## Import ClientConfiguration and OpencgaClient class
from pyopencga.opencga_config import ClientConfiguration
from pyopencga.opencga_client import OpencgaClient

## Create an instance of OpencgaClient passing the configuration
config = ClientConfiguration('opencga-2.0.0/conf/client-configuration.yml')
oc = OpencgaClient(config)

## Two authentication options:
## Option 1. If the user has a valid token, it can be passed to start doing calls as an authenticated user
oc = OpencgaClient(config, token='TOKEN')

## Option 2. If no token is provided, the user must login with valid credentials. Password is optional (if it is not passed to the login method, it will be prompted to the user)
oc.login(user='USER')	## The password will be asked
# or
oc.login(user='USER', password='PASSWORD')

## You can logout by executing the following command, the token will be deleted. 
oc.logout()

## Create main clients
users = oc.users
projects = oc.projects
studies = oc.studies
files = oc.files
jobs = oc.jobs
families = oc.families
individuals = oc.individuals
samples = oc.samples
cohorts = oc.cohorts
panels = oc.panels

## Create analysis clients
alignments = oc.alignment
variants = oc.variant
clinical = oc.clinical
ga4gh = oc.ga4gh

## Create administrative clients
admin = oc.admin
meta = oc.meta
variant_operations = oc.variant_operations

## Look for the first 5 sample IDs of the study "study"
sample_result = oc.samples.search(study='study', limit=5, include='id')

## Returns the list of results for the response in position "response_pos" (response_pos=0 by default)
sample_response.get_results(response_pos)

## Returns the result in position "result_pos" for the response in position "response_pos" (response_pos=0 by default)
sample_response.get_result(result_pos, response_pos)

## Returns the list of responses
sample_response.get_responses()

## Returns the response in position "response_pos" (response_pos=0 by default)
sample_response.get_response(response_pos)

## Returns all results from the response in position "response_pos" as an iterator (response_pos=None returns all results for all QueryResponses)
sample_response.result_iterator(response_pos)

## Returns all response events by type "event_type" ('INFO', 'WARNING' or 'ERROR') (event_type=None returns all types of event)
sample_response.get_response_events(event_type)

## Returns all response events by type "event_type" ('INFO', 'WARNING or 'ERROR') for the response in position "response_pos" (event_type=None returns all types of event; response_pos=0 by default)
sample_response.get_result_events(event_type, response_pos)

## Return number of matches for the response in position "response_pos" (response_pos=None returns the number for all QueryResponses)
sample_response.get_num_matches(response_pos)

## Return number of results for the response in position "response_pos" (response_pos=None returns the number for all QueryResponses)
sample_response.get_num_results(response_pos)

## Return number of insertions for the response in position "response_pos" (response_pos=None returns the number for all QueryResponses)
sample_response.get_num_inserted(response_pos)

## Return number of updates for the response in position "response_pos" (response_pos=None returns the number for all QueryResponses)
sample_response.get_num_updated(response_pos)

## Return number of deletions for the response in position "response_pos" (response_pos=None returns the number for all QueryResponses)
sample_response.get_num_deleted(response_pos)

## Print results of the query for the response in position "response_pos" (response_pos=None returns the results for all QueryResponses)
sample_response.print_results(fields='id', response_pos=0, limit=5, separator='\t', metadata=True, outfile='path/to/output.tsv')

# First, we need to import both the ClientConfiguration and the OpencgaClient
from pyopencga.opencga_config import ClientConfiguration
from pyopencga.opencga_client import OpencgaClient

# Second, we need to set up the configuration
# The main client-configuration.yml file has a "host" section to point to the REST OpenCGA endpoints
# We need to either pass the path to the configuration file or a dictionary with the same structure of the file
config = ClientConfiguration({'rest': {'host': 'http://bioinfo.hpc.cam.ac.uk/opencga-prod'}})

# Third, we create an instance of the OpencgaClient passing the configuration
oc = OpencgaClient(config)

# Finally, we need to authenticate.
oc.login(user='demouser', password='demouser')

# Additionally, we can check that we've logged in successfully by printing the obtained token
print(oc.token)

# We can get the ID of all the available projects in this OpenCGA installation
for project in oc.projects.search().get_results():
    print(project['id'])

# We can get the ID of all the available studies in the project
for study in oc.studies.search(project='family').get_results():
    print(study['id'])

# We can get the ID for all the available families in the study
for family in oc.families.search(study='corpasome').get_results():
    print(family['id'])

# We can get the ID for all the available samples in the study
for sample in oc.samples.search(study='corpasome').get_results():
    print(sample['id'])

# We are interested in looking for all the individuals containing a particular disorder: "OMIM:611597"
individuals_query_response = oc.individuals.search(
    study='corpasome',  # name of the study where the families are stored
    disorders='OMIM:611597',  # id of the disorders of interest
    include='id'  # retrieve only these fields from the results
)

# If we want to know exactly the number of individuals obtained, we can run:
print(individuals_query_response.get_num_results())

# Now we fetch all the variants falling in the "BFSP2" gene for those individuals
# In this case, we will limit the variant query to a maximum of 10 results
# We also exclude sample information (includeSample='none') as it can be huge and would make this query much slower
for individual in individuals_query_response.get_results():
    print('Individual: ' + individual['id'])
    samples = ','.join([sample['id'] for sample in individual['samples']])
    variant_response = oc.variants.query(study='corpasome', sample=samples, gene='BFSP2', includeSample='none', limit=10)
    if variant_response.get_num_results() > 0:
        for variant in variant_response.get_results():
            print('{}:{}-{}\t{}'.format(variant['chromosome'], str(variant['start']), str(variant['end']), variant['type']))
    else:
        print('No variant results found')

# Now we are interested in getting the rs IDs for the first 10 variants for a particular sample
for variant in oc.variants.query(sample='ISDBM322015', study='corpasome', limit=10).get_results():
    print(variant['names'])

# We can also get rs IDs for multiple samples
for variant in oc.variants.query(sample='ISDBM322015,ISDBM322016,ISDBM322017,ISDBM322018', study='corpasome', limit=10).get_results():
    print(variant['names'])

# If we have an ID for a variant, we can obtain its ID in OpenCGA (chromosome:position:reference:alternate)
variant_id = oc.variants.query(study='corpasome', xref='rs1851943').get_result(0)['id']

# Now we are interested in getting all the samples that have that particular ID
for variant in oc.variants.query_sample(study='corpasome', variant=variant_id, debug=True).get_results():
    for study in variant['studies']:
        for sample in study['samples']:
            print(sample['sampleId'])