P Laverania chr 05, 07, 08, 11, 13 Gene Arrangements

Code
elucidator gffRecordIDToGeneInfo --id  PF3D7_0831800,PF3D7_1372200 --dout hrps_geneInfos --gff /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/info/gff/Pf3D7.gff --2bit /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/Pf3D7.2bit --overWriteDir

elucidator extractRefSeqsFromGenomes --bed hrps_geneInfos/out_PF3D7_0831800.1.bed --genomeDir /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/ --primaryGenome Pf3D7 --outputDir extractedHRPII --overWriteDirs --numThreads 7 --extendAndTrim --coverage 95 --keepBestOnly --identity 50
elucidator extractRefSeqsFromGenomes --bed hrps_geneInfos/out_PF3D7_1372200.1.bed --genomeDir /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/ --primaryGenome Pf3D7 --outputDir extractedHRPIII --overWriteDirs --numThreads 7 --extendAndTrim --coverage 95 --keepBestOnly --identity 50
Code
elucidator runnhmmscan --hmmModel ../MappingOutSurroundingRegions/surroundingRegionsMaterials/hmms_PfHRPs.txt --fasta /tank/data/genomes/combinedGenomes/allPLaverania/genomes/allPLaverania.fasta --overWriteDir --trimAtWhiteSpace --dout hmm_hrps_againstAllPlaverania "--defaultParameters=--nonull2 --incT 50 --incdomT 50 -T 50 --notextw --cpu 15" --hardEvalueCutOff 1e-50
Code
ls /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/P*.fasta  | sed 's/.fasta//g'  | sed 's/.*\///g'  > strains.txt

elucidator gffRecordIDToGeneInfo --id  PF3D7_0528800,PF3D7_0724800,PF3D7_0830300,PF3D7_1369500,PF3D7_1147700 --dout upStreamGeneInfos --gff /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/info/gff/Pf3D7.gff --2bit /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/Pf3D7.2bit --overWriteDir

elucidator extractRefSeqsFromGenomes --bed upStreamGeneInfos/out_PF3D7_0528800.1.bed --genomeDir /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/ --primaryGenome Pf3D7 --outputDir extractedPF3D7_0528800 --overWriteDirs --numThreads 7 --extendAndTrim

elucidator extractRefSeqsFromGenomes --bed upStreamGeneInfos/out_PF3D7_0724800.1.bed --genomeDir /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/ --primaryGenome Pf3D7 --outputDir extractedPF3D7_0724800 --overWriteDirs --numThreads 7 --extendAndTrim

elucidator extractRefSeqsFromGenomes --bed upStreamGeneInfos/out_PF3D7_0830300.1.bed --genomeDir /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/ --primaryGenome Pf3D7 --outputDir extractedPF3D7_0830300 --overWriteDirs --numThreads 7 --extendAndTrim

elucidator extractRefSeqsFromGenomes --bed upStreamGeneInfos/out_PF3D7_1147700.1.bed --genomeDir /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/ --primaryGenome Pf3D7 --outputDir extractedPF3D7_1147700 --overWriteDirs --numThreads 7 --extendAndTrim

elucidator extractRefSeqsFromGenomes --bed upStreamGeneInfos/out_PF3D7_1369500.1.bed --genomeDir /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/ --primaryGenome Pf3D7 --outputDir extractedPF3D7_1369500 --overWriteDirs --numThreads 15 --extendAndTrim


mkdir chromLengths 
cd chromLengths 
for x in /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/P*.fasta; do elucidator getReadLens --fasta ${x} --trimAtWhiteSpace > $(basename ${x%%.fasta}).txt; done;
cd ..

mkdir endBeds

for x in /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/P*.fasta; do elucidator extendToEndOfChrom --bed extractedPF3D7_0528800/Pf3D7_05_v3-1180424-1182038-rev/beds/$(basename ${x%%.fasta})_region.bed --chromLengthsTable chromLengths/$(basename ${x%%.fasta}).txt | cut -f 1-3 | elucidator bed3ToBed6 --bed STDIN --out endBeds/$(basename ${x%%.fasta})_chrom05_toEnd.bed --overWrite ; done;

for x in /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/P*.fasta; do elucidator extendToEndOfChrom --bed extractedPF3D7_0724800/Pf3D7_07_v3-1047426-1049362-rev/beds/$(basename ${x%%.fasta})_region.bed --chromLengthsTable chromLengths/$(basename ${x%%.fasta}).txt | cut -f 1-3 | elucidator bed3ToBed6 --bed STDIN --out endBeds/$(basename ${x%%.fasta})_chrom07_toEnd.bed --overWrite ; done;


for x in /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/P*.fasta; do elucidator extendToEndOfChrom --bed extractedPF3D7_0830300/Pf3D7_08_v3-1290239-1291406-rev/beds/$(basename ${x%%.fasta})_region.bed --chromLengthsTable chromLengths/$(basename ${x%%.fasta}).txt | cut -f 1-3 | elucidator bed3ToBed6 --bed STDIN --out endBeds/$(basename ${x%%.fasta})_chrom08_toEnd.bed --overWrite ; done;

for x in /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/P*.fasta; do elucidator extendToEndOfChrom --bed extractedPF3D7_1147700/Pf3D7_11_v3-1897203-1897884-for/beds/$(basename ${x%%.fasta})_region.bed --chromLengthsTable chromLengths/$(basename ${x%%.fasta}).txt | cut -f 1-3 | elucidator bed3ToBed6 --bed STDIN --out endBeds/$(basename ${x%%.fasta})_chrom11_toEnd.bed --overWrite ; done;

for x in /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/P*.fasta; do elucidator extendToEndOfChrom --bed extractedPF3D7_1369500/Pf3D7_13_v3-2769915-2773480-for/beds/$(basename ${x%%.fasta})_region.bed --chromLengthsTable chromLengths/$(basename ${x%%.fasta}).txt | cut -f 1-3 | elucidator bed3ToBed6 --bed STDIN --out endBeds/$(basename ${x%%.fasta})_chrom13_toEnd.bed --overWrite ; done;

cd endBeds 
for x in *toEnd.bed; do elucidator gffToBedByBedLoc  --extraAttributes description --feature gene,pseudogene,ncRNA_gene,protein_coding_gene --bed ${x} --gff /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/info/gff/$(echo $x | sed 's/_.*//g').gff --overWrite  --out ${x%%.bed}_genes.bed; done;

for x in *toEnd_genes.bed; do elucidator splitColumnContainingMeta --addHeader --delim tab --overWrite --removeEmptyColumn --column col.6 --file  ${x} --out split_${x%%.bed}.tab.txt ; done;

cat Pf3D7_chrom*genes.bed | elucidator splitColumnContainingMeta --file STDIN --delim tab --column col.6 --removeEmptyColumn  | elucidator printCol --file STDIN --delim tab --columnName col.10 --sort --unique | egrep -v PF3D7_1148200 > allPf3D7GenesIDs.txt

elucidator gffRecordIDToGeneInfo --id  allPf3D7GenesIDs.txt --dout all3D7End_geneInfos --gff /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/info/gff/Pf3D7.gff --2bit /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/Pf3D7.2bit --overWriteDir

elucidator getOverlappingBedRegions --bed all3D7End_geneInfos/out_allTranscripts.bed --intersectWithBed ../../windowAnalysis/windows/finalHRPII_HRPIII_windows_withTuned.bed --overWrite | egrep -v Pf3D7_11_v3_1972399_1973874_PF3D7_1149100.2 | egrep -v Pf3D7_11_v3_1899180_1905695_PF3D7_1147800.2 | egrep -v Pf3D7_11_v3_1950209_1968726_PF3D7_1149000.1 >  all3D7End_geneInfos/selected_out_allTranscripts.bed
egrep -i ribosomal Pf3D7_chrom11_toEnd_genes.bed >> all3D7End_geneInfos/selected_out_allTranscripts.bed
egrep -i ribosomal Pf3D7_chrom13_toEnd_genes.bed >> all3D7End_geneInfos/selected_out_allTranscripts.bed

elucidator extractRefSeqsFromGenomes --bed all3D7End_geneInfos/selected_out_allTranscripts.bed --genomeDir /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/ --primaryGenome Pf3D7 --outputDir extractedPF3D7_endGenes --overWriteDirs --numThreads 20 --extendAndTrim --keepBestOnly 

cd extractedPF3D7_endGenes 
for x in Pf3D7_*/beds/*bestRegion.bed; do  elucidator addColumn --file ${x} --newColumnName Pf3D7_genomicID --element $(echo ${x} | sed 's/\/.*//g') --overWrite --out ${x%%.bed}_withGenomcId.bed --delim tab; done;
for x in Pf3D7_*/beds/*bestRegion_withGenomcId.bed; do  elucidator addColumn --file ${x} --newColumnName strain --element $(echo ${x} | sed 's/.*\///g' | sed 's/_.*//g') --overWrite --out ${x%%.bed}_withStrain.bed --delim tab; done;

