In [1]:

    

import encode_utils.stream as es
import encode_utils.grab as grab


    

In [559]:

    

def find_pair(experiments, filter_dict):
    filters = []
    for k, v in filter_dict.items():
        filters.append(es.filter_field_by_comparison(field=k, value=v[0], comparison=v[1]))
    yield from es.match(experiments, *filters)

def has_pair(parsed_data, get_data=False):
    for d in parsed_data:
        matches = list(find_pair(parsed_data, {'biosample_term_name': (d['biosample_term_name'], 'equals'),
                                               'biosample_term_id': (d['biosample_term_id'], 'equals'),
                                               'biosample_type': (d['biosample_type'], 'equals'),
                                               'biosample_summary': (d['biosample_summary'], 'equals'),
                                               'target': (d['target'], 'equals'),
                                               'lab': (d['lab'], 'equals'),
                                               'assay_title': (d['assay_title'], 'equals')}))
        if len(matches) == 2:
            has_pair = True
        else:
            has_pair = False
        if get_data:
            if has_pair:
                yield matches
        else:
            yield d['accession'], has_pair
def get_unique_pairs(pairs):           
    unique_set = set()
    for pair in pairs:
        pair_tup_one = (pair[0]['accession'], pair[1]['accession'])
        pair_tup_two = (pair[1]['accession'], pair[0]['accession'])
        if pair_tup_one in unique_set or pair_tup_two in unique_set:
            continue
        else:
            unique_set.add(pair_tup_one)
    return unique_set
    
def parse_experiments(experiments):
    for e in experiments:
        yield {'accession': e.get('accession', e.get('uuid')),
               'biosample_summary': e.get('biosample_summary', ''),
               'biosample_term_name': e.get('biosample_term_name', ''),
               'biosample_term_id': e.get('biosample_term_id', ''), 
               'biosample_type': e.get('biosample_type', ''),
               'target': e.get('target', {}).get('name', ''),
               'lab': e.get('lab', {}).get('name', ''),
               'assay_title': e.get('assay_title', ''),
               'alternate_accessions': e.get('alternate_accessions', [])}
        
def get_pair_data(pair):
    data = grab.quick_grab_data(['{}/{}?{}&frame=embedded'.format(grab.base_url,
                                                                  p,
                                                                  grab.json_only) for p in pair])
    return data

def get_merge_info(e):
    return {'reps': [(r.get('uuid'),
                      r.get('experiment'),
                      r.get('biological_replicate_number'),
                      r.get('technical_replicate_number')) for r in e.get('replicates', {})],
            'original_files': e.get('original_files', {}),
            'dbxrefs': e.get('dbxrefs', []),
            'aliases': e.get('aliases', []),
            'documents': e.get('documents', []),
            'alternate_accessions': e.get('alternate_accessions', [])}

def determine_base_exp(pair_a, pair_b):
    """
    Return True if pair_a should be base experiment else False.
    """
    bio_reps_a = [b[2] for b in get_merge_info(pair_a)['reps']]
    bio_reps_b = [b[2] for b in get_merge_info(pair_b)['reps']]
    if min(bio_reps_a) == min(bio_reps_b):
        # Take one with more tech_reps if bio_rep same.
        if len(bio_reps_b) > len(bio_reps_a):
            return False
        return True
    # Take one with lower bio_rep_number in general.
    if min(bio_reps_a) <= min(bio_reps_b):
        return True
    return False

def rep_patch(base_exp, merge_exp):
    updated_replicates = []
    base_exp_id = base_exp['@id']
    next_bio_rep = max([r[2] for r in get_merge_info(base_exp)['reps']]) + 1
    merge_exp_reps_sorted = sorted(get_merge_info(merge_exp)['reps'], key=lambda x: x[2])
    for j, bio_rep in enumerate(sorted(set([r[2] for r in merge_exp_reps_sorted]))):
        for i, y in enumerate(sorted([r for r in merge_exp_reps_sorted if r[2] == bio_rep], key=lambda x: x[3])):
            d = ({'uuid': y[0],
                 'experiment': base_exp_id,
                 'biological_replicate_number': next_bio_rep + j,
                 'technical_replicate_number': i + 1},
                 'REPLICATE')
            updated_replicates.append(d)
    return updated_replicates

def original_files_patch(base_exp, merg_exp):
    updated_original_files = []
    base_exp_id = base_exp['@id']
    for file in get_merge_info(merg_exp)['original_files']:
        d = ({'accession': file,
             'dataset': base_exp_id},
             'ORIGINAL FILE')
        updated_original_files.append(d)
    return updated_original_files

def parse_pair(pair):
    if determine_base_exp(pair[0], pair[1]):
        base_exp, merge_exp = pair[0], pair[1]
    else:
        base_exp, merge_exp = pair[1], pair[0]
    return base_exp, merge_exp

def values_from_both(field):
    return list(set([*get_merge_info(base_exp)[field],
                     *get_merge_info(merge_exp)[field]]))

def patch_item(url, data, auth, show_output=False):
    r = requests.patch(url,
                       auth=grab.auth,
                       json=data)
    print('PATCHING: {}'.format(item), data)
    #print(json.dumps(data, indent=4, sort_keys=True), '\n')
    if show_output or r.status_code != 200:
        print(json.dumps(r.json(), indent=4, sort_keys=True))
    return r.status_code

def parse_patch_set(patch):
    data = patch[0].copy()
    item = data.get('accession', data.get('uuid'))
    [data.pop(field, None) for field in ['accession', 'uuid']]
    return item, data

def make_patch(patch_set, base_url):
    for p in patch_set:
        item, data = parse_patch_set(p)
        url = grab.urljoin(base_url, item)
        patch_item(url, data, grab.auth)


    

