Python cyvcf2.VCF属性代码示例

# 需要导入模块: import cyvcf2 [as 别名]
# 或者: from cyvcf2 import VCF [as 别名]
def get_vep_csq_fields(cls: Type[V], vcf_raw_headers: List[str]) -> List[str]:
        """Extract the CSQ fields VEP output in the given VCF."""
        # Get CSQ spec
        # Reverse the header order because the newer header appears later
        try:
            csq_info_header = next(
                l for l in reversed(vcf_raw_headers) if l.startswith("##INFO=<ID=CSQ,")
            )
        except StopIteration:
            raise ValueError(f"Cannot find CSQ format in the VCF header")
        m = re.search(r"Format: ([\w\|]+)['\"]", csq_info_header)
        if m:
            csq_format = m.group(1)
        else:
            raise ValueError(
                f"Cannot parse the CSQ field format from its INFO VCF header: {csq_info_header}"
            )
        csq_fields = csq_format.split("|")
        return csq_fields 

# 需要导入模块: import cyvcf2 [as 别名]
# 或者: from cyvcf2 import VCF [as 别名]
def read_vcf(cls: Type[V], path: Path) -> Generator[V, None, None]:
        """
        Read VCF record from `path`.

        This function walks through each variant record in the given VCF using :class:`cyvcf2.VCF
        <cyvcf2.cyvcf2.VCF>`, and yields the record as a :class:`Variant` object.

        See also :meth:`read_and_parse_vcf` to read and parse the VCF.

        Args:
            path: Path to the VCF.

        Returns:
            An generator walking through all variants per record.

        """
        with closing(VCF(str(path))) as vcf:
            for cy_variant in vcf:
                variant = cls.from_cyvcf2(cy_variant)
                yield variant 

# 需要导入模块: import cyvcf2 [as 别名]
# 或者: from cyvcf2 import VCF [as 别名]
def main(vcf):
    variants = VCF(vcf)
    samples = variants.samples
    identifiers = {i: set() for i in samples}
    for v in variants:
        for sample, call in zip(samples, v.gt_types):
            if is_variant(call):
                identifiers[sample].add(v.ID)

    df = pd.DataFrame(index=samples, columns=samples)
    for i_sample, i_values in identifiers.items():
        for j_sample, j_values in identifiers.items():
            df.loc[i_sample, j_sample] = len(i_values & j_values)
    try:
        proper_names = [i.split('/')[1].split('.')[0] for i in samples]
    except IndexError:
        proper_names = samples
    sns.heatmap(data=df,
                annot=True,
                fmt="d",
                linewidths=0.5,
                xticklabels=proper_names,
                yticklabels=proper_names)
    plt.savefig("SV-calls_heatmap.png", bbox_inches="tight") 

# 需要导入模块: import cyvcf2 [as 别名]
# 或者: from cyvcf2 import VCF [as 别名]
def get_vep_scores(vcf_name, vep_vcf_key="CSQ", sel_vep_keys=["phyloP46way_placental", "phyloP46way_primate", "CADD_PHRED", "CADD_RAW"]):
    vcf_fh = cyvcf2.VCF(vcf_name)
    # get the correct elements
    for hdr in vcf_fh.header_iter():
        hdr_info = hdr.info()
        if 'ID' in hdr_info:
            if hdr_info['ID'] == vep_vcf_key:
                vep_keys = hdr_info['Description'].split(": ")[-1].rstrip('"').split("|")
                break
    sel_vep_elms = [vep_keys.index(k) for k in sel_vep_keys]
    info_tags = []
    entries = []
    # Iterate over all entries and extract the `info_tag` if set, otherwise return all INFO tags
    for rec in vcf_fh:
        info_dict = dict(rec.INFO)
        if vep_vcf_key in info_dict:
            vep_entries = info_dict[vep_vcf_key].split(",")[0].split("|")
            variant_uid = ":".join([rec.CHROM, str(rec.POS), rec.REF, rec.ALT[0]])
            vals = [vep_entries[i] for i in sel_vep_elms]
            entries.append(pd.Series([vep_entries[i] for i in sel_vep_elms], name = variant_uid, index = sel_vep_keys))
    # Turn into a data frame
    df = pd.DataFrame(entries,)
    df = df.replace("", "nan").astype(float)
    # dedup
    df = df.loc[~pd.Series(df.index.values).duplicated().values,:]
    return df 