/bin/ls Pf3D7_*/beds/*bestRegion_withGenomcId_withStrain.bed > allBestRegionsFiles.txt 
elucidator rBind --files allBestRegionsFiles.txt --delim tab --overWrite --out allBestRegions.bed

Finding possible fragments in extra contigs

Code
strains = readr::read_tsv("strains.txt", col_names = c("strains")) 

Pf3d7_endRegions = readr::read_tsv("endBeds/all3D7End_geneInfos/selected_out_allTranscripts.bed", col_names = F) %>% 
  mutate(genomicID = paste0(X1, "-", X2, "-", X3, "-", ifelse(X6 == "-", "rev", "for"))) %>% 
  mutate(`Pf3D7_genomicID` = genomicID) %>% 
  mutate(`Pf3D7_GeneID` = gsub(".*ID=", "", gsub(";.*", "", X7))) %>% 
  mutate(`Pf3D7_GeneDescription` = gsub(".*description=", "", gsub(";feature.*", "", X7))) %>% 
  mutate(`Pf3D7_GeneID` = ifelse(grepl("ribosomal RNA", X7), gsub(";.*", "", gsub(".*;ID=", "", X7)), Pf3D7_GeneID))%>% 
  mutate(`Pf3D7_GeneDescription` = ifelse(grepl("ribosomal RNA", X7), gsub(";.*", "", gsub(".*;description=", "", X7)), Pf3D7_GeneDescription))

allStrainLocs = readr::read_tsv("endBeds/extractedPF3D7_endGenes/allBestRegions.bed", col_names = F) %>% 
  rename(Pf3D7_genomicID = X7, 
         strain = X8)

Detecting the prescence of genes using blast

Detecting the presence of the 3D7 genes from chromosomes 8, 11 and 13 in the other strains’ genome assemblies, BLAST setting done at 80% identity and 90% coverage.

Code
allStrainLocsMod = allStrainLocs   %>% 
  complete(Pf3D7_genomicID, strain) %>% 
  left_join(Pf3d7_endRegions %>% 
              select(starts_with("Pf3D7"))) %>% 
  mutate(Pf3D7_chrom = gsub("-.*", "", Pf3D7_genomicID)) %>% 
  replace_na(list(X1 = "none"))


pdf("3D7_geneLocations_in_lstrains_byStrain.pdf", width = 15, height = 20, useDingbats = F)
for(lstrain in strains$strains) {
  allStrainLocsMod_strain = allStrainLocsMod %>%
           filter(strain == lstrain)
  chromHitColors = c(scheme$hex(length(unique(allStrainLocsMod_strain$X1))))
  names(chromHitColors) = unique(allStrainLocsMod_strain$X1)
  chromHitColors["none"] = "white"
  print(ggplot(allStrainLocsMod_strain) +
    geom_bar(aes(
      x = paste0(Pf3D7_genomicID, "\n", Pf3D7_GeneDescription),
      fill = X1
    )) +
    facet_wrap(~Pf3D7_chrom, strip.position = "right",ncol = 1, scales = "free") + 
    scale_fill_manual(values = chromHitColors) +
    sofonias_theme_xRotate +
    labs(title = lstrain, x = "Pf3D7 Genomic ID"))
  
}
dev.off()
quartz_off_screen 
                2

Displayed by strain

Display the blast hits, organized by each strain, and then for each strain it’s then sorted by the 3D7 chromosome from which the gene comes from. The x-axis is the 3D7 gene blasted and a bar represents if hit the strain’s genome assembly and is colored by it’s location within that strain. If there is no bar (white) then there was no hit against that genome.

Code
for(lstrain in strains$strains) {
  allStrainLocsMod_strain = allStrainLocsMod %>%
           filter(strain == lstrain)
  chromHitColors = c(scheme$hex(length(unique(allStrainLocsMod_strain$X1))))
  names(chromHitColors) = unique(allStrainLocsMod_strain$X1)
  chromHitColors["none"] = "white"
  print(ggplot(allStrainLocsMod_strain) +
    geom_bar(aes(
      x = paste0(Pf3D7_genomicID, "\n", Pf3D7_GeneDescription),
      fill = X1
    )) +
    facet_wrap(~Pf3D7_chrom,strip.position = "right", ncol = 1, scales = "free") + 
    scale_fill_manual(values = chromHitColors) +
    sofonias_theme_xRotate +
    labs(title = lstrain, x = "Pf3D7 Genomic ID"))
  
}

Code
pdf("3D7_geneLocations_in_lstrains_byChrom.pdf", width = 15, height = 20, useDingbats = F)
for(chrom in unique(allStrainLocsMod$Pf3D7_chrom)) {
  allStrainLocsMod_chrom = allStrainLocsMod %>%
           filter(Pf3D7_chrom == chrom) %>% 
    mutate(strainChromNumber = sub(".*?_", "", X1)) %>% 
    mutate(strainChromNumber = sub("_v3", "", strainChromNumber))
  
  chromHitColors = c(scheme$hex(length(unique(allStrainLocsMod_chrom$strainChromNumber))))
  names(chromHitColors) = unique(allStrainLocsMod_chrom$strainChromNumber)
  chromHitColors["none"] = "white"
  print(ggplot(allStrainLocsMod_chrom) +
    geom_bar(aes(
      x = paste0(Pf3D7_genomicID, "\n", Pf3D7_GeneDescription),
      fill = strainChromNumber
    ), color = "white") +
    facet_wrap(~strain, strip.position = "right", ncol = 1) + 
    scale_fill_manual(values = chromHitColors) +
    sofonias_theme_xRotate +
    labs(title = chrom, x = "Pf3D7 Genomic ID", fill = "chromosome"))
}
dev.off()
quartz_off_screen 
                2

Displayed by chromsome

Display the blast hits, organized by 3D7 chromosome from which the gene is from. The x-axis is the 3D7 gene blasted and a bar represents if hit the strain’s genome assembly and is colored by it’s location within that strain. If there is no bar (white) then there was no hit against that genome.

Code
for(chrom in unique(allStrainLocsMod$Pf3D7_chrom)) {
  allStrainLocsMod_chrom = allStrainLocsMod %>%
           filter(Pf3D7_chrom == chrom) %>% 
    mutate(strainChromNumber = sub(".*?_", "", X1)) %>% 
    mutate(strainChromNumber = sub("_v3", "", strainChromNumber))
  
  chromHitColors = c(scheme$hex(length(unique(allStrainLocsMod_chrom$strainChromNumber))))
  names(chromHitColors) = unique(allStrainLocsMod_chrom$strainChromNumber)
  chromHitColors["none"] = "white"
  print(ggplot(allStrainLocsMod_chrom) +
    geom_bar(aes(
      x = paste0(Pf3D7_genomicID, "\n", Pf3D7_GeneDescription),
      fill = strainChromNumber
    ), color = "white") +
    facet_wrap(~strain, strip.position = "right", ncol = 1) + 
    scale_fill_manual(values = chromHitColors) +
    sofonias_theme_xRotate +
    labs(title = chrom, x = "Pf3D7 Genomic ID", fill = "chromosome"))
}

finding possible fragments of 8

Code

elucidator fastaToBed --trimAtWhiteSpace --fasta /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/PreichenowiG01.fasta  | egrep PRG01_00_67 | elucidator bed3ToBed6 --bed STDIN --out  PRG01_00_67.bed --overWrite 
elucidator gffToBedByBedLoc  --extraAttributes description --feature gene,pseudogene,ncRNA_gene,protein_coding_gene --bed PRG01_00_67.bed --gff /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/info/gff/PreichenowiG01.gff --overWrite  --out PRG01_00_67_genes.bed

elucidator fastaToBed --trimAtWhiteSpace --fasta /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/PadleriG01.fasta  | egrep PADLG01_00_21 | elucidator bed3ToBed6 --bed STDIN --out  PADLG01_00_21.bed --overWrite 
elucidator gffToBedByBedLoc  --extraAttributes description --feature gene,pseudogene,ncRNA_gene,protein_coding_gene --bed PADLG01_00_21.bed --gff /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/info/gff/PadleriG01.gff --overWrite  --out PADLG01_00_21_genes.bed


echo -e "PGABG01_08\t0\t10000\tPRG01_08-0-10000\t10000\t+" > PGABG01_08_front.bed
elucidator gffToBedByBedLoc  --extraAttributes description --feature gene,pseudogene,ncRNA_gene,protein_coding_gene --bed PGABG01_08_front.bed --gff /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/info/gff/PgaboniG01.gff --overWrite  --out PGABG01_08_front_genes.bed

for x in *_genes.bed; do elucidator splitColumnContainingMeta --addHeader --delim tab --overWrite --removeEmptyColumn --column col.6 --file  ${x} --out split_${x%%.bed}.tab.txt ; done;

