4484553415 bases (100.00%)
Pairs:                          1062720 reads (1.77%)   145407477 bases (3.24%)

genomewalker / anvio-6_env.txt

Created October 18, 2019 20:15

	# packages in environment at /Users/ufo/.pyenv/versions/miniconda3-latest/envs/anvio-6:
	#
	# Name Version Build Channel
	anvio 6 0 bioconda
	anvio-minimal 6 py_0 bioconda
	appdirs 1.4.3 py_1 conda-forge
	asn1crypto 1.2.0 py36_0 conda-forge
	attrs 19.3.0 py_0 conda-forge
	bcftools 1.9 h16e57c4_7 bioconda
	biopython 1.74 py36h01d97ff_0 conda-forge

genomewalker / start_h2o_cluster.R

Created June 25, 2019 15:38

	node_list = Sys.getenv("SLURM_NODELIST")
	cat("SLURM nodes:", node_list, "\n")

	# Loop up IPs of the allocated nodes.
	if (node_list != "") {
	nodes = strsplit(node_list, ",")[[1]]
	ips = rep(NA, length(nodes))
	for (i in 1:length(nodes)) {
	args = c(nodes[i], " \| awk '/has address/ { print $4 ; exit }'")
	result = system2("host", args = args, stdout = T)

genomewalker / cl_updt.o1889

Last active April 30, 2019 18:36

	+ set -e
	+ MMSEQS=/vol/attached/opt/MPI/MMseqs2/bin/mmseqs
	+ DIR=/vol/attached/gtdb
	+ SDIR=/vol/scratch/gtdb
	+ export 'OMPI_MCA_btl=^openib'
	+ OMPI_MCA_btl='^openib'
	+ export OMP_NUM_THREADS=28
	+ OMP_NUM_THREADS=28
	+ RUNNER='mpirun --mca btl_tcp_if_include ens3 -n 10 --map-by ppr:1:node --bind-to none '
	+ /vol/attached/opt/MPI/MMseqs2/bin/mmseqs clusterupdate /vol/scratch/gtdb/marine_hmp_db_03112017 /vol/scratch/gtdb/mg_gtdb_orfs_db /vol/scratch/gtdb/marine_hmp_db_03112017_clu /vol/attached/gtdb/mg_gtdb_update_20190430/mg_gtdb_db_052019 /vol/attached/gtdb/mg_gtdb_update_20190430/mg_gtdb_db_052019_clu /vol/attached/gtdb/mg_gtdb_update_20190430/tmp --min-seq-id 0.3 -s 5 --cov-mode 0 -c 0.8 --split 10

genomewalker / clusterupdate_39ee37f97ab065a3763ee10b834b3e6e25aae491.log

Created April 29, 2019 20:19

	+ set -e
	+ MMSEQS=/vol/attached/opt/MPI/MMseqs2/bin/mmseqs
	+ DIR=/vol/attached/gtdb
	+ SDIR=/vol/scratch/gtdb
	+ export 'OMPI_MCA_btl=^openib'
	+ OMPI_MCA_btl='^openib'
	+ export OMP_NUM_THREADS=28
	+ OMP_NUM_THREADS=28
	+ RUNNER='mpirun --mca btl_tcp_if_include ens3 -n 10 --map-by ppr:1:node --bind-to none '
	+ /vol/attached/opt/MPI/MMseqs2/bin/mmseqs clusterupdate /vol/scratch/gtdb/marine_hmp_db_03112017 /vol/scratch/gtdb/mg_gtdb_orfs_db /vol/scratch/gtdb/marine_hmp_db_03112017_clu /vol/attached/gtdb/mg_gtdb_update/mg_gtdb_db_052019 /vol/attached/gtdb/mg_gtdb_update/mg_gtdb_db_0520

genomewalker / clusterupdate_7-4e23d.log

Created April 29, 2019 20:16

	+ set -e
	+ MMSEQS=/vol/attached/opt/MMseqs2-7-4e23d/bin/mmseqs
	+ DIR=/vol/attached/gtdb
	+ SDIR=/vol/scratch/gtdb
	+ export 'OMPI_MCA_btl=^openib'
	+ OMPI_MCA_btl='^openib'
	+ export OMP_NUM_THREADS=28
	+ OMP_NUM_THREADS=28
	+ RUNNER='mpirun --mca btl_tcp_if_include ens3 -n 10 --map-by ppr:1:node --bind-to none '
	+ /vol/attached/opt/MMseqs2-7-4e23d/bin/mmseqs clusterupdate /vol/scratch/gtdb/marine_hmp_db_03112017 /vol/scratch/gtdb/mg_gtdb_orfs_db /vol/scratch/gtdb/marine_hmp_db_03112017_clu /vol/attached/gtdb/mg_gtdb_update/mg_gtdb_db_052019 /vol/attached/gtdb/mg_gtdb_update/mg_gtdb_db_

genomewalker / annotate_query_sequences.R

Last active March 29, 2019 06:51

	#!/usr/bin/env Rscript

	# Check if basic packages are installed -----------------------------------

	is.installed <- function(pkg){
	is.element(pkg, installed.packages()[,1])
	}

	if (!is.installed("crayon") \|\| !is.installed("optparse")){
	cat("We will try to install the packages crayon and optparse... (this will be only be done once)\n")

genomewalker / mmseqs_20190131.log

Created January 31, 2019 16:21

	ubuntu@bibigrid-master-64y44t0ith2ejcj:/vol/attached/data/opt/test/MMseqs2/build$ cmake -DHAVE_MPI=1 -DCMAKE_BUILD_TYPE=Release -DCMAKE_INSTALL_PREFIX=. ..
	-- The CXX compiler identification is GNU 5.4.0
	-- The C compiler identification is GNU 5.4.0
	-- Check for working CXX compiler: /usr/bin/c++
	-- Check for working CXX compiler: /usr/bin/c++ -- works
	-- Detecting CXX compiler ABI info
	-- Detecting CXX compiler ABI info - done
	-- Detecting CXX compile features
	-- Detecting CXX compile features - done
	-- Check for working C compiler: /usr/bin/cc

genomewalker / create_alluvial.R

Last active December 10, 2018 09:18

	#!/usr/bin/env Rscript

	args = commandArgs(trailingOnly=TRUE)

	# test if there is at least one argument: if not, return an error
	if (length(args) == 0) {
	stop("At least one argument must be supplied (input file).n", call = FALSE)
	} else if (length(args) == 1) {
	# default output file
	args[2] = "alluvial.tsv"

Antonio Fernandez-Guerra genomewalker