In [556]:

    

# Step 0: Get embedded data.
url = 'https://www.encodeproject.org/search/?type=Experiment'\
      '&replicates.library.biosample.donor.uuid=53b21c14-4f83-40c1-bc07-8621fdc70ce2'\
      '&replicates.library.biosample.donor.uuid=6007378b-528a-4dbf-8086-bc3502abc6f5'\
      '&limit=all&status!=revoked&frame=embedded&format=json&limit=all'
# url = 'https://www.encodeproject.org/search/?type=Experiment'\
#       '&replicates.library.biosample.donor.accession=ENCDO981EWY'\
#       '&replicates.library.biosample.donor.accession=ENCDO030VWZ'\
#       '&frame=embedded&format=json&limit=all'
assert 'embedded' in url
data = grab.quick_grab_data([url])
len(data)


    

    
Out[556]:





24

In [557]:

    

# Step I: Match on
#     - biosample_term_name
#     - biosample_term_id
#     - biosample_type
#     - target.name
#     - lab.name

parsed_data = list(parse_experiments(data))
pairs = list(has_pair(parsed_data, get_data=True))
unique_pairs = get_unique_pairs(pairs)


    

In [558]:

    

len(unique_pairs)


    

    
Out[558]:





10

In [560]:

    

list(has_pair(parsed_data))


    

    
Out[560]:





[('ENCSR534RNS', True),
 ('ENCSR584XHX', False),
 ('ENCSR511NSE', True),
 ('ENCSR911WPA', True),
 ('ENCSR575ICR', True),
 ('ENCSR690UYB', True),
 ('ENCSR684NQL', True),
 ('ENCSR064VLH', True),
 ('ENCSR181NUJ', False),
 ('ENCSR850JSG', True),
 ('ENCSR528QDT', True),
 ('ENCSR764XUL', True),
 ('ENCSR517EEQ', True),
 ('ENCSR717BNA', True),
 ('ENCSR696SOJ', True),
 ('ENCSR969JYY', True),
 ('ENCSR736YYJ', True),
 ('ENCSR800JXT', True),
 ('ENCSR820ABR', True),
 ('ENCSR676CFI', True),
 ('ENCSR470JHE', False),
 ('ENCSR494OXB', True),
 ('ENCSR359JHU', True),
 ('ENCSR374BVM', False)]

In [561]:

    

for d in parsed_data:
    matches = list(find_pair(parsed_data, {'biosample_term_name': (d['biosample_term_name'], 'equals'),
                                           'biosample_term_id': (d['biosample_term_id'], 'equals'),
                                           'biosample_type': (d['biosample_type'], 'equals'),
                                           'biosample_summary': (d['biosample_summary'], 'equals'),
                                           'target': (d['target'], 'equals'),
                                           'lab': (d['lab'], 'equals'),
                                           'assay_title': (d['assay_title'], 'equals')}))
    if len(matches) != 2:
        print('\n\n')
        print('SEARCH')
        for k, v in sorted(d.items()):
            print(k, v)
        print()
        print('MATCHES:', len(matches))
        for m in matches:
            for k, v in sorted(m.items()):
                print(k, v)
            print()


    

    






SEARCH
accession ENCSR584XHX
alternate_accessions []
assay_title microRNA-seq
biosample_summary cerebellum male embryo (20 weeks)
biosample_term_id UBERON:0002037
biosample_term_name cerebellum
biosample_type tissue
lab joseph-costello
target 

MATCHES: 1
accession ENCSR584XHX
alternate_accessions []
assay_title microRNA-seq
biosample_summary cerebellum male embryo (20 weeks)
biosample_term_id UBERON:0002037
biosample_term_name cerebellum
biosample_type tissue
lab joseph-costello
target 




SEARCH
accession ENCSR181NUJ
alternate_accessions []
assay_title MRE-seq
biosample_summary germinal matrix male embryo (20 weeks)
biosample_term_id NTR:0001407
biosample_term_name germinal matrix
biosample_type tissue
lab joseph-costello
target 

MATCHES: 1
accession ENCSR181NUJ
alternate_accessions []
assay_title MRE-seq
biosample_summary germinal matrix male embryo (20 weeks)
biosample_term_id NTR:0001407
biosample_term_name germinal matrix
biosample_type tissue
lab joseph-costello
target 




SEARCH
accession ENCSR470JHE
alternate_accessions []
assay_title polyA mRNA RNA-seq
biosample_summary cerebellum male embryo (20 weeks)
biosample_term_id UBERON:0002037
biosample_term_name cerebellum
biosample_type tissue
lab joseph-costello
target 

MATCHES: 1
accession ENCSR470JHE
alternate_accessions []
assay_title polyA mRNA RNA-seq
biosample_summary cerebellum male embryo (20 weeks)
biosample_term_id UBERON:0002037
biosample_term_name cerebellum
biosample_type tissue
lab joseph-costello
target 




SEARCH
accession ENCSR374BVM
alternate_accessions []
assay_title WGBS
biosample_summary germinal matrix male embryo (20 weeks)
biosample_term_id NTR:0001407
biosample_term_name germinal matrix
biosample_type tissue
lab joseph-costello
target 

MATCHES: 1
accession ENCSR374BVM
alternate_accessions []
assay_title WGBS
biosample_summary germinal matrix male embryo (20 weeks)
biosample_term_id NTR:0001407
biosample_term_name germinal matrix
biosample_type tissue
lab joseph-costello
target 

In [554]:

    

base_url = 'https://encd-3608-remove-proposed-9653f4422-keenan.demo.encodedcc.org'
update = False

