Quickstart

Train and run MethylSeg on a WGBS or TCGA HM450K sample.

from pathlib import Path

from methylseg import MethylSegPathway, MethylationStates
from methylseg.helper_classes import DATA_DIR

reference_dir = DATA_DIR / "reference_files"

# WGBS: replace these with your own sample name and count table.
# sample_name = "WGBS_colon-primary-tumor_1"
# sample_file = reference_dir / "WGBS_colon-primary-tumor_1_wgbs.tsv.gz"
# resolution = "wgbs"

# TCGA/HM450K alternative:
sample_name = "TCGA-BD-A3EP-01A"
sample_file = reference_dir / "TCGA-BD-A3EP-01A_450k.tsv.gz"
resolution = "450k"

sample_info, removed_df = MethylSegPathway.prepare_sample_info(
    sample_name=sample_name,
    sample_file=sample_file,
    resolution=resolution,
    remove_low_coverage_like_cpgs=True,
)

pathway = MethylSegPathway(
    train_sample_info=sample_info,
    out_dir=Path("out/quickstart") / sample_name,
)

pathway.run_pathway()

fig = pathway.plot_labels(
    sample_info=sample_info,
    sample_info_removed=removed_df,
    chrom="chr1",
    region_start=2_200_000,
    region_end=3_700_000
)

Fitting pathway...
Generating regions ...