Skip to content

mecfs_bio.constants.protein_coloc_constants

Column names and status values of the trait x protein colocalization outputs.

The dense per-locus window frames use gwaslab column names (CHR, POS, EA, NEA, BETA, SE, EAF, N); the constants below name everything else.

Functions:

  • pair_file_stem –

    File stem for one (locus, protein) pair, free of characters Windows filesystems reject.

Attributes:

BETA_PROTEIN_COL module-attribute

BETA_PROTEIN_COL: Final = 'BETA_PROTEIN'

BETA_TRAIT_COL module-attribute

BETA_TRAIT_COL: Final = 'BETA_TRAIT'

CIS_STATUS_CIS module-attribute

CIS_STATUS_CIS: Final[CisStatus] = 'cis'

CIS_STATUS_COL module-attribute

CIS_STATUS_COL: Final = 'CIS_STATUS'

CIS_STATUS_TRANS module-attribute

CIS_STATUS_TRANS: Final[CisStatus] = 'trans'

CIS_STATUS_UNKNOWN module-attribute

CIS_STATUS_UNKNOWN: Final[CisStatus] = 'unknown'

CisStatus module-attribute

CisStatus = Literal['cis', 'trans', 'unknown']

ColocStatus module-attribute

ColocStatus = Literal[
    "candidate",
    "excluded_mhc",
    "no_candidates",
    "selected",
    "not_selected_budget",
    "tested",
    "failed",
]

DISPLAY_ASSAY_ID_COL module-attribute

DISPLAY_ASSAY_ID_COL: Final = 'assay_id'

DISPLAY_CIS_STATUS_COL module-attribute

DISPLAY_CIS_STATUS_COL: Final = 'cis'

DISPLAY_FDR_SIGNIFICANT_COL module-attribute

DISPLAY_FDR_SIGNIFICANT_COL: Final = 'fdr_sig'

DISPLAY_LEAD_VARIANT_COL module-attribute

DISPLAY_LEAD_VARIANT_COL: Final = 'lead'

DISPLAY_LOCUS_COL module-attribute

DISPLAY_LOCUS_COL: Final = 'locus'

DISPLAY_N_SNP_COL module-attribute

DISPLAY_N_SNP_COL: Final = 'n_snp'

DISPLAY_PP_H4_COL module-attribute

DISPLAY_PP_H4_COL: Final = 'pp_h4'

DISPLAY_PROTEIN_COL module-attribute

DISPLAY_PROTEIN_COL: Final = 'protein'

DISPLAY_PROTEIN_P_COL module-attribute

DISPLAY_PROTEIN_P_COL: Final = 'prot_p'

DISPLAY_Q_VALUE_COL module-attribute

DISPLAY_Q_VALUE_COL: Final = 'q'

DISPLAY_SAME_SIGN_COL module-attribute

DISPLAY_SAME_SIGN_COL: Final = 'same_sign'

DISPLAY_TRAIT_P_COL module-attribute

DISPLAY_TRAIT_P_COL: Final = 'trait_p'

EAF_PROTEIN_COL module-attribute

EAF_PROTEIN_COL: Final = 'EAF_PROTEIN'

EAF_TRAIT_COL module-attribute

EAF_TRAIT_COL: Final = 'EAF_TRAIT'

FAILURE_REASON_COL module-attribute

FAILURE_REASON_COL: Final = 'FAILURE_REASON'

GENE_COL module-attribute

GENE_COL: Final = 'GENE'

GENE_LEAD_DISTANCE_COL module-attribute

GENE_LEAD_DISTANCE_COL: Final = 'GENE_LEAD_DISTANCE_BP'

HIT_CHR_COL module-attribute

HIT_CHR_COL: Final = 'CHR'

HIT_GENE_COL module-attribute

HIT_GENE_COL: Final = GENE_COL

HIT_LEAD_MLOG10P_COL module-attribute

HIT_LEAD_MLOG10P_COL: Final = 'LEAD_MLOG10P'

HIT_LEAD_POS_COL module-attribute

HIT_LEAD_POS_COL: Final = 'LEAD_POS'

HIT_N_SIG_VARIANTS_COL module-attribute

HIT_N_SIG_VARIANTS_COL: Final = 'N_SIG_VARIANTS'

