Mercurial > repos > dvanzessen > vep_emc
diff dir_plugins/plugin_config.txt @ 3:49397129aec0 draft
Uploaded
| author | dvanzessen |
|---|---|
| date | Mon, 15 Jul 2019 05:20:39 -0400 |
| parents | e545d0a25ffe |
| children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/dir_plugins/plugin_config.txt Mon Jul 15 05:20:39 2019 -0400 @@ -0,0 +1,898 @@ +my $VEP_PLUGIN_CONFIG = { + "plugins" => [ + + ## PATHOGENICITY PREDICTIONS + ############################ + + # dbNSFP + # https://github.com/ensembl-variation/VEP_plugins/blob/master/dbNSFP.pm + # Requires tabix-indexed data file as first param + # Field names are listed below and rendered as a multi-selectable autocomplete text field + # Human, GRCh38 only (3.x), for GRCh37 use 2.9.x + { + "key" => "dbNSFP", + "label" => "dbNSFP", + "available" => 0, + "enabled" => 0, + "section" => "Pathogenicity predictions", + "helptip" => "dbNSFP provides pathogenicity predictions for missense variants from various algorithms", + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/dbNSFP.pm", + "requires_data" => 1, + "requires_install" => 1, + "params" => [ + #"/path/to/dbNSFP3.5a.txt.gz", + "@*" + ], + "species" => [ + "homo_sapiens" + ], + "form" => [ + { + "name" => "dbNSFP_fields", + "label" => "Fields to include", + "helptip" => "Fields to fetch from dbNSFP; hold down the Ctrl (Windows) / Command (Mac) button to select multiple options", + "value" => "", + 'type' => 'dropdown', + 'multiple' => 1, + 'style' => 'height:150px', + 'required' => 1, + 'notes' => 'Field descriptions in <a rel="external" href="https://drive.google.com/file/d/0B60wROKy6OqcNGJ2STJlMTJONk0/view">dbNSFP README</a>', + # "class" => "jquery-multiselect", + "values" => [ + # "chr", + # "pos(1-based)", + # "ref", + # "alt", + # "aaref", + # "aaalt", + # "rs_dbSNP150", + # "hg19_chr", + # "hg19_pos(1-based)", + # "hg18_chr", + # "hg18_pos(1-based)", + # "genename", + # "cds_strand", + # "refcodon", + # "codonpos", + "codon_degeneracy", + "Ancestral_allele", + "AltaiNeandertal", + "Denisova", + # "Ensembl_geneid", + # "Ensembl_transcriptid", + # "Ensembl_proteinid", + # "aapos", + # "SIFT_score", + # "SIFT_converted_rankscore", + # "SIFT_pred", + # "Uniprot_acc_Polyphen2", + # "Uniprot_id_Polyphen2", + # "Uniprot_aapos_Polyphen2", + # "Polyphen2_HDIV_score", + # "Polyphen2_HDIV_rankscore", + # "Polyphen2_HDIV_pred", + # "Polyphen2_HVAR_score", + # "Polyphen2_HVAR_rankscore", + # "Polyphen2_HVAR_pred", + "LRT_score", + "LRT_converted_rankscore", + "LRT_pred", + "LRT_Omega", + "MutationTaster_score", + "MutationTaster_converted_rankscore", + "MutationTaster_pred", + "MutationTaster_model", + "MutationTaster_AAE", + "MutationAssessor_UniprotID", + "MutationAssessor_variant", + "MutationAssessor_score", + "MutationAssessor_score_rankscore", + "MutationAssessor_pred", + "FATHMM_score", + "FATHMM_converted_rankscore", + "FATHMM_pred", + "PROVEAN_score", + "PROVEAN_converted_rankscore", + "PROVEAN_pred", + "Transcript_id_VEST3", + "Transcript_var_VEST3", + "VEST3_score", + "VEST3_rankscore", + "MetaSVM_score", + "MetaSVM_rankscore", + "MetaSVM_pred", + "MetaLR_score", + "MetaLR_rankscore", + "MetaLR_pred", + "Reliability_index", + "M-CAP_score", + "M-CAP_rankscore", + "M-CAP_pred", + "REVEL_score", + "REVEL_rankscore", + "MutPred_score", + "MutPred_rankscore", + "MutPred_protID", + "MutPred_AAchange", + "MutPred_Top5features", + "CADD_raw", + "CADD_raw_rankscore", + "CADD_phred", + "DANN_score", + "