my $VEP_PLUGIN_CONFIG = { "plugins" => [ ## PATHOGENICITY PREDICTIONS ############################ # dbNSFP # https://github.com/ensembl-variation/VEP_plugins/blob/main/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/108/dbNSFP.pm", "requires_data" => 1, "requires_install" => 1, "params" => [ #"/path/to/dbNSFP4.3a_grch38.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 dbNSFP README', # "class" => "jquery-multiselect", "values" => [ #"#chr", #"pos(1-based)", #"ref", #"alt", #"aaref", #"aaalt", #"rs_dbSNP", #"hg19_chr", #"hg19_pos(1-based)", #"hg18_chr", #"hg18_pos(1-based)", "aapos", "genename", "Ensembl_geneid", "Ensembl_transcriptid", "Ensembl_proteinid", "Uniprot_acc", "Uniprot_entry", #"HGVSc_ANNOVAR", #"HGVSp_ANNOVAR", #"HGVSc_snpEff", #"HGVSp_snpEff", #"HGVSc_VEP", #"HGVSp_VEP", #"APPRIS", #"GENCODE_basic", #"TSL", #"VEP_canonical", #"cds_strand", #"refcodon", #"codonpos", "codon_degeneracy", "Ancestral_allele", "AltaiNeandertal", "Denisova", "VindijiaNeandertal", "ChagyrskayaNeandertal", #"SIFT_score", #"SIFT_converted_rankscore", #"SIFT_pred", #"SIFT4G_score", #"SIFT4G_converted_rankscore", #"SIFT4G_pred", #"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_score", "MutationAssessor_rankscore", "MutationAssessor_pred", "FATHMM_score", "FATHMM_converted_rankscore", "FATHMM_pred", "PROVEAN_score", "PROVEAN_converted_rankscore", "PROVEAN_pred", "VEST4_score", "VEST4_rankscore", "MetaSVM_score", "MetaSVM_rankscore", "MetaSVM_pred", "MetaLR_score", "MetaLR_rankscore", "MetaLR_pred", "Reliability_index", "MetaRNN_score", "MetaRNN_rankscore", "MetaRNN_pred", "M-CAP_score", "M-CAP_rankscore", "M-CAP_pred", "REVEL_score", "REVEL_rankscore", "MutPred_score", "MutPred_rankscore", "MutPred_protID", "MutPred_AAchange", "MutPred_Top5features", "MVP_score", "MVP_rankscore", "MPC_score", "MPC_rankscore", "PrimateAI_score", "PrimateAI_rankscore", "PrimateAI_pred", "DEOGEN2_score", "DEOGEN2_rankscore", "DEOGEN2_pred", "BayesDel_addAF_score", "BayesDel_addAF_rankscore", "BayesDel_addAF_pred", "BayesDel_noAF_score", "BayesDel_noAF_rankscore", "BayesDel_noAF_pred", "ClinPred_score", "ClinPred_rankscore", "ClinPred_pred", "LIST-S2_score", "LIST-S2_rankscore", "LIST-S2_pred", "Aloft_Fraction_transcripts_affected", "Aloft_prob_Tolerant", "Aloft_prob_Recessive", "Aloft_prob_Dominant", "Aloft_pred", "Aloft_Confidence", "CADD_raw", "CADD_raw_rankscore", "CADD_phred", "CADD_raw_hg19", "CADD_raw_rankscore_hg19", "CADD_phred_hg19", "DANN_score", "DANN_rankscore", "fathmm-MKL_coding_score", "fathmm-MKL_coding_rankscore", "fathmm-MKL_coding_pred", "fathmm-MKL_coding_group", "fathmm-XF_coding_score", "fathmm-XF_coding_rankscore", "fathmm-XF_coding_pred", "Eigen-raw_coding", "Eigen-raw_coding_rankscore", "Eigen-phred_coding", "Eigen-PC-raw_coding", "Eigen-PC-raw_coding_rankscore", "Eigen-PC-phred_coding", "GenoCanyon_score", "GenoCanyon_rankscore", "integrated_fitCons_score", "integrated_fitCons_rankscore", "integrated_confidence_value", "GM12878_fitCons_score", "GM12878_fitCons_rankscore", "GM12878_confidence_value", "H1-hESC_fitCons_score", "H1-hESC_fitCons_rankscore", "H1-hESC_confidence_value", "HUVEC_fitCons_score", "HUVEC_fitCons_rankscore", "HUVEC_confidence_value", "LINSIGHT", "LINSIGHT_rankscore", "GERP++_NR", "GERP++_RS", "GERP++_RS_rankscore", "phyloP100way_vertebrate", "phyloP100way_vertebrate_rankscore", "phyloP30way_mammalian", "phyloP30way_mammalian_rankscore", "phyloP17way_primate", "phyloP17way_primate_rankscore", "phastCons100way_vertebrate", "phastCons100way_vertebrate_rankscore", "phastCons30way_mammalian", "phastCons30way_mammalian_rankscore", "phastCons17way_primate", "phastCons17way_primate_rankscore", "SiPhy_29way_pi", "SiPhy_29way_logOdds", "SiPhy_29way_logOdds_rankscore", "bStatistic", "bStatistic_converted_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", "UK10K_AC", "UK10K_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_flag", "gnomAD_exomes_AC", "gnomAD_exomes_AN", "gnomAD_exomes_AF", "gnomAD_exomes_nhomalt", "gnomAD_exomes_AFR_AC", "gnomAD_exomes_AFR_AN", "gnomAD_exomes_AFR_AF", "gnomAD_exomes_AFR_nhomalt", "gnomAD_exomes_AMR_AC", "gnomAD_exomes_AMR_AN", "gnomAD_exomes_AMR_AF", "gnomAD_exomes_AMR_nhomalt", "gnomAD_exomes_ASJ_AC", "gnomAD_exomes_ASJ_AN", "gnomAD_exomes_ASJ_AF", "gnomAD_exomes_ASJ_nhomalt", "gnomAD_exomes_EAS_AC", "gnomAD_exomes_EAS_AN", "gnomAD_exomes_EAS_AF", "gnomAD_exomes_EAS_nhomalt", "gnomAD_exomes_FIN_AC", "gnomAD_exomes_FIN_AN", "gnomAD_exomes_FIN_AF", "gnomAD_exomes_FIN_nhomalt", "gnomAD_exomes_NFE_AC", "gnomAD_exomes_NFE_AN", "gnomAD_exomes_NFE_AF", "gnomAD_exomes_NFE_nhomalt", "gnomAD_exomes_SAS_AC", "gnomAD_exomes_SAS_AN", "gnomAD_exomes_SAS_AF", "gnomAD_exomes_SAS_nhomalt", "gnomAD_exomes_POPMAX_AC", "gnomAD_exomes_POPMAX_AN", "gnomAD_exomes_POPMAX_AF", "gnomAD_exomes_POPMAX_nhomalt", "gnomAD_exomes_controls_AC", "gnomAD_exomes_controls_AN", "gnomAD_exomes_controls_AF", "gnomAD_exomes_controls_nhomalt", "gnomAD_exomes_non_neuro_AC", "gnomAD_exomes_non_neuro_AN", "gnomAD_exomes_non_neuro_AF", "gnomAD_exomes_non_neuro_nhomalt", "gnomAD_exomes_non_cancer_AC", "gnomAD_exomes_non_cancer_AN", "gnomAD_exomes_non_cancer_AF", "gnomAD_exomes_non_cancer_nhomalt", "gnomAD_exomes_non_topmed_AC", "gnomAD_exomes_non_topmed_AN", "gnomAD_exomes_non_topmed_AF", "gnomAD_exomes_non_topmed_nhomalt", "gnomAD_exomes_controls_AFR_AC", "gnomAD_exomes_controls_AFR_AN", "gnomAD_exomes_controls_AFR_AF", "gnomAD_exomes_controls_AFR_nhomalt", "gnomAD_exomes_controls_AMR_AC", "gnomAD_exomes_controls_AMR_AN", "gnomAD_exomes_controls_AMR_AF", "gnomAD_exomes_controls_AMR_nhomalt", "gnomAD_exomes_controls_ASJ_AC", "gnomAD_exomes_controls_ASJ_AN", "gnomAD_exomes_controls_ASJ_AF", "gnomAD_exomes_controls_ASJ_nhomalt", "gnomAD_exomes_controls_EAS_AC", "gnomAD_exomes_controls_EAS_AN", "gnomAD_exomes_controls_EAS_AF", "gnomAD_exomes_controls_EAS_nhomalt", "gnomAD_exomes_controls_FIN_AC", "gnomAD_exomes_controls_FIN_AN", "gnomAD_exomes_controls_FIN_AF", "gnomAD_exomes_controls_FIN_nhomalt", "gnomAD_exomes_controls_NFE_AC", "gnomAD_exomes_controls_NFE_AN", "gnomAD_exomes_controls_NFE_AF", "gnomAD_exomes_controls_NFE_nhomalt", "gnomAD_exomes_controls_SAS_AC", "gnomAD_exomes_controls_SAS_AN", "gnomAD_exomes_controls_SAS_AF", "gnomAD_exomes_controls_SAS_nhomalt", "gnomAD_exomes_controls_POPMAX_AC", "gnomAD_exomes_controls_POPMAX_AN", "gnomAD_exomes_controls_POPMAX_AF", "gnomAD_exomes_controls_POPMAX_nhomalt", "gnomAD_exomes_non_neuro_AFR_AC", "gnomAD_exomes_non_neuro_AFR_AN", "gnomAD_exomes_non_neuro_AFR_AF", "gnomAD_exomes_non_neuro_AFR_nhomalt", "gnomAD_exomes_non_neuro_AMR_AC", "gnomAD_exomes_non_neuro_AMR_AN", "gnomAD_exomes_non_neuro_AMR_AF", "gnomAD_exomes_non_neuro_AMR_nhomalt", "gnomAD_exomes_non_neuro_ASJ_AC", "gnomAD_exomes_non_neuro_ASJ_AN", "gnomAD_exomes_non_neuro_ASJ_AF", "gnomAD_exomes_non_neuro_ASJ_nhomalt", "gnomAD_exomes_non_neuro_EAS_AC", "gnomAD_exomes_non_neuro_EAS_AN", "gnomAD_exomes_non_neuro_EAS_AF", "gnomAD_exomes_non_neuro_EAS_nhomalt", "gnomAD_exomes_non_neuro_FIN_AC", "gnomAD_exomes_non_neuro_FIN_AN", "gnomAD_exomes_non_neuro_FIN_AF", "gnomAD_exomes_non_neuro_FIN_nhomalt", "gnomAD_exomes_non_neuro_NFE_AC", "gnomAD_exomes_non_neuro_NFE_AN", "gnomAD_exomes_non_neuro_NFE_AF", "gnomAD_exomes_non_neuro_NFE_nhomalt", "gnomAD_exomes_non_neuro_SAS_AC", "gnomAD_exomes_non_neuro_SAS_AN", "gnomAD_exomes_non_neuro_SAS_AF", "gnomAD_exomes_non_neuro_SAS_nhomalt", "gnomAD_exomes_non_neuro_POPMAX_AC", "gnomAD_exomes_non_neuro_POPMAX_AN", "gnomAD_exomes_non_neuro_POPMAX_AF", "gnomAD_exomes_non_neuro_POPMAX_nhomalt", "gnomAD_exomes_non_cancer_AFR_AC", "gnomAD_exomes_non_cancer_AFR_AN", "gnomAD_exomes_non_cancer_AFR_AF", "gnomAD_exomes_non_cancer_AFR_nhomalt", "gnomAD_exomes_non_cancer_AMR_AC", "gnomAD_exomes_non_cancer_AMR_AN", "gnomAD_exomes_non_cancer_AMR_AF", "gnomAD_exomes_non_cancer_AMR_nhomalt", "gnomAD_exomes_non_cancer_ASJ_AC", "gnomAD_exomes_non_cancer_ASJ_AN", "gnomAD_exomes_non_cancer_ASJ_AF", "gnomAD_exomes_non_cancer_ASJ_nhomalt", "gnomAD_exomes_non_cancer_EAS_AC", "gnomAD_exomes_non_cancer_EAS_AN", "gnomAD_exomes_non_cancer_EAS_AF", "gnomAD_exomes_non_cancer_EAS_nhomalt", "gnomAD_exomes_non_cancer_FIN_AC", "gnomAD_exomes_non_cancer_FIN_AN", "gnomAD_exomes_non_cancer_FIN_AF", "gnomAD_exomes_non_cancer_FIN_nhomalt", "gnomAD_exomes_non_cancer_NFE_AC", "gnomAD_exomes_non_cancer_NFE_AN", "gnomAD_exomes_non_cancer_NFE_AF", "gnomAD_exomes_non_cancer_NFE_nhomalt", "gnomAD_exomes_non_cancer_SAS_AC", "gnomAD_exomes_non_cancer_SAS_AN", "gnomAD_exomes_non_cancer_SAS_AF", "gnomAD_exomes_non_cancer_SAS_nhomalt", "gnomAD_exomes_non_cancer_POPMAX_AC", "gnomAD_exomes_non_cancer_POPMAX_AN", "gnomAD_exomes_non_cancer_POPMAX_AF", "gnomAD_exomes_non_cancer_POPMAX_nhomalt", "gnomAD_exomes_non_topmed_AFR_AC", "gnomAD_exomes_non_topmed_AFR_AN", "gnomAD_exomes_non_topmed_AFR_AF", "gnomAD_exomes_non_topmed_AFR_nhomalt", "gnomAD_exomes_non_topmed_AMR_AC", "gnomAD_exomes_non_topmed_AMR_AN", "gnomAD_exomes_non_topmed_AMR_AF", "gnomAD_exomes_non_topmed_AMR_nhomalt", "gnomAD_exomes_non_topmed_ASJ_AC", "gnomAD_exomes_non_topmed_ASJ_AN", "gnomAD_exomes_non_topmed_ASJ_AF", "gnomAD_exomes_non_topmed_ASJ_nhomalt", "gnomAD_exomes_non_topmed_EAS_AC", "gnomAD_exomes_non_topmed_EAS_AN", "gnomAD_exomes_non_topmed_EAS_AF", "gnomAD_exomes_non_topmed_EAS_nhomalt", "gnomAD_exomes_non_topmed_FIN_AC", "gnomAD_exomes_non_topmed_FIN_AN", "gnomAD_exomes_non_topmed_FIN_AF", "gnomAD_exomes_non_topmed_FIN_nhomalt", "gnomAD_exomes_non_topmed_NFE_AC", "gnomAD_exomes_non_topmed_NFE_AN", "gnomAD_exomes_non_topmed_NFE_AF", "gnomAD_exomes_non_topmed_NFE_nhomalt", "gnomAD_exomes_non_topmed_SAS_AC", "gnomAD_exomes_non_topmed_SAS_AN", "gnomAD_exomes_non_topmed_SAS_AF", "gnomAD_exomes_non_topmed_SAS_nhomalt", "gnomAD_exomes_non_topmed_POPMAX_AC", "gnomAD_exomes_non_topmed_POPMAX_AN", "gnomAD_exomes_non_topmed_POPMAX_AF", "gnomAD_exomes_non_topmed_POPMAX_nhomalt", "gnomAD_genomes_flag", "gnomAD_genomes_AC", "gnomAD_genomes_AN", "gnomAD_genomes_AF", "gnomAD_genomes_nhomalt", "gnomAD_genomes_POPMAX_AC", "gnomAD_genomes_POPMAX_AN", "gnomAD_genomes_POPMAX_AF", "gnomAD_genomes_POPMAX_nhomalt", "gnomAD_genomes_AFR_AC", "gnomAD_genomes_AFR_AN", "gnomAD_genomes_AFR_AF", "gnomAD_genomes_AFR_nhomalt", "gnomAD_genomes_AMI_AC", "gnomAD_genomes_AMI_AN", "gnomAD_genomes_AMI_AF", "gnomAD_genomes_AMI_nhomalt", "gnomAD_genomes_AMR_AC", "gnomAD_genomes_AMR_AN", "gnomAD_genomes_AMR_AF", "gnomAD_genomes_AMR_nhomalt", "gnomAD_genomes_ASJ_AC", "gnomAD_genomes_ASJ_AN", "gnomAD_genomes_ASJ_AF", "gnomAD_genomes_ASJ_nhomalt", "gnomAD_genomes_EAS_AC", "gnomAD_genomes_EAS_AN", "gnomAD_genomes_EAS_AF", "gnomAD_genomes_EAS_nhomalt", "gnomAD_genomes_FIN_AC", "gnomAD_genomes_FIN_AN", "gnomAD_genomes_FIN_AF", "gnomAD_genomes_FIN_nhomalt", "gnomAD_genomes_MID_AC", "gnomAD_genomes_MID_AN", "gnomAD_genomes_MID_AF", "gnomAD_genomes_MID_nhomalt", "gnomAD_genomes_NFE_AC", "gnomAD_genomes_NFE_AN", "gnomAD_genomes_NFE_AF", "gnomAD_genomes_NFE_nhomalt", "gnomAD_genomes_SAS_AC", "gnomAD_genomes_SAS_AN", "gnomAD_genomes_SAS_AF", "gnomAD_genomes_SAS_nhomalt", "gnomAD_genomes_controls_and_biobanks_AC", "gnomAD_genomes_controls_and_biobanks_AN", "gnomAD_genomes_controls_and_biobanks_AF", "gnomAD_genomes_controls_and_biobanks_nhomalt", "gnomAD_genomes_non_neuro_AC", "gnomAD_genomes_non_neuro_AN", "gnomAD_genomes_non_neuro_AF", "gnomAD_genomes_non_neuro_nhomalt", "gnomAD_genomes_non_cancer_AC", "gnomAD_genomes_non_cancer_AN", "gnomAD_genomes_non_cancer_AF", "gnomAD_genomes_non_cancer_nhomalt", "gnomAD_genomes_non_topmed_AC", "gnomAD_genomes_non_topmed_AN", "gnomAD_genomes_non_topmed_AF", "gnomAD_genomes_non_topmed_nhomalt", "gnomAD_genomes_controls_and_biobanks_AFR_AC", "gnomAD_genomes_controls_and_biobanks_AFR_AN", "gnomAD_genomes_controls_and_biobanks_AFR_AF", "gnomAD_genomes_controls_and_biobanks_AFR_nhomalt", "gnomAD_genomes_controls_and_biobanks_AMI_AC", "gnomAD_genomes_controls_and_biobanks_AMI_AN", "gnomAD_genomes_controls_and_biobanks_AMI_AF", "gnomAD_genomes_controls_and_biobanks_AMI_nhomalt", "gnomAD_genomes_controls_and_biobanks_AMR_AC", "gnomAD_genomes_controls_and_biobanks_AMR_AN", "gnomAD_genomes_controls_and_biobanks_AMR_AF", "gnomAD_genomes_controls_and_biobanks_AMR_nhomalt", "gnomAD_genomes_controls_and_biobanks_ASJ_AC", "gnomAD_genomes_controls_and_biobanks_ASJ_AN", "gnomAD_genomes_controls_and_biobanks_ASJ_AF", "gnomAD_genomes_controls_and_biobanks_ASJ_nhomalt", "gnomAD_genomes_controls_and_biobanks_EAS_AC", "gnomAD_genomes_controls_and_biobanks_EAS_AN", "gnomAD_genomes_controls_and_biobanks_EAS_AF", "gnomAD_genomes_controls_and_biobanks_EAS_nhomalt", "gnomAD_genomes_controls_and_biobanks_FIN_AC", "gnomAD_genomes_controls_and_biobanks_FIN_AN", "gnomAD_genomes_controls_and_biobanks_FIN_AF", "gnomAD_genomes_controls_and_biobanks_FIN_nhomalt", "gnomAD_genomes_controls_and_biobanks_MID_AC", "gnomAD_genomes_controls_and_biobanks_MID_AN", "gnomAD_genomes_controls_and_biobanks_MID_AF", "gnomAD_genomes_controls_and_biobanks_MID_nhomalt", "gnomAD_genomes_controls_and_biobanks_NFE_AC", "gnomAD_genomes_controls_and_biobanks_NFE_AN", "gnomAD_genomes_controls_and_biobanks_NFE_AF", "gnomAD_genomes_controls_and_biobanks_NFE_nhomalt", "gnomAD_genomes_controls_and_biobanks_SAS_AC", "gnomAD_genomes_controls_and_biobanks_SAS_AN", "gnomAD_genomes_controls_and_biobanks_SAS_AF", "gnomAD_genomes_controls_and_biobanks_SAS_nhomalt", "gnomAD_genomes_non_neuro_AFR_AC", "gnomAD_genomes_non_neuro_AFR_AN", "gnomAD_genomes_non_neuro_AFR_AF", "gnomAD_genomes_non_neuro_AFR_nhomalt", "gnomAD_genomes_non_neuro_AMI_AC", "gnomAD_genomes_non_neuro_AMI_AN", "gnomAD_genomes_non_neuro_AMI_AF", "gnomAD_genomes_non_neuro_AMI_nhomalt", "gnomAD_genomes_non_neuro_AMR_AC", "gnomAD_genomes_non_neuro_AMR_AN", "gnomAD_genomes_non_neuro_AMR_AF", "gnomAD_genomes_non_neuro_AMR_nhomalt", "gnomAD_genomes_non_neuro_ASJ_AC", "gnomAD_genomes_non_neuro_ASJ_AN", "gnomAD_genomes_non_neuro_ASJ_AF", "gnomAD_genomes_non_neuro_ASJ_nhomalt", "gnomAD_genomes_non_neuro_EAS_AC", "gnomAD_genomes_non_neuro_EAS_AN", "gnomAD_genomes_non_neuro_EAS_AF", "gnomAD_genomes_non_neuro_EAS_nhomalt", "gnomAD_genomes_non_neuro_FIN_AC", "gnomAD_genomes_non_neuro_FIN_AN", "gnomAD_genomes_non_neuro_FIN_AF", "gnomAD_genomes_non_neuro_FIN_nhomalt", "gnomAD_genomes_non_neuro_MID_AC", "gnomAD_genomes_non_neuro_MID_AN", "gnomAD_genomes_non_neuro_MID_AF", "gnomAD_genomes_non_neuro_MID_nhomalt", "gnomAD_genomes_non_neuro_NFE_AC", "gnomAD_genomes_non_neuro_NFE_AN", "gnomAD_genomes_non_neuro_NFE_AF", "gnomAD_genomes_non_neuro_NFE_nhomalt", "gnomAD_genomes_non_neuro_SAS_AC", "gnomAD_genomes_non_neuro_SAS_AN", "gnomAD_genomes_non_neuro_SAS_AF", "gnomAD_genomes_non_neuro_SAS_nhomalt", "gnomAD_genomes_non_cancer_AFR_AC", "gnomAD_genomes_non_cancer_AFR_AN", "gnomAD_genomes_non_cancer_AFR_AF", "gnomAD_genomes_non_cancer_AFR_nhomalt", "gnomAD_genomes_non_cancer_AMI_AC", "gnomAD_genomes_non_cancer_AMI_AN", "gnomAD_genomes_non_cancer_AMI_AF", "gnomAD_genomes_non_cancer_AMI_nhomalt", "gnomAD_genomes_non_cancer_AMR_AC", "gnomAD_genomes_non_cancer_AMR_AN", "gnomAD_genomes_non_cancer_AMR_AF", "gnomAD_genomes_non_cancer_AMR_nhomalt", "gnomAD_genomes_non_cancer_ASJ_AC", "gnomAD_genomes_non_cancer_ASJ_AN", "gnomAD_genomes_non_cancer_ASJ_AF", "gnomAD_genomes_non_cancer_ASJ_nhomalt", "gnomAD_genomes_non_cancer_EAS_AC", "gnomAD_genomes_non_cancer_EAS_AN", "gnomAD_genomes_non_cancer_EAS_AF", "gnomAD_genomes_non_cancer_EAS_nhomalt", "gnomAD_genomes_non_cancer_FIN_AC", "gnomAD_genomes_non_cancer_FIN_AN", "gnomAD_genomes_non_cancer_FIN_AF", "gnomAD_genomes_non_cancer_FIN_nhomalt", "gnomAD_genomes_non_cancer_MID_AC", "gnomAD_genomes_non_cancer_MID_AN", "gnomAD_genomes_non_cancer_MID_AF", "gnomAD_genomes_non_cancer_MID_nhomalt", "gnomAD_genomes_non_cancer_NFE_AC", "gnomAD_genomes_non_cancer_NFE_AN", "gnomAD_genomes_non_cancer_NFE_AF", "gnomAD_genomes_non_cancer_NFE_nhomalt", "gnomAD_genomes_non_cancer_SAS_AC", "gnomAD_genomes_non_cancer_SAS_AN", "gnomAD_genomes_non_cancer_SAS_AF", "gnomAD_genomes_non_cancer_SAS_nhomalt", "gnomAD_genomes_non_topmed_AFR_AC", "gnomAD_genomes_non_topmed_AFR_AN", "gnomAD_genomes_non_topmed_AFR_AF", "gnomAD_genomes_non_topmed_AFR_nhomalt", "gnomAD_genomes_non_topmed_AMI_AC", "gnomAD_genomes_non_topmed_AMI_AN", "gnomAD_genomes_non_topmed_AMI_AF", "gnomAD_genomes_non_topmed_AMI_nhomalt", "gnomAD_genomes_non_topmed_AMR_AC", "gnomAD_genomes_non_topmed_AMR_AN", "gnomAD_genomes_non_topmed_AMR_AF", "gnomAD_genomes_non_topmed_AMR_nhomalt", "gnomAD_genomes_non_topmed_ASJ_AC", "gnomAD_genomes_non_topmed_ASJ_AN", "gnomAD_genomes_non_topmed_ASJ_AF", "gnomAD_genomes_non_topmed_ASJ_nhomalt", "gnomAD_genomes_non_topmed_EAS_AC", "gnomAD_genomes_non_topmed_EAS_AN", "gnomAD_genomes_non_topmed_EAS_AF", "gnomAD_genomes_non_topmed_EAS_nhomalt", "gnomAD_genomes_non_topmed_FIN_AC", "gnomAD_genomes_non_topmed_FIN_AN", "gnomAD_genomes_non_topmed_FIN_AF", "gnomAD_genomes_non_topmed_FIN_nhomalt", "gnomAD_genomes_non_topmed_MID_AC", "gnomAD_genomes_non_topmed_MID_AN", "gnomAD_genomes_non_topmed_MID_AF", "gnomAD_genomes_non_topmed_MID_nhomalt", "gnomAD_genomes_non_topmed_NFE_AC", "gnomAD_genomes_non_topmed_NFE_AN", "gnomAD_genomes_non_topmed_NFE_AF", "gnomAD_genomes_non_topmed_NFE_nhomalt", "gnomAD_genomes_non_topmed_SAS_AC", "gnomAD_genomes_non_topmed_SAS_AN", "gnomAD_genomes_non_topmed_SAS_AF", "gnomAD_genomes_non_topmed_SAS_nhomalt", "clinvar_id", "clinvar_clnsig", "clinvar_trait", "clinvar_review", "clinvar_hgvs", "clinvar_var_source", "clinvar_MedGen_id", "clinvar_OMIM_id", "clinvar_Orphanet_id", "Interpro_domain", "GTEx_V8_gene", "GTEx_V8_tissue", "Geuvadis_eQTL_target_gene" ], }, ] }, # CADD # https://github.com/ensembl-variation/VEP_plugins/blob/main/CADD.pm # Requires tabix-indexed data file as first param # No other parameters so no form required { "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/108/CADD.pm", "requires_data" => 1, "species" => [ "homo_sapiens" ], "params" => [ #"/path/to/whole_genome_SNVs.tsv.gz" ] }, # CAPICE # https://github.com/ensembl-variation/VEP_plugins/blob/main/CAPICE.pm # Requires tabix-indexed data files as params (one for InDels, another for SNVs) # No other parameters so no form required # data file currently only available for GRCh37 { "key" => "CAPICE", "label" => "CAPICE", "available" => 0, "enabled" => 0, "section" => "Pathogenicity predictions", "helptip" => "Consequence-Agnostic Pathogenicity Interpretation of Clinical Exome variations (CAPICE) is a tool for scoring the pathogenicity of single nucleotide variants and insertion/deletion variants in the human genome. CAPICE uses a gradient boosting tree model trained with multiple genomic annotations used by CADD score and based on clinical significance.", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/CAPICE.pm", "requires_data" => 1, "species" => [ "homo_sapiens" ], "params" => [ #"/path/to/capice_v1.0_build37_indels.tsv.gz", #"/path/to/capice_v1.0_build37_snvs.tsv.gz" ] }, # FATHMM { "key" => "FATHMM", "label" => "FATHMM", "available" => 0, "enabled" => 0, "section" => "Pathogenicity predictions", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/FATHMM.pm" }, # FATHMM-MKL # https://github.com/ensembl-variation/VEP_plugins/blob/main/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/108/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/main/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/108/Carol.pm", "requires_install" => 1, "species" => [ "homo_sapiens" ], }, # Condel # https://github.com/ensembl-variation/VEP_plugins/blob/main/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/108/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/108/LoFtool.pm", "requires_data" => 1, "species" => [ "homo_sapiens" ], "params" => [ # "/path/to/LoFtool_scores.txt" ] }, # pLI # Requires pLI_values.txt file as first param (available in VEP_plugins GitHub repo) { "key" => "pLI", "helptip" => "Provides a per-gene or per transcript probability of being loss-of-function intolerant (pLI)", "available" => 0, "enabled" => 0, "section" => "Pathogenicity predictions", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/pLI.pm", "requires_data" => 1, "species" => [ "homo_sapiens" ], "params" => [ # "/path/to/pLI_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/108/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/108/MTR.pm", "requires_data" => 1, "species" => [ "homo_sapiens" ], "params" => [ # "/path/to/mtrflatfile_1.0.txt.gz" ] }, # PrimateAI # Requires PrimateAI_scores_v0.2.tsv.gz or PrimateAI_scores_v0.2_hg38.tsv.gz from https://basespace.illumina.com/s/yYGFdGih1rXL. { "key" => "PrimateAI", "helptip" => "PrimateAI scores can be used to assess pathogenicity of variants in humans", "available" => 0, "enabled" => 0, "section" => "Pathogenicity predictions", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/PrimateAI.pm", "requires_data" => 1, "species" => [ "homo_sapiens" ], "params" => [ # "/path/to/PrimateAI_scores_v0.2_GRCh38_sorted.tsv.bgz ] }, # 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/108/REVEL.pm", "requires_data" => 1, "species" => [ "homo_sapiens" ], "params" => [ # "/path/to/revel_all_chromosomes.tsv.gz" ] }, # PON_P2 { "key" => "PON_P2", "label" => "PON_P2", "available" => 0, "enabled" => 0, "section" => "Pathogenicity predictions", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/PON_P2.pm" }, # ClinPred # Requires data file processed from ClinPred.txt.gz { "key" => "ClinPred", "helptip" => "A prediction tool for the identification of disease-relevant nonsynonymous single nucleotide variants", "available" => 0, "enabled" => 0, "section" => "Pathogenicity predictions", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/ClinPred.pm", "requires_data" => 