Refactored function names in R/summarize.R

NAMESPACE

@@ -32,7 +32,7 @@ export(convertAlignment2FA)
 export(convertAlignment2Trees)
 export(convertFA2Tree)
 export(convert_aln2fa)
-export(count_bycol)
+export(countByColumn)
 export(createFA2Tree)
 export(createWordCloud2Element)
 export(createWordCloudElement)
@@ -41,9 +41,9 @@ export(domain_network)
 export(downloadAssemblySummary)
 export(efetchIPG)
 export(extractAccNum)
-export(filter_by_doms)
-export(filter_freq)
-export(find_paralogs)
+export(filterByDomains)
+export(filterByFrequency)
+export(findParalogs)
 export(find_top_acc)
 export(format_job_args)
 export(gc_undirected_network)
@@ -91,15 +91,15 @@ export(selectLongestDuplicate)
 export(send_job_status_email)
 export(shortenLineage)
 export(sinkReset)
-export(summ.DA)
-export(summ.DA.byLin)
-export(summ.GC)
-export(summ.GC.byDALin)
-export(summ.GC.byLin)
-export(summarize_bylin)
+export(summarizeByLineage)
+export(summarizeDomArch)
+export(summarizeDomArch_ByLineage)
+export(summarizeGenContext)
+export(summarizeGenContext_ByDomArchLineage)
+export(summarizeGenContext_ByLineage)
 export(theme_genes2)
 export(to_titlecase)
-export(total_counts)
+export(totalGenContextOrDomArchCounts)
 export(validateCountDF)
 export(wordcloud3)
 export(write.MsaAAMultipleAlignment)

R/cleanup.R

@@ -561,7 +561,7 @@ cleanDomainArchitecture <- function(prot, old = "DomArch.orig", new = "DomArch",
     # Remove rows with no domains contained within domains_keep
     # filter(grepl(domains_for_grep, DomArch))
     if (!is.null(domains_keep)) {
-        prot <- prot %>% filter_by_doms(column = new, doms_keep = domains_keep$domains)
+        prot <- prot %>% filterByDomains(column = new, doms_keep = domains_keep$domains)
     }
 
     # ##!! NOT RUN !!

R/networks_domarch.R

@@ -54,7 +54,7 @@ domain_network <- function(prot, column = "DomArch", domains_of_interest, cutoff
         {
             column_name <- sym(column)
 
-            prot_tc <- prot %>% total_counts(column = column, cutoff = cutoff, RowsCutoff = F, digits = 5)
+            prot_tc <- prot %>% totalGenContextOrDomArchCounts(column = column, cutoff = cutoff, RowsCutoff = F, digits = 5)
 
             # ensure  only Domains that are in the tc cutoff range are kept
             within_list <- prot_tc %>%
@@ -95,7 +95,7 @@ domain_network <- function(prot, column = "DomArch", domains_of_interest, cutoff
             # cleanup domain list
             domain.list <- domain.list$DomArch.ntwrk %>% str_split(pattern = "\\+")
             # Get a table of domain counts
-            wc <- elements2words(prot = prot, column = column, conversion_type = "da2doms") %>% words2wc()
+            wc <- elements2Words(prot = prot, column = column, conversion_type = "da2doms") %>% words2WordCounts()
             wc <- pivot_wider(wc, names_from = words, values_from = freq)
 
             # Remove all isolated domarchs, such that an adjacency list can easily be constructed
@@ -262,7 +262,7 @@ BinaryDomainNetwork <- function(prot, column = "DomArch", domains_of_interest, c
 
     column_name <- sym(column)
 
-    prot_tc <- prot %>% total_counts(column = column, cutoff = cutoff, RowsCutoff = F, digits = 5)
+    prot_tc <- prot %>% totalGenContextOrDomArchCounts(column = column, cutoff = cutoff, RowsCutoff = F, digits = 5)
 
     within_list <- prot_tc %>%
         select({{ column_name }}) %>%
@@ -286,7 +286,7 @@ BinaryDomainNetwork <- function(prot, column = "DomArch", domains_of_interest, c
     domain.list <- domain.list$DomArch.ntwrk %>% str_split(pattern = "\\+")
 
     # Get domain counts before eliminating domarchs with no edges
-    wc <- elements2words(prot = prot, column = column, conversion_type = "da2doms") %>% words2wc()
+    wc <- elements2Words(prot = prot, column = column, conversion_type = "da2doms") %>% words2WordCounts()
 
     nodes <- data.frame(id = wc$words, label = wc$words, size = wc$freq) %>%
         mutate(group = purrr::map(

R/networks_gencontext.R

@@ -46,11 +46,11 @@ gc_undirected_network <- function(prot, column = "GenContext", domains_of_intere
     column_name <- sym(column)
     if (cutoff_type == "Lineage") {
         lin_summary <- prot %>%
-            summ.DA.byLin() %>%
-            summ.DA()
+            summarizeDomArch_ByLineage() %>%
+            summarizeDomArch()
         doms_above_cutoff <- (lin_summary %>% filter(totallin >= cutoff))[[column]]
     } else if (cutoff_type == "Total Count") { # Change this type?
-        GC_above_cutoff <- (prot %>% total_counts(column = column, cutoff = cutoff))[[column]]
+        GC_above_cutoff <- (prot %>% totalGenContextOrDomArchCounts(column = column, cutoff = cutoff))[[column]]
     }
 
     prot <- prot[which(prot[[as_string(column_name)]] %in% GC_above_cutoff), ]
@@ -153,8 +153,8 @@ GenContextNetwork <- function(prot, domains_of_interest, column = "GenContext",
     column_name <- sym(column)
 
