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

fedarko

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

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

# Compute earliest date
min_date = None
for sample_id in m_df.index:

fedarko

# your link goes here
link = "https://github.com/knightlab-analyses/qurro-mackerel-analysis/blob/master/AnalysisOutput/qurro-plot.qzv"

# note: this will break if a repo/organization or subfolder is named "blob" -- would be ideal to use a fancy regex
# to be more precise here
print(link.replace("github.com", "raw.githubusercontent.com").replace("/blob/", "/"))

# example output link:
# https://raw.githubusercontent.com/knightlab-analyses/qurro-mackerel-analysis/master/AnalysisOutput/qurro-plot.qzv

fedarko

# NOTE: Assumes that there's a SAMPLE_METADATA environment variable declared pointing to a metadata file
# NOTE: Assumes that this metadata file contains BarcodeSequence and seq_run_ord columns
import pandas as pd
import os


md = pd.read_csv(os.environ["SAMPLE_METADATA"], sep="\t", index_col=0)
print("There are {} unique barcode sequences in this metadata file.".format(len(md["BarcodeSequence"].unique())))
runs = tuple(md["seq_run_ord"].unique())
print("Also, the {} runs listed in this metadata file are {}.".format(len(runs), runs))

fedarko

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

subject_id = "HOST SUBJECT ID"
subject_birthday = "HOST BIRTHDAY"
subject_birthday_datetime = parse(subject_birthday)
age_col_name = "subject_age_years"