# Must update:
# rep number in EXP_B replicates
# EXP_B.status to replaced
# EXP_A.alternate_accession.append(EXP_B)
# original_files.dataset in EXP_B to point to EXP_A
# dbxrefs in EXP_A to be list(set(EXP_A.dbxrefs, EXP_B.dbxrefs))
# aliases in EXP_A to be list(set(EXP_A.aliases, EXP_B.aliases))
# remove aliases from EXP_B.
# check for unique documents in EXP_B
# add submitter_comment to EXP_A explaining the merge

for z, pair in enumerate(unique_pairs):
    # {'accession': 'UUID', 'field': 'value'} to update.
    patch_set = []
    a, b = pair[0], pair[1]
    pair = get_pair_data([a, b])
    base_exp, merge_exp = parse_pair(pair)
    # Calculate new replicate numbers and point to base experiment.
    patch_set.extend(rep_patch(base_exp, merge_exp))
    # Replace EXP_B.
    patch_set.append(({'accession': merge_exp['uuid'],
                       'status': 'replaced'},
                      'REPLACE'))
    # Add EXP_B to EXP_A alternate_accessions.
    patch_set.append(({'accession': base_exp['accession'],
                       'alternate_accessions': [a for a in
                                                grab.chain(get_merge_info(base_exp)['alternate_accessions'],
                                                      [merge_exp['accession']])]},
                      'ALTERNATE ACCESSIONS'))
    # Update dataset in orignal files of EXP_B.
    patch_set.extend(original_files_patch(base_exp, merge_exp))
    # Update dbxrefs in EXP_A.
    patch_set.append(({'accession': base_exp['accession'],
                       'dbxrefs': values_from_both('dbxrefs')},
                       'UPDATE DBXREFS'))
    # Remove aliases from EXP_B.
    patch_set.append(({'accession': merge_exp['uuid'],
                       'aliases': []},
                      'CLEAR ALIASES'))
    # Update aliases in EXP_A.
    patch_set.append(({'accession': base_exp['accession'],
                       'aliases': values_from_both('aliases')},
                      'UPDATE ALIASES'))
    # Update documents in EXP_A.
    patch_set.append(({'accession': base_exp['accession'],
                       'documents': values_from_both('documents')},
                      'UPDATE DOCUMENTS'))
    comment = 'Experiment {} merged into {}.'.format(merge_exp['uuid'],
                                                     base_exp['accession'])
    patch_set.append(({'accession': base_exp['accession'],
                       'submitter_comment': comment},
                      'ADD COMMENT'))
    
    print('*PAIR {}*\n-----------'.format(z + 1))
    print('Base:', base_exp['accession'],
          '({})\n'.format(base_exp['uuid']),
          json.dumps(get_merge_info(base_exp), indent=4, sort_keys=True),
          '\n\nMerge:', merge_exp['accession'],
          '({})\n'.format(merge_exp['uuid']),
          json.dumps(get_merge_info(merge_exp), indent=4, sort_keys=True), '\n')
    for i, x in enumerate(patch_set):
        print(x[1])
        for k, v in sorted(x[0].items()):
            print('{}:'.format(k), v)
        print()
    if update:
        print('MAKE PATCH')
        make_patch(patch_set, base_url)
    print()


    

    




*PAIR 1*
-----------
Base: ENCSR575ICR (b1453892-1831-4bb7-b45b-b3d6fb6f84a8)
 {
    "aliases": [
        "roadmap-epigenomics:H3K4me3 Brain-Germinal Matrix_Jul-20-2011_25805"
    ],
    "alternate_accessions": [],
    "dbxrefs": [
        "GEO:GSM806940"
    ],
    "documents": [],
    "original_files": [
        "/files/ENCFF881PIP/",
        "/files/ENCFF230KFJ/",
        "/files/ENCFF514QDL/",
        "/files/ENCFF507SDF/",
        "/files/ENCFF065UYM/",
        "/files/SRR2172596/"
    ],
    "reps": [
        [
            "81bc941b-759e-4dba-a1c1-a04cf55ace68",
            "/experiments/ENCSR575ICR/",
            1,
            1
        ]
    ]
} 

Merge: ENCSR528QDT (b10a7e77-4d81-49c9-aa90-102ecc0aab47)
 {
    "aliases": [
        "roadmap-epigenomics:H3K4me3 Germinal Matrix_Apr-07-2011_98586"
    ],
    "alternate_accessions": [],
    "dbxrefs": [
        "GEO:GSM706999"
    ],
    "documents": [],
    "original_files": [
        "/files/SRR2172571/"
    ],
    "reps": [
        [
            "309577e3-59ee-42de-aaca-5032a52a01a6",
            "/experiments/ENCSR528QDT/",
            1,
            1
        ]
    ]
} 

REPLICATE
biological_replicate_number: 2
experiment: /experiments/ENCSR575ICR/
technical_replicate_number: 1
uuid: 309577e3-59ee-42de-aaca-5032a52a01a6

REPLACE
accession: b10a7e77-4d81-49c9-aa90-102ecc0aab47
status: replaced

ALTERNATE ACCESSIONS
accession: ENCSR575ICR
alternate_accessions: ['ENCSR528QDT']

ORIGINAL FILE
accession: /files/SRR2172571/
dataset: /experiments/ENCSR575ICR/

UPDATE DBXREFS
accession: ENCSR575ICR
dbxrefs: ['GEO:GSM706999', 'GEO:GSM806940']

CLEAR ALIASES
accession: b10a7e77-4d81-49c9-aa90-102ecc0aab47
aliases: []

UPDATE ALIASES
accession: ENCSR575ICR
aliases: ['roadmap-epigenomics:H3K4me3 Brain-Germinal Matrix_Jul-20-2011_25805', 'roadmap-epigenomics:H3K4me3 Germinal Matrix_Apr-07-2011_98586']

UPDATE DOCUMENTS
accession: ENCSR575ICR
documents: []

ADD COMMENT
accession: ENCSR575ICR
submitter_comment: Experiment b10a7e77-4d81-49c9-aa90-102ecc0aab47 merged into ENCSR575ICR.