HIT_PROTEIN_ID_COL module-attribute

HIT_PROTEIN_ID_COL: Final = PROTEIN_ID_COL

HIT_SEG_END_COL module-attribute

HIT_SEG_END_COL: Final = 'SEG_END'

HIT_SEG_START_COL module-attribute

HIT_SEG_START_COL: Final = 'SEG_START'

INFO_ENSEMBL_ID_COL module-attribute

INFO_ENSEMBL_ID_COL: Final = 'ensembl_id'

INFO_EVIDENCE_COL module-attribute

INFO_EVIDENCE_COL: Final = 'evidence'

INFO_GENE_NAME_COL module-attribute

INFO_GENE_NAME_COL: Final = 'gene_name'

INFO_GENE_SYMBOL_COL module-attribute

INFO_GENE_SYMBOL_COL: Final = 'gene_symbol'

INFO_PROTEIN_NAMES_COL module-attribute

INFO_PROTEIN_NAMES_COL: Final = 'protein_names'

INFO_SUBCELLULAR_LOCALISATION_COL module-attribute

INFO_SUBCELLULAR_LOCALISATION_COL: Final = 'locale'

INFO_UNIPROT_DESCRIPTION_COL module-attribute

INFO_UNIPROT_DESCRIPTION_COL: Final = 'uniprot_description'

INFO_UNIPROT_ID_COL module-attribute

INFO_UNIPROT_ID_COL: Final = 'uniprot_id'

LOCUS_CHR_COL module-attribute

LOCUS_CHR_COL: Final = 'CHR'

LOCUS_END_COL module-attribute

LOCUS_END_COL: Final = 'END'

LOCUS_ID_COL module-attribute

LOCUS_ID_COL: Final = 'LOCUS_ID'

LOCUS_LEAD_EA_COL module-attribute

LOCUS_LEAD_EA_COL: Final = 'LEAD_EA'

LOCUS_LEAD_MLOG10P_COL module-attribute

LOCUS_LEAD_MLOG10P_COL: Final = 'LEAD_MLOG10P'

LOCUS_LEAD_NEA_COL module-attribute

LOCUS_LEAD_NEA_COL: Final = 'LEAD_NEA'

LOCUS_LEAD_POS_COL module-attribute

LOCUS_LEAD_POS_COL: Final = 'LEAD_POS'

LOCUS_START_COL module-attribute

LOCUS_START_COL: Final = 'START'

METHOD_COL module-attribute

METHOD_COL: Final = 'METHOD'

N_ALIGNED_COL module-attribute

N_ALIGNED_COL: Final = 'N_ALIGNED'

N_DROPPED_PREFIX module-attribute

N_DROPPED_PREFIX: Final = 'N_DROPPED_'

N_DUPLICATE_KEYS_DROPPED_COL module-attribute

N_DUPLICATE_KEYS_DROPPED_COL: Final = (
    "N_DUPLICATE_KEYS_DROPPED"
)

N_OTHER_PROTEINS_COL module-attribute

N_OTHER_PROTEINS_COL: Final = 'N_OTHER_PROTEINS'

N_PROTEINS_COL module-attribute

N_PROTEINS_COL: Final = 'N_PROTEINS'

N_PROTEIN_COL module-attribute

N_PROTEIN_COL: Final = 'N_PROTEIN'

N_PROTEIN_VARIANTS_COL module-attribute

N_PROTEIN_VARIANTS_COL: Final = 'N_PROTEIN_VARIANTS'

N_TRAIT_COL module-attribute

N_TRAIT_COL: Final = 'N_TRAIT'

N_TRAIT_VARIANTS_COL module-attribute

N_TRAIT_VARIANTS_COL: Final = 'N_TRAIT_VARIANTS'

PLOT_PNG_FILENAME_COL module-attribute

PLOT_PNG_FILENAME_COL: Final = 'PNG_FILENAME'

PLOT_SVG_FILENAME_COL module-attribute

PLOT_SVG_FILENAME_COL: Final = 'SVG_FILENAME'

PP_H0_COL module-attribute

PP_H0_COL: Final = 'PP_H0'

PP_H1_COL module-attribute

PP_H1_COL: Final = 'PP_H1'

PP_H2_COL module-attribute

PP_H2_COL: Final = 'PP_H2'

