philippmuench’s gists

philippmuench / hmp1.txt

Last active December 16, 2019 16:09

The Human Microbiome Project Consortium

Curtis Huttenhower, Dirk Gevers, Rob Knight, Sahar Abubucker, Jonathan H. Badger, Asif T. Chinwalla, Heather H. Creasy, Ashlee M. Earl, Michael G. FitzGerald, Robert S. Fulton, Michelle G. Giglio, Kymberlie Hallsworth-Pepin, Elizabeth A. Lobos, Ramana Madupu, Vincent Magrini, John C. Martin, Makedonka Mitreva, Donna M. Muzny, Erica J. Sodergren, James Versalovic, Aye M. Wollam, Kim C. Worley, Jennifer R. Wortman, Sarah K. Young, Qiandong Zeng, Kjersti M. Aagaard, Olukemi O. Abolude, Emma Allen-Vercoe, Eric J. Alm, Lucia Alvarado, Gary L. Andersen, Scott Anderson, Elizabeth Appelbaum, Harindra M. Arachchi, Gary Armitage, Cesar A. Arze, Tulin Ayvaz, Carl C. Baker, Lisa Begg, Tsegahiwot Belachew, Veena Bhonagiri, Monika Bihan, Martin J. Blaser, Toby Bloom, Vivien Bonazzi, J. Paul Brooks, Gregory A. Buck, Christian J. Buhay, Dana A. Busam, Joseph L. Campbell, Shane R. Canon, Brandi L. Cantarel, Patrick S. G. Chain, I-Min A. Chen, Lei Chen, Shaila Chhibba, Ken Chu, Dawn M. C

philippmuench / commands.R

Created November 4, 2019 10:43

	remove.packages("deepG")
	devtools::install_github("hiddengenome/deepG@prepro")
	tensorflow::install_tensorflow(version="1.12.0-gpu", method = "conda", conda_python_version = "2.7")
	library(deepG)
	hist <- trainNetwork(path = "/scratch/pmuench/crispr_refseq/with_crispr", use.cudnn = F, use.codon.cnn = F, maxlen = 80, batch.size = 500, run.name= "CrisprNet_v1_no_cnn", epochs = 50, steps.per.epoch = 1000, layers.lstm = 3, max.queue.size = 100, dropout.rate = 0.15, layer.size = 5, vocabulary.size = 5)
	# ValueError: No data provided for "lstm_input". Need data for each key in: ['lstm_input']

philippmuench / step0-on-bifo-server.sh

Last active August 13, 2019 13:35

	# requirement: anaconda
	conda install virtualenv
	python3 -m venv ~/deepG_env
	source ~/deepG_env/bin/activate
	# deepG is tested with tensorflow 1.14
	pip3 install https://storage.googleapis.com/tensorflow/linux/gpu/tensorflow_gpu-1.14.0-cp37-cp37m-linux_x86_64.whl
	pip3 install keras

	# setup cuda, required is cuda10 and cudnn 7.4
	conda install -c anaconda cudatoolkit

philippmuench / install.sh

Last active August 12, 2019 18:21

installation of CRISPRCasFinder

	wget https://crisprcas.i2bc.paris-saclay.fr/Home/DownloadFile?filename=CRISPRCasFinder.zip
	unzip DownloadFile?filename=CRISPRCasFinder.zip
	cd CRISPRCasFinder

	# install perl modules
	curl -L http://cpanmin.us \| perl - App::cpanminus
	cpanm --local-lib=~/perl5 local::lib && eval $(perl -I ~/perl5/lib/perl5/ -Mlocal::lib)
	cpanm JSON::Parse

	# install prodigal

philippmuench / Snakefile

Last active March 24, 2022 03:58

pipeline OligoMM-Antibiotics

	'''
	oligomm_antibiotics.snakefile
	Philipp Muench

	Maps NGS data to OligoMM reference genomes and performs variant calling
	-----------------------------------------------------------------------

	Requirements:

	samtools

philippmuench / multiplicative_lstm.R

Created June 18, 2019 09:13 — forked from jjallaire/multiplicative_lstm.R

Custom Multiplicative LSTM Layer for R Keras



	library(keras)
	library(reticulate)

	layer_multiplicative_lstm <-function(
	object, units, activation = "tanh", recurrent_activation = "hard_sigmoid", use_bias = TRUE,
	return_sequences = FALSE, return_state = FALSE, go_backwards = FALSE, stateful = FALSE, unroll = FALSE,
	kernel_initializer = "glorot_uniform", recurrent_initializer = "orthogonal", bias_initializer = "zeros",
	unit_forget_bias = TRUE, kernel_regularizer = NULL, recurrent_regularizer = NULL, bias_regularizer = NULL,

philippmuench / gist:59cbbd304619df1bcbf1835c1b771247

Created May 27, 2019 14:18

code for rebuttal of reviewer comments, additional Bayes analysis

	n1 = 9196 # total number of lysis positive genomes
	y1 = 830 # number of lyssis positive genemes among colicin B positive genomes
	n2 = 303 # total number of lysis negative genomes
	y2 = 20 # lysis negative genomes among colicin B positive genomes

	# SIMULATION
	I = 10000 # simulations
	theta1 = rbeta(I, y1 + 1, (n1 - y1) + 1)
	theta2 = rbeta(I, y2 + 1, (n2 - y2) + 1)
	diff = theta1 - theta2 # simulated diffs

philippmuench / run.R

Last active March 7, 2019 12:25

biomartr Linux test

	install.packages("BiocManager")
	BiocManager::install("Biostrings", version = "3.8")
	BiocManager::install("biomaRt", version = "3.8")
	install.packages("biomartr", dependencies = TRUE)

	library(biomartr)
	getGenome(db = "genbank", organism = "GCA_003138775.1", reference = FALSE)

philippmuench / barplot.R

Created March 6, 2018 11:11

script to generate stacked barplot for community

	# cleanup
	rm(list=ls())

	# load packages
	require(vegan)
	require(pander)
	require(ggplot2)
	require(ape)
	library(RColorBrewer)

philippmuench / get_proteins.sh

Last active March 6, 2018 11:08

shell script to download all proteins from taxids listed in intersection_ids.txt

	#! /bin/sh

	rm -rf log.txt # file where the taxid of skipped taxa will written to
	max_treshold=20000
	mkdir -p out
	while read line; do
	pyla_name=$(echo $line \| awk -F';' '{print $1}' \| tr -s ' ' \| tr ' ' '_')
	txid=$(echo $line \| awk -F';' '{print $2}')
	echo "processing $pyla_name"
	num_found=$(esearch -db protein -query "txid$txid[Organism:exp]"\

Philipp Münch philippmuench