ensembl_rest.conf.default

# This is the default configuration for Ensembl REST applications. Take your own copy
# and make it available to Catalyst via the ENSEMBL_REST_CONFIG or CATALYST_CONFIG ENV vars.


name = EnsEMBL::REST
default_view = HTML

site_name = Ensembl Rest API
service_name = Ensembl REST API
service_logo = /static/img/e-ensembl.png
service_parent_url = http://www.ensembl.org
wiki_url = http://github.com/Ensembl/ensembl-rest/wiki
copyright_footer = <a href='http://www.sanger.ac.uk'>WTSI</a> &amp; <a href='http://www.ebi.ac.uk'>EBI</a>

jsonp=1

<Model::Registry>
  ###### Database settings. Use if you want to connect to a single database instance. Common options are given below
  
  host = ensembldb.ensembl.org
  port = 3306
  user = anonymous
  
  # host = mysql.ebi.ac.uk
  # port = 4157
  # user = anonymous
 
  version = 88
  verbose = 0
  
  ###### Registry file settings
  
  # The file to use as a registry file passed into Bio::EnsEMBL::Registry::load_all()
  # file = reg.pm

  ###### Bio::EnsEMBL::LookUp settings. Used for the bacteira databases provided by Ensembl Genomes

  # Load lookup from a local file
  # lookup_file = file.json
  
  # Load lookup from a remote URL. Most common option
  # lookup_url = http://bacteria.ensembl.org/registry.json
  
  # Store the local loookup cache in a location other than the default (lookup_cache.json)
  # lookup_cache_file = lookup_cache.json
  
  # Turn off the local lookup cache storage.
  # lookup_no_cache = 1

  # Turns on per-process connection sharing; experimental feature but is stable. 
  # Results in 1 connection per db per process rather than 1 connection per DBAdaptor instance per process
  connection_sharing = 1

  # Control the reconnection timeout (example is set to 10 mintues in ms). Only works when connection_sharing is on
  reconnect_interval = 600000

  # Control if we close DB connections down once finished with them. If you are not using the 
  # connection_sharing it is recommened to turn this on to avoid DOS attacks from your web processes
  disconnect_if_idle = 0

  # Control if we attempt pings and re-connections before queries. Useful for long running connections
  # if you are using connection_sharing
  reconnect_when_lost = 1

  # Set to control internal Ensembl API caching. Turn this off if your application is persistent (internal
  # caches are not shared, will rarely hit and increase your PSGI processes memory footprint)
  no_caching = 1

  # Trigger a preload of the registry the moment the Model::Registry object is contrstructed. Otherwise we
  # wait until the 1st request for an adaptor comes in. Use in conjunction with pre-fork PSGI deployments
  # to stop registry reload issues
  preload = 0 
  
  # Location of HDF5/SQLite DBs if EQTL endpoint is used
  # <eqtl_dbs>
  #   species = /path/to/hdf5 db
  # </eqtl_dbs>
  
</Model::Registry>

<Model::Lookup>
  # Model to use for ID lookups. Currently defaults to the DatabaseIDLookup which can be stable_ids schema
  # or a simple DBAdaptor loop lookup
  # lookup_model = DatabaseIDLookup
  # Disable completely long lookups
  # no_long_lookup = 1
</Model::Lookup>

<Model::Documentation>
  #Must be an array reference; if you specify only 1 then surround with [] brackets; if you specify more then remove them
  paths=[root/documentation]
  #How long examples stay in the backend caches before being expired; default is 1hr in seconds. 
  #Expire depends on the type of CHI cache configured in Plugin::Cache section
  # example_expire_time=3600
 
  # compara and ensembl genomes end-points had to be taken down for grch37 for e100 as part of removal of non-human resources
  # so maintain and replace a different conf file for documentation
  # change in response object/removal of actual end-points to be handled from haproxy/load balancer
  # removing/commenting this section will lead to processing of both conf files and 
  # use of merged values if keys overlap between the two conf files
  # meant mainly for deployment and to be enabled in conf files under rest_private repo
  # for grch38 deployment, compara_grch37.conf = compara.conf
  # for grch37 deployment, compara.conf = compara_grch37.conf
  <conf_replacements>
    compara_grch37.conf=compara.conf
    info_grch37.conf=info.conf
  </conf_replacements>

