alethiotx.artemis.utils

  1"""
  2**Artemis**: public knowledge graphs enable accessible and scalable drug target discovery.
  3
  4Github Repository   
  5-----------------
  6
  7`GitHub - alethiotx/artemis-paper <https://github.com/alethiotx/artemis-paper>`_
  8"""
  9
 10def find_overlapping_genes(genes: list, overlap = 1, common_genes = []):
 11    """
 12    Find genes that overlap across multiple gene lists.
 13
 14    :param genes: A list of gene lists to check for overlapping genes.
 15    :type genes: list
 16    :param overlap: Minimum number of lists a gene must appear in to be considered overlapping, defaults to 1.
 17    :type overlap: int
 18    :param common_genes: Initial list of common genes to include in the result, defaults to [].
 19    :type common_genes: list
 20    :return: A list of genes that appear in more than ``overlap`` lists but not in all lists.
 21    :rtype: list
 22
 23    **Example**
 24    >>> genes_list = [['gene1', 'gene2'], ['gene2', 'gene3'], ['gene2', 'gene4']]
 25    >>> find_overlapping_genes(genes_list, overlap=1)
 26    ['gene2']
 27
 28    .. note::
 29
 30        Genes that appear in all input lists are excluded from the result by default.
 31        To include them, modify the condition ``d[i] < len(genes)`` to ``d[i] <= len(genes)``.
 32
 33    """
 34    d = {}
 35    overlapping_genes = common_genes.copy()
 36
 37    for i in [x for y in genes for x in y]:
 38        if i in d.keys():
 39            d[i]=d[i]+1
 40        else:
 41            d[i]=1
 42    for i in d.keys():
 43        if d[i]>overlap and d[i] < len(genes): # the second condition excludes genes present in all lists, if you want to include those, change < to <=, or remove the condition entirely
 44            overlapping_genes.append(i)
 45    return overlapping_genes
 46
 47# run when file is directly executed
 48if __name__ == '__main__': 
 49    print("Artemis module. Run tests or examples here.")
 50    # # 'Breast Cancer', 
 51    # # 'Lung Cancer',
 52    # # 'Prostate Cancer',
 53    # # 'Bowel Cancer',
 54    # # 'Melanoma',
 55    # # 'Diabetes Mellitus Type 2',
 56    # # 'Cardiovascular Disease',
 57    # df = get_pathway_genes("acute myeloid leukemia")
 58    # print(df.loc["FLT3", ["gene_count", "rank"]])
 59    # breast, lung, prostate, melanoma, bowel, diabetes, cardiovascular = load_clinical_scores(date="2025-11-11")
 60    # print('Clinical scores:\n\n')
 61    # print([breast, lung, prostate, melanoma, bowel, diabetes, cardiovascular])
 62    # print('All target genes:\n\n')
 63    # known_targets = get_all_targets([breast, lung, prostate, melanoma, bowel, diabetes, cardiovascular])
 64    # print(known_targets)
 65    # print('Cut clinical scores:\n\n')
 66    # print(cut_clinical_scores([breast, lung, prostate, melanoma, bowel, diabetes, cardiovascular], lowest_score = 10))
 67    # breast_pg, lung_pg, prostate_pg, melanoma_pg, bowel_pg, diabetes_pg, cardiovascular_pg = load_pathway_genes(date='2025-09-15', n=50)
 68    # print('Uniquified clinical scores:\n\n')
 69    # print(uniquify_clinical_scores([breast, lung, prostate, melanoma, bowel, diabetes, cardiovascular]))
 70    # print('Uniquified pathway genes:\n\n')
 71    # print(uniquify_pathway_genes([breast_pg, lung_pg, prostate_pg, melanoma_pg, bowel_pg, diabetes_pg, cardiovascular_pg]))
 72    # print(prepare_upset(breast, lung, prostate, melanoma, bowel, diabetes, cardiovascular, mode='ct'))
 73
 74    # # X is always bigger than y!!!
 75    # X = DataFrame({
 76    #     'term1' : [0, 1, 2, 3, 4, 5, 4, 3, 2, 1, 0, 1, 2, 3, 4, 5, 0, 0, 1, 1, 2, 2, 0, 1, 2, 3, 4, 5, 4, 3, 2, 1, 0, 1, 2, 3, 4, 5, 0, 0, 1, 1, 2, 2], 
 77    #     'term2' : [1, 2, 3, 4, 5, 0, 0, 1, 1, 2, 2, 2, 3, 4, 5, 6, 5, 7, 2, 9, 2, 1, 1, 2, 3, 4, 5, 0, 0, 1, 1, 2, 2, 2, 3, 4, 5, 6, 5, 7, 2, 9, 2, 1], 
 78    #     'term3' : [2, 3, 4, 5, 6, 5, 7, 2, 9, 2, 1, 3, 4, 5, 6, 7, 4, 5, 0, 0, 1, 2, 2, 3, 4, 5, 6, 5, 7, 2, 9, 2, 1, 3, 4, 5, 6, 7, 4, 5, 0, 0, 1, 2], 
 79    #     'term4' : [3, 4, 5, 6, 7, 4, 5, 0, 0, 1, 2, 9, 2, 1, 3, 4, 5, 6, 7, 5, 7, 2, 3, 4, 5, 6, 7, 4, 5, 0, 0, 1, 2, 9, 2, 1, 3, 4, 5, 6, 7, 5, 7, 2], 
 80    #     'term5' : [4, 5, 6, 7, 8, 6, 5, 7, 2, 9, 3, 0, 1, 2, 3, 4, 5, 4, 3, 2, 1, 0, 4, 5, 6, 7, 8, 6, 5, 7, 2, 9, 3, 0, 1, 2, 3, 4, 5, 4, 3, 2, 1, 0]
 81    # })
 82    # y = DataFrame({
 83    #     'Target Gene' : ['gene1', 'gene2', 'gene3', 'gene4', 'gene5', 'gene6', 'gene7', 'gene8', 'gene9', 'gene10', 'gene11', 'gene12', 'gene13', 'gene14', 'gene15'], 
 84    #     'Clinical Score' : [1, 1, 1, 4, 5, 10, 5, 3, 2, 5, 1, 100, 200, 300, 400]
 85    # })
 86    # # X is always bigger than y!!!
 87    # X.index = ['gene1', 'gene2', 'gene3', 'gene4', 'gene5', 'gene6', 'gene7', 'gene8', 'gene9', 'gene10', 'gene11', 'gene12', 'gene13', 'gene14', 'gene15', 'gene16', 'gene17', 'gene18', 'gene19', 'gene20', 'gene21', 'gene22', 'gene23', 'gene24', 'gene25', 'gene26', 'gene27', 'gene28', 'gene29', 'gene30', 'gene31', 'gene32', 'gene33', 'gene34', 'gene35', 'gene36', 'gene37', 'gene38', 'gene39', 'gene40', 'gene41', 'gene42', 'gene43', 'gene44']
 88    # print('\nInput term matrix:')
 89    # print(X)
 90    # print('\nInput clinical scores:')
 91    # print(y)
 92    # print('\nCheck binning:')
 93    # res = pre_model(X, y, bins = 5)
 94    # print(res['y_encoded'])
 95
 96    # known_targets = ['gene32', 'gene33']
 97
 98    # res = pre_model(X, y, known_targets = known_targets, bins = 5)
 99    # print(res['y_encoded'])
100
101    # print('\nResults of cross validation pipeline:')
102    # print(cv_pipeline(X, y, n_iterations = 3))
103    # print(cv_pipeline(X, y, y_slot = 'y_encoded', scoring = 'accuracy', n_iterations = 3))