DANN_rankscore", + "fathmm-MKL_coding_score", + "fathmm-MKL_coding_rankscore", + "fathmm-MKL_coding_pred", + "fathmm-MKL_coding_group", + "Eigen_coding_or_noncoding", + "Eigen-raw", + "Eigen-phred", + "Eigen-PC-raw", + "Eigen-PC-phred", + "Eigen-PC-raw_rankscore", + "GenoCanyon_score", + "GenoCanyon_score_rankscore", + "integrated_fitCons_score", + "integrated_fitCons_score_rankscore", + "integrated_confidence_value", + "GM12878_fitCons_score", + "GM12878_fitCons_score_rankscore", + "GM12878_confidence_value", + "H1-hESC_fitCons_score", + "H1-hESC_fitCons_score_rankscore", + "H1-hESC_confidence_value", + "HUVEC_fitCons_score", + "HUVEC_fitCons_score_rankscore", + "HUVEC_confidence_value", + "GERP++_NR", + "GERP++_RS", + "GERP++_RS_rankscore", + "phyloP100way_vertebrate", + "phyloP100way_vertebrate_rankscore", + "phyloP20way_mammalian", + "phyloP20way_mammalian_rankscore", + "phastCons100way_vertebrate", + "phastCons100way_vertebrate_rankscore", + "phastCons20way_mammalian", + "phastCons20way_mammalian_rankscore", + "SiPhy_29way_pi", + "SiPhy_29way_logOdds", + "SiPhy_29way_logOdds_rankscore", + "1000Gp3_AC", + "1000Gp3_AF", + "1000Gp3_AFR_AC", + "1000Gp3_AFR_AF", + "1000Gp3_EUR_AC", + "1000Gp3_EUR_AF", + "1000Gp3_AMR_AC", + "1000Gp3_AMR_AF", + "1000Gp3_EAS_AC", + "1000Gp3_EAS_AF", + "1000Gp3_SAS_AC", + "1000Gp3_SAS_AF", + "TWINSUK_AC", + "TWINSUK_AF", + "ALSPAC_AC", + "ALSPAC_AF", + "ESP6500_AA_AC", + "ESP6500_AA_AF", + "ESP6500_EA_AC", + "ESP6500_EA_AF", + "ExAC_AC", + "ExAC_AF", + "ExAC_Adj_AC", + "ExAC_Adj_AF", + "ExAC_AFR_AC", + "ExAC_AFR_AF", + "ExAC_AMR_AC", + "ExAC_AMR_AF", + "ExAC_EAS_AC", + "ExAC_EAS_AF", + "ExAC_FIN_AC", + "ExAC_FIN_AF", + "ExAC_NFE_AC", + "ExAC_NFE_AF", + "ExAC_SAS_AC", + "ExAC_SAS_AF", + "ExAC_nonTCGA_AC", + "ExAC_nonTCGA_AF", + "ExAC_nonTCGA_Adj_AC", + "ExAC_nonTCGA_Adj_AF", + "ExAC_nonTCGA_AFR_AC", + "ExAC_nonTCGA_AFR_AF", + "ExAC_nonTCGA_AMR_AC", + "ExAC_nonTCGA_AMR_AF", + "ExAC_nonTCGA_EAS_AC", + "ExAC_nonTCGA_EAS_AF", + "ExAC_nonTCGA_FIN_AC", + "ExAC_nonTCGA_FIN_AF", + "ExAC_nonTCGA_NFE_AC", + "ExAC_nonTCGA_NFE_AF", + "ExAC_nonTCGA_SAS_AC", + "ExAC_nonTCGA_SAS_AF", + "ExAC_nonpsych_AC", + "ExAC_nonpsych_AF", + "ExAC_nonpsych_Adj_AC", + "ExAC_nonpsych_Adj_AF", + "ExAC_nonpsych_AFR_AC", + "ExAC_nonpsych_AFR_AF", + "ExAC_nonpsych_AMR_AC", + "ExAC_nonpsych_AMR_AF", + "ExAC_nonpsych_EAS_AC", + "ExAC_nonpsych_EAS_AF", + "ExAC_nonpsych_FIN_AC", + "ExAC_nonpsych_FIN_AF", + "ExAC_nonpsych_NFE_AC", + "ExAC_nonpsych_NFE_AF", + "ExAC_nonpsych_SAS_AC", + "ExAC_nonpsych_SAS_AF", + "gnomAD_exomes_AC", + "gnomAD_exomes_AN", + "gnomAD_exomes_AF", + "gnomAD_exomes_AFR_AC", + "gnomAD_exomes_AFR_AN", + "gnomAD_exomes_AFR_AF", + "gnomAD_exomes_AMR_AC", + "gnomAD_exomes_AMR_AN", + "gnomAD_exomes_AMR_AF", + "gnomAD_exomes_ASJ_AC", + "gnomAD_exomes_ASJ_AN", + "gnomAD_exomes_ASJ_AF", + "gnomAD_exomes_EAS_AC", + "gnomAD_exomes_EAS_AN", + "gnomAD_exomes_EAS_AF", + "gnomAD_exomes_FIN_AC", + "gnomAD_exomes_FIN_AN", + "gnomAD_exomes_FIN_AF", + "gnomAD_exomes_NFE_AC", + "gnomAD_exomes_NFE_AN", + "gnomAD_exomes_NFE_AF", + "gnomAD_exomes_SAS_AC", + "gnomAD_exomes_SAS_AN", + "gnomAD_exomes_SAS_AF", + "gnomAD_exomes_OTH_AC", + "gnomAD_exomes_OTH_AN", + "gnomAD_exomes_OTH_AF", + "gnomAD_genomes_AC", + "gnomAD_genomes_AN", + "gnomAD_genomes_AF", + "gnomAD_genomes_AFR_AC", + "gnomAD_genomes_AFR_AN", + "gnomAD_genomes_AFR_AF", + "gnomAD_genomes_AMR_AC", + "gnomAD_genomes_AMR_AN", + "gnomAD_genomes_AMR_AF", + "