finding possible fragments of 11

Code

PGABG01_00_71,PGABG01_00_69 

elucidator fastaToBed --trimAtWhiteSpace --fasta /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/PgaboniG01.fasta  | egrep PGABG01_00_71 | elucidator bed3ToBed6 --bed STDIN --out  PGABG01_00_71.bed --overWrite 
elucidator gffToBedByBedLoc  --extraAttributes description --feature gene,pseudogene,ncRNA_gene,protein_coding_gene --bed PGABG01_00_71.bed --gff /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/info/gff/PgaboniG01.gff --overWrite  --out PGABG01_00_71_genes.bed

elucidator fastaToBed --trimAtWhiteSpace --fasta /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/PgaboniG01.fasta  | egrep PGABG01_00_69 | elucidator bed3ToBed6 --bed STDIN --out  PGABG01_00_69.bed --overWrite 
elucidator gffToBedByBedLoc  --extraAttributes description --feature gene,pseudogene,ncRNA_gene,protein_coding_gene --bed PGABG01_00_69.bed --gff /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/info/gff/PgaboniG01.gff --overWrite  --out PGABG01_00_69_genes.bed

finding possible fragments of 13

Code
#PADLG01_00_60 just EBL-1 fragment 
#PADLG01_00_44 
elucidator fastaToBed --trimAtWhiteSpace --fasta /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/genomes/PadleriG01.fasta  | egrep PADLG01_00_44 | elucidator bed3ToBed6 --bed STDIN --out  PADLG01_00_44.bed --overWrite 
elucidator gffToBedByBedLoc  --extraAttributes description --feature gene,pseudogene,ncRNA_gene,protein_coding_gene --bed PADLG01_00_44.bed --gff /tank/data/genomes/plasmodium/genomes/pLaveraniaPlus3D7/info/gff/PadleriG01.gff --overWrite  --out PADLG01_00_44_genes.bed

Reading In Genes

Code
strains = readr::read_tsv("strains.txt", col_names = c("strains")) 

chromLengths = tibble()

for(strain in strains$strains){
  strainLens = readr::read_tsv(paste0("chromLengths/", strain, ".txt"), col_names = c("chrom", "length")) %>% 
    mutate(strain = strain)
  chromLengths = bind_rows(chromLengths, strainLens)
}

05

Code
all05 = tibble()

for(strain in strains$strains){
  strain05 = readr::read_tsv(paste0("endBeds/split_", strain, "_chrom05_toEnd_genes.tab.txt")) %>% 
    mutate(strain = strain ) %>% 
  mutate(chromGlobal = gsub(paste0(strain, "_"), "", col.0)) %>% 
  mutate(chromGlobal = gsub("_v3", "", chromGlobal)) %>% 
    rename(chrom = col.0, 
           start = col.1, 
           end = col.2)
  all05 = bind_rows(all05, strain05)
}


all05  = all05  %>% 
  mutate(description = gsub("unknownfunction", "unknown function", description)) %>% 
  mutate(description = gsub(" \\(SURFIN", "\\(SURFIN", description)) %>% 
  mutate(description = ifelse(grepl("Plasmodium exported protein", description), "Plasmodium exported protein (PHIST)", description)) %>% 
  mutate(description = ifelse("erythrocyte membrane protein 1 (PfEMP1), exon 2"==description, "erythrocyte membrane protein 1 (PfEMP1), exon 2, pseudogene", description)) %>% 
  mutate(description = ifelse("membrane associated erythrocyte binding-like protein"==description, "merozoite adhesive erythrocytic binding protein", description)) %>% 
  mutate(description = ifelse("membrane associated erythrocyte binding-likeprotein"==description, "merozoite adhesive erythrocytic binding protein", description)) %>% 
  mutate(description = ifelse("membrane associated histidine-rich protein 1"==description, "membrane associated histidine-rich protein", description)) %>% 
  mutate(description = gsub(",putative", ", putative", description)) %>% 
  mutate(description = gsub(",pseudogene", ", pseudogene", description))%>% 
  mutate(description = gsub("unknownfunction", "unknown function", description))%>% 
  mutate(description = gsub("conserved protein, unknown function", "conserved Plasmodium protein, unknown function", description)) %>% 
  mutate(description = gsub(" \\(SURFIN", "\\(SURFIN", description)) %>% 
  mutate(description = ifelse(grepl("Plasmodium exported protein", description), "Plasmodium exported protein (PHIST)", description)) %>% 
  mutate(description = ifelse("erythrocyte membrane protein 1 (PfEMP1), exon 2"==description, "erythrocyte membrane protein 1 (PfEMP1), exon 2, pseudogene", description)) %>% 
  mutate(description = ifelse("membrane associated histidine-rich protein 1"==description, "membrane associated histidine-rich protein", description))%>% 
  mutate(description = gsub(",pseudogene", ", pseudogene", description))%>% 
  mutate(description = gsub("unknownfunction", "unknown function", description))%>% 
  mutate(description = gsub(" \\(SURFIN", "\\(SURFIN", description)) %>% 
  mutate(description = ifelse(grepl("Plasmodium exported protein", description), "Plasmodium exported protein (PHIST)", description)) %>% 
  mutate(description = ifelse("erythrocyte membrane protein 1 (PfEMP1), exon 2"==description, "erythrocyte membrane protein 1 (PfEMP1), exon 2, pseudogene", description)) %>% 
  mutate(description = ifelse(grepl("sporozoite and liver stage tryptophan-rich protein, putative", description), "tryptophan/threonine-rich antigen", description))%>% 
  mutate(description = ifelse(grepl("CRA domain-containing protein, putative", description), "conserved Plasmodium protein, unknown function", description))%>% 
  mutate(description = gsub(",pseudogene", ", pseudogene", description)) %>% 
  mutate(description = gsub("surfaceantigen", "surface antigen", description))  %>% 
  mutate(description = gsub("Tetratricopeptide repeat, putative", "tetratricopeptide repeat protein, putative", description)) %>% 
  mutate(description = gsub("transmembraneprotein", "transmembrane protein", description)) %>% 
  mutate(description = ifelse(grepl("PfEMP1", description) & grepl("pseudogene", description), "erythrocyte membrane protein 1 (PfEMP1), pseudogene", description)) %>% 
  mutate(description = gsub("PIR protein", "stevor", description)) %>% 
  mutate(description = gsub("erythrocyte membrane protein 1-like", "erythrocyte membrane protein 1 (PfEMP1), pseudogene", description)) %>% 
  mutate(description = gsub("acidic terminal segments, variant surface antigen of PfEMP1, putative", "erythrocyte membrane protein 1 (PfEMP1), pseudogene", description))%>% 
  mutate(description = ifelse(grepl("CoA binding protein", description, ignore.case = T), "acyl-CoA binding protein", description)) %>% 
  mutate(description = ifelse(grepl("transfer RNA", description) | grepl("tRNA", description), "tRNA", description))%>% 
  mutate(description = ifelse(grepl("cytoadherence", description), "CLAG", description))%>% 
  mutate(description = ifelse(grepl("surface-associated interspersed protein", description), "SURFIN", description))%>% 
  mutate(description = ifelse(grepl("SURFIN", description), "SURFIN", description))%>% 
  mutate(description = ifelse(grepl("stevor-like", description), "stevor, pseudogene", description)) %>% 
  mutate(description = ifelse(grepl("exported protein family", description), "exported protein family", description)) %>% 
  mutate(description = ifelse(grepl("ribosomal RNA", description), "rRNA", description)) %>% 
  mutate(description = ifelse(grepl("serine/threonine protein kinase", description), "serine/threonine protein kinase, FIKK family", description)) %>% 
  mutate(description = ifelse(grepl("hypothetical protein", description), "hypothetical protein, conserved", description)) %>% 
  mutate(description = ifelse(grepl("conserved Plasmodium protein, unknown function", description), "hypothetical protein, conserved", description)) %>% 
  mutate(description = ifelse(grepl("Rifin/stevor family, putative", description), "stevor", description))  %>% 
  mutate(description = ifelse(grepl("stevor", description), "stevor", description)) %>% 
  mutate(description = ifelse(grepl("rifin", description), "rifin", description)) %>% 
  mutate(description = ifelse(grepl("erythrocyte membrane protein 1 (PfEMP1), pseudogene", description), "erythrocyte membrane protein 1 (PfEMP1)", description)) %>% 
  mutate(description = ifelse(grepl("erythrocyte membrane protein 1", description), "erythrocyte membrane protein 1 (PfEMP1)", description)) %>% 
  mutate(description = ifelse(grepl("probably protein", description), "unspecified product", description)) %>% 
  mutate(description = ifelse(grepl("RESA", description), "RESA", description)) %>% 
  mutate(description = ifelse(grepl("ring-infected erythrocyte surface antigen", description), "ring-infected erythrocyte surface antigen", description)) %>% 
  mutate(description = ifelse(grepl("Duffy binding domain/Erythrocyte binding antigen175, putative", description), "erythrocyte binding like protein 1", description)) %>% 
  mutate(description = ifelse(grepl("erythrocyte binding like protein 1", description), "erythrocyte binding like protein 1", description))  %>% 
  mutate(description = ifelse(grepl("unspecified product", description), "hypothetical protein, conserved", description))%>% 
  mutate(description = ifelse(grepl("probable protein, unknown function", description), "hypothetical protein, conserved", description))%>% 
  mutate(description = ifelse(grepl("RESA", description), "ring-infected erythrocyte surface antigen", description)) %>% 
  mutate(description = gsub(", putative", "", description))




all05_strainStarts = all05 %>% 
  group_by(strain, chrom) %>% 
  summarise(minStart = min(start))

all05 = all05 %>% 
  left_join(all05_strainStarts) %>% 
  mutate(globalStart = start - minStart, 
         globalEnd = end - minStart)

chromLengths_05 = chromLengths %>% 
  filter(chrom %in% all05_strainStarts$chrom) %>% 
  left_join(all05_strainStarts)%>% 
  mutate(globalStart = 0, 
         globalEnd = length - minStart) %>% 
  mutate(chrom = factor(chrom, levels = chrom))

all05 = all05 %>% 
  mutate(chrom = factor(chrom, levels = chromLengths_05$chrom))

