chasemc

pfam_df <- readLines("pfamscan_out.txt")

pfam_df <- lapply(pfam_df, function(x){
  x <- scan(text = x, what = "text", comment.char = "#", quiet = T)
  if (!identical(x,character(0))){
    return(x)
  }
})
pfam_df <- do.call(rbind.data.frame, pfam_df)

chasemc

library(remotes)
remotes::install_github("chasemc/IDBacApp@prioritizer")
library(IDBacApp)
library(here)

# connect_to_idbac_database
pool <- IDBacApp::idbac_connect('VNBacterialLibrary_db-2_0_0', # name of sqlite database
                                here::here('data')) # directory containing sqlite database

# get_protein_peaks

chasemc

Contributor Covenant Code of Conduct

Our Pledge

We as members, contributors, and leaders pledge to make participation in our community a harassment-free experience for everyone, regardless of age, body size, visible or invisible disability, ethnicity, sex characteristics, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, caste, color, religion, or sexual

chasemc

Create directory ./tmp
easy-cluster fail.fasta mmseqs2_fail ./tmp --threads 24 

MMseqs Version:                     	13.45111
Substitution matrix                 	nucl:nucleotide.out,aa:blosum62.out
Seed substitution matrix            	nucl:nucleotide.out,aa:VTML80.out
Sensitivity                         	4
k-mer length                        	0
k-score                             	2147483647
Alphabet size                       	nucl:5,aa:21

chasemc

Create directory ./tmp
easy-cluster pass.fasta mmseqs2_pass ./tmp --threads 24 

MMseqs Version:                     	13.45111
Substitution matrix                 	nucl:nucleotide.out,aa:blosum62.out
Seed substitution matrix            	nucl:nucleotide.out,aa:VTML80.out
Sensitivity                         	4
k-mer length                        	0
k-score                             	2147483647
Alphabet size                       	nucl:5,aa:21

chasemc

• Download and install RStudio

  • https://www.rstudio.com/products/rstudio/download/#download

• Download and install R (follow the link for your type of comput, under "Download and Install R")

  • https://cran.r-project.org/

We're probably not going to do much actual work within IDBac, but installing IDBac will also install some other dependencies we will use.

Open RStudio and run the following commands:

chasemc

FROM mambaorg/micromamba:0.23.3

COPY --chown=$MAMBA_USER:$MAMBA_USER antismash.yml /tmp/env.yaml
RUN micromamba create -n antismash
RUN micromamba install --yes --file /tmp/env.yaml && \
    micromamba clean --all --yes
ARG MAMBA_DOCKERFILE_ACTIVATE=1 
ENV ENV_NAME=antismash

chasemc

import zstandard as zstd

def decompress_zstd(bytes_input):
    dctx = zstd.ZstdDecompressor()
    decompressed_domtblout = dctx.decompress(bytes_input)
    return decompressed_domtblout.decode("utf-8").splitlines()

cctx = zstandard.ZstdCompressor()
compressed = cctx.compress(b"data to compress")

chasemc

/*
========================================================================================
    Nextflow minimal test
========================================================================================
    Defines input files and everything required to run a fast and simple pipeline test.

    Use as follows:

        outdir='/home/chase/Documents/socialgene_data/buchnera'

chasemc

# template.sub
# starter submit file for CHTC jobs

universe = vanilla
log = logs/job_$(Cluster).log
error = errors/job_$(Cluster)_$(Process).err
output = outputs/job_$(Cluster)_$(Process).out

executable = hmmsearch.sh
arguments = $(hmm_model_basename) $(fasta_file_basename)