gnomAD_genomes_ASJ_AC", + "gnomAD_genomes_ASJ_AN", + "gnomAD_genomes_ASJ_AF", + "gnomAD_genomes_EAS_AC", + "gnomAD_genomes_EAS_AN", + "gnomAD_genomes_EAS_AF", + "gnomAD_genomes_FIN_AC", + "gnomAD_genomes_FIN_AN", + "gnomAD_genomes_FIN_AF", + "gnomAD_genomes_NFE_AC", + "gnomAD_genomes_NFE_AN", + "gnomAD_genomes_NFE_AF", + "gnomAD_genomes_OTH_AC", + "gnomAD_genomes_OTH_AN", + "gnomAD_genomes_OTH_AF", + "clinvar_rs", + "clinvar_clnsig", + "clinvar_trait", + "clinvar_golden_stars", + "Interpro_domain", + "GTEx_V6p_gene", + "GTEx_V6p_tissue" + ], + }, + ] + }, + + # CADD + # https://github.com/ensembl-variation/VEP_plugins/blob/master/CADD.pm + # Requires tabix-indexed data file as first param + # No other parameters so no form required + # data file currently only available for GRCh37 + { + "key" => "CADD", + "label" => "CADD", + "available" => 0, + "enabled" => 0, + "section" => "Pathogenicity predictions", + "helptip" => "Combined Annotation Dependent Depletion (CADD) is a tool for scoring the deleteriousness of single nucleotide variants and insertion/deletion variants in the human genome. CADD integrates multiple annotations into one metric by contrasting variants that survived natural selection with simulated mutations.", + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/CADD.pm", + "requires_data" => 1, + "species" => [ + "homo_sapiens" + ], + "params" => [ + #"/path/to/whole_genome_SNVs.tsv.gz" + ] + }, + + # FATHMM-MKL + # https://github.com/ensembl-variation/VEP_plugins/blob/master/FATHMM_MKL.pm + # Requires tabix-indexed data file as first param + # No other parameters so no form required + # data file currently only available for GRCh37 + { + "key" => "FATHMM_MKL", + "label" => "FATHMM-MKL", + "available" => 0, + "enabled" => 0, + "section" => "Pathogenicity predictions", + "helptip" => "FATHMM-MKL predicts functional consequences of variants, both coding and non-coding.", + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/FATHMM_MKL.pm", + "requires_data" => 1, + "species" => [ + "homo_sapiens" + ], + "params" => [ + #"/path/to/fathmm-MKL_Current.tab.gz" + ] + }, + + # GWAVA + # https://www.sanger.ac.uk/sanger/StatGen_Gwava + # Requires tabix-indexed BED data file from ftp://ftp.sanger.ac.uk/pub/resources/software/gwava/v1.0/VEP_plugin/ + # data file currently only available for GRCh37 + { + "key" => "Gwava", + "label" => "GWAVA", + "available" => 0, + "enabled" => 0, + "section" => "Pathogenicity predictions", + "helptip" => "Retrieves precomputed Genome Wide Annotation of VAriants (GWAVA) scores for any variant that overlaps a known variant from the Ensembl variation database", + "plugin_url" => "ftp://ftp.sanger.ac.uk/pub/resources/software/gwava/v1.0/VEP_plugin/Gwava.pm", + "requires_data" => 1, + "species" => [ + "homo_sapiens" + ], + "params" => [ + "@*", + # "/path/to/gwava_scores.bed.gz" + ], + "form" => [ + { + "name" => "model", + "label" => "Model", + "type" => "dropdown", + "values" => [ + { "value" => "region", "caption" => "Region" }, + { "value" => "tss", "caption" => "TSS" }, + { "value" => "unmatched", "caption" => "Unmatched" } + ], + "value" => "region", + }, + ], + }, + + # Carol + # https://github.com/ensembl-variation/VEP_plugins/blob/master/Carol.pm + # Requires Math/CDF Perl module + { + "key" => "Carol", + "helptip" => "Calculates the Combined Annotation scoRing toOL (CAROL) score for a missense mutation based on the pre-calculated SIFT and PolyPhen