07

Code
all07 = tibble()

for(strain in strains$strains){
  strain07 = readr::read_tsv(paste0("endBeds/split_", strain, "_chrom07_toEnd_genes.tab.txt")) %>% 
    mutate(strain = strain ) %>% 
  mutate(chromGlobal = gsub(paste0(strain, "_"), "", col.0)) %>% 
  mutate(chromGlobal = gsub("_v3", "", chromGlobal)) %>% 
    rename(chrom = col.0, 
           start = col.1, 
           end = col.2)
  all07 = bind_rows(all07, strain07)
}


all07  = all07  %>% 
  mutate(description = gsub("unknownfunction", "unknown function", description)) %>% 
  mutate(description = gsub(" \\(SURFIN", "\\(SURFIN", description)) %>% 
  mutate(description = ifelse(grepl("Plasmodium exported protein", description), "Plasmodium exported protein (PHIST)", description)) %>% 
  mutate(description = ifelse("erythrocyte membrane protein 1 (PfEMP1), exon 2"==description, "erythrocyte membrane protein 1 (PfEMP1), exon 2, pseudogene", description)) %>% 
  mutate(description = ifelse("membrane associated erythrocyte binding-like protein"==description, "merozoite adhesive erythrocytic binding protein", description)) %>% 
  mutate(description = ifelse("membrane associated erythrocyte binding-likeprotein"==description, "merozoite adhesive erythrocytic binding protein", description)) %>% 
  mutate(description = ifelse("membrane associated histidine-rich protein 1"==description, "membrane associated histidine-rich protein", description)) %>% 
  mutate(description = gsub(",putative", ", putative", description)) %>% 
  mutate(description = gsub(",pseudogene", ", pseudogene", description))%>% 
  mutate(description = gsub("unknownfunction", "unknown function", description))%>% 
  mutate(description = gsub("conserved protein, unknown function", "conserved Plasmodium protein, unknown function", description)) %>% 
  mutate(description = gsub(" \\(SURFIN", "\\(SURFIN", description)) %>% 
  mutate(description = ifelse(grepl("Plasmodium exported protein", description), "Plasmodium exported protein (PHIST)", description)) %>% 
  mutate(description = ifelse("erythrocyte membrane protein 1 (PfEMP1), exon 2"==description, "erythrocyte membrane protein 1 (PfEMP1), exon 2, pseudogene", description)) %>% 
  mutate(description = ifelse("membrane associated histidine-rich protein 1"==description, "membrane associated histidine-rich protein", description))%>% 
  mutate(description = gsub(",pseudogene", ", pseudogene", description))%>% 
  mutate(description = gsub("unknownfunction", "unknown function", description))%>% 
  mutate(description = gsub(" \\(SURFIN", "\\(SURFIN", description)) %>% 
  mutate(description = ifelse(grepl("Plasmodium exported protein", description), "Plasmodium exported protein (PHIST)", description)) %>% 
  mutate(description = ifelse("erythrocyte membrane protein 1 (PfEMP1), exon 2"==description, "erythrocyte membrane protein 1 (PfEMP1), exon 2, pseudogene", description)) %>% 
  mutate(description = ifelse(grepl("sporozoite and liver stage tryptophan-rich protein, putative", description), "tryptophan/threonine-rich antigen", description))%>% 
  mutate(description = ifelse(grepl("CRA domain-containing protein, putative", description), "conserved Plasmodium protein, unknown function", description))%>% 
  mutate(description = gsub(",pseudogene", ", pseudogene", description)) %>% 
  mutate(description = gsub("surfaceantigen", "surface antigen", description))  %>% 
  mutate(description = gsub("Tetratricopeptide repeat, putative", "tetratricopeptide repeat protein, putative", description)) %>% 
  mutate(description = gsub("transmembraneprotein", "transmembrane protein", description)) %>% 
  mutate(description = ifelse(grepl("PfEMP1", description) & grepl("pseudogene", description), "erythrocyte membrane protein 1 (PfEMP1), pseudogene", description)) %>% 
  mutate(description = gsub("PIR protein", "stevor", description)) %>% 
  mutate(description = gsub("erythrocyte membrane protein 1-like", "erythrocyte membrane protein 1 (PfEMP1), pseudogene", description)) %>% 
  mutate(description = gsub("acidic terminal segments, variant surface antigen of PfEMP1, putative", "erythrocyte membrane protein 1 (PfEMP1), pseudogene", description))%>% 
  mutate(description = ifelse(grepl("CoA binding protein", description, ignore.case = T), "acyl-CoA binding protein", description)) %>% 
  mutate(description = ifelse(grepl("transfer RNA", description) | grepl("tRNA", description), "tRNA", description))%>% 
  mutate(description = ifelse(grepl("cytoadherence", description), "CLAG", description))%>% 
  mutate(description = ifelse(grepl("surface-associated interspersed protein", description), "SURFIN", description))%>% 
  mutate(description = ifelse(grepl("SURFIN", description), "SURFIN", description))%>% 
  mutate(description = ifelse(grepl("stevor-like", description), "stevor, pseudogene", description)) %>% 
  mutate(description = ifelse(grepl("exported protein family", description), "exported protein family", description)) %>% 
  mutate(description = ifelse(grepl("ribosomal RNA", description), "rRNA", description)) %>% 
  mutate(description = ifelse(grepl("serine/threonine protein kinase", description), "serine/threonine protein kinase, FIKK family", description)) %>% 
  mutate(description = ifelse(grepl("hypothetical protein", description), "hypothetical protein, conserved", description)) %>% 
  mutate(description = ifelse(grepl("conserved Plasmodium protein, unknown function", description), "hypothetical protein, conserved", description)) %>% 
  mutate(description = ifelse(grepl("Rifin/stevor family, putative", description), "stevor", description))  %>% 
  mutate(description = ifelse(grepl("stevor", description), "stevor", description)) %>% 
  mutate(description = ifelse(grepl("rifin", description), "rifin", description)) %>% 
  mutate(description = ifelse(grepl("erythrocyte membrane protein 1 (PfEMP1), pseudogene", description), "erythrocyte membrane protein 1 (PfEMP1)", description)) %>% 
  mutate(description = ifelse(grepl("erythrocyte membrane protein 1", description), "erythrocyte membrane protein 1 (PfEMP1)", description)) %>% 
  mutate(description = ifelse(grepl("probably protein", description), "unspecified product", description)) %>% 
  mutate(description = ifelse(grepl("RESA", description), "RESA", description)) %>% 
  mutate(description = ifelse(grepl("ring-infected erythrocyte surface antigen", description), "ring-infected erythrocyte surface antigen", description)) %>% 
  mutate(description = ifelse(grepl("Duffy binding domain/Erythrocyte binding antigen175, putative", description), "erythrocyte binding like protein 1", description)) %>% 
  mutate(description = ifelse(grepl("erythrocyte binding like protein 1", description), "erythrocyte binding like protein 1", description))  %>% 
  mutate(description = ifelse(grepl("unspecified product", description), "hypothetical protein, conserved", description))%>% 
  mutate(description = ifelse(grepl("probable protein, unknown function", description), "hypothetical protein, conserved", description)) %>% 
  mutate(description = ifelse(grepl("RESA", description), "ring-infected erythrocyte surface antigen", description)) %>% 
  mutate(description = gsub(", putative", "", description))  %>% 
  mutate(description = ifelse(grepl("transcription factor with AP2 domain(s)", description, fixed = T), "AP2 domain transcription factor AP2-L", description))  %>% 
  mutate(description = ifelse(grepl("zinc finger, C3HC4 type", description, fixed = T), "RING zinc finger protein", description))  %>% 
  mutate(description = ifelse(grepl("eukaryotic translation initiation factor 2 subunit alpha", description, fixed = T), "eukaryotic translation initiation factor 2 alpha subunit", description)) 




all07_strainStarts = all07 %>% 
  group_by(strain, chrom) %>% 
  summarise(minStart = min(start))

all07 = all07 %>% 
  left_join(all07_strainStarts) %>% 
  mutate(globalStart = start - minStart, 
         globalEnd = end - minStart)

chromLengths_07 = chromLengths %>% 
  filter(chrom %in% all07_strainStarts$chrom) %>% 
  left_join(all07_strainStarts)%>% 
  mutate(globalStart = 0, 
         globalEnd = length - minStart) %>% 
  mutate(chrom = factor(chrom, levels = chrom))

all07 = all07 %>% 
  mutate(chrom = factor(chrom, levels = chromLengths_07$chrom))

