Supplementary tables for prophage analysis

Author

Lakhansing Pardeshi

Published

July 20, 2025

Metadata for all the genome in the current pangenome

Pangenome statistics: Homology group counts for the genus pangenome and individual species pangenome

GO enrichment for core, accessory and unique homology groups with respect to the pangenome background

geNomad prophage prediction result summary for 454 genomes

Prophage statistics for individual genomes

Species wise and pangenome wide prophage statistics

Prophage clustering based on syntenic Jaccard index

Prophage homology group functional categories

Anti-phage defense systems from DefenseFinder

Warning in instance$preRenderHook(instance): It seems your data is too big for
client-side DataTables. You may consider server-side processing:
https://rstudio.github.io/DT/server.html

Inhouse sample information

--- title: "Supplementary tables for prophage analysis" author: "Lakhansing Pardeshi" date: "`r Sys.Date()`" format: html: embed-resources: true df-print: paged knitr: opts_chunk: fig.height: 7 --- ```{r} #| label: setup #| echo: false #| warning: false suppressPackageStartupMessages(library(tidyverse)) suppressPackageStartupMessages(library(org.Pectobacterium.spp.pan.eg.db)) suppressPackageStartupMessages(library(DT)) suppressPackageStartupMessages(library(openxlsx)) rm(list = ls()) source("https://raw.githubusercontent.com/lakhanp1/omics_utils/main/RScripts/utils.R") source("scripts/utils/config_functions.R") source("scripts/utils/homology_groups.R") ################################################################################ set.seed(124) confs <- prefix_config_paths( conf = suppressWarnings(configr::read.config(file = "project_config.yaml")), dir = "." ) pangenome <- confs$data$pangenomes$pectobacterium.v2$name panConf <- confs$data$pangenomes[[pangenome]] panOrgDb <- org.Pectobacterium.spp.pan.eg.db ## write tables to excel file wb <- openxlsx::createWorkbook() table_counter <- 1 ``` ::: {.panel-tabset} ## Table S`r table_counter` Metadata for all the genome in the current pangenome ```{r} #| echo: false #| column: screen-inset-right metadata <- suppressMessages(readr::read_csv(panConf$files$metadata)) %>% dplyr::select(-starts_with("nodepath."), -Genome) %>% dplyr::select( genomeId, source, SpeciesName, strain, geo_loc_country, collection_year, host, blackleg_phenotype = virulence, blackleg_PCR = virulence_pcr, AssemblyAccession, BioSampleAccn, everything() ) currentSheet <- paste("Table_S", table_counter, sep = "") openxlsx::addWorksheet(wb, sheetName = currentSheet) openxlsx::writeData( wb = wb, sheet = currentSheet, x = paste("## Table S", table_counter, " Metadata for all the genome in the current pangenome", sep = "") ) openxlsx::writeDataTable( wb = wb, x = metadata, sheet = currentSheet, startCol = 1, startRow = 2, withFilter = TRUE, keepNA = TRUE, na.string = "NA" ) openxlsx::freezePane(wb = wb, sheet = currentSheet, firstActiveRow = 3, firstActiveCol = 2) DT::datatable( data = metadata, rownames = FALSE, filter = "top", class = 'compact hover', extensions = c('KeyTable', 'Scroller', 'Select', 'SearchBuilder', 'FixedColumns'), options = list( autoWidth = FALSE, dom = 'Qlfrtip', scrollX = TRUE, fixedColumns = list(leftColumns = 2), keys = TRUE, scroller = TRUE, scrollY = 600 ), selection = 'none' ) table_counter <- table_counter + 1 ``` ## Table S`r table_counter` Pangenome statistics: Homology group counts for the genus pangenome and individual species pangenome ```{r} #| echo: false #| column: screen-inset-right hg_stats <- suppressMessages( readr::read_tsv(confs$analysis$homology_groups$files$spp_group_stats) ) %>% dplyr::rename( HGs_per_class = count, HGs_pangenome = nHgs ) currentSheet <- paste("Table_S", table_counter, sep = "") openxlsx::addWorksheet(wb, sheetName = currentSheet) openxlsx::writeData( wb = wb, sheet = currentSheet, x = paste("## Table