scores", + "available" => 0, + "enabled" => 0, + "section" => "Pathogenicity predictions", + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/Carol.pm", + "requires_install" => 1, + "species" => [ + "homo_sapiens" + ], + }, + + # Condel + # https://github.com/ensembl-variation/VEP_plugins/blob/master/Condel.pm + # Requires path to config directory as first param + # config directory is checked out as part of VEP_plugins repo, as /[path]/VEP_plugins/config/Condel/config + # Within that dir, edit condel_SP.conf so that condel.dir points to /[path]/VEP_plugins/config/Condel + { + "key" => "Condel", + "helptip" => "Calculates the Consensus Deleteriousness (Condel) score for a missense mutation based on the pre-calculated SIFT and PolyPhen scores", + "available" => 0, + "enabled" => 0, + "section" => "Pathogenicity predictions", + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/Condel.pm", + "requires_install" => 1, + "species" => [ + "homo_sapiens" + ], + "params" => [ + # "/path/to/config/Condel/config", + "@*" + ], + "form" => [ + { + "name" => "score_pred", + "label" => "Score/prediction", + "type" => "dropdown", + "values" => [ + { "value" => "b", "caption" => "Prediction and score" }, + { "value" => "p", "caption" => "Prediction only" }, + { "value" => "s", "caption" => "Score only" } + ], + "value" => "b", + }, + ], + }, + + # LOFTEE + # See https://github.com/konradjk/loftee for details + { + "key" => "LoF", + "helptip" => "LOFTEE identifies LoF (loss-of-function) variation", + "available" => 0, + "enabled" => 0, + "section" => "Pathogenicity predictions", + "plugin_url" => "https://raw.githubusercontent.com/konradjk/loftee/master/LoF.pm", + "requires_data" => 1, + "requires_install" => 1, + "params" => [ + "@*" + ] + }, + + # LoFtool + # Requires LoFtool_scores.txt file as first param (available in VEP_plugins GitHub repo) + { + "key" => "LoFtool", + "helptip" => "Provides a per-gene rank of genic intolerance and consequent susceptibility to disease based on the ratio of Loss-of-function (LoF) to synonymous mutations in ExAC data", + "available" => 0, + "enabled" => 0, + "section" => "Pathogenicity predictions", + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/LoFtool.pm", + "requires_data" => 1, + "species" => [ + "homo_sapiens" + ], + "params" => [ + # "/path/to/LoFtool_scores.txt" + ] + }, + + # ExACpLI + # Requires ExACpLI_values.txt file as first param (available in VEP_plugins GitHub repo) + { + "key" => "ExACpLI", + "helptip" => "Provides a per-gene probability of being loss-of-function intolerant (pLI) from ExAC data", + "available" => 0, + "enabled" => 0, + "section" => "Pathogenicity predictions", + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/ExACpLI.pm", + "requires_data" => 1, + "species" => [ + "homo_sapiens" + ], + "params" => [ + # "/path/to/ExACpLI_values.txt" + ] + }, + + # MPC + # Requires fordist_constraint_official_mpc_values.txt.gz data file + { + "key" => "MPC", + "helptip" => "MPC is a missense deleteriousness metric based on the analysis of genic regions depleted of missense mutations in ExAC", + "available" => 0, + "enabled" => 0, + "section" => "Pathogenicity predictions", + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/MPC.pm", + "requires_data" => 1, + "species" => [ + "homo_sapiens" + ], + "params" => [ + # "/path/to/fordist_constraint_official_mpc_values.txt.gz" + ] + }, + + # MTR + # Requires mtrflatfile_1.0.txt.gz data file from ftp://mtr-viewer.mdhs.unimelb.edu.au/pub + { + "key" => "MTR", + "helptip" => "MTR scores quantify the amount of purifying selection acting specifically on missense variants in a given window of protein-coding sequence", + "available" => 0, + "enabled" => 0, + "section" => "Pathogenicity predictions", + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/MTR.pm", + "requires_data" => 1, + "species" => [ + "homo_sapiens" + ], + "params" => [ + # "/path/to/mtrflatfile_1.0.txt.gz" + ] + }, + + # REVEL + # Requires data file processed from revel_all_chromosomes.csv.zip + { + "key" => "REVEL", + "helptip" => "An ensemble method for predicting the pathogenicity of rare missense variants", + "available" => 0, + "enabled" => 0, + "section" => "Pathogenicity predictions", + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/REVEL.pm", + "requires_data" => 1, + "species" => [ + "homo_sapiens" + ], + "params" => [ + # "/path/to/revel_all_chromosomes.tsv.gz" + ] + }, + + + + ## SPLICING PREDICTIONS + ####################### + + # dbscSNV + { + "key" => "dbscSNV", + "label" => "dbscSNV", + "available" => 0, + "enabled" => 0, + "section" => "Splicing predictions", + "helptip" => "Retrieves data for splicing variants from a tabix-indexed dbscSNV file", + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/dbscSNV.pm", + "requires_data" => 1, + "requires_install" => 1, + "params" => [ + #"/path/to/dbscSNV1.1.txt.gz" + ], + "species" => [ + "homo_sapiens" + ], + }, + + # GeneSplicer + { + "key" => "GeneSplicer", + "label" => "GeneSplicer", + "helptip" => "Detects splice sites in genomic DNA", + "available" => 0, + "enabled" => 0, + "section" => "Splicing predictions", + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/GeneSplicer.pm", + "requires_install" => 1, + "species" => [ + "homo_sapiens" + ], + "params" => [ + #"/path/to/genesplicer/bin/linux/genesplicer", + #"/path/to/genesplicer/human", + "@*" + ] + }, + + # MaxEntScan + { + "key" => "MaxEntScan", + "label" => "MaxEntScan", + "helptip" => "Sequence motif and maximum entropy based splice site consensus predictions", + "available" => 0, + "enabled" => 0, + "section" => "Splicing predictions", + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/MaxEntScan.pm", + "requires_install" => 1, + "species" => [ + "homo_sapiens" + ], + "params" => [ + #"/path/to/maxentscan" + ] + }, + + # SpliceRegion + { + "key" => "SpliceRegion", + "label" => "SpliceRegion", + "helptip" => "More granular predictions of splicing effects", + "available" => 0, + "enabled" => 0, + "section" => "Splicing predictions", + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/SpliceRegion.pm", + }, + + + ## CONSERVATION + ############### + + # Blosum62 + { + "key" => "Blosum62", + "label" => "BLOSUM62", + "helptip" => "BLOSUM62 amino acid conservation score", + "available" => 0, + "enabled" => 0, + "section" => "Conservation", + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/Blosum62.pm", + }, + + # Conservation + # Use the following query to get valid species sets: + # + # SELECT group_concat(concat("_stt_", gd.name) SEPARATOR ' '), REPLACE(mlss.name, "Gerp Conservation Scores ", ""), sst.value + # FROM method_link ml, + # method_link_species_set mlss, + # genome_db gd, species_set ss, species_set_tag sst + # WHERE mlss.method_link_id = ml.method_link_id AND + # mlss.species_set_id = ss.species_set_id AND + # ss.genome_db_id = gd.genome_db_id AND + # ss.species_set_id = sst.species_set_id AND + # (ml.class = "ConservationScore.conservation_score") + # GROUP BY mlss.species_set_id + { + "key" => "Conservation", + "helptip" => "Retrieves a conservation score from the Ensembl Compara databases for variant positions", + "available" => 0, + "enabled" => 0, + "section" => "Conservation", + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/Conservation.pm", + "params" => [ + "@*" + ], + "form" => [ + { + "name" => "method_link_type", + "label" => "Method", + "type" => "dropdown", + "values" => [ + { "value" => "GERP_CONSERVATION_SCORE", "caption" => "GERP"} + ] + }, + { + "name" => "species_set", + "label" => "Species set", + "type" => "dropdown", + "values" => [ + { "value" => "mammals", "caption" => "39 eutherian mammals" }, #"class" => "_stt_macaca_mulatta _stt_echinops_telfairi _stt_tupaia_belangeri _stt_erinaceus_europaeus _stt_sorex_araneus _stt_microcebus_murinus _stt_pongo_abelii _stt_equus_caballus _stt_ochotona_princeps _stt_cavia_porcellus _stt_choloepus_hoffmanni _stt_procavia_capensis _stt_tursiops_truncatus _stt_tarsius_syrichta _stt_dipodomys_ordii _stt_vicugna_pacos _stt_pteropus_vampyrus _stt_loxodonta_africana _stt_oryctolagus_cuniculus _stt_ailuropoda_melanoleuca _stt_nomascus_leucogenys _stt_callithrix_jacchus _stt_myotis_lucifugus _stt_bos_taurus _stt_gorilla_gorilla _stt_otolemur_garnettii _stt_pan_troglodytes _stt_ictidomys_tridecemlineatus _stt_sus_scrofa _stt_mus_musculus _stt_canis_familiaris _stt_mustela_putorius_furo _stt_felis_catus _stt_ovis_aries _stt_dasypus_novemcinctus _stt_homo_sapiens _stt_papio_anubis _stt_chlorocebus_sabaeus _stt_rattus_norvegicus" }, + { "value" => "amniotes", "caption" => "23 amniota vertebrates" }, #"class" => "_stt_macaca_mulatta _stt_ornithorhynchus_anatinus _stt_monodelphis_domestica _stt_pongo_abelii _stt_equus_caballus _stt_taeniopygia_guttata _stt_oryctolagus_cuniculus _stt_anolis_carolinensis _stt_meleagris_gallopavo _stt_callithrix_jacchus _stt_bos_taurus _stt_gorilla_gorilla _stt_pan_troglodytes _stt_sus_scrofa _stt_mus_musculus _stt_canis_familiaris _stt_felis_catus _stt_gallus_gallus _stt_ovis_aries _stt_homo_sapiens _stt_papio_anubis _stt_chlorocebus_sabaeus _stt_rattus_norvegicus" }, + { "value" => "sauropsids", "caption" => "7 sauropsids" }, #"class" => "_stt_taeniopygia_guttata _stt_anolis_carolinensis _stt_meleagris_gallopavo _stt_pelodiscus_sinensis _stt_gallus_gallus _stt_anas_platyrhynchos _stt_ficedula_albicollis" }, + { "value" => "fish", "caption" => "11 fish" }, #"class" => "_stt_takifugu_rubripes _stt_gasterosteus_aculeatus _stt_oryzias_latipes _stt_tetraodon_nigroviridis _stt_gadus_morhua _stt_oreochromis_niloticus _stt_xiphophorus_maculatus _stt_astyanax_mexicanus _stt_lepisosteus_oculatus _stt_poecilia_formosa _stt_danio_rerio" }, + ] + }, + ] + }, + + # AncestralAllele + # Requires processed FASTA file from ftp://ftp.ensembl.org/pub/current_fasta/ancestral_alleles/ + { + "key" => "AncestralAllele", + "label" => "Ancestral allele", + "helptip" => "Retrieves the ancestral allele for variants inferred from the Ensembl Compara Enredo-Pecan-Ortheus (EPO) pipeline", + "available" => 0, + "enabled" => 0, + "section" => "Conservation", + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/AncestralAllele.pm", + "requires_data" => 1, + "species" => [ + "homo_sapiens" + ], + "params" => [ + # "/path/to/homo_sapiens_ancestor_GRCh38_e93.fa.gz" + ] + }, + + + ## FREQUENCY DATA + ################# + + # ExAC + { + "key" => "ExAC", + "label" => "ExAC