*PAIR 2*
-----------
Base: ENCSR684NQL (0970f127-bac2-4588-b952-e3409d7e72e2)
 {
    "aliases": [
        "roadmap-epigenomics:Bisulfite-Seq analysis of brain (cerebellum) tissue from HuFGM02 (A27336)_Jun-05-2014_37212"
    ],
    "alternate_accessions": [],
    "dbxrefs": [
        "GEO:GSM1582520"
    ],
    "documents": [],
    "original_files": [
        "/files/SRR2126659/",
        "/files/SRR2126658/",
        "/files/SRR2126657/",
        "/files/SRR2126656/"
    ],
    "reps": [
        [
            "19bfff75-3a8d-4907-848c-51ae5936beac",
            "/experiments/ENCSR684NQL/",
            1,
            1
        ]
    ]
} 

Merge: ENCSR696SOJ (33c73d49-d643-4ac9-b493-823807b7c4d8)
 {
    "aliases": [
        "roadmap-epigenomics:Bisulfite-Seq analysis of brain (cerebellum) tissue from HuFGM01 (A27335)_Jun-05-2014_33497"
    ],
    "alternate_accessions": [],
    "dbxrefs": [
        "GEO:GSM1582513"
    ],
    "documents": [],
    "original_files": [
        "/files/SRR2126654/",
        "/files/SRR2126655/",
        "/files/SRR2126653/",
        "/files/SRR2126652/"
    ],
    "reps": [
        [
            "45d3d544-d1ee-4dc6-a218-bb8b5f65fce4",
            "/experiments/ENCSR696SOJ/",
            1,
            1
        ]
    ]
} 

REPLICATE
biological_replicate_number: 2
experiment: /experiments/ENCSR684NQL/
technical_replicate_number: 1
uuid: 45d3d544-d1ee-4dc6-a218-bb8b5f65fce4

REPLACE
accession: 33c73d49-d643-4ac9-b493-823807b7c4d8
status: replaced

ALTERNATE ACCESSIONS
accession: ENCSR684NQL
alternate_accessions: ['ENCSR696SOJ']

ORIGINAL FILE
accession: /files/SRR2126654/
dataset: /experiments/ENCSR684NQL/

ORIGINAL FILE
accession: /files/SRR2126655/
dataset: /experiments/ENCSR684NQL/

ORIGINAL FILE
accession: /files/SRR2126653/
dataset: /experiments/ENCSR684NQL/

ORIGINAL FILE
accession: /files/SRR2126652/
dataset: /experiments/ENCSR684NQL/

UPDATE DBXREFS
accession: ENCSR684NQL
dbxrefs: ['GEO:GSM1582520', 'GEO:GSM1582513']

CLEAR ALIASES
accession: 33c73d49-d643-4ac9-b493-823807b7c4d8
aliases: []

UPDATE ALIASES
accession: ENCSR684NQL
aliases: ['roadmap-epigenomics:Bisulfite-Seq analysis of brain (cerebellum) tissue from HuFGM01 (A27335)_Jun-05-2014_33497', 'roadmap-epigenomics:Bisulfite-Seq analysis of brain (cerebellum) tissue from HuFGM02 (A27336)_Jun-05-2014_37212']

UPDATE DOCUMENTS
accession: ENCSR684NQL
documents: []

ADD COMMENT
accession: ENCSR684NQL
submitter_comment: Experiment 33c73d49-d643-4ac9-b493-823807b7c4d8 merged into ENCSR684NQL.


*PAIR 3*
-----------
Base: ENCSR534RNS (9cead9b8-7355-4107-8b8e-e553dccb9f6b)
 {
    "aliases": [],
    "alternate_accessions": [],
    "dbxrefs": [
        "GEO:GSM959123"
    ],
    "documents": [],
    "original_files": [
        "/files/SRR2126713/"
    ],
    "reps": [
        [
            "443faca8-d1bb-45f8-ac65-1d4fe2ec646e",
            "/experiments/ENCSR534RNS/",
            1,
            1
        ]
    ]
} 

Merge: ENCSR676CFI (d9141c3e-2a56-4bd6-af29-8e628a05865a)
 {
    "aliases": [
        "roadmap-epigenomics:MeDIP-Seq Brain Germinal Matrix_Apr-05-2011_26772"
    ],
    "alternate_accessions": [],
    "dbxrefs": [
        "GEO:GSM707023"
    ],
    "documents": [],
    "original_files": [
        "/files/SRR2172920/",
        "/files/SRR2172919/",
        "/files/SRR2172921/"
    ],
    "reps": [
        [
            "d1f5548f-8152-4b76-b3ce-e5d8daf1ead7",
            "/experiments/ENCSR676CFI/",
            1,
            3
        ]
    ]
} 

REPLICATE
biological_replicate_number: 2
experiment: /experiments/ENCSR534RNS/
technical_replicate_number: 1
uuid: d1f5548f-8152-4b76-b3ce-e5d8daf1ead7

REPLACE
accession: d9141c3e-2a56-4bd6-af29-8e628a05865a
status: replaced

ALTERNATE ACCESSIONS
accession: ENCSR534RNS
alternate_accessions: ['ENCSR676CFI']

ORIGINAL FILE
accession: /files/SRR2172920/
dataset: /experiments/ENCSR534RNS/

ORIGINAL FILE
accession: /files/SRR2172919/
dataset: /experiments/ENCSR534RNS/

ORIGINAL FILE
accession: /files/SRR2172921/
dataset: /experiments/ENCSR534RNS/

UPDATE DBXREFS
accession: ENCSR534RNS
dbxrefs: ['GEO:GSM707023', 'GEO:GSM959123']

CLEAR ALIASES
accession: d9141c3e-2a56-4bd6-af29-8e628a05865a
aliases: []

UPDATE ALIASES
accession: ENCSR534RNS
aliases: ['roadmap-epigenomics:MeDIP-Seq Brain Germinal Matrix_Apr-05-2011_26772']

UPDATE DOCUMENTS
accession: ENCSR534RNS
documents: []

ADD COMMENT
accession: ENCSR534RNS
submitter_comment: Experiment d9141c3e-2a56-4bd6-af29-8e628a05865a merged into ENCSR534RNS.