S", table_counter, ": Pangenome statistics: Homology group counts for the genus pangenome", "and individual species pangenome", sep = "") ) openxlsx::writeDataTable( wb = wb, x = hg_stats, sheet = currentSheet, startCol = 1, startRow = 2, withFilter = TRUE, keepNA = TRUE, na.string = "NA" ) openxlsx::freezePane(wb = wb, sheet = currentSheet, firstActiveRow = 3, firstActiveCol = 2) DT::datatable( data = hg_stats, rownames = FALSE, filter = "top", class = 'compact hover', extensions = c('KeyTable', 'Scroller', 'Select', 'SearchBuilder', 'FixedColumns'), options = list( autoWidth = FALSE, dom = 'Qlfrtip', scrollX = TRUE, fixedColumns = list(leftColumns = 2), keys = TRUE, scroller = TRUE, scrollY = 600 ), selection = 'none' ) table_counter <- table_counter + 1 ``` ## Table S`r table_counter` GO enrichment for core, accessory and unique homology groups with respect to the pangenome background ```{r} #| echo: false #| column: screen-inset-right go_table <- suppressMessages( readr::read_tsv(confs$analysis$homology_groups$files$spp_group_go) ) %>% dplyr::filter(SpeciesName == "pangenome") %>% dplyr::select(-SpeciesName, -subpan_class) currentSheet <- paste("Table_S", table_counter, sep = "") openxlsx::addWorksheet(wb, sheetName = currentSheet) openxlsx::writeData( wb = wb, sheet = currentSheet, x = paste("## Table S", table_counter, ": GO enrichment for core, accessory and unique homology groups", " with respect to the pangenome background", sep = "") ) openxlsx::writeDataTable( wb = wb, x = go_table, sheet = currentSheet, startCol = 1, startRow = 2, withFilter = TRUE, keepNA = TRUE, na.string = "NA" ) openxlsx::freezePane(wb = wb, sheet = currentSheet, firstActiveRow = 3, firstActiveCol = 2) DT::datatable( data = go_table, rownames = FALSE, filter = "top", class = 'compact hover', extensions = c('KeyTable', 'Scroller', 'Select', 'SearchBuilder', 'FixedColumns'), options = list( autoWidth = FALSE, dom = 'Qlfrtip', scrollX = TRUE, fixedColumns = list(leftColumns = 2), keys = TRUE, scroller = TRUE, scrollY = 600 ), selection = 'none' ) table_counter <- table_counter + 1 ``` ## Table S`r table_counter` geNomad prophage prediction result summary for 454 genomes ```{r} #| echo: false #| column: screen-inset-right prophages <- suppressMessages(readr::read_tsv(confs$data$prophages$files$data)) %>% dplyr::mutate( integrated = dplyr::if_else( condition = is.na(start) & is.na(end), true = "N", false = "Y" ) ) %>% dplyr::select(prophage_id, genomeId, everything()) %>% dplyr::relocate(integrated, .after = end) %>% dplyr::left_join( y = dplyr::select(metadata, genomeId, strain, blackleg_phenotype, blackleg_PCR), by = "genomeId" ) %>% dplyr::relocate(strain, blackleg_phenotype, blackleg_PCR, .after = SpeciesName) currentSheet <- paste("Table_S", table_counter, sep = "") openxlsx::addWorksheet(wb, sheetName = currentSheet) openxlsx::writeData( wb = wb, sheet = currentSheet, x = paste("## Table S", table_counter, ": geNomad prophage prediction result summary for 454 genomes", sep = "") ) openxlsx::writeDataTable( wb = wb, x = prophages, sheet = currentSheet, startCol = 1, startRow = 2, withFilter = TRUE, keepNA = TRUE, na.string = "NA" ) openxlsx::freezePane(wb = wb, sheet = currentSheet, firstActiveRow = 3, firstActiveCol = 2) DT::datatable( data = prophages, rownames = FALSE, filter = "top", class = 'compact hover', extensions = c('KeyTable', 'Scroller', 'Select', 'SearchBuilder', 'FixedColumns'), options = list( autoWidth = FALSE, dom = 'Qlfrtip', scrollX = TRUE, fixedColumns = list(leftColumns = 2), keys = TRUE, scroller = TRUE, scrollY = 600 ), selection = 'none' ) table_counter <- table_counter + 1 ``` ## Table S`r table_counter` Prophage statistics for individual genomes ```{r} #| echo: false #| column: screen-inset-right phage_stats_genomes <- suppressMessages( readr::read_tsv(confs$analysis$prophages$summary$files$prophage_stats_genome) ) %>% dplyr::select(-dplyr::starts_with("nodepath")) %>% dplyr::left_join( y = dplyr::select(metadata, genomeId, strain, blackleg_phenotype, blackleg_PCR), by = "genomeId" ) %>% dplyr::relocate(strain, blackleg_phenotype, blackleg_PCR, .after = SpeciesName) currentSheet <- paste("Table_S", table_counter, sep = "") openxlsx::addWorksheet(wb, sheetName = currentSheet) openxlsx::writeData( wb = wb, sheet = currentSheet, x = paste("## Table S", table_counter, ": Prophage statistics for individual genomes", sep = "") ) openxlsx::writeDataTable( wb = wb, x = phage_stats_genomes, sheet = currentSheet, startCol = 1, startRow = 2, withFilter = TRUE, keepNA = TRUE, na.string = "NA" ) openxlsx::freezePane(wb = wb, sheet = currentSheet, firstActiveRow = 3, firstActiveCol = 2) DT::datatable( data = phage_stats_genomes, rownames = FALSE, filter = "top", class = 'compact hover', extensions = c('KeyTable', 'Scroller', 'Select', 'SearchBuilder', 'FixedColumns'), options = list( autoWidth = FALSE, dom = 'Qlfrtip', scrollX = TRUE, fixedColumns = list(leftColumns = 2), keys = TRUE, scroller = TRUE, scrollY = 600 ), selection = 'none' ) table_counter <- table_counter + 1 ``` ## Table S`r table_counter` Species wise and pangenome wide prophage statistics ```{r} #| echo: false #| column: screen-inset-right phage_stats <- suppressMessages( readr::read_tsv(confs$analysis$prophages$summary$files$prophage_stats_species) ) %>% dplyr::rename( n_phages = n_vir_sp, phages_per_genome = mean_vir_per_g, HG_core = core, HG_accessory = accessory, HG_unique = unique, HG_total = total, HG_phage = phage_nHgs.total, phage_HG_ratio = phageRatio.total, phage_HG_core = phage_nHgs.core, phage_HG_accessory = phage_nHgs.accessory, phage_HG_unique = phage_nHgs.unique ) %>% dplyr::select(-dplyr::starts_with("phageRatio.")) currentSheet <- paste("Table_S", table_counter, sep = "") openxlsx::addWorksheet(wb, sheetName = currentSheet) openxlsx::writeData( wb = wb, sheet = currentSheet, x = paste("## Tabls S", table_counter, ": Species wise and pangenome wide prophage statistics", sep = "") ) openxlsx::writeDataTable( wb = wb, x = phage_stats, sheet = currentSheet, startCol = 1, startRow = 2, withFilter = TRUE, keepNA = TRUE, na.string = "NA" ) openxlsx::freezePane(wb = wb, sheet = currentSheet, firstActiveRow = 3, firstActiveCol = 2) DT::datatable( data = phage_stats, rownames = FALSE, filter = "top", class = 'compact hover', extensions = c('KeyTable', 'Scroller', 'Select', 'SearchBuilder', 'FixedColumns'), options = list( autoWidth = FALSE, dom = 'Qlfrtip', scrollX = TRUE, fixedColumns = list(leftColumns = 2), keys = TRUE, scroller = TRUE, scrollY = 600 ), selection = 'none' ) table_counter <- table_counter + 1 ``` ## Table S`r table_counter` Prophage clustering based on syntenic Jaccard index ```{r} #| echo: false #| column: screen-inset-right phage_grps <- suppressMessages( readr::read_tsv(confs$analysis$prophages$files$clusters) ) %>% dplyr::select(-starts_with("nodepath.")) %>% dplyr::left_join( y = dplyr::select(metadata, genomeId, strain, blackleg_phenotype, blackleg_PCR), by = "genomeId" ) %>% dplyr::relocate(strain, blackleg_phenotype, blackleg_PCR, .after = SpeciesName) currentSheet <- paste("Table_S", table_counter, sep = "") openxlsx::addWorksheet(wb, sheetName = currentSheet) openxlsx::writeData( wb = wb, sheet = currentSheet, x = paste("## Table S", table_counter, ": Prophage clustering based on syntenic Jaccard index", sep = "") ) openxlsx::writeDataTable( wb = wb, x = phage_grps, sheet = currentSheet, startCol = 1, startRow = 2, withFilter = TRUE, keepNA = TRUE, na.string = "NA" ) openxlsx::freezePane(wb = wb, sheet = currentSheet, firstActiveRow = 3, firstActiveCol = 2) DT::datatable( data = phage_grps, rownames = FALSE, filter = "top", class = 'compact hover', extensions = c('KeyTable', 'Scroller', 'Select', 'SearchBuilder', 'FixedColumns'), options = list( autoWidth = FALSE, dom = 'Qlfrtip', scrollX = TRUE, fixedColumns = list(leftColumns = 2), keys = TRUE, scroller = TRUE, scrollY = 600 ), selection = 'none' ) table_counter <- table_counter + 1 ``` ## Table S`r table_counter` Prophage homology group functional categories ```{r} #| echo: false #| column: screen-inset-right prophage_hg_ann <- suppressMessages( readr::read_tsv(confs$analysis$prophages$files$hg_broad_functions) ) %>% dplyr::rename(homology_group = hgId, pangenome_class = class) currentSheet <- paste("Table_S", table_counter, sep = "") openxlsx::addWorksheet(wb, sheetName = currentSheet) openxlsx::writeData( wb = wb, sheet = currentSheet, x = paste("## Table S", table_counter, ": Prophage homology group functional categories", sep = "") ) openxlsx::writeDataTable( wb = wb, x = prophage_hg_ann, sheet = currentSheet, startCol = 1, startRow = 2, withFilter = TRUE, keepNA = TRUE, na.string = "NA" ) openxlsx::freezePane(wb = wb, sheet = currentSheet, firstActiveRow = 3, firstActiveCol = 2) DT::datatable( data = prophage_hg_ann, rownames = FALSE, filter = "top", class = 'compact hover', extensions = c('KeyTable', 'Scroller', 'Select', 'SearchBuilder', 'FixedColumns'), options = list( autoWidth = FALSE, dom = 'Qlfrtip', scrollX = TRUE, fixedColumns = list(leftColumns = 3), keys = TRUE, scroller = TRUE, scrollY = 600 ), selection = 'none' ) table_counter <- table_counter + 1 ``` ## Table S`r table_counter` Anti-phage defense systems from DefenseFinder ```{r} #| echo: false #| column: screen-inset-right defense_systems <- suppressMessages( readr::read_tsv(confs$analysis$defense_systems$files$data) ) currentSheet <- paste("Table_S", table_counter, sep = "") openxlsx::addWorksheet(wb, sheetName = currentSheet) openxlsx::writeData( wb = wb, sheet = currentSheet, x = paste("## Table S", table_counter, ": Anti-phage defense systems identified by DefenseFinder", sep = "") ) openxlsx::writeDataTable( wb = wb, x = defense_systems, sheet = currentSheet, startCol = 1, startRow = 2, withFilter = TRUE, keepNA = TRUE, na.string = "NA" ) openxlsx::freezePane(wb = wb, sheet = currentSheet, firstActiveRow = 3, firstActiveCol = 2) DT::datatable( data = defense_systems, rownames = FALSE, filter = "top", class = 'compact hover', extensions = c('KeyTable', 'Scroller', 'Select', 'SearchBuilder', 'FixedColumns'), options = list( autoWidth = FALSE, dom = 'Qlfrtip', scrollX = TRUE, fixedColumns = list(leftColumns = 3), keys = TRUE, scroller = TRUE, scrollY = 600 ), selection = 'none' ) table_counter <- table_counter + 1 ``` ## Table S`r table_counter` Inhouse sample information ```{r} #| echo: false #| column: screen-inset-right inhouse_samples <- dplyr::filter(metadata, source != "NCBI") %>% dplyr::select(genomeId, source, sampleId, AssemblyAccession, BioSampleAccn, BioprojectAccn) currentSheet <- paste("Table_S", table_counter, sep = "") openxlsx::addWorksheet(wb, sheetName = currentSheet) openxlsx::writeData( wb = wb, sheet = currentSheet, x = paste("## Table S", table_counter, ": Inhouse genome assemblies", sep = "") ) openxlsx::writeDataTable( wb = wb, x = inhouse_samples, sheet = currentSheet, startCol = 1, startRow = 2, withFilter = TRUE, keepNA = TRUE, na.string = "NA" ) openxlsx::freezePane(wb = wb, sheet = currentSheet, firstActiveRow = 3, firstActiveCol = 2) DT::datatable( data = inhouse_samples, rownames = FALSE, filter = "top", class = 'compact hover', extensions = c('KeyTable', 'Scroller', 'Select', 'SearchBuilder', 'FixedColumns'), options = list( autoWidth = FALSE, dom = 'Qlfrtip', scrollX = TRUE, fixedColumns = list(leftColumns = 2), keys = TRUE, scroller = TRUE, scrollY = 600 ), selection = 'none' ) table_counter <- table_counter + 1 ``` ::: ```{r} #| echo: false # save all table to Excel file openxlsx::saveWorkbook( wb = wb, overwrite = TRUE, file = file.path("reports/manuscript_prophages", "ms_prophages_supplementary_data.xlsx") ) ```