Cross resources example¶

import requests
import csv
import os
import pandas as pd
from tempfile import NamedTemporaryFile

INDEX_PAGE = "https://idr.openmicroscopy.org/webclient/?experimenter=-1"

# create http session
with requests.Session() as session:
    request = requests.Request('GET', INDEX_PAGE)
    prepped = session.prepare_request(request)
    response = session.send(prepped)
    if response.status_code != 200:
        response.raise_for_status()

URL = "https://idr.openmicroscopy.org/mapr/api/{key}/?value={value}&case_sensitive=false&orphaned=true"
SCREENS_PROJECTS_URL = "https://idr.openmicroscopy.org/mapr/api/{key}/?value={value}"
PLATES_URL = "https://idr.openmicroscopy.org/mapr/api/{key}/plates/?value={value}&id={screen_id}"
DATASETS_URL = "https://idr.openmicroscopy.org/mapr/api/{key}/datasets/?value={value}&id={project_id}"
IMAGES_URL = "https://idr.openmicroscopy.org/mapr/api/{key}/images/?value={value}&node={parent_type}&id={parent_id}"
ATTRIBUTES_URL = "https://idr.openmicroscopy.org/webclient/api/annotations/?type=map&image={image_id}"

URL_OXO = "https://www.ebi.ac.uk/spot/oxo/api/search"

TERM = "HGNC_5009"
TYPE = "gene"

KEYS = {"phenotype":
    ("Phenotype",
     "Phenotype Term Name",
     "Phenotype Term Accession",
     "Phenotype Term Accession URL")
}

# Prepare the query
headers = {
    'Accept': 'application/json',
    'Content-Type': 'application/json'
}

data = {
    "ids" : [ TERM.replace("_", ":") ], "distance" : 2
}

response = requests.post(URL_OXO, headers=headers, json=data)

def parse_annotation(writer, json_data, name, data_type):
    screen_name = "-"
    plate_name = "-"
    project_name = "-"
    dataset_name = "-"
    if data_type == 'datasets':
        project_name = name
    else:
        screen_name = name
     
    for p in json_data[data_type]:
        parent_id = p['id']
        if data_type == 'datasets':
            dataset_name = p['name']
        else:
            plate_name = p['name']
        qs3 = {'key': TYPE, 'value': gene,
                'parent_type': data_type[:-1], 'parent_id': parent_id}
        url3 = IMAGES_URL.format(**qs3)
        for i in session.get(url3).json()['images']:

            image_id = i['id']
            url4 = ATTRIBUTES_URL.format(**{'image_id': image_id})
            for a in session.get(url4).json()['annotations']:
                ontologies = []  # for ontology terms for a phenotype
                row = {}
                for v in a['values']:
                    if str(v[0]) in KEYS['phenotype']:
                        if str(v[0]) in ['Phenotype']:  # has phenotype
                            row[str(v[0])] = v[1]  # so create row
   
                        # if there are ontology mappings for the
                        # phenotype, add them to the ontologies list
                        ontList = ['Phenotype Term Name',
                                   'Phenotype Term Accession',
                                   'Phenotype Term Accession URL']

                        if str(v[0]) in ontList:
                            ontologies.extend([str(v[0]), str(v[1])])
                    if row:
                        if (len(ontologies) > 0):  # 1+ ontology mapping
                            row.update({'Gene': gene,
                                        'Screen': screen_name,
                                        'Plate': plate_name,
                                        'Image': image_id,
                                        'Project' : project_name,
                                        'Dataset': dataset_name})
                            # we have the start of a row now
                            # but we want to print out as many rows
                            # as there are ontology mappings
                            # so if there is mapping to 1 ontology term
                            # print 1 row, if there are 2 ontology terms
                            # print 2 rows etc
                            numberOfRows = len(ontologies)/6
                            # this is 3 pairs of ontology values per
                            # mapping, add the ontology mappings and print
                            n = 1
                            while (n <= numberOfRows):
                                row.update({ontologies[0]: ontologies[1],
                                            ontologies[2]: ontologies[3],
                                            ontologies[4]: ontologies[5]})
                                # remove that set of ontology mappings
                                ontologies = ontologies[6:]
                                writer.writerow(row)
                                n = n + 1

home = os.path.expanduser("~")
csvfile = NamedTemporaryFile("w", delete=False, newline='', dir=home, suffix=".csv")

try:
    fieldnames = [
        'Gene', 'Screen', 'Plate', 'Project', 'Dataset', 'Image',
        'Phenotype', 'Phenotype Term Name', 'Phenotype Term Accession',
        'Phenotype Term Accession URL']
    writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
    writer.writeheader()
    
    for v in terms:
        qs1 = {'key': TYPE, 'value': v}
        url1 = URL.format(**qs1)
        json = session.get(url1).json()
        for m in json['maps']:
            qs2 = {'key': TYPE, 'value': v, 'compound_id': m['id']}
            url2 = SCREENS_PROJECTS_URL.format(**qs2)
            json = session.get(url2).json()
            for s in json['screens']:
                id = s['id']
                if id in to_keep:
                    gene = s['extra']['value']
                    qs3 = {'key': TYPE, 'value': gene, 'screen_id': s['id']}
                    url3 = PLATES_URL.format(**qs3)
                    parse_annotation(writer, session.get(url3).json(), s['name'], 'plates')
finally:
    csvfile.close()

term = df["Phenotype Term Accession"][0]
term = term.replace("_", ":")
data = {
    "ids" : [ term ], "distance" : 2
}

response = requests.post(URL_OXO, headers=headers, json=data)