*PAIR 4*
-----------
Base: ENCSR850JSG (20736168-7f7e-48ba-88bd-85b8ed35c45f)
 {
    "aliases": [
        "roadmap-epigenomics:HuFGM01-germinal matrix-Control"
    ],
    "alternate_accessions": [],
    "dbxrefs": [],
    "documents": [],
    "original_files": [
        "/files/SRR2172575/"
    ],
    "reps": [
        [
            "7928492a-956c-48db-92d0-6b832287b72c",
            "/experiments/ENCSR850JSG/",
            1,
            1
        ]
    ]
} 

Merge: ENCSR517EEQ (42383f9b-25ca-4461-848a-85b6bdda25dd)
 {
    "aliases": [
        "roadmap-epigenomics:Input Brain-Germinal Matrix_Jul-20-2011_46866"
    ],
    "alternate_accessions": [],
    "dbxrefs": [
        "GEO:GSM806947"
    ],
    "documents": [],
    "original_files": [
        "/files/ENCFF066CHK/",
        "/files/SRR2172603/",
        "/files/SRR2172602/"
    ],
    "reps": [
        [
            "eb250f8c-31ca-4822-8729-8618ddde1331",
            "/experiments/ENCSR517EEQ/",
            1,
            1
        ]
    ]
} 

REPLICATE
biological_replicate_number: 2
experiment: /experiments/ENCSR850JSG/
technical_replicate_number: 1
uuid: eb250f8c-31ca-4822-8729-8618ddde1331

REPLACE
accession: 42383f9b-25ca-4461-848a-85b6bdda25dd
status: replaced

ALTERNATE ACCESSIONS
accession: ENCSR850JSG
alternate_accessions: ['ENCSR517EEQ']

ORIGINAL FILE
accession: /files/ENCFF066CHK/
dataset: /experiments/ENCSR850JSG/

ORIGINAL FILE
accession: /files/SRR2172603/
dataset: /experiments/ENCSR850JSG/

ORIGINAL FILE
accession: /files/SRR2172602/
dataset: /experiments/ENCSR850JSG/

UPDATE DBXREFS
accession: ENCSR850JSG
dbxrefs: ['GEO:GSM806947']

CLEAR ALIASES
accession: 42383f9b-25ca-4461-848a-85b6bdda25dd
aliases: []

UPDATE ALIASES
accession: ENCSR850JSG
aliases: ['roadmap-epigenomics:HuFGM01-germinal matrix-Control', 'roadmap-epigenomics:Input Brain-Germinal Matrix_Jul-20-2011_46866']

UPDATE DOCUMENTS
accession: ENCSR850JSG
documents: []

ADD COMMENT
accession: ENCSR850JSG
submitter_comment: Experiment 42383f9b-25ca-4461-848a-85b6bdda25dd merged into ENCSR850JSG.


*PAIR 5*
-----------
Base: ENCSR064VLH (ea69a462-9481-4057-adc4-487c5329fcdd)
 {
    "aliases": [
        "roadmap-epigenomics:H3K4me1 Brain-Germinal Matrix_Jul-20-2011_33353"
    ],
    "alternate_accessions": [],
    "dbxrefs": [
        "GEO:GSM806939"
    ],
    "documents": [],
    "original_files": [
        "/files/ENCFF481OXJ/",
        "/files/ENCFF755JZG/",
        "/files/ENCFF481VWM/",
        "/files/ENCFF475NDU/",
        "/files/ENCFF992QBH/",
        "/files/SRR2172595/"
    ],
    "reps": [
        [
            "e6446390-decb-4150-ad92-6763844e339b",
            "/experiments/ENCSR064VLH/",
            1,
            1
        ]
    ]
} 

Merge: ENCSR764XUL (f424b50a-6b7c-41ca-9450-42bb0fbf8cec)
 {
    "aliases": [
        "roadmap-epigenomics:H3K4me1 Brain-Germinal Matrix_Oct-13-2011_71796"
    ],
    "alternate_accessions": [],
    "dbxrefs": [
        "GEO:GSM817228"
    ],
    "documents": [],
    "original_files": [
        "/files/SRR2172609/",
        "/files/SRR2172610/"
    ],
    "reps": [
        [
            "b0e2474c-d8a1-42e5-8235-f27b689d61f6",
            "/experiments/ENCSR764XUL/",
            1,
            2
        ]
    ]
} 

REPLICATE
biological_replicate_number: 2
experiment: /experiments/ENCSR064VLH/
technical_replicate_number: 1
uuid: b0e2474c-d8a1-42e5-8235-f27b689d61f6

REPLACE
accession: f424b50a-6b7c-41ca-9450-42bb0fbf8cec
status: replaced

ALTERNATE ACCESSIONS
accession: ENCSR064VLH
alternate_accessions: ['ENCSR764XUL']

