chasemc

parse_domtblout_file <- function(dom){
  dom = readLines(dom)
  dom <- dom[!grepl("^#", dom)]
  dom <- lapply(strsplit(dom, "[ ]{1,}"), 
                function(x){
                  parsed <- c(x[1:22], paste0(x[23:length(x)], collapse = " "))
                  as.data.frame(t(parsed))
                })
  dom <- do.call(rbind, dom)
  colnames(dom) <- c("target_name",

chasemc

library(data.table)
library(ggplot2)
library(gganimate)

population <- fread("/Users/chase/Downloads/csvData.csv") # https://worldpopulationreview.com/states
population <- population[, c("State", "Pop")]
colnames(population) <- c("state", "population")

covid <- "https://raw.githubusercontent.com/nytimes/covid-19-data/master/rolling-averages/us-states.csv"
covid <- fread(covid)

chasemc

library(ggplot2)

execution_trace <- '/home/chase/Documents/pipeline_info/execution_trace_2021-08-14_09-52-45.txt' 

execution_trace <- read.delim(execution_trace, sep = "\t")
process_names <- sapply(strsplit(execution_trace$name, " "), function(x) x[[1]])


split_names <- strsplit(process_names, ":")
max_len <- max(lengths(split_names))

chasemc

assembly_summary_refseq <- readr::read_delim("https://ftp.ncbi.nih.gov/genomes/ASSEMBLY_REPORTS/assembly_summary_refseq.txt", quote='', skip = 2, delim = "\t", col_names = c("assembly_accession", "bioproject", "biosample", "wgs_master", "refseq_category", "taxid", "species_taxid", "organism_name", "infraspecific_name", "isolate", "version_status", "assembly_level", "release_type", "genome_rep", "seq_rel_date", "asm_name", "submitter", "gbrs_paired_asm", "paired_asm_comp", "ftp_path", "excluded_from_refseq", "relation_to_type_material"))

chasemc

#!/usr/bin/bash

# $1 is the file(s') name to find and hash
# $2 is the extension to be given to each renamed file

find $1 -print0 | xargs -0 md5sum | 
  while read -r newname oldname; do
      mv -v "$oldname" "$newname".$2
  done
 

chasemc

#!/usr/bin/env Rscript
args = commandArgs(trailingOnly=TRUE)

message("Installing necessary libraries if not already installed")
if (!requireNamespace("BiocManager", quietly = TRUE))
  install.packages("BiocManager")
if (!requireNamespace("mzR", quietly = TRUE))
  install.packages("mzR")
if (!requireNamespace("data.table", quietly = TRUE))
  install.packages("data.table")

chasemc

#!/usr/bin/bash
curl -s $1 |\
sed -ne '/# Sequence-Name\tSequence-Role\tAssigned-Molecule\tAssigned-Molecule-Location\/Type\tGenBank-Accn\tRelationship\tRefSeq-Accn\tAssembly-Unit\tSequence-Length\tUCSC-style-name/,$ p' |\
awk -F"\t" 'NR==1 {for (i=1; i<=NF; i++) {f[$i] = i}}{ print $(f["RefSeq-Accn"]), $(f["Sequence-Length"])}' |\
sed 1d

chasemc

https://github.com/Micromeda/InterProScan-Docker/blob/master/LICENSE

                                 Apache License
                           Version 2.0, January 2004
                        http://www.apache.org/licenses/

   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION

   1. Definitions.

chasemc

find -name "*region*gbk" | xargs grep "CDS    " -A3 | grep "/ID=" | cut -d'"' -f2

chasemc

npm install neo4j-driver

node test-neo-driver.js