08

Code
all08 = tibble()

for(strain in strains$strains){
  strain08 = readr::read_tsv(paste0("endBeds/split_", strain, "_chrom08_toEnd_genes.tab.txt")) %>% 
    mutate(strain = strain ) %>% 
  mutate(chromGlobal = gsub(paste0(strain, "_"), "", col.0)) %>% 
  mutate(chromGlobal = gsub("_v3", "", chromGlobal)) %>% 
    rename(chrom = col.0, 
           start = col.1, 
           end = col.2)
  all08 = bind_rows(all08, strain08)
}


all08_fragments = bind_rows(
  readr::read_tsv("possibleFragments/split_PRG01_00_67_genes.tab.txt"), 
  readr::read_tsv("possibleFragments/split_PADLG01_00_21_genes.tab.txt"), 
  readr::read_tsv("possibleFragments/split_PGABG01_08_front_genes.tab.txt")
)%>% 
  mutate(chromGlobal = gsub(paste0(strain, "_"), "", col.0)) %>% 
  mutate(chromGlobal = gsub("_v3", "", chromGlobal)) %>% 
    rename(chrom = col.0, 
           start = col.1, 
           end = col.2)

all08  = all08  %>% 
  mutate(description = gsub("unknownfunction", "unknown function", description)) %>% 
  mutate(description = gsub(" \\(SURFIN", "\\(SURFIN", description)) %>% 
  mutate(description = ifelse(grepl("Plasmodium exported protein", description), "Plasmodium exported protein (PHIST)", description)) %>% 
  mutate(description = ifelse("erythrocyte membrane protein 1 (PfEMP1), exon 2"==description, "erythrocyte membrane protein 1 (PfEMP1), exon 2, pseudogene", description)) %>% 
  mutate(description = ifelse("membrane associated erythrocyte binding-like protein"==description, "merozoite adhesive erythrocytic binding protein", description)) %>% 
  mutate(description = ifelse("membrane associated erythrocyte binding-likeprotein"==description, "merozoite adhesive erythrocytic binding protein", description)) %>% 
  mutate(description = ifelse("membrane associated histidine-rich protein 1"==description, "membrane associated histidine-rich protein", description)) %>% 
  mutate(description = gsub(",putative", ", putative", description)) %>% 
  mutate(description = gsub(",pseudogene", ", pseudogene", description))%>% 
  mutate(description = gsub("unknownfunction", "unknown function", description))%>% 
  mutate(description = gsub("conserved protein, unknown function", "conserved Plasmodium protein, unknown function", description)) %>% 
  mutate(description = gsub(" \\(SURFIN", "\\(SURFIN", description)) %>% 
  mutate(description = ifelse(grepl("Plasmodium exported protein", description), "Plasmodium exported protein (PHIST)", description)) %>% 
  mutate(description = ifelse("erythrocyte membrane protein 1 (PfEMP1), exon 2"==description, "erythrocyte membrane protein 1 (PfEMP1), exon 2, pseudogene", description)) %>% 
  mutate(description = ifelse("membrane associated histidine-rich protein 1"==description, "membrane associated histidine-rich protein", description))%>% 
  mutate(description = gsub(",pseudogene", ", pseudogene", description))%>% 
  mutate(description = gsub("unknownfunction", "unknown function", description))%>% 
  mutate(description = gsub(" \\(SURFIN", "\\(SURFIN", description)) %>% 
  mutate(description = ifelse(grepl("Plasmodium exported protein", description), "Plasmodium exported protein (PHIST)", description)) %>% 
  mutate(description = ifelse("erythrocyte membrane protein 1 (PfEMP1), exon 2"==description, "erythrocyte membrane protein 1 (PfEMP1), exon 2, pseudogene", description)) %>% 
  mutate(description = ifelse(grepl("sporozoite and liver stage tryptophan-rich protein, putative", description), "tryptophan/threonine-rich antigen", description))%>% 
  mutate(description = ifelse(grepl("CRA domain-containing protein, putative", description), "conserved Plasmodium protein, unknown function", description))%>% 
  mutate(description = gsub(",pseudogene", ", pseudogene", description)) %>% 
  mutate(description = gsub("surfaceantigen", "surface antigen", description))  %>% 
  mutate(description = gsub("Tetratricopeptide repeat, putative", "tetratricopeptide repeat protein, putative", description)) %>% 
  mutate(description = gsub("transmembraneprotein", "transmembrane protein", description)) %>% 
  mutate(description = ifelse(grepl("PfEMP1", description) & grepl("pseudogene", description), "erythrocyte membrane protein 1 (PfEMP1), pseudogene", description)) %>% 
  mutate(description = gsub("PIR protein", "stevor", description)) %>% 
  mutate(description = gsub("erythrocyte membrane protein 1-like", "erythrocyte membrane protein 1 (PfEMP1), pseudogene", description)) %>% 
  mutate(description = gsub("acidic terminal segments, variant surface antigen of PfEMP1, putative", "erythrocyte membrane protein 1 (PfEMP1), pseudogene", description))%>% 
  mutate(description = ifelse(grepl("CoA binding protein", description, ignore.case = T), "acyl-CoA binding protein", description)) %>% 
  mutate(description = ifelse(grepl("transfer RNA", description) | grepl("tRNA", description), "tRNA", description))%>% 
  mutate(description = ifelse(grepl("cytoadherence", description), "CLAG", description))%>% 
  mutate(description = ifelse(grepl("surface-associated interspersed protein", description), "SURFIN", description))%>% 
  mutate(description = ifelse(grepl("SURFIN", description), "SURFIN", description))%>% 
  mutate(description = ifelse(grepl("stevor-like", description), "stevor, pseudogene", description)) %>% 
  mutate(description = ifelse(grepl("exported protein family", description), "exported protein family", description)) %>% 
  mutate(description = ifelse(grepl("ribosomal RNA", description), "rRNA", description)) %>% 
  mutate(description = ifelse(grepl("serine/threonine protein kinase", description), "serine/threonine protein kinase, FIKK family", description)) %>% 
  mutate(description = ifelse(grepl("hypothetical protein", description), "hypothetical protein, conserved", description)) %>% 
  mutate(description = ifelse(grepl("conserved Plasmodium protein, unknown function", description), "hypothetical protein, conserved", description)) %>% 
  mutate(description = ifelse(grepl("Rifin/stevor family, putative", description), "stevor", description))  %>% 
  mutate(description = ifelse(grepl("stevor", description), "stevor", description)) %>% 
  mutate(description = ifelse(grepl("rifin", description), "rifin", description)) %>% 
  mutate(description = ifelse(grepl("erythrocyte membrane protein 1 (PfEMP1), pseudogene", description), "erythrocyte membrane protein 1 (PfEMP1)", description)) %>% 
  mutate(description = ifelse(grepl("erythrocyte membrane protein 1", description), "erythrocyte membrane protein 1 (PfEMP1)", description)) %>% 
  mutate(description = ifelse(grepl("probably protein", description), "unspecified product", description)) %>% 
  mutate(description = ifelse(grepl("RESA", description), "RESA", description)) %>% 
  mutate(description = ifelse(grepl("ring-infected erythrocyte surface antigen", description), "ring-infected erythrocyte surface antigen", description)) %>% 
  mutate(description = ifelse(grepl("Duffy binding domain/Erythrocyte binding antigen175, putative", description), "erythrocyte binding like protein 1", description)) %>% 
  mutate(description = ifelse(grepl("erythrocyte binding like protein 1", description), "erythrocyte binding like protein 1", description))  %>% 
  mutate(description = ifelse(grepl("unspecified product", description), "hypothetical protein, conserved", description))%>% 
  mutate(description = ifelse(grepl("probable protein, unknown function", description), "hypothetical protein, conserved", description))%>% 
  mutate(description = ifelse(grepl("RESA", description), "ring-infected erythrocyte surface antigen", description))  %>% 
  mutate(description = gsub(", putative", "", description))




all08_strainStarts = all08 %>% 
  group_by(strain, chrom) %>% 
  summarise(minStart = min(start))

all08 = all08 %>% 
  left_join(all08_strainStarts) %>% 
  mutate(globalStart = start - minStart, 
         globalEnd = end - minStart)

chromLengths_08 = chromLengths %>% 
  filter(chrom %in% all08_strainStarts$chrom) %>% 
  left_join(all08_strainStarts)%>% 
  mutate(globalStart = 0, 
         globalEnd = length - minStart) %>% 
  mutate(chrom = factor(chrom, levels = chrom))

all08 = all08 %>% 
  mutate(chrom = factor(chrom, levels = chromLengths_08$chrom))