ORIGINAL FILE
accession: /files/SRR2172609/
dataset: /experiments/ENCSR064VLH/

ORIGINAL FILE
accession: /files/SRR2172610/
dataset: /experiments/ENCSR064VLH/

UPDATE DBXREFS
accession: ENCSR064VLH
dbxrefs: ['GEO:GSM817228', 'GEO:GSM806939']

CLEAR ALIASES
accession: f424b50a-6b7c-41ca-9450-42bb0fbf8cec
aliases: []

UPDATE ALIASES
accession: ENCSR064VLH
aliases: ['roadmap-epigenomics:H3K4me1 Brain-Germinal Matrix_Oct-13-2011_71796', 'roadmap-epigenomics:H3K4me1 Brain-Germinal Matrix_Jul-20-2011_33353']

UPDATE DOCUMENTS
accession: ENCSR064VLH
documents: []

ADD COMMENT
accession: ENCSR064VLH
submitter_comment: Experiment f424b50a-6b7c-41ca-9450-42bb0fbf8cec merged into ENCSR064VLH.


*PAIR 6*
-----------
Base: ENCSR690UYB (d246ffd0-7d77-47d8-b382-80437a9f2af7)
 {
    "aliases": [
        "roadmap-epigenomics:H3K36me3 Germinal Matrix_Apr-07-2011_67829"
    ],
    "alternate_accessions": [],
    "dbxrefs": [
        "GEO:GSM707002"
    ],
    "documents": [],
    "original_files": [
        "/files/SRR2172574/"
    ],
    "reps": [
        [
            "2a3dfea6-5cce-4eff-8a17-c3d10e6d00f5",
            "/experiments/ENCSR690UYB/",
            1,
            1
        ]
    ]
} 

Merge: ENCSR717BNA (555197fb-f9d9-44ae-83f3-8823b78d89b7)
 {
    "aliases": [
        "roadmap-epigenomics:H3K36me3 Brain-Germinal Matrix_Oct-13-2011_73569"
    ],
    "alternate_accessions": [],
    "dbxrefs": [
        "GEO:GSM817227"
    ],
    "documents": [],
    "original_files": [
        "/files/ENCFF258XTK/",
        "/files/ENCFF807HJC/",
        "/files/ENCFF432WPV/",
        "/files/ENCFF562HYQ/",
        "/files/ENCFF214JPF/",
        "/files/SRR2172601/",
        "/files/SRR2172600/"
    ],
    "reps": [
        [
            "a4c3f866-90c3-4317-bd98-17482e8ee394",
            "/experiments/ENCSR717BNA/",
            1,
            2
        ]
    ]
} 

REPLICATE
biological_replicate_number: 2
experiment: /experiments/ENCSR690UYB/
technical_replicate_number: 1
uuid: a4c3f866-90c3-4317-bd98-17482e8ee394

REPLACE
accession: 555197fb-f9d9-44ae-83f3-8823b78d89b7
status: replaced

ALTERNATE ACCESSIONS
accession: ENCSR690UYB
alternate_accessions: ['ENCSR717BNA']

ORIGINAL FILE
accession: /files/ENCFF258XTK/
dataset: /experiments/ENCSR690UYB/

ORIGINAL FILE
accession: /files/ENCFF807HJC/
dataset: /experiments/ENCSR690UYB/

ORIGINAL FILE
accession: /files/ENCFF432WPV/
dataset: /experiments/ENCSR690UYB/

ORIGINAL FILE
accession: /files/ENCFF562HYQ/
dataset: /experiments/ENCSR690UYB/

ORIGINAL FILE
accession: /files/ENCFF214JPF/
dataset: /experiments/ENCSR690UYB/

ORIGINAL FILE
accession: /files/SRR2172601/
dataset: /experiments/ENCSR690UYB/

ORIGINAL FILE
accession: /files/SRR2172600/
dataset: /experiments/ENCSR690UYB/

UPDATE DBXREFS
accession: ENCSR690UYB
dbxrefs: ['GEO:GSM817227', 'GEO:GSM707002']

CLEAR ALIASES
accession: 555197fb-f9d9-44ae-83f3-8823b78d89b7
aliases: []

UPDATE ALIASES
accession: ENCSR690UYB
aliases: ['roadmap-epigenomics:H3K36me3 Brain-Germinal Matrix_Oct-13-2011_73569', 'roadmap-epigenomics:H3K36me3 Germinal Matrix_Apr-07-2011_67829']

UPDATE DOCUMENTS
accession: ENCSR690UYB
documents: []

ADD COMMENT
accession: ENCSR690UYB
submitter_comment: Experiment 555197fb-f9d9-44ae-83f3-8823b78d89b7 merged into ENCSR690UYB.


*PAIR 7*
-----------
Base: ENCSR911WPA (7865912d-8b11-47d2-bcaa-05109da99f11)
 {
    "aliases": [
        "roadmap-epigenomics:H3K27me3 Germinal Matrix_Apr-07-2011_16134"
    ],
    "alternate_accessions": [],
    "dbxrefs": [
        "GEO:GSM707001"
    ],
    "documents": [],
    "original_files": [
        "/files/SRR2172573/"
    ],
    "reps": [
        [
            "cf6aad2d-6fbc-416d-a33d-67cb0e4b042b",
            "/experiments/ENCSR911WPA/",
            1,
            1
        ]
    ]
} 

Merge: ENCSR494OXB (e171351d-0a81-49fd-b2cd-e102db67c72d)
 {
    "aliases": [
        "roadmap-epigenomics:H3K27me3 Brain-Germinal Matrix_Oct-13-2011_61330"
    ],
    "alternate_accessions": [],
    "dbxrefs": [
        "GEO:GSM817226"
    ],
    "documents": [],
    "original_files": [
        "/files/ENCFF948ALR/",
        "/files/ENCFF229MOV/",
        "/files/ENCFF303PGJ/",
        "/files/ENCFF927VUM/",
        "/files/ENCFF509WOK/",
        "/files/SRR2172598/",
        "/files/SRR2172599/"
    ],
    "reps": [
        [
            "e4ddba24-12b5-4d4c-bbd3-743e1183a0a1",
            "/experiments/ENCSR494OXB/",
            1,
            2
        ]
    ]
} 

