fedarko

#! /usr/bin/env python3
#
# Computes the total number of reads, total read length, and average read
# length of a set of (maybe gzipped) FASTA / FASTQ files. Requires the pyfastx
# library (https://github.com/lmdu/pyfastx). I designed this in the context of
# computing read statistics, but if you have a set of other sequences (e.g.
# contigs) then I guess this would still work for that.
#
# USAGE:
# ./read_stats.py file1.fa [file2.fa ...]

fedarko

#! /usr/bin/env python
#
# Shortens edge labels in a DOT file output by LJA to just show the first line
# and then a count of how many other lines are omitted. (If an edge's label
# spans exactly one or two lines, then the entire label is preserved.)
#
# USAGE:
# ./shorten_edge_labels.py in.dot out.dot

import sys

fedarko

#! /usr/bin/env python
#
# Scans through a jumboDBG / LJA output DOT file; looks for cases where
# the same node is "defined" on multiple lines. This can be caused by the
# same truncated node ID being misused across lines.
#
# USAGE:
# ./check_for_conflicting_node_ids.py graph.dot
#
# Note that this assumes that the input graph was output by jumboDBG / LJA --

fedarko

#! /usr/bin/env python3
#
# SUMMARY
# =======
# Outputs a copy of a GFA 1 file with each segment (S) line that contains a
# sequence (not just a "*" character) altered as follows:
#
#   - If an LN:i tag does not exist for this sequence:
#       - We will add an LN:i tag describing the length of the sequence.
#       - We will replace the sequence with a "*" character.

fedarko

#! /usr/bin/env python3
# NOTE: this is a hack, so it will probably break if you have BBL files that
# don't look like the natbib-generated ones I'm used to. It is also pretty
# unintelligent about *how* it sorts entries (it defers most of the work
# to python), so if you have cases where some of your references are by
# the same person or whatever then that might cause the output to not match
# your expectations.

import sys

fedarko

#! /usr/bin/env python3
# Converts a GFA assembly graph to a FASTA file of all sequences
# within the graph. Notably, this ignores connections between sequences
# in the graph.
#
# Depends on Python 3.6 or later.
#
# Usage:
# $ ./gfa_to_fasta.py mygraph.gfa contigs.fasta

fedarko

#! /usr/bin/env python3
import os
from collections import Counter
from math import ceil
import re
from numpy import argmax
import pandas as pd
from qiime2 import Metadata

# "Parameters" of this script

fedarko

#! /usr/bin/env python3
from dateutil.parser import parse
import pandas as pd


df = pd.read_csv("20191209_metadata.txt", sep="\t", index_col=0)

# Subset to a certain host subject ID, if desired
df = df[df["host_subject_id"] == "M03"]

fedarko

#! /usr/bin/env python3
"""
This is a small script that looks through the annotated taxonomies of all
features present in a dataset's negative control samples. It's handy for
checking that certain features are (for the most part) absent from these
samples.

This obviously isn't a very formal way of accounting for contamination,
but it is useful for quickly verifying that certain taxa are probably not
the product of contamination. (Better approaches include e.g. the decontam

fedarko

#! /usr/bin/env python3
from qiime2 import Metadata
from dateutil.parser import parse
from dateutil.relativedelta import relativedelta

m = Metadata.load("metadata-with-age.tsv")
m_df = m.to_dataframe()

m_df["ordinal-timestamp"] = 0