# 需要导入模块: import cyvcf2 [as 别名]
# 或者: from cyvcf2 import VCF [as 别名]
def get_vep_scores(vcf_name,
                   vep_vcf_key="CSQ",
                   sel_vep_keys=["phyloP46way_placental",
                                 "phyloP46way_primate",
                                 "CADD_phred",
                                 "CADD_raw"]):
    vcf_fh = cyvcf2.VCF(vcf_name)
    # get the correct elements
    for hdr in vcf_fh.header_iter():
        hdr_info = hdr.info()
        if 'ID' in hdr_info:
            if hdr_info['ID'] == vep_vcf_key:
                vep_keys = hdr_info['Description'].split(": ")[-1].rstrip('"').split("|")
                break
    sel_vep_elms = [vep_keys.index(k) for k in sel_vep_keys]
    info_tags = []
    entries = []
    # Iterate over all entries and extract the `info_tag` if set, otherwise return all INFO tags
    for rec in vcf_fh:
        info_dict = dict(rec.INFO)
        if vep_vcf_key in info_dict:
            vep_entries = info_dict[vep_vcf_key].split(",")[0].split("|")
            variant_uid = ":".join([rec.CHROM, str(rec.POS), rec.REF, rec.ALT[0]])
            vals = [vep_entries[i] for i in sel_vep_elms]
            entries.append(pd.Series([vep_entries[i] for i in sel_vep_elms], name = variant_uid, index = sel_vep_keys))
    # Turn into a data frame
    df = pd.DataFrame(entries,)
    df = df.replace("", "nan").astype(float)
    # dedup
    df = df.loc[~pd.Series(df.index.values).duplicated().values,:]
    return df 

# 需要导入模块: import cyvcf2 [as 别名]
# 或者: from cyvcf2 import VCF [as 别名]
def test_hemi():
    """
    make sure that we are getting the correct gt_types
    for hemizygous variants
    """

    for p in (HEM_PATH, VCF_PATH):
        vcf = VCF(p)

        for v in vcf:
            check_var(v) 

# 需要导入模块: import cyvcf2 [as 别名]
# 或者: from cyvcf2 import VCF [as 别名]
def from_cyvcf2(cls: Type[V], variant: CyVCF2Variant) -> V:
        """
        Create one Variant object based on the given
        :class:`cyvcf2.Variant <cyvcf2.cyvcf2.Variant>` VCF record.
        """
        return cls(
            chrom=variant.CHROM,
            start_pos=variant.start + 1,
            end_pos=variant.end,
            ref_allele=variant.REF,
            alt_allele=variant.ALT[0],
            id=variant.ID,
            filter=variant.FILTER,
            info=dict(variant.INFO),
        ) 

# 需要导入模块: import cyvcf2 [as 别名]
# 或者: from cyvcf2 import VCF [as 别名]
def get_vep_version(cls: Type[V], vcf_raw_headers: List[str]) -> str:
        """Extract the VEP version in the given VCF."""
        # Find VEP version
        # Reverse the header order because the newer header appears later
        try:
            vep_header = next(
                l for l in reversed(vcf_raw_headers) if l.startswith("##VEP=")
            )
            vep_version = re.match(r"^##VEP=['\"]?v(\d+)['\"]?", vep_header).group(1)  # type: ignore
        except (StopIteration, AttributeError):
            logger.warning(f"Cannot find VEP version in the VCF header")
            vep_version = "UNKNOWN"
        return vep_version 

# 需要导入模块: import cyvcf2 [as 别名]
# 或者: from cyvcf2 import VCF [as 别名]
def __init__(self, *args, **kwargs):
        from cyvcf2 import VCF
        super(MultiSampleVCF, self).__init__(*args, **kwargs, strict_gt=True)
        self.sample_mapping = dict(zip(self.samples, range(len(self.samples)))) 

# 需要导入模块: import cyvcf2 [as 别名]
# 或者: from cyvcf2 import VCF [as 别名]
def one_variant(request, variant_clinical_file):
    LOG.info("Return one parsed variant")
    variant_parser = VCF(variant_clinical_file)

    variant = next(variant_parser)
    return variant 

# 需要导入模块: import cyvcf2 [as 别名]
# 或者: from cyvcf2 import VCF [as 别名]
def one_vep97_annotated_variant(request, vep_97_annotated_variant_clinical_file):
    LOG.info("Return one parsed variant")
    variant_parser = VCF(vep_97_annotated_variant_clinical_file)

    variant = next(variant_parser)
    return variant 

# 需要导入模块: import cyvcf2 [as 别名]
# 或者: from cyvcf2 import VCF [as 别名]
def one_cancer_manta_SV_variant(request, vep_94_manta_annotated_SV_variants_file):
    LOG.info("Return one parsed cancer SV variant")
    variant_parser = VCF(vep_94_manta_annotated_SV_variants_file)

    variant = next(variant_parser)
    return variant 

# 需要导入模块: import cyvcf2 [as 别名]
# 或者: from cyvcf2 import VCF [as 别名]
def one_variant_customannotation(request, customannotation_snv_file):
    LOG.info("Return one parsed variant with custom annotations")
    variant_parser = VCF(customannotation_snv_file)

    variant = next(variant_parser)
    return variant 

# 需要导入模块: import cyvcf2 [as 别名]
# 或者: from cyvcf2 import VCF [as 别名]
def one_sv_variant(request, sv_clinical_file):
    LOG.info("Return one parsed SV variant")
    variant_parser = VCF(sv_clinical_file)

    variant = next(variant_parser)
    return variant 

# 需要导入模块: import cyvcf2 [as 别名]
# 或者: from cyvcf2 import VCF [as 别名]
def rank_results_header(request, variant_clinical_file):
    LOG.info("Return a VCF parser with one variant")
    variants = VCF(variant_clinical_file)
    rank_results = parse_rank_results_header(variants)

    return rank_results