 
-    # Perform cutoff through total_counts
-    prot_tc <- prot %>% total_counts(column = column, cutoff = cutoff)
+    # Perform cutoff through totalGenContextOrDomArchCounts
+    prot_tc <- prot %>% totalGenContextOrDomArchCounts(column = column, cutoff = cutoff)
 
     within_list <- prot_tc %>%
         select({{ column_name }}) %>%
@@ -218,7 +218,7 @@ GenContextNetwork <- function(prot, domains_of_interest, column = "GenContext",
     }
 
     # Get domain counts before eliminating domarchs with no edges
-    wc <- elements2words(prot = prot, column = column, conversion_type = "gc2da") %>% words2wc()
+    wc <- elements2Words(prot = prot, column = column, conversion_type = "gc2da") %>% words2WordCounts()
     nodes <- data.frame(id = wc$words, label = wc$words, size = wc$freq)
 
     max_size <- max(nodes$size)

R/plotting.R

@@ -108,7 +108,7 @@ plotUpSet <- function(query_data = "toast_rack.sub",
     # colname = string(colname)
     tryCatch(
         {
-            tc <- query_data %>% total_counts(column = colname, cutoff = cutoff, RowsCutoff = RowsCutoff, digits = 5)
+            tc <- query_data %>% totalGenContextOrDomArchCounts(column = colname, cutoff = cutoff, RowsCutoff = RowsCutoff, digits = 5)
             ##### Remove Tails ####
             # tails comprise of less than 1% of data each
             # ie) individual percent is less than 1
@@ -128,7 +128,7 @@ plotUpSet <- function(query_data = "toast_rack.sub",
             words.tc <- tc %>%
                 select({{ column }}) %>%
                 distinct() %>%
-                elements2words(column = colname, conversion_type = type)
+                elements2Words(column = colname, conversion_type = type)
             # names(words.tc)[1] <- "words"
             words.tc <- words.tc %>% str_split(pattern = " ")
             words.tc <- as.data.frame(words.tc, col.names = "Words", stringsAsFactors = F) %>%
@@ -273,7 +273,7 @@ plotLineageDA <- function(query_data = "prot",
 
     query_data <- shortenLineage(query_data, "Lineage", abr_len = 1)
 
-    query.summ.byLin <- query_data %>% total_counts(cutoff = cutoff, column = colname, RowsCutoff = RowsCutoff)
+    query.summ.byLin <- query_data %>% totalGenContextOrDomArchCounts(cutoff = cutoff, column = colname, RowsCutoff = RowsCutoff)
 
     query.summ.byLin$Lineage <- map(query.summ.byLin$Lineage, function(x) str_replace_all(string = x, pattern = ">", replacement = "_")) %>%
         unlist()
@@ -390,7 +390,7 @@ plotLineageQuery <- function(query_data = all,
     }
     col <- sym(colname)
 
-    query_data <- query_data %>% total_counts(column = colname, cutoff = cutoff)
+    query_data <- query_data %>% totalGenContextOrDomArchCounts(column = colname, cutoff = cutoff)
     # query_data contains all rows that possess a lineage
     query_data <- query_data %>% filter(grepl("a", Lineage))
 
@@ -831,7 +831,7 @@ plotStackedLineage <- function(prot, column = "DomArch", cutoff, Lineage_col = "
         prot <- shortenLineage(prot, Lineage_col, abr_len = 3)
     }
 
-    total_count <- total_counts(prot, column, cutoff, lineage_col = Lineage_col)
+    total_count <- totalGenContextOrDomArchCounts(prot, column, cutoff, lineage_col = Lineage_col)
     # total_count = prot
 
     # Order bars by descending freq
@@ -1054,7 +1054,7 @@ createWordCloudElement <- function(query_data = "prot",
     colname = "DomArch",
     cutoff = 70,
     UsingRowsCutoff = FALSE) {
-    tc <- query_data %>% total_counts(column = colname, cutoff = cutoff, RowsCutoff = UsingRowsCutoff, digits = 5)
+    tc <- query_data %>% totalGenContextOrDomArchCounts(column = colname, cutoff = cutoff, RowsCutoff = UsingRowsCutoff, digits = 5)
 
     column <- sym(colname)
     # Get words from filter
@@ -1069,11 +1069,11 @@ createWordCloudElement <- function(query_data = "prot",
     }
 
     words.tc <- query_data %>%
-        elements2words(
+        elements2Words(
             column = colname,
             conversion_type = type
         ) %>%
-        words2wc()
+        words2WordCounts()
 
     # names(words.tc) <- c("words", "freq")
 
@@ -1134,7 +1134,7 @@ createWordCloud2Element <- function(query_data = "prot",
     # @param type Character. Default is "da2doms" for Domain Architectures.
     # Other alternative: "gc2da" for Genomic Contexts.
 
-    tc <- query_data %>% total_counts(column = colname, cutoff = cutoff, RowsCutoff = UsingRowsCutoff, digits = 5)
+    tc <- query_data %>% totalGenContextOrDomArchCounts(column = colname, cutoff = cutoff, RowsCutoff = UsingRowsCutoff, digits = 5)
 
     column <- sym(colname)
     query_data <- query_data %>% filter({{ column }} %in% pull(tc, {{ colname }}))
@@ -1146,11 +1146,11 @@ createWordCloud2Element <- function(query_data = "prot",
     }
 
     words.tc <- query_data %>%
-        elements2words(
+        elements2Words(
             column = colname,
             conversion_type = type
         ) %>%
-        words2wc()
+        words2WordCounts()
 
     names(words.tc) <- c("words", "freq")