  #Used to control the parameters used in examples. Please edit as you see fit for your infrastructure
  <replacements>
    gene_stable_id=ENSG00000157764
    gene_stable_id_2=ENSG00000248378
    gene_stable_id_3=ENSG00000122435
    gene_stable_id_4=ENSG00000161526
    gene_stable_id_5=ENSG00000009950
    transcript_stable_id=ENST00000288602
    transcript_stable_id_2=ENST00000513398
    exon_stable_id=ENSE00001154485
    translation_stable_id=ENSP00000288602

    vcf=21  26960070  rs116645811 G A . . .
    vcf2=21  26965148  rs1135638 G A . . .
    
    gene_symbol=BRCA2
    gene_symbol2=BRAF
    gene_symbol3=TRMT13
    gene_symbol4=SAP30BP
    gene_symbol5=MLXIPL
    gene_symbol_db=HGNC
    gene_symbol_compara37=CNP
    transcript_symbol_db=PDB
    
    prediction_transcript_stable_id=GENSCAN00000000001
    other_features_transcript_stable_id=CCDS5863.1
    
    sequence_region_name=X
    sequence_region=X:1000000..1000100:1
    sequence_region_negative=X:1000000..1000100:-1
    sequence_region_strandless=X:1000000..1000100
    contig_sequence_region=ABBA01004489.1:1..100
    contig_coord_system=seqlevel
    
    species=homo_sapiens
    species_common=human
    
    taxon=9606
    taxon_name=Homo sapiens
    taxon_nameish=Homo%25
    target_taxon=10090
    target_ancestral_taxon=9526
    target_species=cow
    
    ontology=GO
    ontology_term_id=GO:0005667
    ontology_term_name=transcription factor complex
    
    compara=vertebrates
    compara_method=EPO
    compara_method_type=GenomicAlign
    compara_hom_format=full
    compara_hom_type=all
    compara_aligned=1
    compara_sequence=protein
    compara_cigar_line=1
    compara_species_set_group=mammals
    compara_compact=1

    dbnsfp_readme=https://drive.google.com/file/d/1VINShZQYN63HvigJA_SiuOYIk8TWl5Fh/view   
 
    genetree_stable_id=ENSGT00390000003602
    compara_gene_stable_id=ENSG00000173786
    family_stable_id=PTHR15573
    
    from_coord_system=GRCh37
    to_coord_system=GRCh38
    
    cdna_coordinates=100..300
    cds_coordinates=1..1000
    translation_coordinates=100..300

    regulation_id=ENSR00000060894

    phenotype_region=9:22125500-22136000

    variation_region=9:22125503-22125502:1
    variation_allele=C
    variation_region_two=1:6524705:6524705
    variation_allele_two=T
    variation_region_three=7:100318423-100321323:1
    variation_allele_three=DUP
    
    variation_id=rs56116432
    variation_id_two=COSM476

    variation_id_three=rs1042779
    variation_id_four=rs699
    variation_id1=rs6792369
    variation_id2=rs1042779

    variation_pmid=26318936
    variation_pmcid=PMC5002951

    population_name=EUROPE

    ld_population_name=1000GENOMES:phase_3:KHV
    r2=0.85
    d_prime=1.0
    window_size=500
    ld_sequence_region=6:25837556..25843455
    
    vep_hgvs=AGT:c.803T>C
    vep_hgvs_two=9:g.22125504G>C
    vep_hgvs_three=ENST00000003084:c.1431_1433delTTC
    vep_spdi=NC_000023.11:284252:C:G
    vep_hgvs_four=ENSP00000401091.1:p.Tyr124Cys

    genomic_alignment_species=taeniopygia_guttata
    genomic_alignment_region=2:106040000-106040050:1
    genomic_alignment_group=sauropsids
    genomic_alignment_pw_method=LASTZ_NET
    genomic_alignment_species2=gallus_gallus
    genomic_alignment_pw_region=2:106041430-106041480:1

    info_division=EnsemblVertebrates

    biotype_name=protein_coding
    biotype_group=coding
    biotype_ot=gene

    # from eg...
    genome_name=nanoarchaeum_equitans_kin4_m
    division_name=EnsemblPlants
    accession=U00096
    assembly_id=GCA_000005005.6
  </replacements>
</Model::Documentation>

