alethiotx.artemis.upset

 4def prepare(breast, lung, prostate, melanoma, bowel, diabetes, cardiovascular, mode):
 5    """
 6    Prepare data for UpSet plot visualization.
 7
 8    This function processes disease-related data and converts it into a format
 9    suitable for UpSet plot generation using the `from_contents` function.
10
11    :param breast: Breast cancer data. In ``ct`` mode, should be a DataFrame with
12                   ``Target Gene`` column. In ``pg`` mode, should be a list.
13    :type breast: pandas.DataFrame or list
14    :param lung: Lung cancer data. In ``ct`` mode, should be a DataFrame with
15                 ``Target Gene`` column. In ``pg`` mode, should be a list.
16    :type lung: pandas.DataFrame or list
17    :param prostate: Prostate cancer data. In ``ct`` mode, should be a DataFrame with
18                     ``Target Gene`` column. In ``pg`` mode, should be a list.
19    :type prostate: pandas.DataFrame or list
20    :param melanoma: Melanoma data. In ``ct`` mode, should be a DataFrame with
21                     ``Target Gene`` column. In ``pg`` mode, should be a list.
22    :type melanoma: pandas.DataFrame or list
23    :param bowel: Bowel cancer data. In ``ct`` mode, should be a DataFrame with
24                  ``Target Gene`` column. In ``pg`` mode, should be a list.
25    :type bowel: pandas.DataFrame or list
26    :param diabetes: Diabetes data. In ``ct`` mode, should be a DataFrame with
27                     ``Target Gene`` column. In ``pg`` mode, should be a list.
28    :type diabetes: pandas.DataFrame or list
29    :param cardiovascular: Cardiovascular disease data. In ``ct`` mode, should be a
30                           DataFrame with ``Target Gene`` column. In ``pg`` mode,
31                           should be a list.
32    :type cardiovascular: pandas.DataFrame or list
33    :param mode: Processing mode. ``ct`` extracts ``Target Gene`` column from DataFrames,
34                 ``pg`` uses the data directly as lists.
35    :type mode: str
36    :return: Dictionary formatted for UpSet plot with disease names as keys and
37             gene lists or data lists as values.
38    :rtype: dict
39    :raises ValueError: If mode is not ``ct`` or ``pg``.
40    """
41    if mode == 'ct':
42        return from_contents(
43            {
44                "breast": breast['Target Gene'].tolist(), 
45                "lung": lung['Target Gene'].tolist(), 
46                "prostate": prostate['Target Gene'].tolist(), 
47                "melanoma": melanoma['Target Gene'].tolist(), 
48                "bowel": bowel['Target Gene'].tolist(), 
49                "diabetes": diabetes['Target Gene'].tolist(), 
50                "cardiovascular": cardiovascular['Target Gene'].tolist()
51            }
52        )
53    elif mode == 'pg':
54        return from_contents(
55            {
56                "breast": breast, 
57                "lung": lung, 
58                "prostate": prostate, 
59                "melanoma": melanoma, 
60                "bowel": bowel, 
61                "diabetes": diabetes, 
62                "cardiovascular": cardiovascular
63            }
64        )
65    else:
66        raise ValueError("Mode must be either 'ct' or 'pg'")

 68def create(indications, min_subset_size):
 69    """
 70    Create an UpSet plot for visualizing set intersections.
 71
 72    :param indications: Data structure containing set membership information for creating the UpSet plot
 73    :type indications: pandas.DataFrame or similar data structure compatible with UpSet
 74    :param min_subset_size: Minimum size threshold for subsets to be displayed in the plot
 75    :type min_subset_size: int
 76    :return: An UpSet plot object configured with the specified parameters
 77    :rtype: UpSet
 78    :raises TypeError: If indications is not a compatible data structure
 79    :raises ValueError: If min_subset_size is negative
 80
 81    .. note::
 82
 83        The plot is configured with the following settings:
 84        
 85        - subset_size: "count" - shows count of elements in each subset
 86        - orientation: "vertical" - displays plot in vertical orientation
 87        - show_counts: "{:d}" - formats counts as integers
 88        - sort_by: ``cardinality`` - sorts subsets by their size
 89        - sort_categories_by: ``input`` - maintains input order for categories
 90        - min_subset_size: filters out subsets smaller than the specified threshold
 91
 92    .. seealso::
 93
 94        `UpSet documentation <https://upsetplot.readthedocs.io/>`_
 95    """
 96    return UpSet(
 97        indications, 
 98        subset_size="count", 
 99        orientation="vertical", 
100        show_counts="{:d}", 
101        sort_by='cardinality', 
102        sort_categories_by = 'input',
103        min_subset_size = min_subset_size,
104    )