1, "species" => [ "homo_sapiens" ], "params" => [ # "/path/to/ClinPred_tabbed.tsv.gz" ] }, # LOEUF # Requires data file processed from supplementary_dataset_11_full_constraint_metrics.tsv.gz # Only available for GRCh37 { "key" => "LOEUF", "helptip" => "LOEUF stands for the 'loss-of-function observed/expected upper bound fraction'. This plugin adds constraint scores derived from gnomAD to VEP", "available" => 0, "enabled" => 0, "section" => "Pathogenicity predictions", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/LOEUF.pm", "requires_data" => 1, "species" => [ "homo_sapiens" ], "params" => [ # "/path/to/loeuf_dataset.gz", "@*" ] }, # EVE # https://github.com/ensembl-variation/VEP_plugins/blob/main/EVE.pm # Requires tabix-indexed data file as params # No other parameters so no form required # data file currently only available for GRCh38 # We only report EVE scores for input variants and # don't consider adjacent variants. { "key" => "EVE", "label" => "EVE", "available" => 0, "enabled" => 0, "section" => "Pathogenicity predictions", "helptip" => "EVE (evolutionary model of variant effect) is a computational method for the classification of human genetic variants trained solely on evolutionary sequences.", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/EVE.pm", "requires_data" => 1, "species" => [ "homo_sapiens" ], "params" => [ #"/path/to/eve_merged.vcf.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/108/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/108/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/108/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/108/SpliceRegion.pm", }, # SpliceAI { "key" => "SpliceAI", "label" => "SpliceAI", "helptip" => "Pre-calculated annotations from SpliceAI a deep neural network, developed by Illumina, Inc that predicts splice junctions from an arbitrary pre-mRNA transcript sequence. Used for non-commercial purposes (https://github.com/Illumina/SpliceAI)", "available" => 0, "enabled" => 0, "section" => "Splicing predictions", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/SpliceAI.pm", "form" => [ { "name" => "file_type", "label" => "Select analysis mode", "type" => "dropdown", "values" => [ { "value" => "snv", "caption" => "Masked scores (Ensembl/GENCODE v24 canonical transcripts)" }, { "value" => "snv_ensembl", "caption" => "Raw scores (Ensembl/GENCODE v37 MANE transcripts, SNV only)" } ], "value" => "snv", }, ], }, ## 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/108/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/108/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 https://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/108/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/108/ExAC.pm", "section" => "Frequency data", "requires_data" => 1, "species" => [ "homo_sapiens" ], "params" => [ # "/path/to/ExAC.r0.3.sites.vep.vcf.gz" ] }, # gnomADc { "key" => "gnomADc", "label" => "gnomADc", "helptip" => "Reports coverage data from the gmomAD coverage files", "available" => 0, "enabled" => 0, "section" => "Frequency data", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/gnomADc.pm", "requires_data" => 1, "species" => [ "homo_sapiens" ] }, ## PHENOTYPES DATA AND CITATIONS ################## # Phenotypes { "key" => "Phenotypes", "label" => "Phenotypes", "helptip" => "Retrieves overlapping phenotype annotations", "section" => "Phenotype data and citations", "requires_data" => 1, "available" => 0, "enabled" => 0, "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/Phenotypes.pm", "params" => [ #"/path/to/Phenotypes_data_files/phenotypes_dir_with_dumps_for_all_species.gvf.gz" ] }, # GO { "key" => "GO", "label" => "Gene Ontology", "helptip" => "Retrieves Gene Ontology terms associated with transcripts/translations", "available" => 0, "enabled" => 0, "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/GO.pm", "section" => "Phenotype data and citations", "params" => [ #"/path/to/GO_data_dir" ] }, # G2P { "key" => "G2P", "label" => "G2P", "helptip" => "Assesses variants using G2P allelic requirements for potential phenotype involvement.", "available" => 0, "enabled" => 0, "requires_data" => 1, "section" => "Phenotype data and citations", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/G2P.pm", }, # PostGAP { "key" => "PostGAP", "label" => "PostGAP", "available" => 0, "enabled" => 0, "section" => "Phenotype data and citations", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/PostGAP.pm" }, # satMutMPRA { "key" => "satMutMPRA", "helptip" => "Reports saturation mutagenesis MPRA measures of variant effects on gene RNA expression for 21 enhancers/promoters", "section" => "Phenotype data and citations", "available" => 0, "enabled" => 0, "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/satMutMPRA.pm", }, # DisGeNET { "key" => "DisGeNET", "helptip" => "Variant-Disease-PMID associations from the DisGeNET database (https://www.disgenet.org/)", "section" => "Phenotype data and citations", "available" => 0, "enabled" => 0, "species" => [ "homo_sapiens" ], "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/DisGeNET.pm", }, # Mastermind { "key" => "Mastermind", "label" => "Mastermind", "helptip" => "Variants with clinical evidence cited in the medical literature reported by Mastermind Genomic Search Engine (https://www.genomenon.com/mastermind)", "available" => 0, "enabled" => 0, "species" => [ "homo_sapiens" ], "section" => "Phenotype data and citations", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/Mastermind.pm" }, ## VARIANT DATA ############### # 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/108/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/108/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/108/LOVD.pm", "section" => "Variant data", }, # SubsetVCF { "key" => "SubsetVCF", "label" => "SubsetVCF", "available" => 0, "enabled" => 0, "section" => "Variant data", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/SubsetVCF.pm" }, ## NEARBY FEATURES ################## # NearestGene { "key" => "NearestGene", "label" => "Nearest gene", "helptip" => "Finds the nearest gene to non-genic variants", "available" => 0, "enabled" => 0, "section" => "Nearby features", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/NearestGene.pm", }, # NearestExonJB { "key" => "NearestExonJB", "label" => "NearestExonJB", "available" => 0, "enabled" => 0, "section" => "Nearby features", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/NearestExonJB.pm" }, # 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, "section" => "Nearby features", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/Downstream.pm", }, # TSSDistance { "key" => "TSSDistance", "label" => "TSS distance", "helptip" => "Calculates the distance from the transcription start site for upstream variants ", "available" => 0, "enabled" => 0, "section" => "Nearby features", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/TSSDistance.pm", }, ## SEQUENCE ########### # 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, "section" => "Sequence", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/ProteinSeqs.pm", }, # ReferenceQuality { "key" => "ReferenceQuality", "label" => "ReferenceQuality", "available" => 0, "enabled" => 0, "section" => "Sequence", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/ReferenceQuality.pm" }, ## VISUALISATION ################ # Draw { "key" => "Draw", "label" => "Draw", "helptip" => "Creates images of the transcript model showing variant location", "available" => 0, "enabled" => 0, "requires_install" => 1, "section" => "Visualisation", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/Draw.pm", }, ## LOCAL ID ########### # LocalID { "key" => "LocalID", "label" => "LocalID", "helptip" => "Allows you to use variant IDs as VEP input without making a database connection.", "available" => 0, "enabled" => 0, "section" => "Look up", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/LocalID.pm", }, ## EXTERNAL ID ############## # FlagLRG { "key" => "FlagLRG", "label" => "FlagLRG", "available" => 0, "enabled" => 0, "section" => "External ID", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/FlagLRG.pm" }, ## MOTIF ######## # FunMotifs { "key" => "FunMotifs", "label" => "FunMotifs", "available" => 0, "enabled" => 0, "section" => "Motif", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/FunMotifs.pm" }, ## HGVS ####### # HGVSIntronOffset { "key" => "HGVSIntronOffset", "label" => "HGVSIntronOffset", "available" => 0, "enabled" => 0, "section" => "HGVS", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/HGVSIntronOffset.pm" }, # SingleLetterAA { "key" => "SingleLetterAA", "label" => "SingleLetterAA", "available" => 0, "enabled" => 0, "section" => "HGVS", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/SingleLetterAA.pm" }, ## STRUCTURAL VARIANT DATA ########################## # StructuralVariantOverlap { "key" => "StructuralVariantOverlap", "label" => "StructuralVariantOverlap", "available" => 0, "enabled" => 0, "section" => "Structural variant data", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/StructuralVariantOverlap.pm" }, ## TRANSCRIPT ANNOTATION ############ # NMD { "key" => "NMD", "helptip" => "Nonsense-mediated mRNA decay escaping variants prediction", "available" => 0, "enabled" => 0, "section" => "Transcript annotation", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/NMD.pm" }, # UTRAnnotator # https://github.com/ensembl-variation/VEP_plugins/blob/main/UTRAnnotator.pm { "key" => "UTRAnnotator", "label" => "UTRAnnotator", "available" => 0, "enabled" => 0, "section" => "Transcript annotation", "helptip" => "A VEP plugin that annotates the effect of 5' UTR variant especially for variant creating/disrupting upstream ORFs.", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/UTRAnnotator.pm" }, ## PROTEIN DATA ############### # neXtProt { "key" => "neXtProt", "label" => "neXtProt", "helptip" => "Retrieves protein-related data from neXtProt", "available" => 0, "enabled" => 0, "section" => "Protein data", "requires_data" => 1, "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/neXtProt.pm" }, ## PROTEIN ANNOTATION ##################### # IntAct { "key" => "IntAct", "label" => "IntAct", "available" => 0, "enabled" => 0, "section" => "Protein annotation", "helptip" => "IntAct provides molecular interaction data for variants as reported by IntAct database", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/IntAct.pm", "requires_data" => 1, "params" => [ "#mapping_file=/path/to/mutation_gc_map.txt.gz", "#mutation_file=/path/to/mutations.tsv", "@*" ], "species" => [ "homo_sapiens", "mus_musculus" ], "form" => [ { "name" => "IntAct_efields", "label" => "Extra fields to include", "helptip" => "Extra fields to show; hold down the Ctrl (Windows) / Command (Mac) button to select multiple options", "value" => "", "type" => "dropdown", "multiple" => 1, "style" => "height:150px", "values" => [ { "value" => "feature_ac=1", "caption" => "Feature AC" }, { "value" => "feature_short_label=1", "caption" => "Feature short label" }, { "value" => "feature_annotation=1", "caption" => "Feature annotation" }, { "value" => "ap_ac=1", "caption" => "Affected protein AC" }, { "value" => "interaction_participants=1", "caption" => "Interaction participants" }, { "value" => "pmid=1", "caption" => "PubMedID" }, ], }, ] }, # mutfunc { "key" => "mutfunc", "label" => "mutfunc", "available" => 0, "enabled" => 0, "section" => "Protein annotation", "helptip" => "mutfunc predicts destabilization effect of protein structure, interaction, regulatory region etc. caused by a variant", "plugin_url" => "https://raw.githubusercontent.com/Ensembl/VEP_plugins/release/108/mutfunc.pm", "requires_data" => 1, "params" => [ "#db=/path/to/mutfunc_data.db", "@*" ], "species" => [ "homo_sapiens", "saccharomyces_cerevisiae" ], "form" => [ { "name" => "mutfunc_fields", "label" => "Fields to include", "helptip" => "Select which analysis you want to see in the output", "value" => "", "type" => "checklist", "multiple" => 1, "style" => "height:150px", "values" => [ { "value" => "motif=1", "caption" => "Linear Motifs", "helptip" => "Effect on linear motifs", 'checked' => 1 }, { "value" => "int=1", "caption" => "Protein Interactions", "helptip" => "Effect on protein interactions", 'checked' => 1 }, { "value" => "mod=1", "caption" => "Protein Structure", "helptip" => "Effect on protein structure", 'checked' => 1 }, { "value" => "exp=1", "caption" => "Protein Structure (exp.)", "helptip" => "Effect on protein structure (experimental)", 'checked' => 1 } ], }, { "name" => "mutfunc_extend", "label" => "Extended output", "helptip" => "By default mutfunc outputs the most significant field for any analysis. Select this option to get more verbose output.", "value" => "extended=1", "type" => "checkbox", "style" => "height:150px" } ] }, ## 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/108/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/108/miRNA.pm", } ] };