<Controller::Archive>
  max_post_size = 1000
</Controller::Archive>

<Controller::Lookup>
  max_post_size = 1000
</Controller::Lookup>

<Controller::Taxonomy>
  # specify the registry alias for the database containing ncbi_taxa_node tables (normally a compara schema)
  # taxonomy = plants
</Controller::Taxonomy>

<Controller::Ontology>
  # specify the registry alias for the database containing ontology tables (normally called ontology)
  # ontology = ontology
</Controller::Ontology>

<Controller::Sequence>
  # Set to limit the maximum allowed size of sequence to return from the service. 
  # This will impact on memory footprint so tread carefully
  max_slice_length = 1e7
  max_post_size = 50
</Controller::Sequence>

<Controller::Overlap>
  # Set to limit the maximum allowed size of feature slices to return from the service. 
  # This will impact on memory footprint so tread carefully
  max_slice_length = 5e6
</Controller::Overlap>

<Controller::Homology>
  # Sets the default compara to use when finding the best compara fails. Defaults to multi
  # default_compara=multi
</Controller::Homology>

<Controller::Regulatory>
  # Sets the default regulation to use when finding the best regulation fails. Defaults to multi
  # default_regulation=multi
</Controller::Regulatory>

<Controller::GenomicAlignment>
  # Sets the default compara to use when finding the best compara fails. Defaults to multi
  # default_compara=multi
  # Sets the base location of data-files (usually contains multi/hal_files/*.hal)
  # compara_base_dir_location = /path/to/data/
</Controller::GenomicAlignment>

<Controller::Variaton>
  max_post_size = 1000
</Controller::Variaton>

<Controller::VEP>
# Supply a fasta path for Human in order to allow VEP to work locally
  fasta             = Homo_sapiens.GRCh37.75.dna.toplevel.fa # path to Human toplevel fasta file
  dir               = # path to vep cache directory
# Default parameters for running vep
  cache_region_size = 1000000
  chunk_size        = 50000
  whole_genome      = 1
  compress          = gzip -dc
  terms             = SO
  cache             = 1
  failed            = 0
  core_type         = core
  quiet             = 1
  sift              = b
  polyphen          = b
  symbol            = 1
  regulatory        = 1
  biotype           = 1
  rest              = 1
  check_existing    = 1 # adds some performance penalty, mitigated by tabix-converting the cache (http://www.ensembl.org/info/docs/tools/vep/script/vep_cache.html#convert)
  fork              = 3
  max_post_size     = 1000
  warning_file      = STDERR # controls VEP logging, not Catalyst
  plugin_config     = # path to plugin config
  dir_plugins       = # path to VEP_plugins checkout
</Controller::VEP>


<View::GFF3>
  # Set the default source of a GFF3 record
  # default_source=.
</View::GFF3>

<View::HTML>
  # To configure any templates to your own needs provide new includes 
  # here and replace the template toolkit file. Pay attention to order 
  # (1st defined is 1st consulted)

  # INCLUDE_PATH __path_to(alternative/root)__
  INCLUDE_PATH __path_to(root)__
</View::HTML>

<Plugin::Cache>
  <backend>
    #Default 
    class = CHI
    driver = Memory
    global = 1
    # Memcache
    # driver = Memcached
    # namespace = endpoint_examples
    # servers = [127.0.0.1:11211]
    # debug = 0
    # <l1_cache>
    #   driver = Memory
    #   global = 1
    #   max_size = 126976
    # </l1_cache>
  </backend>
</Plugin::Cache>

<Model::ga4gh::callSet>
   ga_config = __path_to(ga_vcf_config.json)__
</Model::ga4gh::callSet>

<Model::ga4gh::variants>
   ga_config = __path_to(ga_vcf_config.json)__
</Model::ga4gh::variants>

<Model::ga4gh::variantSet>
   ga_config = __path_to(ga_vcf_config.json)__
</Model::ga4gh::variantSet>

<Model::Variation>
   use_vcf    = 1
   vcf_config = __path_to(vcf_config.json)__
</Model::Variation>

<Model::Compara>
  species_set_group = mammals
  method            = EPO
  no_branch_lengths = 0
  compact           = 1
  aligned           = 1
  cigar_line        = 1
  format            = full
  sequence          = protein
  type              = all
</Model::Compara>

<Model::LDFeatureContainer>
   use_vcf = 1
   vcf_config = __path_to(vcf_config.json)__
</Model::LDFeatureContainer>