frequencies", + "helptip" => "Reports allele frequencies from the Exome Aggregation Consortium", + "available" => 0, + "enabled" => 0, + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/ExAC.pm", + "section" => "Frequency data", + "requires_data" => 1, + "species" => [ + "homo_sapiens" + ], + "params" => [ + # "/path/to/ExAC.r0.3.sites.vep.vcf.gz" + ] + }, + + + ## OTHER + ######## + + # CSN + { + "key" => "CSN", + "helptip" => "Reports Clinical Sequencing Nomenclature (CSN) for variants", + "available" => 0, + "enabled" => 0, + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/CSN.pm", + }, + + # miRNA + { + "key" => "miRNA", + "label" => "miRNA structure", + "helptip" => "Determines where in the secondary structure of a miRNA a variant falls", + "available" => 0, + "enabled" => 0, + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/miRNA.pm", + }, + + + + # NearestGene + { + "key" => "NearestGene", + "label" => "Nearest gene", + "helptip" => "Finds the nearest gene to non-genic variants", + "available" => 0, + "enabled" => 0, + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/NearestGene.pm", + }, + + # LD + { + "key" => "LD", + "label" => "Linkage disequilibrium", + "helptip" => "Finds variants in linkage disequilibrium with any overlapping existing variants from the Ensembl variation databases", + "available" => 0, + "enabled" => 0, + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/LD.pm", + "section" => "Variant data", + "params" => [ + "@*" + ], + "form" => [ + { + "name" => "population", + "label" => "Population", + "type" => "dropdown", + "values" => [ + { "value" => "1000GENOMES:phase_3:ACB", "caption" => "African Caribbean in Barbados" }, + { "value" => "1000GENOMES:phase_3:ASW", "caption" => "African Ancestry in Southwest US" }, + { "value" => "1000GENOMES:phase_3:BEB", "caption" => "Bengali in Bangladesh" }, + { "value" => "1000GENOMES:phase_3:CDX", "caption" => "Chinese Dai in Xishuangbanna, China" }, + { "value" => "1000GENOMES:phase_3:CEU", "caption" => "Utah residents with Northern and Western European ancestry" }, + { "value" => "1000GENOMES:phase_3:CHB", "caption" => "Han Chinese in Bejing, China" }, + { "value" => "1000GENOMES:phase_3:CHS", "caption" => "Southern Han Chinese, China" }, + { "value" => "1000GENOMES:phase_3:CLM", "caption" => "Colombian in Medellin, Colombia" }, + { "value" => "1000GENOMES:phase_3:ESN", "caption" => "Esan in Nigeria" }, + { "value" => "1000GENOMES:phase_3:FIN", "caption" => "Finnish in Finland" }, + { "value" => "1000GENOMES:phase_3:GBR", "caption" => "British in England and Scotland" }, + { "value" => "1000GENOMES:phase_3:GIH", "caption" => "Gujarati Indian in Houston, TX" }, + { "value" => "1000GENOMES:phase_3:IBS", "caption" => "Iberian populations in Spain" }, + { "value" => "1000GENOMES:phase_3:ITU", "caption" => "Indian Telugu in the UK" }, + { "value" => "1000GENOMES:phase_3:JPT", "caption" => "Japanese in Tokyo, Japan" }, + { "value" => "1000GENOMES:phase_3:KHV", "caption" => "Kinh in Ho Chi Minh City, Vietnam" }, + { "value" => "1000GENOMES:phase_3:LWK", "caption" => "Luhya in Webuye, Kenya" }, + { "value" => "1000GENOMES:phase_3:MAG", "caption" => "Mandinka in The Gambia" }, + { "value" => "1000GENOMES:phase_3:MSL", "caption" => "Mende in Sierra Leone" }, + { "value" => "1000GENOMES:phase_3:MXL", "caption" => "Mexican Ancestry in Los Angeles, California" }, + { "value" => "1000GENOMES:phase_3:PEL", "caption" => "Peruvian