fedarko

import numpy as np
import patsy
import pandas as pd
from biom import Table

# This is the main function
def poisson_cat(table, metadata, category, ref=None):
    """ Poisson differential abundance.

    Parameters

fedarko

#! /usr/bin/env python3
import biom
from qiime2 import Artifact, Metadata

YOUR_QZA_TABLE_FILEPATH_GOES_HERE = "table.qza"
YOUR_METADATA_FILEPATH_GOES_HERE = "metadata.tsv"

# Load the table
tbl_qza = Artifact.load(YOUR_QZA_TABLE_FILEPATH_GOES_HERE)
t = tbl_qza.view(biom.Table)

fedarko

#! /usr/bin/env python3
# note that this is very preliminary + untested code

# We use pd.read_csv() because, unlike QIIME 2's Metadata object, it allows
# duplicate sample IDs.
import pandas as pd
import sys
if len(sys.argv) < 2:
    raise ValueError("You need to specify a metadata file to check.")
df = pd.read_csv(sys.argv[1], sep='\t', index_col=0)

fedarko

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

m = pd.read_csv("metadata.tsv", sep='\t', index_col=0)
# Find all sample IDs in the metadata that include a "date"
# We assume that sample IDs that start with a 5-digit Qiita ID, then a period,
# then a two-character host ID string, then another period, will follow this
# convention.

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"

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

# 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

#! /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

#! /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
"""
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