formats

DynamX_v3_cluster

Source code in hdxms_datasets/stable/v020/formats.py

class DynamX_v3_cluster:
    columns = [
        "Protein",
        "Start",
        "End",
        "Sequence",
        "Modification",
        "Fragment",
        "MaxUptake",
        "MHP",
        "State",
        "Exposure",
        "File",
        "z",
        "RT",
        "Inten",
        "Center",
    ]
    state_name = "State"
    exposure_name = "Exposure"
    aggregated = False

    def convert(self, df: nw.DataFrame) -> nw.DataFrame:
        """
        Convert the DataFrame to a standard format.
        """
        return from_dynamx_cluster(df)

convert(df)

Convert the DataFrame to a standard format.

Source code in hdxms_datasets/stable/v020/formats.py

def convert(self, df: nw.DataFrame) -> nw.DataFrame:
    """
    Convert the DataFrame to a standard format.
    """
    return from_dynamx_cluster(df)

DynamX_vx_state

There are also DynamX state data files which do not have 'Modification' and 'Fragment' columns. not sure which version this is.

Source code in hdxms_datasets/stable/v020/formats.py

class DynamX_vx_state:
    """There are also DynamX state data files which do not have 'Modification' and 'Fragment' columns.
    not sure which version this is.
    """

    columns = [
        "Protein",
        "Start",
        "End",
        "Sequence",
        "MaxUptake",
        "MHP",
        "State",
        "Exposure",
        "Center",
        "Center SD",
        "Uptake",
        "Uptake SD",
        "RT",
        "RT SD",
    ]

    state_name = "State"
    exposure_name = "Exposure"
    aggregated = True

    def convert(self, df: nw.DataFrame) -> nw.DataFrame:
        """
        Convert the DataFrame to a standard format.
        """
        return from_dynamx_state(df)

convert(df)

Convert the DataFrame to a standard format.

Source code in hdxms_datasets/stable/v020/formats.py

def convert(self, df: nw.DataFrame) -> nw.DataFrame:
    """
    Convert the DataFrame to a standard format.
    """
    return from_dynamx_state(df)

HDExaminer_v3

Source code in hdxms_datasets/stable/v020/formats.py

class HDExaminer_v3:
    columns = [
        "Protein State",
        "Deut Time",
        "Experiment",
        "Start",
        "End",
        "Sequence",
        "Charge",
        "Search RT",
        "Actual RT",
        "# Spectra",
        "Peak Width Da",
        "m/z Shift Da",
        "Max Inty",
        "Exp Cent",
        "Theor Cent",
        "Score",
        "Cent Diff",
        "# Deut",
        "Deut %",
        "Confidence",
    ]
    state_name = "Protein State"
    exposure_name = "Deut Time"
    aggregated = False

    def convert(self, df: nw.DataFrame) -> nw.DataFrame:
        """
        Convert the DataFrame to a standard format.
        """
        return from_hdexaminer(df)

convert(df)

Convert the DataFrame to a standard format.

Source code in hdxms_datasets/stable/v020/formats.py

def convert(self, df: nw.DataFrame) -> nw.DataFrame:
    """
    Convert the DataFrame to a standard format.
    """
    return from_hdexaminer(df)

HDXFormat

Bases: Protocol

Source code in hdxms_datasets/stable/v020/formats.py

class HDXFormat(Protocol):
    columns: list[str]
    state_name: str
    exposure_name: str
    # aggregated: bool = False  # whether the data is aggregated or expanded as multiple replicates

    def convert(self, df: nw.DataFrame) -> nw.DataFrame:
        """
        Convert the DataFrame to a standard format.
        """
        ...

    @property
    def aggregated(self) -> bool: ...

convert(df)

Convert the DataFrame to a standard format.

Source code in hdxms_datasets/stable/v020/formats.py

def convert(self, df: nw.DataFrame) -> nw.DataFrame:
    """
    Convert the DataFrame to a standard format.
    """
    ...

OpenHDXFormat dataclass

A format where columns names are standardized to a common set.

Hence OpenHDXFormat.convert() is a no-op.

Source code in hdxms_datasets/stable/v020/formats.py

@dataclass
class OpenHDXFormat:
    """A format where columns names are standardized to a common set.

    Hence OpenHDXFormat.convert() is a no-op.

    """

    columns = STANDARD_COLUMNS + OPTIONAL_COLUMNS
    state_name = "state"
    exposure_name = "exposure"
    aggregated: bool  #  = True  # whether the data is aggregated or expanded as multiple replicates

    def convert(self, df: nw.DataFrame) -> nw.DataFrame:
        """
        Convert the DataFrame to a standard format.
        """

        return df

convert(df)

Convert the DataFrame to a standard format.

Source code in hdxms_datasets/stable/v020/formats.py

def convert(self, df: nw.DataFrame) -> nw.DataFrame:
    """
    Convert the DataFrame to a standard format.
    """

    return df

identify_format(df, *, exact=True)

Identify which HDXFormat subclass the given column list matches. If there is no match, return an OpenHDXFormat instance with aggregated set to True if 'replicate' is in the columns.

Parameters:

Name	Type	Description	Default
cols		The column names to check.	required
exact	bool	If True, order must match; otherwise, uses set equality.	True

Returns:

Type	Description
Optional[HDXFormat]	The matching HDXFormat subclass, or None if no match.

Source code in hdxms_datasets/stable/v020/formats.py

def identify_format(df: nw.DataFrame, *, exact: bool = True) -> Optional[HDXFormat]:
    """
    Identify which HDXFormat subclass the given column list matches. If there is no match,
    return an OpenHDXFormat instance with aggregated set to True if 'replicate' is in the columns.

    Args:
        cols: The column names to check.
        exact: If True, order must match; otherwise, uses set equality.

    Returns:
        The matching HDXFormat subclass, or None if no match.
    """
    cols = df.columns
    for fmt in HDX_FORMATS:
        template = fmt.columns
        if exact and cols == template:
            return fmt
        elif not exact and set(cols) == set(template):
            return fmt

    # it there is no match, we try to return the OpenHDXFormat
    aggregated = "replicate" not in cols
    fmt = OpenHDXFormat(aggregated=aggregated)

    return fmt