REPLICATE
biological_replicate_number: 2
experiment: /experiments/ENCSR911WPA/
technical_replicate_number: 1
uuid: e4ddba24-12b5-4d4c-bbd3-743e1183a0a1

REPLACE
accession: e171351d-0a81-49fd-b2cd-e102db67c72d
status: replaced

ALTERNATE ACCESSIONS
accession: ENCSR911WPA
alternate_accessions: ['ENCSR494OXB']

ORIGINAL FILE
accession: /files/ENCFF948ALR/
dataset: /experiments/ENCSR911WPA/

ORIGINAL FILE
accession: /files/ENCFF229MOV/
dataset: /experiments/ENCSR911WPA/

ORIGINAL FILE
accession: /files/ENCFF303PGJ/
dataset: /experiments/ENCSR911WPA/

ORIGINAL FILE
accession: /files/ENCFF927VUM/
dataset: /experiments/ENCSR911WPA/

ORIGINAL FILE
accession: /files/ENCFF509WOK/
dataset: /experiments/ENCSR911WPA/

ORIGINAL FILE
accession: /files/SRR2172598/
dataset: /experiments/ENCSR911WPA/

ORIGINAL FILE
accession: /files/SRR2172599/
dataset: /experiments/ENCSR911WPA/

UPDATE DBXREFS
accession: ENCSR911WPA
dbxrefs: ['GEO:GSM817226', 'GEO:GSM707001']

CLEAR ALIASES
accession: e171351d-0a81-49fd-b2cd-e102db67c72d
aliases: []

UPDATE ALIASES
accession: ENCSR911WPA
aliases: ['roadmap-epigenomics:H3K27me3 Germinal Matrix_Apr-07-2011_16134', 'roadmap-epigenomics:H3K27me3 Brain-Germinal Matrix_Oct-13-2011_61330']

UPDATE DOCUMENTS
accession: ENCSR911WPA
documents: []

ADD COMMENT
accession: ENCSR911WPA
submitter_comment: Experiment e171351d-0a81-49fd-b2cd-e102db67c72d merged into ENCSR911WPA.


*PAIR 8*
-----------
Base: ENCSR800JXT (5fdf89c4-0e50-43ef-852c-14b8a956d85a)
 {
    "aliases": [
        "roadmap-epigenomics:RNA-Seq polyA+ Brain-Germinal Matrix_May-19-2011_32929"
    ],
    "alternate_accessions": [],
    "dbxrefs": [
        "GEO:GSM751275"
    ],
    "documents": [],
    "original_files": [
        "/files/SRR2173241/"
    ],
    "reps": [
        [
            "b9140ef1-7b4f-4e08-bdb4-90fa4bbf3075",
            "/experiments/ENCSR800JXT/",
            1,
            1
        ]
    ]
} 

Merge: ENCSR969JYY (d0cbd74e-c401-4e84-b852-5722a2d74ef1)
 {
    "aliases": [
        "roadmap-epigenomics:RNA-Seq analysis of brain (germinal matrix) tissue from HuFGM02 (A21768)_Jun-05-2014_13911"
    ],
    "alternate_accessions": [],
    "dbxrefs": [
        "GEO:GSM1582473"
    ],
    "documents": [],
    "original_files": [
        "/files/SRR2173277/"
    ],
    "reps": [
        [
            "b8203d10-7c09-4a0f-b8d1-d58cf238510c",
            "/experiments/ENCSR969JYY/",
            1,
            1
        ]
    ]
} 

REPLICATE
biological_replicate_number: 2
experiment: /experiments/ENCSR800JXT/
technical_replicate_number: 1
uuid: b8203d10-7c09-4a0f-b8d1-d58cf238510c

REPLACE
accession: d0cbd74e-c401-4e84-b852-5722a2d74ef1
status: replaced

ALTERNATE ACCESSIONS
accession: ENCSR800JXT
alternate_accessions: ['ENCSR969JYY']

ORIGINAL FILE
accession: /files/SRR2173277/
dataset: /experiments/ENCSR800JXT/

UPDATE DBXREFS
accession: ENCSR800JXT
dbxrefs: ['GEO:GSM751275', 'GEO:GSM1582473']

CLEAR ALIASES
accession: d0cbd74e-c401-4e84-b852-5722a2d74ef1
aliases: []

UPDATE ALIASES
accession: ENCSR800JXT
aliases: ['roadmap-epigenomics:RNA-Seq analysis of brain (germinal matrix) tissue from HuFGM02 (A21768)_Jun-05-2014_13911', 'roadmap-epigenomics:RNA-Seq polyA+ Brain-Germinal Matrix_May-19-2011_32929']

UPDATE DOCUMENTS
accession: ENCSR800JXT
documents: []

ADD COMMENT
accession: ENCSR800JXT
submitter_comment: Experiment d0cbd74e-c401-4e84-b852-5722a2d74ef1 merged into ENCSR800JXT.