13

Code
all13 = tibble()

for(strain in strains$strains){
  strain13 = readr::read_tsv(paste0("endBeds/split_", strain, "_chrom13_toEnd_genes.tab.txt")) %>% 
    mutate(strain = strain ) %>% 
  mutate(chromGlobal = gsub(paste0(strain, "_"), "", col.0)) %>% 
  mutate(chromGlobal = gsub("_v3", "", chromGlobal)) %>% 
    rename(chrom = col.0, 
           start = col.1, 
           end = col.2)
  all13 = bind_rows(all13, strain13)
}

all13  = all13  %>% 
  filter(col.3 %!in% c("Pf3D7_13_v3_2794236_2794851_PF3D7_1370500", "Pf3D7_13_v3_2796118_2797144_PF3D7_1370800", "Pf3D7_13_v3_2797506_2798103_PF3D7_1370900")) %>% 
  mutate(description = gsub(" \\(SURFIN", "\\(SURFIN", description)) %>% 
  mutate(description = ifelse(grepl("Plasmodium exported protein", description), "Plasmodium exported protein (PHIST)", description)) %>% 
  mutate(description = ifelse("erythrocyte membrane protein 1 (PfEMP1), exon 2"==description, "erythrocyte membrane protein 1 (PfEMP1), exon 2, pseudogene", description)) %>% 
  mutate(description = ifelse("membrane associated erythrocyte binding-like protein"==description, "merozoite adhesive erythrocytic binding protein", description)) %>% 
  mutate(description = ifelse("membrane associated erythrocyte binding-likeprotein"==description, "merozoite adhesive erythrocytic binding protein", description)) %>% 
  mutate(description = ifelse("membrane associated histidine-rich protein 1"==description, "membrane associated histidine-rich protein", description)) %>% 
  mutate(description = gsub(",putative", ", putative", description)) %>% 
  mutate(description = gsub(",pseudogene", ", pseudogene", description))%>% 
  mutate(description = gsub("unknownfunction", "unknown function", description))%>% 
  mutate(description = gsub("conserved protein, unknown function", "conserved Plasmodium protein, unknown function", description)) %>% 
  mutate(description = gsub(" \\(SURFIN", "\\(SURFIN", description)) %>% 
  mutate(description = ifelse(grepl("Plasmodium exported protein", description), "Plasmodium exported protein (PHIST)", description)) %>% 
  mutate(description = ifelse("erythrocyte membrane protein 1 (PfEMP1), exon 2"==description, "erythrocyte membrane protein 1 (PfEMP1), exon 2, pseudogene", description)) %>% 
  mutate(description = ifelse("membrane associated histidine-rich protein 1"==description, "membrane associated histidine-rich protein", description))%>% 
  mutate(description = gsub(",pseudogene", ", pseudogene", description))%>% 
  mutate(description = gsub("unknownfunction", "unknown function", description))%>% 
  mutate(description = gsub(" \\(SURFIN", "\\(SURFIN", description)) %>% 
  mutate(description = ifelse(grepl("Plasmodium exported protein", description), "Plasmodium exported protein (PHIST)", description)) %>% 
  mutate(description = ifelse("erythrocyte membrane protein 1 (PfEMP1), exon 2"==description, "erythrocyte membrane protein 1 (PfEMP1), exon 2, pseudogene", description)) %>% 
  mutate(description = ifelse(grepl("sporozoite and liver stage tryptophan-rich protein, putative", description), "tryptophan/threonine-rich antigen", description))%>% 
  mutate(description = ifelse(grepl("CRA domain-containing protein, putative", description), "conserved Plasmodium protein, unknown function", description))%>% 
  mutate(description = gsub(",pseudogene", ", pseudogene", description)) %>% 
  mutate(description = gsub("surfaceantigen", "surface antigen", description))  %>% 
  mutate(description = gsub("Tetratricopeptide repeat, putative", "tetratricopeptide repeat protein, putative", description)) %>% 
  mutate(description = gsub("transmembraneprotein", "transmembrane protein", description)) %>% 
  mutate(description = ifelse(grepl("PfEMP1", description) & grepl("pseudogene", description), "erythrocyte membrane protein 1 (PfEMP1), pseudogene", description)) %>% 
  mutate(description = gsub("PIR protein", "stevor", description)) %>% 
  mutate(description = gsub("erythrocyte membrane protein 1-like", "erythrocyte membrane protein 1 (PfEMP1), pseudogene", description)) %>% 
  mutate(description = gsub("acidic terminal segments, variant surface antigen of PfEMP1, putative", "erythrocyte membrane protein 1 (PfEMP1), pseudogene", description))%>% 
  mutate(description = ifelse(grepl("CoA binding protein", description, ignore.case = T), "acyl-CoA binding protein", description)) %>% 
  mutate(description = ifelse(grepl("transfer RNA", description) | grepl("tRNA", description), "tRNA", description))%>% 
  mutate(description = ifelse(grepl("cytoadherence", description), "CLAG", description))%>% 
  mutate(description = ifelse(grepl("surface-associated interspersed protein", description), "SURFIN", description))%>% 
  mutate(description = ifelse(grepl("SURFIN", description), "SURFIN", description))%>% 
  mutate(description = ifelse(grepl("stevor-like", description), "stevor, pseudogene", description)) %>% 
  mutate(description = ifelse(grepl("exported protein family", description), "exported protein family", description)) %>% 
  mutate(description = ifelse(grepl("ribosomal RNA", description), "rRNA", description)) %>% 
  mutate(description = ifelse(grepl("serine/threonine protein kinase", description), "serine/threonine protein kinase, FIKK family", description)) %>% 
  mutate(description = ifelse(grepl("hypothetical protein", description), "hypothetical protein, conserved", description)) %>% 
  mutate(description = ifelse(grepl("conserved Plasmodium protein, unknown function", description), "hypothetical protein, conserved", description)) %>% 
  mutate(description = ifelse(grepl("Rifin/stevor family, putative", description), "stevor", description))  %>% 
  mutate(description = ifelse(grepl("stevor", description), "stevor", description)) %>% 
  mutate(description = ifelse(grepl("rifin", description), "rifin", description)) %>% 
  mutate(description = ifelse(grepl("erythrocyte membrane protein 1 (PfEMP1), pseudogene", description), "erythrocyte membrane protein 1 (PfEMP1)", description)) %>% 
  mutate(description = ifelse(grepl("erythrocyte membrane protein 1", description), "erythrocyte membrane protein 1 (PfEMP1)", description)) %>% 
  mutate(description = ifelse(grepl("probably protein", description), "unspecified product", description)) %>% 
  mutate(description = ifelse(grepl("RESA", description), "RESA", description)) %>% 
  mutate(description = ifelse(grepl("ring-infected erythrocyte surface antigen", description), "ring-infected erythrocyte surface antigen", description))%>% 
  mutate(description = ifelse(grepl("Duffy binding domain/Erythrocyte binding antigen175, putative", description), "erythrocyte binding like protein 1", description))%>% 
  mutate(description = ifelse(grepl("erythrocyte binding like protein 1", description), "erythrocyte binding like protein 1", description)) %>% 
  mutate(description = ifelse(grepl("unspecified product", description), "hypothetical protein, conserved", description))%>% 
  mutate(description = ifelse(grepl("probable protein, unknown function", description), "hypothetical protein, conserved", description))%>% 
  mutate(description = ifelse(grepl("RESA", description), "ring-infected erythrocyte surface antigen", description))   %>% 
  mutate(description = gsub(", putative", "", description))

all13_strainStarts = all13 %>% 
  group_by(strain, chrom) %>% 
  summarise(minStart = min(start))

all13 = all13 %>% 
  left_join(all13_strainStarts) %>% 
  mutate(globalStart = start - minStart, 
         globalEnd = end - minStart)

chromLengths_13 = chromLengths %>% 
  filter(chrom %in% all13_strainStarts$chrom) %>% 
  left_join(all13_strainStarts)%>% 
  mutate(globalStart = 0, 
         globalEnd = length - minStart) %>% 
  mutate(chrom = factor(chrom, levels = chrom))

all13 = all13 %>% 
  mutate(chrom = factor(chrom, levels = chromLengths_13$chrom))

11

Code
all11 = tibble()

for(strain in strains$strains){
  strain11 = readr::read_tsv(paste0("endBeds/split_", strain, "_chrom11_toEnd_genes.tab.txt")) %>% 
    mutate(strain = strain ) %>% 
  mutate(chromGlobal = gsub(paste0(strain, "_"), "", col.0)) %>% 
  mutate(chromGlobal = gsub("_v3", "", chromGlobal)) %>% 
    rename(chrom = col.0, 
           start = col.1, 
           end = col.2)
  all11 = bind_rows(all11, strain11)
}




