Splits up a QIIME 2 metadata file into separate metadata files, such that there is one file per specified "run" column. This is useful if multiple samples from different runs share barcode sequences, which can make QIIME 2 angry.

split_metadata_by_run.py

# 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))

for run_id in runs:
    md_subset = md[md["seq_run_ord"] == run_id]
    md_subset_name = "metadata-{}.tsv".format(run_id)
    md_subset.to_csv(md_subset_name, sep="\t")
    print("Generated a subset of the metadata called {}".format(md_subset_name))