dnanto

import sys

# https://www.ncbi.nlm.nih.gov/books/NBK279682/#_cookbook_Traceback_operations_BTOP_
# BTOP operations consist of 
# 1.) a number with a count of matching letters, 
# 2.) two letters showing a mismatch (e.g., “AG” means A was replaced by G), or 
# 3.) a dash (“-“) and a letter showing a gap. 

def decode_btop(btop):
	pos, digis, chars = 0, [], []

dnanto

#!/usr/bin/env bash
# based on: https://stackoverflow.com/a/2538846
for _ in $(seq 1 100); do echo $(( $RANDOM % 100 )); done | \
  gnuplot -p -e "set terminal dumb; W=2; bin(x, w)=w*floor(x/w); plot '< cat -' using (bin(\$1, W)):(1.0) smooth freq with boxes"

dnanto

from collections import OrderedDict


def parse_outfmt7(file):
	fields = []
	for line in map(str.strip, file):
		if line.startswith("# Fields: "):
			fields = line[10:].split(", ")
		elif line and not line.startswith("#"):
			yield OrderedDict(zip(fields, line.split("\t")))

dnanto

read_dist <- function(path)
{	
	lines <- read_lines(path)
	n <- as.integer(lines[1])
	str_split_fixed(tail(lines, -1), "\t", n) %>% 
		as.data.frame() %>% 
		column_to_rownames("V1") %>% 
		add_column(" ") %>% 
		set_names(rownames(.))
}

dnanto

parse_outfmt7 <- function(lines)
{
  comments <- lines[grep("#", lines)]
  ver <- comments[grep("^# BLASTN", comments)] %>% str_split_fixed(" ", 2) %>% .[ , 2]
  db <- comments[grep("^# Database: ", comments)] %>% str_split_fixed(" ", 3) %>% .[ , 3]
  fields <- comments[grep("^# Fields: ", comments)] %>% str_split_fixed(" ", 3) %>% .[ , 3] %>% str_split(", ", simplify = T)
  read_tsv(lines, comment = "#", col_names = fields) %>% mutate(ver = ver, db = db)
}

read_outfmt7 <- function(path)

dnanto

#!/usr/bin/env bash

# install edirect utils from here: ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect/

taxid="$1"
db="${2:-nuccore}"

printf "extra\ttaxid\tslen\ttitle\n"
esearch \
	-db "$db" \