# PfIT_00_10 = readr::read_tsv(paste0("possibleFragmentsOf11/split_PfIT_00_10_genes.tab.txt")) %>% 
#   mutate(strain = "PfIT" ) %>% 
#   mutate(chromGlobal = gsub(paste0("PfIT", "_"), "", col.0)) %>% 
#   mutate(chromGlobal = gsub("_v3", "", chromGlobal)) %>% 
#     rename(chrom = col.0, 
#            start = col.1, 
#            end = col.2)
# all11 = bind_rows(all11, PfIT_00_10)

# PfKH01_00_27 = readr::read_tsv(paste0("possibleFragmentsOf11/split_PfKH01_00_27_genes.tab.txt")) %>% 
#   mutate(strain = "PfKH01" ) %>% 
#   mutate(chromGlobal = gsub(paste0("PfKH01", "_"), "", col.0)) %>% 
#   mutate(chromGlobal = gsub("_v3", "", chromGlobal)) %>% 
#     rename(chrom = col.0, 
#            start = col.1, 
#            end = col.2) %>% 
#   mutate(start = abs(start - 160672))%>% 
#   mutate(end = abs(end - 160672))
# 
# all11 = bind_rows(all11, PfKH01_00_27)


all11  = all11  %>% 
  filter(col.3 %!in% c("Pf3D7_11_v3_1916391_1918050_PF3D7_1148100", "Pf3D7_11_v3_1920267_1920811_PF3D7_1148200", "Pf3D7_11_v3_1922655_1922928_PF3D7_1148500")) %>% 
  mutate(description = gsub(" \\(SURFIN", "\\(SURFIN", description)) %>% 
  mutate(description = ifelse(grepl("Plasmodium exported protein", description), "Plasmodium exported protein (PHIST)", description)) %>% 
  mutate(description = ifelse("erythrocyte membrane protein 1 (PfEMP1), exon 2"==description, "erythrocyte membrane protein 1 (PfEMP1), exon 2, pseudogene", description)) %>% 
  mutate(description = ifelse("membrane associated erythrocyte binding-like protein"==description, "merozoite adhesive erythrocytic binding protein", description)) %>% 
  mutate(description = ifelse("membrane associated erythrocyte binding-likeprotein"==description, "merozoite adhesive erythrocytic binding protein", description)) %>% 
  mutate(description = ifelse("membrane associated histidine-rich protein 1"==description, "membrane associated histidine-rich protein", description)) %>% 
  mutate(description = gsub(",putative", ", putative", description)) %>% 
  mutate(description = gsub(",pseudogene", ", pseudogene", description))%>% 
  mutate(description = gsub("unknownfunction", "unknown function", description))%>% 
  mutate(description = gsub("conserved protein, unknown function", "conserved Plasmodium protein, unknown function", description)) %>% 
  mutate(description = gsub(" \\(SURFIN", "\\(SURFIN", description)) %>% 
  mutate(description = ifelse(grepl("Plasmodium exported protein", description), "Plasmodium exported protein (PHIST)", description)) %>% 
  mutate(description = ifelse("erythrocyte membrane protein 1 (PfEMP1), exon 2"==description, "erythrocyte membrane protein 1 (PfEMP1), exon 2, pseudogene", description)) %>% 
  mutate(description = ifelse("membrane associated histidine-rich protein 1"==description, "membrane associated histidine-rich protein", description))%>% 
  mutate(description = gsub(",pseudogene", ", pseudogene", description))%>% 
  mutate(description = gsub("unknownfunction", "unknown function", description))%>% 
  mutate(description = gsub(" \\(SURFIN", "\\(SURFIN", description)) %>% 
  mutate(description = ifelse(grepl("Plasmodium exported protein", description), "Plasmodium exported protein (PHIST)", description)) %>% 
  mutate(description = ifelse("erythrocyte membrane protein 1 (PfEMP1), exon 2"==description, "erythrocyte membrane protein 1 (PfEMP1), exon 2, pseudogene", description)) %>% 
  mutate(description = ifelse(grepl("sporozoite and liver stage tryptophan-rich protein, putative", description), "tryptophan/threonine-rich antigen", description))%>% 
  mutate(description = ifelse(grepl("CRA domain-containing protein, putative", description), "conserved Plasmodium protein, unknown function", description))%>% 
  mutate(description = gsub(",pseudogene", ", pseudogene", description)) %>% 
  mutate(description = gsub("surfaceantigen", "surface antigen", description))  %>% 
  mutate(description = gsub("Tetratricopeptide repeat, putative", "tetratricopeptide repeat protein, putative", description)) %>% 
  mutate(description = gsub("transmembraneprotein", "transmembrane protein", description)) %>% 
  mutate(description = ifelse(grepl("PfEMP1", description) & grepl("pseudogene", description), "erythrocyte membrane protein 1 (PfEMP1), pseudogene", description)) %>% 
  mutate(description = gsub("PIR protein", "stevor", description)) %>% 
  mutate(description = gsub("erythrocyte membrane protein 1-like", "erythrocyte membrane protein 1 (PfEMP1), pseudogene", description)) %>% 
  mutate(description = gsub("acidic terminal segments, variant surface antigen of PfEMP1, putative", "erythrocyte membrane protein 1 (PfEMP1), pseudogene", description))%>% 
  mutate(description = ifelse(grepl("CoA binding protein", description, ignore.case = T), "acyl-CoA binding protein", description)) %>% 
  mutate(description = ifelse(grepl("transfer RNA", description) | grepl("tRNA", description), "tRNA", description))%>% 
  mutate(description = ifelse(grepl("cytoadherence", description), "CLAG", description))%>% 
  mutate(description = ifelse(grepl("surface-associated interspersed protein", description), "SURFIN", description))%>% 
  mutate(description = ifelse(grepl("SURFIN", description), "SURFIN", description))%>% 
  mutate(description = ifelse(grepl("stevor-like", description), "stevor, pseudogene", description)) %>% 
  mutate(description = ifelse(grepl("exported protein family", description), "exported protein family", description)) %>% 
  mutate(description = ifelse(grepl("ribosomal RNA", description), "rRNA", description)) %>% 
  mutate(description = ifelse(grepl("serine/threonine protein kinase", description), "serine/threonine protein kinase, FIKK family", description)) %>% 
  mutate(description = ifelse(grepl("hypothetical protein", description), "hypothetical protein, conserved", description)) %>% 
  mutate(description = ifelse(grepl("conserved Plasmodium protein, unknown function", description), "hypothetical protein, conserved", description)) %>% 
  mutate(description = ifelse(grepl("Rifin/stevor family, putative", description), "stevor", description))  %>% 
  mutate(description = ifelse(grepl("stevor", description), "stevor", description)) %>% 
  mutate(description = ifelse(grepl("rifin", description), "rifin", description)) %>% 
  mutate(description = ifelse(grepl("erythrocyte membrane protein 1 (PfEMP1), pseudogene", description), "erythrocyte membrane protein 1 (PfEMP1)", description)) %>% 
  mutate(description = ifelse(grepl("erythrocyte membrane protein 1", description), "erythrocyte membrane protein 1 (PfEMP1)", description)) %>% 
  mutate(description = ifelse(grepl("probably protein", description), "unspecified product", description)) %>% 
  mutate(description = ifelse(grepl("RESA", description), "RESA", description)) %>% 
  mutate(description = ifelse(grepl("ring-infected erythrocyte surface antigen", description), "ring-infected erythrocyte surface antigen", description))%>% 
  mutate(description = ifelse(grepl("Duffy binding domain/Erythrocyte binding antigen175, putative", description), "erythrocyte binding like protein 1", description)) %>% 
  mutate(description = ifelse(grepl("erythrocyte binding like protein 1", description), "erythrocyte binding like protein 1", description))%>% 
  mutate(description = ifelse(grepl("unspecified product", description), "hypothetical protein, conserved", description))%>% 
  mutate(description = ifelse(grepl("probable protein, unknown function", description), "hypothetical protein, conserved", description)) %>% 
  mutate(description = ifelse(grepl("RESA", description), "ring-infected erythrocyte surface antigen", description)) %>% 
  mutate(description = gsub(", putative", "", description))


all11_strainStarts = all11 %>% 
  group_by(strain, chrom) %>% 
  summarise(minStart = min(start))

all11 = all11 %>% 
  left_join(all11_strainStarts) %>% 
  mutate(globalStart = start - minStart, 
         globalEnd = end - minStart)

chromLengths_11 = chromLengths %>% 
  filter(chrom %in% all11_strainStarts$chrom) %>% 
  left_join(all11_strainStarts) %>% 
  mutate(globalStart = 0, 
         globalEnd = length - minStart) %>% 
  mutate(chrom = factor(chrom, levels = chrom))

all11 = all11 %>% 
  mutate(chrom = factor(chrom, levels = chromLengths_11$chrom)) 
# %>% 
#   mutate(globalStart = ifelse("PfKH01_00_27" == chrom, globalStart + 17822, globalStart))%>% 
#   mutate(globalEnd = ifelse("PfKH01_00_27" == chrom, globalEnd + 17822, globalEnd)) 
# %>% 
#   mutate(globalStart = ifelse("PfIT_00_10" == chrom, globalStart + 28623, globalStart))%>% 
#   mutate(globalEnd = ifelse("PfIT_00_10" == chrom, globalEnd + 28623 , globalEnd))


# chromLengths_11 = chromLengths_11 %>% 
#   mutate(globalStart = ifelse("PfKH01_00_27" == chrom, globalStart + 17822, globalStart))%>% 
#   mutate(globalEnd = ifelse("PfKH01_00_27" == chrom, globalEnd + 17822, globalEnd)) 
# %>% 
#   mutate(globalStart = ifelse("PfIT_00_10" == chrom, globalStart + 28623, globalStart))%>% 
#   mutate(globalEnd = ifelse("PfIT_00_10" == chrom, globalEnd + 28623, globalEnd))

Plotting

Code
descriptionColorsNames = unique(c(all05$description, all07$description,all08$description, all13$description, all11$description))
descriptionColors = scheme$hex(length(descriptionColorsNames))
names(descriptionColors) = descriptionColorsNames

Interactive plots of the other genome assemblies for chromosomes 8, 11 and 13. Assemblies are displayed from a common homology gene from each chromosome, genes are colored by the genome annotations that accompany the assemblies.

