diff options
Diffstat (limited to 'Code/parse_ena_xml.py')
| -rw-r--r-- | Code/parse_ena_xml.py | 39 |
1 files changed, 26 insertions, 13 deletions
diff --git a/Code/parse_ena_xml.py b/Code/parse_ena_xml.py index 0a08a7e..0055ec5 100644 --- a/Code/parse_ena_xml.py +++ b/Code/parse_ena_xml.py @@ -120,7 +120,7 @@ def parse_sample(fname): if title != None and title.text != None: d2['title'] = title.text - tissue_type = 'Unknown' + tissue_type = '' for i in c.findall('./SAMPLE_ATTRIBUTES/SAMPLE_ATTRIBUTE'): #print(i) tag = i.find('./TAG') @@ -170,6 +170,18 @@ def parse_experiment(fname): if source != None and source.text != None: d2['library_source'] = source.text + protocol = c.find('./DESIGN/LIBRARY_DESCRIPTOR/LIBRARY_CONSTRUCTION_PROTOCOL') + d2['protocol'] = 'None!' + if protocol != None and protocol.text != None: + d2['protocol'] = protocol.text + + attribute = '' + for i in c.findall('./EXPERIMENT_ATTRIBUTES/EXPERIMENT_ATTRIBUTE'): + tag = i.find('./TAG') + value = i.find('./VALUE') + attribute += value.text + ' ' + d2['attribute'] = attribute + d[primary_id] = d2 return d @@ -182,24 +194,25 @@ def get_singular_form(w): return w -def get_tissue(sample_id, d_sample): +def get_tissue(sample_id, d_sample, experiment_id, d_experiment): ''' Extract tissue name from s. s may contain several tissue names, return them ordered by frequency. ''' - tissue = 'Unknown' - result0 = '' - #print(sample_id) - #print(list(d.keys())[0:10]) + tissue = '' if sample_id in d_sample: tissue = d_sample[sample_id]['tissue'] - if tissue != 'Unknown': - result0 = tissue + if tissue: + return tissue s = '' if sample_id in d_sample: - s += d_sample[sample_id]['title'] - s += d_sample[sample_id]['description'] + s += ' ' + d_sample[sample_id]['title'] + s += ' ' + d_sample[sample_id]['description'] + + if experiment_id in d_experiment: + s += ' ' + d_experiment[experiment_id]['protocol'] + s += ' ' + d_experiment[experiment_id]['attribute'] - lst = ['seedling', 'seedlings', 'root', 'roots', 'leaves', 'leaf', 'flower', 'flowers', 'floral', 'shoot', 'shoots', 'apex', 'apices', 'stamen', 'stem', 'stems', 'seed', 'seeds', 'petal', 'petals', 'sepal', 'sepals', 'embryo', 'embryos', 'embryonic', 'cotyledon', 'cotyledons', 'xylem', 'hair', 'hairs', 'phloem', 'pericycle', 'primordia', 'columella', 'cortex', 'meristem', 'meristems', 'cambium', 'epidermis', 'epidermal', 'phloem', 'mesophyll', 'apical', 'lateral', 'intercalary', 'parenchyma', 'collenchyma', 'sclerenchyma', 'bud', 'buds', 'endosperm', 'colletotrichum', 'stele', 'vacuoles', 'vacuole', 'vacuolar', 'tip', 'tips', 'pollen', 'hypocotyl', 'hypocotyls', 'tube', 'tubes', 'basal', 'stomatal', 'stomata', 'surface', 'progeny', 'ovules', 'carpel', 'carpels', 'gynoecium', 'pistil', 'pistils', 'anthers', 'anther', 'endodermis', 'dicotyledonous', 'hyphae', 'adabaxial', 'axial', 'cauline', 'rosette', 'pedicle', 'pedicel', 'inflorescence', 'petiole', 'lamina', 'vascular', 'bundle', 'sheath'] # possible tissue names, lower case. refer to /home/hui/network/test/rnaseq.word.count.txt for distinct words in rna seq. rnaseq.word.count.txt is generated by /home/hui/network/test/count_word.py + lst = ['seedling', 'seedlings', 'root', 'roots', 'leaves', 'leaf', 'flower', 'flowers', 'floral', 'shoot', 'shoots', 'apex', 'apices', 'stamen', 'stem', 'stems', 'seed', 'seeds', 'petal', 'petals', 'sepal', 'sepals', 'embryo', 'embryos', 'embryonic', 'cotyledon', 'cotyledons', 'xylem', 'hair', 'hairs', 'phloem', 'pericycle', 'primordia', 'columella', 'cortex', 'meristem', 'meristems', 'cambium', 'epidermis', 'epidermal', 'phloem', 'mesophyll', 'apical', 'lateral', 'intercalary', 'parenchyma', 'collenchyma', 'sclerenchyma', 'bud', 'buds', 'endosperm', 'colletotrichum', 'stele', 'vacuoles', 'vacuole', 'vacuolar', 'tip', 'tips', 'pollen', 'hypocotyl', 'hypocotyls', 'tube', 'tubes', 'basal', 'stomatal', 'stomata', 'surface', 'progeny', 'ovules', 'carpel', 'carpels', 'gynoecium', 'pistil', 'pistils', 'anthers', 'anther', 'endodermis', 'dicotyledonous', 'hyphae', 'adabaxial', 'axial', 'cauline', 'rosette', 'pedicle', 'pedicel', 'inflorescence', 'petiole', 'lamina', 'vascular', 'bundle', 'sheath', 'microspore'] # possible tissue names, lower case. refer to /home/hui/network/test/rnaseq.word.count.txt for distinct words in rna seq. rnaseq.word.count.txt is generated by /home/hui/network/test/count_word.py # build a count dictionary, where key is a word d = {} @@ -222,7 +235,7 @@ def get_tissue(sample_id, d_sample): tlst = sorted(d.items(), key=operator.itemgetter(1), reverse=True) for t in tlst: result += '%s(%d);' % (t[0], t[1]) - return result0 + ';' + result.rstrip(';') + return result.rstrip(';') def get_tissue2(sample_id, d): @@ -291,7 +304,7 @@ if __name__ == '__main__': d['tissue'] = d['library_strategy'] = d['library_source'] = d['sample_id'] = '.' if k2 in d_experiment: d['sample_id'] = d_experiment[k2]['sample_id'] - d['tissue'] = get_tissue(d_experiment[k2]['sample_id'], d_sample) + d['tissue'] = get_tissue(d_experiment[k2]['sample_id'], d_sample, k2, d_experiment) d['library_strategy'] = d_experiment[k2]['library_strategy'] d['library_source'] = d_experiment[k2]['library_source'] d['detail'] = 'TBA' |