PP_H3_COL module-attribute

PP_H3_COL: Final = 'PP_H3'

PP_H4_COL module-attribute

PP_H4_COL: Final = 'PP_H4'

PRIOR_P12_COL module-attribute

PRIOR_P12_COL: Final = 'P12'

PRIOR_P1_COL module-attribute

PRIOR_P1_COL: Final = 'P1'

PRIOR_P2_COL module-attribute

PRIOR_P2_COL: Final = 'P2'

PROTEIN_ID_COL module-attribute

PROTEIN_ID_COL: Final = 'PROTEIN_ID'

PROTEIN_LEAD_MLOG10P_COL module-attribute

PROTEIN_LEAD_MLOG10P_COL: Final = 'PROTEIN_LEAD_MLOG10P'

PROTEIN_LEAD_POS_COL module-attribute

PROTEIN_LEAD_POS_COL: Final = 'PROTEIN_LEAD_POS'

PROTEIN_MLOG10P_COL module-attribute

PROTEIN_MLOG10P_COL: Final = 'PROTEIN_MLOG10P'

ProteinId module-attribute

ProteinId = NewType('ProteinId', str)

RAW_RESULTS_FILENAME module-attribute

RAW_RESULTS_FILENAME: Final = 'raw_results.parquet'

SCORE_COL module-attribute

SCORE_COL: Final = 'SCORE'

SCORE_PENALTY_COL module-attribute

SCORE_PENALTY_COL: Final = 'SCORE_PENALTY'

SCORE_PROTEIN_COL module-attribute

SCORE_PROTEIN_COL: Final = 'SCORE_PROTEIN'

SCORE_TRAIT_COL module-attribute

SCORE_TRAIT_COL: Final = 'SCORE_TRAIT'

SE_PROTEIN_COL module-attribute

SE_PROTEIN_COL: Final = 'SE_PROTEIN'

SE_TRAIT_COL module-attribute

SE_TRAIT_COL: Final = 'SE_TRAIT'

STATUS_CANDIDATE module-attribute

STATUS_CANDIDATE: Final[ColocStatus] = 'candidate'

STATUS_COL module-attribute

STATUS_COL: Final = 'STATUS'

STATUS_EXCLUDED_MHC module-attribute

STATUS_EXCLUDED_MHC: Final[ColocStatus] = 'excluded_mhc'

STATUS_FAILED module-attribute

STATUS_FAILED: Final[ColocStatus] = 'failed'

STATUS_NOT_SELECTED_BUDGET module-attribute

STATUS_NOT_SELECTED_BUDGET: Final[ColocStatus] = (
    "not_selected_budget"
)

STATUS_NO_CANDIDATES module-attribute

STATUS_NO_CANDIDATES: Final[ColocStatus] = 'no_candidates'

STATUS_SELECTED module-attribute

STATUS_SELECTED: Final[ColocStatus] = 'selected'

STATUS_TESTED module-attribute

STATUS_TESTED: Final[ColocStatus] = 'tested'

WINDOWS_DIRNAME module-attribute

WINDOWS_DIRNAME: Final = 'windows'

WINDOW_SCHEMA module-attribute

WINDOW_SCHEMA: Final = pl.Schema(
    {
        GWASLAB_CHROM_COL: pl.Int64,
        GWASLAB_POS_COL: pl.Int64,
        GWASLAB_EFFECT_ALLELE_COL: pl.String,
        GWASLAB_NON_EFFECT_ALLELE_COL: pl.String,
        GWASLAB_BETA_COL: pl.Float64,
        GWASLAB_SE_COL: pl.Float64,
        GWASLAB_EFFECT_ALLELE_FREQ_COL: pl.Float64,
        GWASLAB_SAMPLE_SIZE_COLUMN: pl.Float64,
    }
)

pair_file_stem

pair_file_stem(locus_id: str, protein_id: str) -> str

File stem for one (locus, protein) pair, free of characters Windows filesystems reject.

Source code in mecfs_bio/constants/protein_coloc_constants.py
def pair_file_stem(locus_id: str, protein_id: str) -> str:
    """File stem for one (locus, protein) pair, free of characters Windows filesystems reject."""
    return f"{locus_id}__{protein_id}".replace(":", "_")