05

Code
chrom05_plot = ggplot() + 
  geom_rect(data = chromLengths_05, aes(xmin = globalStart, xmax = globalEnd, 
                                        ymin = as.numeric(chrom) - 0.4,
                                        ymax = as.numeric(chrom) + 0.4), fill= "grey80") + 
  geom_rect(data = all05,           aes(xmin = globalStart, xmax = globalEnd, 
                                        ymin = as.numeric(chrom) - 0.4,
                                        ymax = as.numeric(chrom) + 0.4, 
                                        fill = description, ID = ID, strain = strain), color = "black") + 
  scale_y_continuous(breaks = 1:max(as.numeric(chromLengths_05$chrom)), labels = as.character(chromLengths_05$chrom)) + 
  scale_fill_manual("Genes\nDescription",values = descriptionColors[names(descriptionColors) %in% all05$description], 
                    guide = guide_legend(nrow = 26)) + 
  sofonias_theme_xRotate  + 
  theme(legend.text = element_text(size = 30), axis.text.x = element_text(size = 30, color = "black"), axis.text.y = element_text(size = 30, color = "black"), 
        legend.title = element_text(size = 30, face = "bold"), 
        legend.box="vertical", legend.margin=margin(),
        legend.background = element_blank(),
        legend.box.background = element_rect(colour = "black"))
Code
pdf("P_Laverania_chrom05_plot.pdf", height = 20, width = 30, useDingbats = F)
print(chrom05_plot)
dev.off()
quartz_off_screen 
                2
Code
plotly::ggplotly(chrom05_plot)

07

Code
chrom07_plot = ggplot() + 
  geom_rect(data = chromLengths_07, aes(xmin = globalStart, xmax = globalEnd, 
                                        ymin = as.numeric(chrom) - 0.4,
                                        ymax = as.numeric(chrom) + 0.4), fill= "grey80") + 
  geom_rect(data = all07,           aes(xmin = globalStart, xmax = globalEnd, 
                                        ymin = as.numeric(chrom) - 0.4,
                                        ymax = as.numeric(chrom) + 0.4, 
                                        fill = description, ID = ID, strain = strain), color = "black") + 
  scale_y_continuous(breaks = 1:max(as.numeric(chromLengths_07$chrom)), labels = as.character(chromLengths_07$chrom)) + 
  scale_fill_manual("Genes\nDescription",values = descriptionColors[names(descriptionColors) %in% all07$description], 
                    guide = guide_legend(nrow = 26)) + 
  sofonias_theme_xRotate  + 
  theme(legend.text = element_text(size = 30), axis.text.x = element_text(size = 30, color = "black"), axis.text.y = element_text(size = 30, color = "black"), 
        legend.title = element_text(size = 30, face = "bold"), 
        legend.box="vertical", legend.margin=margin(),
        legend.background = element_blank(),
        legend.box.background = element_rect(colour = "black"))
Code
pdf("P_Laverania_chrom07_plot.pdf", height = 20, width = 30, useDingbats = F)
print(chrom07_plot)
dev.off()
quartz_off_screen 
                2
Code
plotly::ggplotly(chrom07_plot)

08

Code
chrom08_plot = ggplot() + 
  geom_rect(data = chromLengths_08, aes(xmin = globalStart, xmax = globalEnd, 
                                        ymin = as.numeric(chrom) - 0.4,
                                        ymax = as.numeric(chrom) + 0.4), fill= "grey80") + 
  geom_rect(data = all08,           aes(xmin = globalStart, xmax = globalEnd, 
                                        ymin = as.numeric(chrom) - 0.4,
                                        ymax = as.numeric(chrom) + 0.4, 
                                        fill = description, ID = ID, strain = strain), color = "black") + 
  scale_y_continuous(breaks = 1:max(as.numeric(chromLengths_08$chrom)), labels = as.character(chromLengths_08$chrom)) + 
  scale_fill_manual("Genes\nDescription",values = descriptionColors[names(descriptionColors) %in% all08$description], 
                    guide = guide_legend(nrow = 7)) + 
  sofonias_theme_xRotate  + 
  theme(legend.text = element_text(size = 30), , axis.text.x = element_text(size = 30, color = "black"), axis.text.y = element_text(size = 30, color = "black"), 
        legend.title = element_text(size = 30, face = "bold"), 
        legend.box="vertical", legend.margin=margin(),
        legend.background = element_blank(),
        legend.box.background = element_rect(colour = "black"))
Code
pdf("P_Laverania_chrom08_plot.pdf", height = 17, width = 27, useDingbats = F)
print(chrom08_plot)
dev.off()
quartz_off_screen 
                2
Code
plotly::ggplotly(chrom08_plot)

13

Code
chrom13_plot = ggplot() + 
  geom_rect(data = chromLengths_13, aes(xmin = globalStart, xmax = globalEnd, 
                                        ymin = as.numeric(chrom) - 0.4,
                                        ymax = as.numeric(chrom) + 0.4), fill= "grey80") + 
  geom_rect(data = all13,           aes(xmin = globalStart, xmax = globalEnd, 
                                        ymin = as.numeric(chrom) - 0.4,
                                        ymax = as.numeric(chrom) + 0.4, 
                                        fill = description, ID = ID, strain = strain), color = "black") + 
  scale_y_continuous(breaks = 1:max(as.numeric(chromLengths_13$chrom)), labels = as.character(chromLengths_13$chrom)) + 
  scale_fill_manual("Genes\nDescription",values = descriptionColors[names(descriptionColors) %in% all13$description], 
                    guide = guide_legend(nrow = 7)) + 
  sofonias_theme_xRotate  + 
  theme(legend.text = element_text(size = 30), axis.text.x = element_text(size = 30, color = "black"), axis.text.y = element_text(size = 30, color = "black"), 
        legend.title = element_text(size = 30, face = "bold"), 
        legend.box="vertical", legend.margin=margin(),
        legend.background = element_blank(),
        legend.box.background = element_rect(colour = "black"))
Code
pdf("P_Laverania_chrom13_plot.pdf", height = 17, width = 27, useDingbats = F)
print(chrom13_plot)
dev.off()
quartz_off_screen 
                2
Code
plotly::ggplotly(chrom13_plot)

11

Code
chrom11_plot = ggplot() + 
  geom_rect(data = chromLengths_11, aes(xmin = globalStart, xmax = globalEnd, 
                                        ymin = as.numeric(chrom) - 0.4,
                                        ymax = as.numeric(chrom) + 0.4), fill= "grey80") + 
  geom_rect(data = all11,           aes(xmin = globalStart, xmax = globalEnd, 
                                        ymin = as.numeric(chrom) - 0.4,
                                        ymax = as.numeric(chrom) + 0.4, 
                                        fill = description, ID = ID, strain = strain
                                        ), color = "black") + 
  scale_y_continuous(breaks = 1:max(as.numeric(chromLengths_11$chrom)), labels = as.character(chromLengths_11$chrom)) + 
  scale_fill_manual("Genes\nDescription",values = descriptionColors[names(descriptionColors) %in% all11$description], 
                    guide = guide_legend(nrow = 8)) + 
  sofonias_theme_xRotate  + 
  theme(legend.text = element_text(size = 30), axis.text.x = element_text(size = 30, color = "black"), axis.text.y = element_text(size = 30, color = "black"), 
        legend.title = element_text(size = 30, face = "bold"), 
        legend.box="vertical", legend.margin=margin(),
        legend.background = element_blank(),
        legend.box.background = element_rect(colour = "black"))
Code
pdf("P_Laverania_chrom11_plot.pdf", height = 17, width = 27, useDingbats = F)
print(chrom11_plot)
dev.off()
quartz_off_screen 
                2
Code
plotly::ggplotly(chrom11_plot)