in Lima, Peru" }, + { "value" => "1000GENOMES:phase_3:PJL", "caption" => "Punjabi in Lahore, Pakistan" }, + { "value" => "1000GENOMES:phase_3:PUR", "caption" => "Puerto Rican in Puerto Rico" }, + { "value" => "1000GENOMES:phase_3:STU", "caption" => "Sri Lankan Tamil in the UK" }, + { "value" => "1000GENOMES:phase_3:TSI", "caption" => "Toscani in Italy" }, + { "value" => "1000GENOMES:phase_3:YRI", "caption" => "Yoruba in Ibadan, Nigeria" }, + ], + "value" => "1000GENOMES:phase_3:CEU", + }, + { + "name" => "threshold", + "label" => "r2 cutoff", + "type" => "string", + "value" => 0.8, + }, + ] + }, + + # SameCodon + { + "key" => "SameCodon", + "label" => "Variants in same codon", + "helptip" => "Reports existing variants that fall in the same codon", + "available" => 0, + "enabled" => 0, + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/SameCodon.pm", + "section" => "Variant data", + }, + # LOVD + { + "key" => "LOVD", + "label" => "LOVD", + "helptip" => "Retrieves LOVD variation data", + "available" => 0, + "enabled" => 0, + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/LOVD.pm", + "section" => "Variant data", + }, + + # GO + { + "key" => "GO", + "label" => "Gene Ontology", + "helptip" => "Retrieves Gene Ontology terms associated with transcripts/translations via the Ensembl API", + "available" => 0, + "enabled" => 0, + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/GO.pm", + "section" => "Gene data", + }, + + # Downstream + { + "key" => "Downstream", + "label" => "Downstream", + "helptip" => "Predicts the downstream effects of a frameshift variant on the protein sequence of a transcript", + "available" => 0, + "enabled" => 0, + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/Downstream.pm", + }, + + # ProteinSeqs + { + "key" => "ProteinSeqs", + "label" => "Protein sequences", + "helptip" => "Prints out the reference and mutated protein sequences of any proteins found with non-synonymous mutations", + "available" => 0, + "enabled" => 0, + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/ProteinSeqs.pm", + }, + + # TSSDistance + { + "key" => "TSSDistance", + "label" => "TSS distance", + "helptip" => "Calculates the distance from the transcription start site for upstream variants ", + "available" => 0, + "enabled" => 0, + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/TSSDistance.pm", + }, + + # Phenotypes + { + "key" => "Phenotypes", + "label" => "Phenotypes", + "helptip" => "Retrieves overlapping phenotype annotations", + "available" => 0, + "enabled" => 0, + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/Phenotypes.pm", + }, + # Draw + { + "key" => "Draw", + "label" => "Draw", + "helptip" => "Creates images of the transcript model showing variant location", + "available" => 0, + "enabled" => 0, + "requires_install" => 1, + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/Draw.pm", + }, + # G2P + { + "key" => "G2P", + "label" => "G2P", + "helptip" => "Assesses variants using G2P allelic requirements for potential phenotype involvement.", + "available" => 0, + "enabled" => 0, + "requires_data" => 1, + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/G2P.pm", + }, + + # LocalID + { + "key" => "LocalID", + "label" => "LocalID", + "helptip" => "Allows you to use variant IDs as VEP input without making a database connection.", + "available" => 0, + "enabled" => 0, + "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/94/LocalID.pm", + }, + + + ] +};