*PAIR 9*
-----------
Base: ENCSR736YYJ (2389bfff-b307-4a99-8e47-c5ed26f63049)
 {
    "aliases": [
        "roadmap-epigenomics:smRNA-Seq analysis of brain germinal matrix tissue from HuFGM02_Apr-16-2013_72710",
        "roadmap-epigenomics:smRNA-Seq Brain-Germinal Matrix_May-20-2011_81564"
    ],
    "alternate_accessions": [],
    "dbxrefs": [
        "GEO:GSM1127161",
        "GEO:GSM751284"
    ],
    "documents": [],
    "original_files": [
        "/files/SRR2173066/",
        "/files/SRR2173097/"
    ],
    "reps": [
        [
            "776ddf85-e0be-4bd5-bdf6-a491d21dd66d",
            "/experiments/ENCSR736YYJ/",
            1,
            1
        ],
        [
            "e5041a25-6e37-4c90-9b66-ada874198534",
            "/experiments/ENCSR736YYJ/",
            1,
            2
        ]
    ]
} 

Merge: ENCSR511NSE (c8687000-624c-4113-b624-7402c17cc6f0)
 {
    "aliases": [
        "roadmap-epigenomics:smRNA-Seq Brain-Germinal Matrix_May-20-2011_47820"
    ],
    "alternate_accessions": [],
    "dbxrefs": [
        "GEO:GSM751283"
    ],
    "documents": [],
    "original_files": [
        "/files/SRR2173056/"
    ],
    "reps": [
        [
            "3c6b5f4a-7d09-4bbf-9996-acbaafcc1b85",
            "/experiments/ENCSR511NSE/",
            1,
            1
        ]
    ]
} 

REPLICATE
biological_replicate_number: 2
experiment: /experiments/ENCSR736YYJ/
technical_replicate_number: 1
uuid: 3c6b5f4a-7d09-4bbf-9996-acbaafcc1b85

REPLACE
accession: c8687000-624c-4113-b624-7402c17cc6f0
status: replaced

ALTERNATE ACCESSIONS
accession: ENCSR736YYJ
alternate_accessions: ['ENCSR511NSE']

ORIGINAL FILE
accession: /files/SRR2173056/
dataset: /experiments/ENCSR736YYJ/

UPDATE DBXREFS
accession: ENCSR736YYJ
dbxrefs: ['GEO:GSM1127161', 'GEO:GSM751283', 'GEO:GSM751284']

CLEAR ALIASES
accession: c8687000-624c-4113-b624-7402c17cc6f0
aliases: []

UPDATE ALIASES
accession: ENCSR736YYJ
aliases: ['roadmap-epigenomics:smRNA-Seq analysis of brain germinal matrix tissue from HuFGM02_Apr-16-2013_72710', 'roadmap-epigenomics:smRNA-Seq Brain-Germinal Matrix_May-20-2011_81564', 'roadmap-epigenomics:smRNA-Seq Brain-Germinal Matrix_May-20-2011_47820']

UPDATE DOCUMENTS
accession: ENCSR736YYJ
documents: []

ADD COMMENT
accession: ENCSR736YYJ
submitter_comment: Experiment c8687000-624c-4113-b624-7402c17cc6f0 merged into ENCSR736YYJ.


*PAIR 10*
-----------
Base: ENCSR820ABR (271a81e6-6dc7-47bb-b984-11ca2d940e98)
 {
    "aliases": [
        "roadmap-epigenomics:H3K9me3 Brain-Germinal Matrix_Jul-20-2011_82397"
    ],
    "alternate_accessions": [],
    "dbxrefs": [
        "GEO:GSM806941"
    ],
    "documents": [],
    "original_files": [
        "/files/ENCFF439BHN/",
        "/files/ENCFF863KMY/",
        "/files/ENCFF890HMM/",
        "/files/ENCFF520ZSY/",
        "/files/ENCFF024JQK/",
        "/files/SRR2172597/"
    ],
    "reps": [
        [
            "72d8c117-6aeb-429e-b59a-2fbd85a7740f",
            "/experiments/ENCSR820ABR/",
            1,
            1
        ]
    ]
} 

Merge: ENCSR359JHU (4dec2c1d-ed5e-4585-8df7-afb42c88841f)
 {
    "aliases": [
        "roadmap-epigenomics:H3K9me3 Germinal Matrix_Apr-07-2011_34823"
    ],
    "alternate_accessions": [],
    "dbxrefs": [
        "GEO:GSM707000"
    ],
    "documents": [],
    "original_files": [
        "/files/SRR2172572/"
    ],
    "reps": [
        [
            "4cd0a235-5d17-42cb-94d5-c75398dc6f97",
            "/experiments/ENCSR359JHU/",
            1,
            1
        ]
    ]
} 

REPLICATE
biological_replicate_number: 2
experiment: /experiments/ENCSR820ABR/
technical_replicate_number: 1
uuid: 4cd0a235-5d17-42cb-94d5-c75398dc6f97

REPLACE
accession: 4dec2c1d-ed5e-4585-8df7-afb42c88841f
status: replaced

ALTERNATE ACCESSIONS
accession: ENCSR820ABR
alternate_accessions: ['ENCSR359JHU']

ORIGINAL FILE
accession: /files/SRR2172572/
dataset: /experiments/ENCSR820ABR/

UPDATE DBXREFS
accession: ENCSR820ABR
dbxrefs: ['GEO:GSM707000', 'GEO:GSM806941']

CLEAR ALIASES
accession: 4dec2c1d-ed5e-4585-8df7-afb42c88841f
aliases: []

UPDATE ALIASES
accession: ENCSR820ABR
aliases: ['roadmap-epigenomics:H3K9me3 Brain-Germinal Matrix_Jul-20-2011_82397', 'roadmap-epigenomics:H3K9me3 Germinal Matrix_Apr-07-2011_34823']

UPDATE DOCUMENTS
accession: ENCSR820ABR
documents: []

ADD COMMENT
accession: ENCSR820ABR
submitter_comment: Experiment 4dec2c1d-ed5e-4585-8df7-afb42c88841f merged into ENCSR820ABR.

In [ ]:

    




    

In [ ]:

    




    

In [ ]: