From 8472ea875e291d3c668285b82254308033d9887b Mon Sep 17 00:00:00 2001 From: sebastianlieske Date: Fri, 30 Aug 2019 14:51:56 +0200 Subject: [PATCH] filter chromosom started --- NAMESPACE | 13 +- R/preprocess_assay.R | 14 +- R/use_biomaRt.R | 7 +- example/DAVID_280819.R | 34 +++++ example/preprocessing.R | 13 +- man/add_coldata_classification.Rd | 25 +++ man/{correct_out.Rd => correct_output.Rd} | 14 +- man/filter_fold_change.Rd | 6 +- man/filter_mean.Rd | 2 +- man/filter_unimodal.Rd | 2 +- man/is_correct.Rd | 2 +- man/plot_heatmap.Rd | 14 +- man/rerun_mclust.Rd | 2 +- man/transform_assay.Rd | 6 +- man/use_biomaRt.Rd | 2 +- man/use_mclust.Rd | 6 +- man/use_siber.Rd | 13 +- man/verify_mclust.Rd | 2 +- termClusterBimodalBRCA.tab | 177 ++++++++++++++++++++++ 19 files changed, 297 insertions(+), 57 deletions(-) create mode 100644 example/DAVID_280819.R create mode 100644 man/add_coldata_classification.Rd rename man/{correct_out.Rd => correct_output.Rd} (59%) create mode 100644 termClusterBimodalBRCA.tab diff --git a/NAMESPACE b/NAMESPACE index bce4f71..5012163 100644 --- a/NAMESPACE +++ b/NAMESPACE @@ -3,9 +3,11 @@ export(above_percentage) export(add_assay_classification) export(add_assay_norm) +export(add_coldata_classification) export(calc_auc) export(calc_prediction) export(calculate_fit) +export(correct_output) export(factorize_columns) export(filter_duplicates) export(filter_for_factor) @@ -13,20 +15,27 @@ export(filter_rare) export(filter_single_level) export(filter_zero) export(get_no_cores) +export(is_correct) export(make_coeff_frame) export(make_explicit_na) export(make_model_matrix) export(merge_duplicated) export(methyl_frame) export(not_zero) +export(plot_heatmap) export(preprocess_assay) export(preprocess_coldata) export(reorder_all) +export(transform_assay) export(use_cvglmnet) export(use_glmnet) +export(use_p_adjust) +export(use_siber) export(use_silvermantest) import(AUC) +import(ComplexHeatmap) import(GenomicRanges) +import(Heatmap) import(SIBER) import(SummarizedExperiment) import(doParallel) @@ -41,10 +50,12 @@ import(rlang) import(snow) import(survival) import(survminer) -importFrom(ComplexHeatmap,Heatmap) +importFrom(Biobase,isUnique) importFrom(ComplexHeatmap,HeatmapAnnotation) importFrom(FactoMineR,catdes) importFrom(RColorBrewer,brewer.pal) +importFrom(biomaRt,getBM) +importFrom(biomaRt,useMart) importFrom(dplyr,"%>%") importFrom(dplyr,group_by_) importFrom(dplyr,mutate) diff --git a/R/preprocess_assay.R b/R/preprocess_assay.R index 7db5c17..08106a5 100644 --- a/R/preprocess_assay.R +++ b/R/preprocess_assay.R @@ -116,7 +116,19 @@ above_percentage <- function(vector, min_counts, min_percentage) { return(isAbove) } -filter_chromosome <- function(summarized_experiment, chromosomes = NULL) { +#' Filter Specific Genes on Chromosome +#' @description This function filters genes that are located on specific chromosomes. +#' @param summarized_experiment SummarizedExperiment or matrix like object. +#' @param chromosome Name of chromosomes to be filtered out | 1-24, X, Y +#' @param df_biomart Data frame containing biomaRt results +#' @details Gene names have to be in rows and as ensembl gene IDs. e.g ENSG00000091831. If there is already a data frame with genes and their location on the chromosome, you can use that df instead. +#' That data frame needs to have the columns "ensembl_gene_id" and "chromosome_name". +#' @return +#' @import SummarizedExperiment +#' @importFrom biomaRt +#' @export + +filter_chromosome <- function(summarized_experiment, chromosome = NULL, df_biomart) { } diff --git a/R/use_biomaRt.R b/R/use_biomaRt.R index a02e34d..4badf92 100644 --- a/R/use_biomaRt.R +++ b/R/use_biomaRt.R @@ -1,13 +1,10 @@ #' Use biomaRt #' @description Short function get information from biomaRt. -#' @param summarized_experiment SE -#' @param gene_names Names of genes to be mapped -#' -#' @importFrom magrittr %>% +#' @param gene_names Vector of gene names as ensembl_gene_id #' @examples # #' @return - +#' @importFrom biomaRt useMart getBM use_biomaRt <- function(gene_names, ... ) { ensembl = useMart("ensembl", dataset="hsapiens_gene_ensembl") ensg_de_lung <- getBM(mart=ensembl, diff --git a/example/DAVID_280819.R b/example/DAVID_280819.R new file mode 100644 index 0000000..4eabe45 --- /dev/null +++ b/example/DAVID_280819.R @@ -0,0 +1,34 @@ +#DAVID Web Service 28.08 +#http://bioconductor.org/packages/release/bioc/vignettes/RDAVIDWebService/inst/doc/RDavidWS-vignette.pdf +library("RDAVIDWebService") + +david <-DAVIDWebService$new(email="sebastian.lieske@bioinfsys.uni-giessen.de") # does not work +david <- DAVIDWebService(email="sebastian.lieske@bioinfsys.uni-giessen.de", url="https://david.ncifcrf.gov/webservice/services/DAVIDWebService.DAVIDWebServiceHttpSoap12Endpoint/") +geneNames <- rownames(subBRCA) +result <- addList(david, geneNames, idType = "ENSEMBL_GENE_ID", listName = "bimodal", listType = "Gene") +#getIdTypes(david) +#do it again with ENTREZ +ensemblgene <- use_biomaRt(geneNames) +hgnc <- ensemblgene$hgnc_symbol %>% na.omit() %>% .[.!= ""] +entrez <- ensemblgene$entrezgene_id %>% na.omit() + +result2 <- addList(david, entrez, idType = "ENTREZ_GENE_ID", listName = "bimodal1", listType = "Gene") +#adds directly to david + +termCluster <- getClusterReport(david, type="Term") #terms or genes +getClusterReportFile(david, type="Term", + fileName="termClusterBimodalBRCA.tab") +plot2D(termCluster, 1) + +davidGODag<-DAVIDGODag(members(termCluster)[[3]], + pvalueCutoff=0.1, "MF") +plotGOTermGraph(g=goDag(davidGODag), + r=davidGODag, max.nchar=40, node.shape="ellipse") + +clust1 <- termCluster@cluster[1] +clust1df <- data.frame(clust1[[1]]$Members) + +silver <- use_silvermantest(subBRCA, 2, filter = F, alpha = 0.05, k = 1) +silver2 <- use_silvermantest(subBRCA, 2, filter = F, alpha = 0.05, k = 2) + +a <- filter_all(ensemblgene, "X" %in% chromosome_name) diff --git a/example/preprocessing.R b/example/preprocessing.R index 2e8ff8e..5ef1038 100644 --- a/example/preprocessing.R +++ b/example/preprocessing.R @@ -102,14 +102,5 @@ a <- t(assay(subBRCA, 2)[1:100,1:100]) b <- dist(scale(a), method = "euclidean") c <- hclust(b, method = "ward.D2") -a <- apply(X = assay(subBRCA, 3), MARGIN = 2, FUN = function(x) table(x)) %>% t() #count occurence of each class in patient -colnames(a) <- paste("class", colnames(a), sep = "_") #change colnames -b <- data.frame(a) -b <- data.frame(a) -a <- add_coldata_classification(a, 3, to_coldata = F) -b <- apply(X = a, MARGIN = 2, FUN = function(x) table(x)) %>% t() -colnames(b) <- paste("class", colnames(b), sep = "_") -colnames(countMatrix) <- paste("class", colnames(b), sep = "_") #change colnames - -c <- unnest_dataframe(colData(subBRCA)) -c <- cbind(c, b) +a <- add_coldata_classification(subBRCA, 3, T) +b <- unnest_dataframe(colData(a)) %>% group_by() \ No newline at end of file diff --git a/man/add_coldata_classification.Rd b/man/add_coldata_classification.Rd new file mode 100644 index 0000000..8322d63 --- /dev/null +++ b/man/add_coldata_classification.Rd @@ -0,0 +1,25 @@ +% Generated by roxygen2: do not edit by hand +% Please edit documentation in R/add_coldata_classification.R +\name{add_coldata_classification} +\alias{add_coldata_classification} +\title{Add Classification Counts to colData} +\usage{ +add_coldata_classification(summarized_experiment, assay_index = 3, + to_coldata = F, column_data = NULL) +} +\arguments{ +\item{assay_index}{Integer - index of assay of classification made by mclust} + +\item{to_coldata}{Logical - should the count matrix be added to colData/column_data?} + +\item{column_data}{Data frame like object} +} +\value{ +SummarizedExperiment or data frame with additonal columns. +} +\description{ +This function adds new columns showing the counts of the overall classification of a sample. +} +\details{ +If summarized_experiment is not a SummarizedExperiment then give a matrix where samples are in columns and genes are in rows. +} diff --git a/man/correct_out.Rd b/man/correct_output.Rd similarity index 59% rename from man/correct_out.Rd rename to man/correct_output.Rd index 94ca784..c86b5ab 100644 --- a/man/correct_out.Rd +++ b/man/correct_output.Rd @@ -1,20 +1,14 @@ % Generated by roxygen2: do not edit by hand -% Please edit documentation in R/verify_output.R -\name{correct_out} -\alias{correct_out} +% Please edit documentation in R/verify_mclust.R +\name{correct_output} +\alias{correct_output} \title{Correct Output of Mclust} \usage{ -correct_out(mclust_result, min_proportion = NULL) +correct_output(mclust_result, min_proportion = NULL) } \arguments{ \item{mclust_result}{Object of class Mclust (Result of Mclust)} } -\value{ -A character vector of gene names. -} \description{ This function combines multiple SummarizedExperiments via cbind. Automatically adds missing column names(varaibles in colData) and rows (gene names) while adding NA. } -\examples{ -lungKegg <- filterForKnownInCancer(lungXY) -} diff --git a/man/filter_fold_change.Rd b/man/filter_fold_change.Rd index 62ac37b..632876b 100644 --- a/man/filter_fold_change.Rd +++ b/man/filter_fold_change.Rd @@ -1,16 +1,16 @@ % Generated by roxygen2: do not edit by hand -% Please edit documentation in R/verify_output.R +% Please edit documentation in R/verify_mclust.R \name{filter_fold_change} \alias{filter_fold_change} \title{Filter For log2 Fold Change} \usage{ filter_fold_change(mclust_result, summarized_experiment = NULL, - assay_index = 1, classification_index = 2, min_fold = 2) + min_fold = 2) } \arguments{ \item{mclust_result}{Object of class Mclust (Result of Mclust)} -\item{data}{Either SummarizedExperiment or matrix like object of expression values.} +\item{summarized_experiment}{Either SummarizedExperiment or matrix like object of expression values.} } \value{ A character vector of gene names. diff --git a/man/filter_mean.Rd b/man/filter_mean.Rd index 16b0c92..bc50a36 100644 --- a/man/filter_mean.Rd +++ b/man/filter_mean.Rd @@ -1,5 +1,5 @@ % Generated by roxygen2: do not edit by hand -% Please edit documentation in R/verify_output.R +% Please edit documentation in R/verify_mclust.R \name{filter_mean} \alias{filter_mean} \title{Filter For Mean (not as important imo)} diff --git a/man/filter_unimodal.Rd b/man/filter_unimodal.Rd index 7974f34..ac38619 100644 --- a/man/filter_unimodal.Rd +++ b/man/filter_unimodal.Rd @@ -1,5 +1,5 @@ % Generated by roxygen2: do not edit by hand -% Please edit documentation in R/verify_output.R +% Please edit documentation in R/verify_mclust.R \name{filter_unimodal} \alias{filter_unimodal} \title{Filter Out Unimodal Genes} diff --git a/man/is_correct.Rd b/man/is_correct.Rd index b6684d1..3cbc6fa 100644 --- a/man/is_correct.Rd +++ b/man/is_correct.Rd @@ -1,5 +1,5 @@ % Generated by roxygen2: do not edit by hand -% Please edit documentation in R/verify_output.R +% Please edit documentation in R/verify_mclust.R \name{is_correct} \alias{is_correct} \title{Check classification} diff --git a/man/plot_heatmap.Rd b/man/plot_heatmap.Rd index c020924..6426400 100644 --- a/man/plot_heatmap.Rd +++ b/man/plot_heatmap.Rd @@ -4,19 +4,19 @@ \alias{plot_heatmap} \title{Plot Heatmap} \usage{ -plot_heatmap(df_expression, df_meta, id = "case_id", - col_annotation = NULL, ...) +plot_heatmap(summarized_experiment, assay_index = 2, + column_data = NULL, id = NULL, col_annotation = NULL, ...) } \arguments{ -\item{df_expression}{Expression matrix or data frame} - -\item{df_meta}{Data frame of meta data} - \item{id}{Unique ID (i.e. patient); default = "case_id"} -\item{col_annotation}{Character - column name} +\item{col_annotation}{Either character of column names the Annotation is calculated from or am annotation object.} \item{...}{further arguments for \link[gplots]{heatmap.2}} + +\item{df_expression}{Expression matrix or data frame} + +\item{df_meta}{Data frame of meta data} } \value{ Returns a large Heatmap object diff --git a/man/rerun_mclust.Rd b/man/rerun_mclust.Rd index 792dac6..fa50063 100644 --- a/man/rerun_mclust.Rd +++ b/man/rerun_mclust.Rd @@ -1,5 +1,5 @@ % Generated by roxygen2: do not edit by hand -% Please edit documentation in R/verify_output.R +% Please edit documentation in R/verify_mclust.R \name{rerun_mclust} \alias{rerun_mclust} \title{Rerun Mclust} diff --git a/man/transform_assay.Rd b/man/transform_assay.Rd index 4e5310c..dcee92e 100644 --- a/man/transform_assay.Rd +++ b/man/transform_assay.Rd @@ -9,12 +9,10 @@ transform_assay(summarized_experiment, assay_index = 2) \arguments{ \item{summarized_experiment}{SE} -\item{assay_index}{Either Integer for Index of Assay or a matrix or dataframe the norm factor is to be calculated from.} - -\item{name}{Name of assay} +\item{assay_index}{Integer - index of to be transformed assay} } \description{ -Short function to add assay to SE. +Short function log2 transform assay } \examples{ diff --git a/man/use_biomaRt.Rd b/man/use_biomaRt.Rd index 0c7dfac..3c9fc1d 100644 --- a/man/use_biomaRt.Rd +++ b/man/use_biomaRt.Rd @@ -12,5 +12,5 @@ use_biomaRt(gene_names, ...) \item{summarized_experiment}{SE} } \description{ -Short function to add assay to SE. +Short function get information from biomaRt. } diff --git a/man/use_mclust.Rd b/man/use_mclust.Rd index 644189f..15fbf1c 100644 --- a/man/use_mclust.Rd +++ b/man/use_mclust.Rd @@ -4,11 +4,11 @@ \alias{use_mclust} \title{MClust to Identify Multimodal Genes} \usage{ -use_mclust(summExperiment, index_assay = 1, parallel = TRUE, +use_mclust(summarized_experiment, index_assay = 1, parallel = TRUE, no_cluster = NULL, ...) } \arguments{ -\item{summExperiment}{SummarizedExperiment or any data frame like object.} +\item{summarized_experiment}{SummarizedExperiment or any data frame like object.} \item{index_assay}{Integer - index of assay of gene expression if input object is a SummarizedExperiment.} @@ -34,5 +34,5 @@ This function applies the silvermantest on every row (gene) } \details{ Also pay attention to your memory. If you have many -If filter is set to TRUE the function returns an object with the same class as summExperiment. Otherwise a vector of p-values is returned. +If filter is set to TRUE the function returns an object with the same class as summarized_experiment. Otherwise a vector of p-values is returned. } diff --git a/man/use_siber.Rd b/man/use_siber.Rd index 1e64f77..7ca7164 100644 --- a/man/use_siber.Rd +++ b/man/use_siber.Rd @@ -4,15 +4,16 @@ \alias{use_siber} \title{SIBER to calculate BI} \usage{ -use_siber(summExperiment, index_assay = 1, norm_or_method = "TMM", - model = "LN", parallel = TRUE, no_cluster = NULL, ...) +use_siber(summarized_experiment, index_assay = 1, + norm_or_method = "TMM", model = "LN", parallel = TRUE, + no_cluster = NULL, ...) } \arguments{ -\item{summExperiment}{SummarizedExperiment or any data frame like object.} +\item{summarized_experiment}{SummarizedExperiment or any data frame like object.} \item{index_assay}{Integer - index of assay of gene expression if input object is a SummarizedExperiment.} -\item{norm_or_method}{Character/Numeric - normalization method or a scaling vector that is applied to the expression.} +\item{norm_or_method}{Character/Numeric - normalization method or a scaling vector that is applied to the expression data} \item{model}{Character - model used in the calculation of the bimodal index (see SIBER::model)} @@ -26,8 +27,8 @@ use_siber(summExperiment, index_assay = 1, norm_or_method = "TMM", Returns either a vector of pValues or a filtered input object. } \description{ -This function applies SIBER::SIBER to calculate the bimodal index for a set of genes. +SIBER to calculate BI } \details{ -If filter is set to TRUE the function returns an object with the same class as summExperiment. Otherwise a vector of p-values is returned. +If filter is set to TRUE the function returns an object with the same class as summarized_experiment. Otherwise a vector of p-values is returned. } diff --git a/man/verify_mclust.Rd b/man/verify_mclust.Rd index d84b353..fc5e2cc 100644 --- a/man/verify_mclust.Rd +++ b/man/verify_mclust.Rd @@ -1,5 +1,5 @@ % Generated by roxygen2: do not edit by hand -% Please edit documentation in R/verify_output.R +% Please edit documentation in R/verify_mclust.R \name{verify_mclust} \alias{verify_mclust} \title{Verify Results of Mclust} diff --git a/termClusterBimodalBRCA.tab b/termClusterBimodalBRCA.tab new file mode 100644 index 0000000..e824881 --- /dev/null +++ b/termClusterBimodalBRCA.tab @@ -0,0 +1,177 @@ +Annotation Cluster 1 Enrichment Score: 3.449809186275346 +Category Term Count % PValue Genes List Total Pop Hits Pop Total Fold Enrichment Bonferroni Benjamini FDR +UP_KEYWORDS Developmental protein 26 14.285714285714285 6.162599422415074E-7 6657, 2066, 3227, 3228, 7546, 2019, 222171, 3215, 22854, 1750, 1745, 3226, 2016, 3169, 56165, 11197, 55859, 9118, 170302, 3195, 246777, 150094, 2020, 91646, 6664, 7545 178 949 20581 3.1677697398799447 1.3310332949412196E-4 1.3310332949412196E-4 7.821418825715298E-4 +UP_KEYWORDS Neurogenesis 9 4.945054945054945 0.0014810359293973804 9118, 7546, 170302, 22854, 6607, 6664, 6606, 7545, 55859 178 250 20581 4.162449438202247 0.27395326241548223 0.051958323270428264 1.8635121250236808 +UP_KEYWORDS Differentiation 15 8.241758241758241 0.0019297798814502073 23581, 7546, 84072, 22854, 23532, 56165, 55859, 9118, 130951, 170302, 9699, 150094, 91646, 6664, 7545 178 667 20581 2.6002307834846623 0.34113404379702283 0.057863418829128266 2.4217963024020017 +GOTERM_BP_DIRECT GO:0030154~cell differentiation 11 6.043956043956044 0.00901417420991699 9118, 25803, 7546, 10551, 130951, 155465, 23532, 91646, 7031, 7545, 55859 152 462 16792 2.630325814536341 0.9986775839964753 0.8093038065318 12.83546461161894 + +Annotation Cluster 2 Enrichment Score: 2.941170231391956 +Category Term Count % PValue Genes List Total Pop Hits Pop Total Fold Enrichment Bonferroni Benjamini FDR +UP_KEYWORDS GPI-anchor 9 4.945054945054945 2.4866009586286438E-5 10942, 10232, 8581, 22854, 646627, 54742, 419, 2674, 762 178 137 20581 7.595710653653736 0.005356726149665203 0.0017887731848771349 0.03155485108400358 +GOTERM_CC_DIRECT GO:0031225~anchored component of membrane 8 4.395604395604396 6.497538540705425E-5 10942, 10232, 8581, 646627, 54742, 419, 2674, 762 162 113 18224 7.964164754725227 0.009313121217743081 0.009313121217743081 0.07701599254249514 +UP_SEQ_FEATURE lipid moiety-binding region:GPI-anchor amidated serine 6 3.296703296703297 1.0455277255433607E-4 10942, 10232, 22854, 419, 2674, 762 172 55 20063 12.724947145877378 0.05450172552966992 0.018507662239645617 0.1519240698996116 +UP_SEQ_FEATURE propeptide:Removed in mature form 9 4.945054945054945 9.941837450356693E-4 10942, 10232, 8581, 22854, 646627, 54742, 419, 2674, 762 172 237 20063 4.429570209007949 0.41324478396872233 0.10114137138370471 1.4359657739775655 +UP_KEYWORDS Lipoprotein 15 8.241758241758241 0.015579903179937581 10232, 5241, 8581, 22854, 2925, 646627, 54742, 762, 2891, 2099, 10942, 123099, 367, 419, 2674 178 852 20581 2.0356266814369364 0.9663502550016845 0.2653351653110254 18.069064340027353 +GOTERM_CC_DIRECT GO:0009986~cell surface 4 2.197802197802198 0.8615027816827123 10232, 8581, 54742, 762 162 542 18224 0.8302127465719101 1.0 0.9999975992804818 99.99999999339578 + +Annotation Cluster 3 Enrichment Score: 2.403837544782845 +Category Term Count % PValue Genes List Total Pop Hits Pop Total Fold Enrichment Bonferroni Benjamini FDR +UP_SEQ_FEATURE repeat:PXXP 5 5 2.7472527472527473 6.462995547664862E-6 56137, 56138, 56144, 56136, 56142 172 15 20063 38.88178294573643 0.0034581834702003267 0.0017305892045976767 0.009397520650167301 +UP_SEQ_FEATURE repeat:PXXP 1 5 2.7472527472527473 6.462995547664862E-6 56137, 56138, 56144, 56136, 56142 172 15 20063 38.88178294573643 0.0034581834702003267 0.0017305892045976767 0.009397520650167301 +UP_SEQ_FEATURE repeat:PXXP 2 5 2.7472527472527473 6.462995547664862E-6 56137, 56138, 56144, 56136, 56142 172 15 20063 38.88178294573643 0.0034581834702003267 0.0017305892045976767 0.009397520650167301 +UP_SEQ_FEATURE repeat:PXXP 3 5 2.7472527472527473 6.462995547664862E-6 56137, 56138, 56144, 56136, 56142 172 15 20063 38.88178294573643 0.0034581834702003267 0.0017305892045976767 0.009397520650167301 +UP_SEQ_FEATURE repeat:PXXP 4 5 2.7472527472527473 6.462995547664862E-6 56137, 56138, 56144, 56136, 56142 172 15 20063 38.88178294573643 0.0034581834702003267 0.0017305892045976767 0.009397520650167301 +INTERPRO IPR013164:Cadherin, N-terminal 5 2.7472527472527473 0.002617747448134698 56137, 56138, 56144, 56136, 56142 165 65 18559 8.652214452214453 0.6228373919195992 0.14999508222174218 3.552762287120337 +UP_SEQ_FEATURE domain:Cadherin 6 5 2.7472527472527473 0.005551477202542897 56137, 56138, 56144, 56136, 56142 172 83 20063 7.0268282432053795 0.9494039587302974 0.39183780039064253 7.775992768507556 +UP_SEQ_FEATURE domain:Cadherin 5 5 2.7472527472527473 0.012509403473718933 56137, 56138, 56144, 56136, 56142 172 105 20063 5.554540420819491 0.9988259915381295 0.5697618639130624 16.727206050923627 +UP_SEQ_FEATURE domain:Cadherin 3 5 2.7472527472527473 0.015530200906551363 56137, 56138, 56144, 56136, 56142 172 112 20063 5.207381644518272 0.9997727598025916 0.6063003601155474 20.35562334080472 +UP_SEQ_FEATURE domain:Cadherin 4 5 2.7472527472527473 0.015530200906551363 56137, 56138, 56144, 56136, 56142 172 112 20063 5.207381644518272 0.9997727598025916 0.6063003601155474 20.35562334080472 +UP_SEQ_FEATURE domain:Cadherin 1 5 2.7472527472527473 0.016953533307482414 56137, 56138, 56144, 56136, 56142 172 115 20063 5.071536905965622 0.9998953621126668 0.6000838928643006 22.013725054459055 +UP_SEQ_FEATURE domain:Cadherin 2 5 2.7472527472527473 0.016953533307482414 56137, 56138, 56144, 56136, 56142 172 115 20063 5.071536905965622 0.9998953621126668 0.6000838928643006 22.013725054459055 +INTERPRO IPR020894:Cadherin conserved site 5 2.7472527472527473 0.017991616172398226 56137, 56138, 56144, 56136, 56142 165 113 18559 4.976937516760525 0.9988335859323794 0.49103809782218244 22.163326818269912 +INTERPRO IPR002126:Cadherin 5 2.7472527472527473 0.020735130492242248 56137, 56138, 56144, 56136, 56142 165 118 18559 4.766050333846944 0.9995880305535352 0.5076652896586751 25.11132597477047 +INTERPRO IPR015919:Cadherin-like 5 2.7472527472527473 0.02190057706778876 56137, 56138, 56144, 56136, 56142 165 120 18559 4.686616161616162 0.9997354687427732 0.4966465113192675 26.33201176862292 +SMART SM00112:CA 5 2.7472527472527473 0.02397239486397685 56137, 56138, 56144, 56136, 56142 96 116 10057 4.515535201149426 0.8817870941710311 0.6561789624979749 23.112130611586114 +GOTERM_BP_DIRECT GO:0007156~homophilic cell adhesion via plasma membrane adhesion molecules 5 2.7472527472527473 0.05441915298132508 56137, 56138, 56144, 56136, 56142 152 158 16792 3.496002664890073 1.0 0.9894441897943838 57.21136182571813 +UP_SEQ_FEATURE compositionally biased region:Poly-Lys 5 2.7472527472527473 0.11355124788923103 56137, 56138, 56144, 56136, 56142 172 216 20063 2.7001238156761413 1.0 0.977635981657511 82.6689775962143 +UP_KEYWORDS Calcium 11 6.043956043956044 0.2239851598387258 56137, 56138, 50487, 6278, 56144, 56136, 7137, 56142, 143425, 5816, 55584 178 877 20581 1.450238940207295 1.0 0.8684895654734903 95.99822589253306 +UP_KEYWORDS Cell adhesion 7 3.8461538461538463 0.2314936515882698 56137, 56138, 10232, 8581, 56144, 56136, 56142 178 479 20581 1.6896976378691562 1.0 0.8498028444878685 96.46279200126315 +GOTERM_MF_DIRECT GO:0005509~calcium ion binding 8 4.395604395604396 0.3708077676831756 56137, 56138, 6278, 56144, 56136, 56142, 143425, 5816 139 717 16881 1.3550465067276722 1.0 0.9999974257621121 99.75677792934601 + +Annotation Cluster 4 Enrichment Score: 2.157560080779194 +Category Term Count % PValue Genes List Total Pop Hits Pop Total Fold Enrichment Bonferroni Benjamini FDR +INTERPRO IPR020479:Homeodomain, metazoa 11 6.043956043956044 8.526245408158355E-9 3227, 3228, 3110, 2019, 3195, 3215, 1750, 1745, 3226, 2016, 2020 165 92 18559 13.448550724637682 3.1717582634760433E-6 3.1717582634760433E-6 1.176680550774023E-5 +UP_KEYWORDS Developmental protein 26 14.285714285714285 6.162599422415074E-7 6657, 2066, 3227, 3228, 7546, 2019, 222171, 3215, 22854, 1750, 1745, 3226, 2016, 3169, 56165, 11197, 55859, 9118, 170302, 3195, 246777, 150094, 2020, 91646, 6664, 7545 178 949 20581 3.1677697398799447 1.3310332949412196E-4 1.3310332949412196E-4 7.821418825715298E-4 +UP_SEQ_FEATURE DNA-binding region:Homeobox 12 6.593406593406594 7.6761131015336E-7 3227, 3228, 3110, 2019, 170302, 3195, 3215, 1750, 1745, 3226, 2016, 2020 172 191 20063 7.3285035918665535 4.1135519041468616E-4 4.1135519041468616E-4 0.0011161885003052596 +INTERPRO IPR017970:Homeobox, conserved site 12 6.593406593406594 1.0208928670832577E-6 3227, 3228, 3110, 2019, 170302, 3195, 3215, 1750, 1745, 3226, 2016, 2020 165 190 18559 7.1039234449760755 3.7970023603928205E-4 1.8986814297550225E-4 0.0014088932987044167 +UP_KEYWORDS Homeobox 12 6.593406593406594 1.7495518305153124E-5 3227, 3228, 3110, 2019, 170302, 3195, 3215, 1750, 1745, 3226, 2016, 2020 178 262 20581 5.295737198730595 0.003771933332686772 0.0018877484634740593 0.02220268836310435 +INTERPRO IPR001356:Homeodomain 12 6.593406593406594 1.7801227608488038E-5 3227, 3228, 3110, 2019, 170302, 3195, 3215, 1750, 1745, 3226, 2016, 2020 165 256 18559 5.272443181818182 0.006600237723128344 0.002204937416770525 0.024564121938963623 +SMART SM00389:HOX 12 6.593406593406594 2.2208456057993085E-5 3227, 3228, 3110, 2019, 170302, 3195, 3215, 1750, 1745, 3226, 2016, 2020 96 250 10057 5.0285 0.0019524573055281769 0.0019524573055281769 0.024052657303619274 +GOTERM_MF_DIRECT GO:0043565~sequence-specific DNA binding 16 8.791208791208792 2.2332851696634933E-5 7021, 6657, 3110, 3228, 5241, 1745, 1750, 3226, 2016, 3169, 2099, 2297, 25803, 3195, 367, 2020 139 518 16881 3.751229132524097 0.0055677177556745505 0.0055677177556745505 0.029008629503490813 +GOTERM_MF_DIRECT GO:0001077~transcriptional activator activity, RNA polymerase II core promoter proximal region sequence-specific binding 11 6.043956043956044 2.4421571632239284E-5 7021, 3227, 6657, 2297, 5241, 3195, 367, 3169, 2099, 6664, 7545 139 236 16881 5.660620656017558 0.006086866968626592 0.0030480788767326406 0.03172131627743324 +INTERPRO IPR009057:Homeodomain-like 12 6.593406593406594 2.0368991593803905E-4 3227, 3228, 3110, 2019, 170302, 3195, 3215, 1750, 1745, 3226, 2016, 2020 165 336 18559 4.017099567099566 0.07298021151188017 0.01876676139692912 0.28073993935475716 +GOTERM_BP_DIRECT GO:0009954~proximal/distal pattern formation 4 2.197802197802198 0.00125597389246845 3227, 2019, 1745, 3226 152 24 16792 18.412280701754383 0.6014613223400103 0.3687008017904745 1.8885540179769733 +GOTERM_BP_DIRECT GO:0045944~positive regulation of transcription from RNA polymerase II promoter 18 9.89010989010989 0.007116494229406417 3227, 7021, 6657, 2019, 658, 5241, 3215, 3169, 2099, 1081, 55859, 2297, 25803, 367, 51442, 2020, 6664, 7545 152 981 16792 2.0270400772573636 0.9946352101365252 0.8249410825485105 10.268576245977112 +UP_SEQ_FEATURE compositionally biased region:Poly-Ala 10 5.4945054945054945 0.007957900558843722 84107, 6657, 3110, 2297, 7546, 2019, 54777, 246777, 367, 7545 172 404 20063 2.8872611098319134 0.9861918631492692 0.45761832019781523 10.968489659631276 +GOTERM_MF_DIRECT GO:0000978~RNA polymerase II core promoter proximal region sequence-specific DNA binding 9 4.945054945054945 0.008822542167403385 3227, 2297, 2019, 5241, 3195, 367, 148198, 2099, 7545 139 355 16881 3.0789137703921368 0.8908926267969245 0.4252704528344541 10.87424700626155 +GOTERM_MF_DIRECT GO:0000981~RNA polymerase II transcription factor activity, sequence-specific DNA binding 6 3.296703296703297 0.013246097894541826 7021, 25803, 2297, 170302, 114821, 3169 139 171 16881 4.2612646724725485 0.9643373902896029 0.4866156516198409 15.905528449184981 +UP_SEQ_FEATURE compositionally biased region:Poly-Gly 7 3.8461538461538463 0.039530488152679163 6657, 3110, 2297, 7546, 2019, 367, 6664 172 292 20063 2.796292609111182 0.9999999995914918 0.8104234224978338 44.37226861674358 +UP_KEYWORDS DNA-binding 26 14.285714285714285 0.04675184610827686 6657, 84107, 7021, 3110, 3215, 1745, 3169, 2099, 25803, 2297, 170302, 3195, 367, 6664, 7545, 3227, 3228, 7546, 2019, 5241, 1750, 2016, 3226, 148198, 2020, 80032 178 2050 20581 1.466445601534667 0.9999677529389418 0.45575614064546643 45.53890138437471 +GOTERM_MF_DIRECT GO:0003700~transcription factor activity, sequence-specific DNA binding 14 7.6923076923076925 0.05102494836929841 7021, 6657, 3110, 7546, 5241, 114821, 1750, 3169, 2099, 91074, 2297, 367, 6664, 7545 139 961 16881 1.7692451657820467 0.9999979407988836 0.8872067455854185 49.35716637329214 +UP_SEQ_FEATURE cross-link:Glycyl lysine isopeptide (Lys-Gly) (interchain with G-Cter in SUMO) 4 2.197802197802198 0.05668134613278205 7021, 6657, 5241, 367 172 102 20063 4.574327405380757 0.9999999999999739 0.8757029084068846 57.194005451734675 +GOTERM_BP_DIRECT GO:0006366~transcription from RNA polymerase II promoter 9 4.945054945054945 0.09199908005556745 7021, 3227, 6657, 2297, 3215, 3169, 2099, 6664, 7545 152 513 16792 1.938134810710988 1.0 0.9972249960845962 76.87221913688774 +GOTERM_BP_DIRECT GO:0045893~positive regulation of transcription, DNA-templated 8 4.395604395604396 0.18237456901879484 7021, 6657, 2066, 7546, 367, 2099, 6664, 7545 152 515 16792 1.716096065406234 1.0 0.9998283297829117 95.28613629127734 +UP_KEYWORDS Activator 9 4.945054945054945 0.2103020644493676 7021, 6657, 2066, 25803, 7546, 367, 3169, 2099, 7545 178 661 20581 1.5743000900916213 1.0 0.8593507046676503 95.00430738220386 +GOTERM_BP_DIRECT GO:0008284~positive regulation of cell proliferation 7 3.8461538461538463 0.24279210297475026 7021, 2066, 367, 3226, 23532, 1081, 6664 152 466 16792 1.6594759430765755 1.0 0.9999777871576536 98.52906786737466 +GOTERM_BP_DIRECT GO:0000122~negative regulation of transcription from RNA polymerase II promoter 9 4.945054945054945 0.32141102452344417 7021, 6657, 25803, 2019, 170302, 1745, 3169, 2099, 6664 152 720 16792 1.380921052631579 1.0 0.9999975048367102 99.72117327259171 +GOTERM_MF_DIRECT GO:0003682~chromatin binding 5 2.7472527472527473 0.3973382606889987 7021, 170302, 1745, 367, 2099 139 391 16881 1.5530184548013763 1.0 0.9999968242923429 99.86102213300703 +UP_KEYWORDS Transcription regulation 22 12.087912087912088 0.44602041828179195 6657, 2066, 3227, 7021, 3110, 3228, 7546, 5241, 3215, 23532, 3226, 148198, 3169, 2099, 2297, 25803, 170302, 367, 51442, 80032, 6664, 7545 178 2332 20581 1.0907886368454525 1.0 0.9738789849405709 99.94447680285867 +GOTERM_BP_DIRECT GO:0006355~regulation of transcription, DNA-templated 15 8.241758241758241 0.4873109600437807 6657, 7021, 3228, 1750, 1745, 3226, 2016, 148198, 2099, 91074, 162998, 3195, 367, 51442, 80032 152 1504 16792 1.101798712206047 1.0 0.9999999968045936 99.99603500019678 +UP_KEYWORDS Transcription 22 12.087912087912088 0.49969021881735076 6657, 2066, 3227, 7021, 3110, 3228, 7546, 5241, 3215, 23532, 3226, 148198, 3169, 2099, 2297, 25803, 170302, 367, 51442, 80032, 6664, 7545 178 2398 20581 1.0607669312442016 1.0 0.9762375856178189 99.9847664222823 +GOTERM_MF_DIRECT GO:0003677~DNA binding 15 8.241758241758241 0.5059373225963903 84107, 7021, 6657, 3110, 7546, 5241, 114821, 1745, 2016, 3169, 2099, 91074, 2297, 367, 80032 139 1674 16881 1.0882261932389572 1.0 0.9999995826894886 99.9894819449431 +GOTERM_CC_DIRECT GO:0005634~nucleus 46 25.274725274725274 0.7158114800082865 7021, 23581, 84107, 6657, 3110, 84072, 54102, 64073, 3215, 1745, 23532, 260434, 3169, 9576, 2099, 91074, 27443, 3948, 2297, 117283, 25803, 170302, 3195, 367, 51442, 6664, 7545, 2066, 3228, 2019, 7546, 5241, 6278, 1750, 2016, 3226, 148198, 26095, 55859, 150094, 2020, 80032, 6607, 5816, 6606, 84084 162 5415 18224 0.9556262325729854 1.0 0.9999574546361264 99.99996679088787 +UP_KEYWORDS Isopeptide bond 9 4.945054945054945 0.763656359770372 653781, 7021, 3227, 6657, 5241, 4137, 367, 3226, 9720 178 1132 20581 0.9192688688609203 1.0 0.9977778454996519 99.99999888018655 +UP_KEYWORDS Nucleus 41 22.52747252747253 0.8338293351033866 7021, 6657, 84107, 23581, 3110, 84072, 64073, 3215, 1745, 23532, 3169, 2099, 768, 2297, 143244, 25803, 170302, 5822, 3195, 367, 51442, 6664, 7545, 3227, 2066, 3228, 2019, 7546, 5241, 1750, 2016, 3226, 148198, 26095, 55859, 150094, 2020, 80032, 6607, 6606, 84084 178 5244 20581 0.903998363030194 1.0 0.9992375393580226 99.99999998719342 +UP_KEYWORDS Ubl conjugation 12 6.593406593406594 0.8760597396255827 653781, 7021, 3227, 6657, 2066, 7546, 5241, 4137, 367, 3226, 2099, 55859 178 1705 20581 0.8137731061978979 1.0 0.9996820266650444 99.99999999969009 +GOTERM_BP_DIRECT GO:0006351~transcription, DNA-templated 14 7.6923076923076925 0.9068902621679622 2066, 3110, 3228, 7546, 5241, 23532, 3226, 148198, 2099, 25803, 170302, 367, 51442, 80032 152 1955 16792 0.7911158971597793 1.0 1.0 99.99999999999997 +GOTERM_CC_DIRECT GO:0005654~nucleoplasm 13 7.142857142857142 0.9991324394029946 3227, 2066, 6657, 5241, 114821, 3226, 2099, 9118, 5822, 367, 6607, 6606, 7545 162 2784 18224 0.5252944515396621 1.0 0.9999999999999998 100.0 + +Annotation Cluster 5 Enrichment Score: 2.1192432946109103 +Category Term Count % PValue Genes List Total Pop Hits Pop Total Fold Enrichment Bonferroni Benjamini FDR +UP_KEYWORDS Glycoprotein 60 32.967032967032964 3.751516211355481E-4 340895, 2099, 55584, 11197, 11012, 50487, 40, 2674, 80736, 6564, 2066, 771, 10232, 8581, 6545, 2891, 4588, 1081, 9543, 390928, 9118, 246777, 10720, 64167, 2562, 139411, 22854, 646627, 762, 866, 768, 55117, 3760, 6538, 10942, 56137, 56138, 57094, 162998, 63982, 3359, 2528, 419, 4948, 56136, 440348, 27202, 4137, 27344, 2925, 10218, 54742, 56142, 1114, 9568, 8001, 116844, 56144, 144568, 147381 178 4551 20581 1.5243717271670134 0.07785053014231835 0.01607892231413932 0.4750920619621346 +UP_SEQ_FEATURE signal peptide 46 25.274725274725274 9.135603355703297E-4 2562, 22854, 646627, 762, 866, 768, 55584, 11197, 374897, 56137, 10942, 56138, 57094, 11012, 50487, 3359, 419, 56136, 2674, 2066, 1469, 658, 771, 10232, 8581, 155465, 27344, 10218, 29989, 54742, 2891, 56142, 4588, 1081, 1114, 9543, 9568, 7031, 390928, 8001, 10551, 116844, 3938, 246777, 10720, 56144 172 3346 20063 1.603612088019016 0.38730752863949636 0.11527024018179977 1.3202353969828606 +UP_KEYWORDS Signal 52 28.57142857142857 0.0038321398928943466 340895, 55584, 11197, 374897, 11012, 50487, 2674, 6664, 2066, 771, 10232, 8581, 155465, 29989, 2891, 4588, 1081, 9543, 7031, 390928, 246777, 10720, 8209, 2562, 22854, 646627, 762, 866, 768, 10942, 56137, 56138, 57094, 3359, 419, 56136, 440348, 1469, 658, 27344, 10218, 54742, 56142, 1114, 9568, 8001, 10551, 116844, 3938, 56144, 144568, 147381 178 4160 20581 1.4452949438202247 0.5636594630367275 0.09847412677045075 4.756191572530854 +UP_KEYWORDS Cell membrane 40 21.978021978021978 0.012180345176653343 2562, 139411, 22854, 54102, 646627, 23532, 762, 2099, 768, 55584, 56137, 10942, 56138, 9699, 162998, 63982, 50487, 3359, 419, 40, 56136, 2674, 10804, 2066, 27202, 658, 10232, 4137, 8581, 5174, 2925, 54742, 2891, 56142, 9568, 375519, 8001, 3938, 2849, 56144 178 3175 20581 1.4566752189684153 0.9291442271275756 0.23257220613104213 14.404689210370469 +UP_KEYWORDS Disulfide bond 42 23.076923076923077 0.015883384675607366 2562, 22854, 340895, 762, 768, 55584, 11197, 10942, 57094, 11012, 162998, 3359, 50487, 419, 40, 2674, 2066, 1469, 27202, 658, 771, 10232, 4137, 8581, 6278, 2925, 10218, 29989, 2891, 4588, 1081, 143425, 1114, 9543, 9568, 7031, 8001, 10551, 116844, 2849, 144568, 64167 178 3434 20581 1.4141499741514136 0.9685183211997886 0.2503851921963267 18.389057206115 +UP_SEQ_FEATURE glycosylation site:N-linked (GlcNAc...) 48 26.373626373626376 0.027667021717424377 2562, 139411, 22854, 646627, 866, 768, 55117, 6538, 55584, 11197, 56137, 10942, 56138, 57094, 162998, 11012, 63982, 50487, 3359, 2528, 419, 40, 56136, 4948, 2674, 80736, 6564, 2066, 27202, 771, 10232, 6545, 2925, 10218, 54742, 2891, 56142, 4588, 1081, 9543, 9568, 390928, 8001, 116844, 246777, 10720, 56144, 64167 172 4234 20063 1.3223846821412486 0.999999705660547 0.7144136977961463 33.50079592878764 +UP_KEYWORDS Secreted 26 14.285714285714285 0.03043235525887196 646627, 100462977, 866, 374897, 11197, 57094, 11012, 50487, 440348, 1469, 10232, 6278, 10218, 29989, 27344, 54742, 56142, 4588, 1114, 1081, 390928, 7031, 116844, 10551, 144568, 147381 178 1965 20581 1.5298796351888384 0.9987385423064324 0.37924606987478915 32.445834822830676 +UP_SEQ_FEATURE disulfide bond 34 18.681318681318682 0.05197178097005234 2562, 22854, 340895, 762, 768, 11197, 55584, 10942, 57094, 11012, 162998, 3359, 50487, 419, 40, 2674, 2066, 1469, 27202, 771, 4137, 8581, 6278, 2925, 10218, 29989, 4588, 1081, 1114, 9543, 7031, 8001, 116844, 2849 172 2917 20063 1.3595961126037421 0.9999999999996231 0.8704058001085256 53.97913458813029 + +Annotation Cluster 6 Enrichment Score: 1.3904267278499998 +Category Term Count % PValue Genes List Total Pop Hits Pop Total Fold Enrichment Bonferroni Benjamini FDR +UP_KEYWORDS Ligand-gated ion channel 5 2.7472527472527473 0.005032680068280737 2562, 8001, 3359, 2891, 55584 178 80 20581 7.226474719101123 0.6637174389689773 0.11404514169004909 6.202785886059359 +INTERPRO IPR018000:Neurotransmitter-gated ion-channel, conserved site 4 2.197802197802198 0.007786495629578381 2562, 8001, 3359, 55584 165 46 18559 9.78076416337286 0.9454104249268537 0.30475365528838494 10.22642816296695 +INTERPRO IPR006202:Neurotransmitter-gated ion-channel ligand-binding 4 2.197802197802198 0.008758838603804806 2562, 8001, 3359, 55584 165 48 18559 9.373232323232322 0.9620938246935589 0.3048494268116566 11.43296786001603 +INTERPRO IPR006201:Neurotransmitter-gated ion-channel 4 2.197802197802198 0.008758838603804806 2562, 8001, 3359, 55584 165 48 18559 9.373232323232322 0.9620938246935589 0.3048494268116566 11.43296786001603 +INTERPRO IPR006029:Neurotransmitter-gated ion-channel transmembrane domain 4 2.197802197802198 0.008758838603804806 2562, 8001, 3359, 55584 165 48 18559 9.373232323232322 0.9620938246935589 0.3048494268116566 11.43296786001603 +KEGG_PATHWAY hsa04080:Neuroactive ligand-receptor interaction 7 3.8461538461538463 0.014484859452634228 2562, 8001, 2925, 2891, 1081, 9568, 55584 51 277 6879 3.408579316203016 0.7961551312892555 0.7961551312892555 15.174389086280316 +UP_KEYWORDS Postsynaptic cell membrane 6 3.296703296703297 0.019433904563110997 2562, 8001, 3359, 2891, 9568, 55584 178 179 20581 3.875651245998368 0.9855786963918078 0.27825304037746146 22.04819303871558 +UP_KEYWORDS Synapse 8 4.395604395604396 0.03564714271807114 2562, 8001, 9699, 3359, 2891, 143425, 9568, 55584 178 357 20581 2.5910049413023635 0.9996064772327075 0.4070774183535971 36.914996999423266 +UP_KEYWORDS Ion channel 8 4.395604395604396 0.03619971885191092 2562, 8001, 54102, 3359, 40, 2891, 3760, 55584 178 359 20581 2.5765703733842447 0.9996523017467516 0.3921097793247278 37.37224437478 +GOTERM_CC_DIRECT GO:0045211~postsynaptic membrane 6 3.296703296703297 0.03936953161720598 2562, 8001, 3359, 2891, 9568, 55584 162 211 18224 3.1988766017202037 0.9969230855738785 0.6854982375141658 37.88939412246527 +GOTERM_BP_DIRECT GO:0034220~ion transmembrane transport 6 3.296703296703297 0.04132404919171412 2562, 8001, 63982, 3359, 40, 2891 152 210 16792 3.1563909774436087 0.9999999999999617 0.9878829366154407 47.28352225766842 +GOTERM_CC_DIRECT GO:0030054~cell junction 9 4.945054945054945 0.05136089931154651 2562, 8001, 9699, 3359, 2891, 10804, 143425, 9568, 55584 162 459 18224 2.2057613168724277 0.9994958647493926 0.7178860829899036 46.48441241940434 +GOTERM_CC_DIRECT GO:0005887~integral component of plasma membrane 19 10.43956043956044 0.07489584349598365 2562, 27202, 658, 6545, 2925, 56142, 2891, 9543, 9568, 55117, 6538, 55584, 56138, 8001, 3938, 56144, 419, 40, 6564 162 1415 18224 1.510517820529599 0.999986465224888 0.7983988494607317 60.27053535109786 +UP_KEYWORDS Cell junction 10 5.4945054945054945 0.12883470835786498 2562, 8001, 9699, 3359, 2891, 10804, 143425, 9568, 375519, 55584 178 675 20581 1.7129421556387847 0.9999999999998848 0.726179368023149 82.63125529707513 +UP_KEYWORDS Ion transport 9 4.945054945054945 0.18939841463683946 2562, 8001, 54102, 3359, 40, 2891, 55117, 3760, 55584 178 642 20581 1.6208915257796912 1.0 0.8370342432869968 93.04010774549528 +UP_KEYWORDS Receptor 18 9.89010989010989 0.2515645923122232 2562, 2066, 27202, 658, 5241, 2925, 2891, 219995, 2099, 9568, 26095, 55584, 8001, 162998, 2849, 3359, 367, 2674 178 1648 20581 1.2628790771244682 1.0 0.8672178136950223 97.47191276176753 +GOTERM_BP_DIRECT GO:0007165~signal transduction 12 6.593406593406594 0.47400687237427164 2562, 2066, 2974, 5241, 3359, 367, 2891, 1081, 2099, 343578, 55584, 11197 152 1161 16792 1.141846865225078 1.0 0.999999996910472 99.99415163534418 +UP_KEYWORDS Transport 18 9.89010989010989 0.5386874557880941 2562, 6545, 54102, 29989, 2891, 866, 55117, 3760, 6538, 55584, 8001, 143244, 63982, 3359, 4948, 40, 6564, 2172 178 1978 20581 1.0521864100612353 1.0 0.9812942276379711 99.99456129374636 + +Annotation Cluster 7 Enrichment Score: 0.9738877944073565 +Category Term Count % PValue Genes List Total Pop Hits Pop Total Fold Enrichment Bonferroni Benjamini FDR +UP_KEYWORDS Glycoprotein 60 32.967032967032964 3.751516211355481E-4 340895, 2099, 55584, 11197, 11012, 50487, 40, 2674, 80736, 6564, 2066, 771, 10232, 8581, 6545, 2891, 4588, 1081, 9543, 390928, 9118, 246777, 10720, 64167, 2562, 139411, 22854, 646627, 762, 866, 768, 55117, 3760, 6538, 10942, 56137, 56138, 57094, 162998, 63982, 3359, 2528, 419, 4948, 56136, 440348, 27202, 4137, 27344, 2925, 10218, 54742, 56142, 1114, 9568, 8001, 116844, 56144, 144568, 147381 178 4551 20581 1.5243717271670134 0.07785053014231835 0.01607892231413932 0.4750920619621346 +UP_KEYWORDS Cell membrane 40 21.978021978021978 0.012180345176653343 2562, 139411, 22854, 54102, 646627, 23532, 762, 2099, 768, 55584, 56137, 10942, 56138, 9699, 162998, 63982, 50487, 3359, 419, 40, 56136, 2674, 10804, 2066, 27202, 658, 10232, 4137, 8581, 5174, 2925, 54742, 2891, 56142, 9568, 375519, 8001, 3938, 2849, 56144 178 3175 20581 1.4566752189684153 0.9291442271275756 0.23257220613104213 14.404689210370469 +UP_SEQ_FEATURE glycosylation site:N-linked (GlcNAc...) 48 26.373626373626376 0.027667021717424377 2562, 139411, 22854, 646627, 866, 768, 55117, 6538, 55584, 11197, 56137, 10942, 56138, 57094, 162998, 11012, 63982, 50487, 3359, 2528, 419, 40, 56136, 4948, 2674, 80736, 6564, 2066, 27202, 771, 10232, 6545, 2925, 10218, 54742, 2891, 56142, 4588, 1081, 9543, 9568, 390928, 8001, 116844, 246777, 10720, 56144, 64167 172 4234 20063 1.3223846821412486 0.999999705660547 0.7144136977961463 33.50079592878764 +GOTERM_CC_DIRECT GO:0005887~integral component of plasma membrane 19 10.43956043956044 0.07489584349598365 2562, 27202, 658, 6545, 2925, 56142, 2891, 9543, 9568, 55117, 6538, 55584, 56138, 8001, 3938, 56144, 419, 40, 6564 162 1415 18224 1.510517820529599 0.999986465224888 0.7983988494607317 60.27053535109786 +UP_SEQ_FEATURE topological domain:Extracellular 31 17.032967032967033 0.10342997600018805 2562, 768, 3760, 55117, 55584, 6538, 56137, 56138, 63982, 162998, 3359, 56136, 4948, 40, 10804, 80736, 6564, 2066, 27202, 658, 771, 2925, 56142, 2891, 9543, 9568, 375519, 8001, 3938, 2849, 56144 172 2787 20063 1.2974545439373837 1.0 0.9742028821988331 79.55813776750928 +GOTERM_CC_DIRECT GO:0005886~plasma membrane 44 24.175824175824175 0.12541476527099324 2562, 139411, 54102, 646627, 23532, 762, 2099, 768, 3760, 55117, 6538, 55584, 56137, 10942, 2974, 162998, 63982, 50487, 3359, 367, 40, 56136, 2674, 80736, 6564, 2066, 27202, 658, 771, 10232, 4137, 8581, 1733, 5174, 2925, 54742, 2891, 143425, 9568, 8001, 3938, 2849, 56144, 64167 162 4121 18224 1.2010988583018025 0.9999999958360231 0.9103730662478297 79.58584358370081 +UP_KEYWORDS Receptor 18 9.89010989010989 0.2515645923122232 2562, 2066, 27202, 658, 5241, 2925, 2891, 219995, 2099, 9568, 26095, 55584, 8001, 162998, 2849, 3359, 367, 2674 178 1648 20581 1.2628790771244682 1.0 0.8672178136950223 97.47191276176753 +UP_SEQ_FEATURE topological domain:Cytoplasmic 34 18.681318681318682 0.2635404003509408 2562, 768, 3760, 55117, 55584, 6538, 56137, 56138, 63982, 162998, 3359, 2528, 40, 56136, 4948, 10804, 80736, 6564, 2066, 27202, 658, 771, 2925, 56142, 2891, 143425, 9543, 9568, 375519, 8001, 3938, 2849, 56144, 64167 172 3456 20063 1.14755262166236 1.0 0.9991983359698856 98.82997795472974 +UP_SEQ_FEATURE transmembrane region 46 25.274725274725274 0.39656355093251966 2562, 139411, 54102, 340895, 343702, 768, 55117, 3760, 6538, 55584, 56137, 56138, 123099, 162998, 63982, 3359, 2528, 40, 56136, 4948, 10804, 80736, 6564, 2066, 27202, 658, 771, 93273, 6545, 1733, 2925, 2891, 56142, 219995, 143425, 54898, 9543, 9568, 375519, 8001, 3938, 2849, 10720, 56144, 147381, 64167 172 5056 20063 1.061251195908154 1.0 0.9998796026766295 99.93541485405774 +UP_KEYWORDS Transmembrane 51 28.021978021978022 0.4346845015184348 54102, 340895, 343702, 2099, 55584, 123099, 40, 80736, 6564, 2066, 771, 6545, 2891, 219995, 54898, 9543, 2849, 10720, 8293, 64167, 2562, 139411, 762, 768, 55117, 3760, 6538, 3948, 56137, 56138, 162998, 63982, 3359, 2528, 367, 419, 4948, 56136, 10804, 27202, 658, 93273, 1733, 2925, 56142, 143425, 9568, 375519, 8001, 3938, 56144 178 5651 20581 1.0434973227369522 1.0 0.9733118414821873 99.92819975628457 +UP_KEYWORDS Transmembrane helix 50 27.472527472527474 0.4918281953117448 54102, 340895, 343702, 55584, 123099, 40, 80736, 6564, 2066, 771, 6545, 2891, 219995, 54898, 9543, 2849, 10720, 8293, 64167, 2562, 139411, 762, 768, 55117, 3760, 6538, 3948, 56137, 56138, 162998, 63982, 3359, 2528, 367, 419, 4948, 56136, 10804, 27202, 658, 93273, 1733, 2925, 56142, 143425, 9568, 375519, 8001, 3938, 56144 178 5634 20581 1.026123495790007 1.0 0.9786743557889206 99.98143284624086 +UP_KEYWORDS Membrane 66 36.26373626373626 0.4940562982488419 54102, 340895, 343702, 2099, 55584, 143244, 123099, 9699, 50487, 40, 2674, 80736, 6564, 2066, 771, 10232, 8581, 5174, 6545, 2891, 219995, 9543, 54898, 2849, 10720, 8293, 64167, 2562, 139411, 22854, 646627, 23532, 762, 55117, 768, 3760, 6538, 3948, 10942, 56137, 56138, 162998, 63982, 3359, 2528, 367, 419, 4948, 56136, 10804, 2172, 27202, 5241, 658, 93273, 4137, 1733, 2925, 54742, 56142, 143425, 9568, 375519, 8001, 3938, 56144 178 7494 20581 1.0183022822752585 1.0 0.9770289217135221 99.98243999349927 +GOTERM_CC_DIRECT GO:0016021~integral component of membrane 45 24.725274725274726 0.6406244356726754 2562, 139411, 340895, 762, 343702, 2099, 768, 3760, 55117, 6538, 56137, 3948, 123099, 130951, 162998, 63982, 3359, 2528, 367, 419, 56136, 4948, 10804, 80736, 6564, 2066, 658, 771, 93273, 6545, 1733, 2925, 2891, 219995, 143425, 54898, 9543, 9568, 375519, 8001, 2849, 10720, 56144, 8293, 64167 162 5163 18224 0.9804807713000625 1.0 0.9999000145291634 99.99946295248922 + +Annotation Cluster 8 Enrichment Score: 0.42768254431417846 +Category Term Count % PValue Genes List Total Pop Hits Pop Total Fold Enrichment Bonferroni Benjamini FDR +UP_SEQ_FEATURE repeat:LRR 7 4 2.197802197802198 0.19027927345202658 116844, 79782, 23532, 55655 172 176 20063 2.6510306553911205 1.0 0.9974052869828252 95.3538825142897 +UP_SEQ_FEATURE repeat:LRR 6 4 2.197802197802198 0.2661511371550725 116844, 79782, 23532, 55655 172 209 20063 2.2324468676977856 1.0 0.9990033378358589 98.8888640025681 +UP_SEQ_FEATURE repeat:LRR 5 4 2.197802197802198 0.31445881316343505 116844, 79782, 23532, 55655 172 231 20063 2.0198328802979963 1.0 0.9994441439127867 99.5871987208959 +UP_SEQ_FEATURE repeat:LRR 4 4 2.197802197802198 0.37159397412643835 116844, 79782, 23532, 55655 172 255 20063 1.8297309621523026 1.0 0.9998626768779335 99.88353788155375 +UP_SEQ_FEATURE repeat:LRR 3 4 2.197802197802198 0.4751489608616047 116844, 79782, 23532, 55655 172 302 20063 1.5449715077776065 1.0 0.9999716399536385 99.99150809042443 +UP_KEYWORDS Leucine-rich repeat 4 2.197802197802198 0.5016150035993112 116844, 79782, 23532, 55655 178 311 20581 1.48712019942917 1.0 0.9744915723171945 99.98549374151091 +UP_SEQ_FEATURE repeat:LRR 1 4 2.197802197802198 0.517297353396843 116844, 79782, 23532, 55655 172 321 20063 1.4535245961022967 1.0 0.9999896889429261 99.99748613382812 +UP_SEQ_FEATURE repeat:LRR 2 4 2.197802197802198 0.5193341038114501 116844, 79782, 23532, 55655 172 322 20063 1.4490105445616062 1.0 0.9999865829344973 99.99763604483924 + +Annotation Cluster 9 Enrichment Score: 0.3260497679395017 +Category Term Count % PValue Genes List Total Pop Hits Pop Total Fold Enrichment Bonferroni Benjamini FDR +UP_KEYWORDS Zymogen 5 2.7472527472527473 0.11343101684752654 10942, 23581, 3938, 57094, 11012 178 214 20581 2.7014858762994858 0.9999999999949195 0.6933576423643788 78.30408306571553 +GOTERM_BP_DIRECT GO:0006508~proteolysis 5 2.7472527472527473 0.6620167254591071 10942, 23581, 57094, 11012, 64167 152 500 16792 1.104736842105263 1.0 0.9999999999995169 99.9999928723469 +UP_KEYWORDS Protease 5 2.7472527472527473 0.6916273316979858 10942, 23581, 57094, 11012, 64167 178 544 20581 1.0627168704560477 1.0 0.9968966765667909 99.99996723169261 +UP_KEYWORDS Hydrolase 10 5.4945054945054945 0.9557141009357408 10942, 23581, 3938, 57094, 11012, 50487, 91646, 26095, 64167, 390928 178 1671 20581 0.6919425224752722 1.0 0.9999771637675823 100.0 + +Annotation Cluster 10 Enrichment Score: 0.22165335801452607 +Category Term Count % PValue Genes List Total Pop Hits Pop Total Fold Enrichment Bonferroni Benjamini FDR +UP_SEQ_FEATURE metal ion-binding site:Zinc; catalytic 5 2.7472527472527473 0.024659026670566384 771, 57094, 762, 64167, 768 172 129 20063 4.521137551829818 0.999998458770289 0.703773227640793 30.445904936985237 +GOTERM_MF_DIRECT GO:0008270~zinc ion binding 11 6.043956043956044 0.48834647656967145 23217, 5241, 771, 57094, 6278, 367, 762, 7681, 2099, 64167, 768 139 1169 16881 1.142777138426128 1.0 0.9999997568817945 99.98343013242581 +UP_SEQ_FEATURE zinc finger region:C2H2-type 5 5 2.7472527472527473 0.6932252262936823 84107, 7546, 148198, 80032, 7545 172 550 20063 1.0604122621564482 1.0 0.9999999771274437 99.99999655036657 +GOTERM_MF_DIRECT GO:0003676~nucleic acid binding 8 4.395604395604396 0.7014263446596662 84107, 7546, 23217, 114821, 148198, 80032, 91646, 7545 139 985 16881 0.9863638023591279 1.0 0.9999999982182036 99.99998484988643 +UP_KEYWORDS Zinc 19 10.43956043956044 0.7328189704456822 84107, 7546, 5241, 771, 6278, 762, 148198, 2099, 56165, 390928, 768, 57094, 79083, 9699, 367, 7681, 80032, 64167, 7545 178 2348 20581 0.9356253469364316 1.0 0.9966595861614569 99.99999468953658 +UP_SEQ_FEATURE zinc finger region:C2H2-type 4 5 2.7472527472527473 0.7419717822092301 84107, 7546, 148198, 80032, 7545 172 588 20063 0.9918822180034804 1.0 0.999999996999975 99.9999997214066 +UP_SEQ_FEATURE zinc finger region:C2H2-type 3 5 2.7472527472527473 0.7949257904891233 84107, 7546, 148198, 80032, 7545 172 636 20063 0.9170231826824632 1.0 0.9999999998030644 99.99999999012805 +INTERPRO IPR015880:Zinc finger, C2H2-like 6 3.296703296703297 0.808327727155604 84107, 7546, 23217, 148198, 80032, 7545 165 762 18559 0.88565974707707 1.0 1.0 99.9999999874448 +GOTERM_MF_DIRECT GO:0046872~metal ion binding 15 8.241758241758241 0.811568333184451 84107, 7546, 658, 254295, 7137, 148198, 56165, 390928, 8001, 2974, 79083, 9699, 50487, 80032, 7545 139 2069 16881 0.8804691384639992 1.0 0.9999999999780973 99.9999999616686 +UP_KEYWORDS Metal-binding 28 15.384615384615385 0.8286902979377528 84107, 254295, 762, 2099, 768, 2974, 57094, 79083, 9699, 50487, 367, 7681, 7545, 7546, 658, 5241, 771, 6278, 7137, 148198, 143425, 56165, 390928, 8001, 150094, 80032, 5816, 64167 178 3640 20581 0.8894122731201383 1.0 0.9992461237484709 99.99999998114984 +INTERPRO IPR007087:Zinc finger, C2H2 6 3.296703296703297 0.8395934347660585 84107, 7546, 23217, 148198, 80032, 7545 165 799 18559 0.8446467174877688 1.0 1.0 99.99999999892472 +SMART SM00355:ZnF_C2H2 6 3.296703296703297 0.8559477826110863 84107, 7546, 23217, 148198, 80032, 7545 96 762 10057 0.8248851706036745 1.0 1.0 99.9999999231869 +INTERPRO IPR013087:Zinc finger C2H2-type/integrase DNA-binding domain 5 2.7472527472527473 0.8789939673483322 84107, 7546, 148198, 80032, 7545 165 712 18559 0.7898791283622745 1.0 1.0 99.99999999997802 +UP_KEYWORDS Zinc-finger 12 6.593406593406594 0.9073500438889529 84107, 7546, 5241, 79083, 9699, 367, 148198, 7681, 80032, 2099, 56165, 7545 178 1781 20581 0.7790472465285883 1.0 0.9998579670565123 99.99999999999228 + +Annotation Cluster 11 Enrichment Score: 0.02408525893228304 +Category Term Count % PValue Genes List Total Pop Hits Pop Total Fold Enrichment Bonferroni Benjamini FDR +UP_KEYWORDS Transferase 13 7.142857142857142 0.8063502679729133 6898, 2066, 2938, 117283, 658, 2944, 10720, 2528, 419, 150094, 9, 54898, 25830 178 1708 20581 0.8800390758624319 1.0 0.9989076095525489 99.99999991067723 +UP_KEYWORDS Kinase 4 2.197802197802198 0.9543290040003465 2066, 117283, 658, 150094 178 735 20581 0.6292440571734312 1.0 0.9999786026302252 100.0 +UP_SEQ_FEATURE nucleotide phosphate-binding region:ATP 5 2.7472527472527473 0.9726131460850646 2066, 658, 150094, 547, 55655 172 994 20063 0.5867472275513547 1.0 1.0 100.0 +UP_KEYWORDS ATP-binding 7 3.8461538461538463 0.9825254351213697 2066, 117283, 658, 150094, 547, 55655, 91646 178 1391 20581 0.5818584964337353 1.0 0.9999988301733781 100.0 +GOTERM_MF_DIRECT GO:0005524~ATP binding 7 3.8461538461538463 0.9860415465410931 2066, 117283, 658, 150094, 547, 55655, 91646 139 1495 16881 0.568643680373427 1.0 1.0 100.0 +UP_KEYWORDS Nucleotide-binding 9 4.945054945054945 0.9887521416480745 2066, 2974, 117283, 658, 150094, 547, 55655, 91646, 84084 178 1788 20581 0.5819979639544529 1.0 0.999999666147098 100.0 + +Annotation Cluster 12 Enrichment Score: 0.021806617928766064 +Category Term Count % PValue Genes List Total Pop Hits Pop Total Fold Enrichment Bonferroni Benjamini FDR +UP_KEYWORDS G-protein coupled receptor 5 2.7472527472527473 0.9347261242676015 27202, 2849, 162998, 2925, 9568 178 842 20581 0.6866009234300354 1.0 0.9999459168671053 99.99999999999991 +UP_KEYWORDS Transducer 5 2.7472527472527473 0.9534046475073696 27202, 2849, 162998, 2925, 9568 178 899 20581 0.6430678281736261 1.0 0.9999807414767424 100.0 +INTERPRO IPR000276:G protein-coupled receptor, rhodopsin-like 4 2.197802197802198 0.9556769204175043 27202, 2849, 162998, 2925 165 719 18559 0.6257512538458296 1.0 1.0 100.0 +INTERPRO IPR017452:GPCR, rhodopsin-like, 7TM 4 2.197802197802198 0.9605075544297046 27202, 2849, 162998, 2925 165 736 18559 0.6112977602108037 1.0 1.0 100.0 +