gwas_catalog_sumstat_preprocess

gentropy.gwas_catalog_sumstat_preprocess.GWASCatalogSumstatsPreprocessStep

Step to preprocess GWAS Catalog harmonised summary stats.

Source code in src/gentropy/gwas_catalog_sumstat_preprocess.py

class GWASCatalogSumstatsPreprocessStep:
    """Step to preprocess GWAS Catalog harmonised summary stats."""

    def __init__(
        self, session: Session, raw_sumstats_path: str, out_sumstats_path: str
    ) -> None:
        """Run step to preprocess GWAS Catalog harmonised summary stats and produce SummaryStatistics dataset.

        Args:
            session (Session): Session object.
            raw_sumstats_path (str): Input GWAS Catalog harmonised summary stats path.
            out_sumstats_path (str): Output SummaryStatistics dataset path.
        """
        # Processing dataset:
        GWASCatalogSummaryStatistics.from_gwas_harmonized_summary_stats(
            session.spark, raw_sumstats_path
        ).df.write.mode(session.write_mode).parquet(out_sumstats_path)
        session.logger.info("Processing dataset successfully completed.")

__init__(session: Session, raw_sumstats_path: str, out_sumstats_path: str) -> None

Run step to preprocess GWAS Catalog harmonised summary stats and produce SummaryStatistics dataset.

Parameters:

Name	Type	Description	Default
session	Session	Session object.	required
raw_sumstats_path	str	Input GWAS Catalog harmonised summary stats path.	required
out_sumstats_path	str	Output SummaryStatistics dataset path.	required

Source code in src/gentropy/gwas_catalog_sumstat_preprocess.py

def __init__(
    self, session: Session, raw_sumstats_path: str, out_sumstats_path: str
) -> None:
    """Run step to preprocess GWAS Catalog harmonised summary stats and produce SummaryStatistics dataset.

    Args:
        session (Session): Session object.
        raw_sumstats_path (str): Input GWAS Catalog harmonised summary stats path.
        out_sumstats_path (str): Output SummaryStatistics dataset path.
    """
    # Processing dataset:
    GWASCatalogSummaryStatistics.from_gwas_harmonized_summary_stats(
        session.spark, raw_sumstats_path
    ).df.write.mode(session.write_mode).parquet(out_sumstats_path)
    session.logger.info("Processing dataset successfully completed.")

---

• 2023-03-30
• 2024-01-18
• Contributors