Procesamiento en R
Cargar resultados de Kaiju
tabla.kaiju <- read.csv('/home/manuel/bioinformatica/tesisviu/compresion/tabla_final-especies.txt',
sep='\t',header=T)
head(tabla.kaiju)## numero classified reino filo subfilo
## 1 7 root Bamfordvirae Nucleocytoviricota Pokkesviricetes
## 2 1 root Bamfordvirae Nucleocytoviricota Megaviricetes
## 3 4 root Pararnavirae Artverviricota Revtraviricetes
## 4 10 root Orthornavirae Negarnaviricota Polyploviricotina
## 5 139 root Orthornavirae Negarnaviricota Polyploviricotina
## 6 43 root Orthornavirae Negarnaviricota Polyploviricotina
## clase orden familia genero
## 1 Chitovirales Poxviridae Chordopoxvirinae Centapoxvirus
## 2 Algavirales Phycodnaviridae Prasinovirus unclassified Prasinovirus
## 3 Ortervirales Retroviridae Orthoretrovirinae Alpharetrovirus
## 4 Ellioviricetes Bunyavirales Peribunyaviridae Orthobunyavirus
## 5 Ellioviricetes Bunyavirales Peribunyaviridae Orthobunyavirus
## 6 Ellioviricetes Bunyavirales Peribunyaviridae Orthobunyavirus
## especies complejo muestra
## 1 Yokapox virus 146V
## 2 Yellowstone lake phycodnavirus 2 146V
## 3 Y73 sarcoma virus 146V
## 4 Wyeomyia orthobunyavirus 146V
## 5 Wolkberg orthobunyavirus 146V
## 6 Witwatersrand orthobunyavirus 146VView(tabla.kaiju)
names(tabla.kaiju)## [1] "numero" "classified" "reino" "filo" "subfilo"
## [6] "clase" "orden" "familia" "genero" "especies"
## [11] "complejo" "muestra"library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionoptions(digits = 20) Obener los totales de las tablas
library(dplyr)
total_146V <-tabla.kaiju %>%
select(numero,classified,especies,muestra) %>%
filter(muestra == '146V') %>%
filter(especies != 'nd') %>%
filter(classified == 'root') %>%
summarize(total_numeros = sum(numero, na.rm = TRUE))
total_146V## total_numeros
## 1 34228993total_171V <-tabla.kaiju %>%
select(numero,classified,especies,muestra) %>%
filter(muestra == '171V') %>%
filter(especies != 'nd') %>%
filter(classified == 'root') %>%
summarize(total_numeros = sum(numero, na.rm = TRUE))
total_171V$total_numeros ## [1] 12187397total_273V <-tabla.kaiju %>%
select(numero,classified,especies,muestra) %>%
filter(muestra == '273V') %>%
filter(especies != 'nd') %>%
filter(classified == 'root') %>%
summarize(total_numeros = sum(numero, na.rm = TRUE))
total_273V$total_numeros ## [1] 22293880total_52V <-tabla.kaiju %>%
select(numero,classified,especies,muestra) %>%
filter(muestra == '52V_') %>%
filter(especies != 'nd') %>%
filter(classified == 'root') %>%
summarize(total_numeros = sum(numero, na.rm = TRUE))
total_52V$total_numeros ## [1] 21184195total_53V <-tabla.kaiju %>%
select(numero,classified,especies,muestra) %>%
filter(muestra == '53V_') %>%
filter(especies != 'nd') %>%
filter(classified == 'root') %>%
summarize(total_numeros = sum(numero, na.rm = TRUE))
total_53V$total_numeros ## [1] 376738total_Und <-tabla.kaiju %>%
select(numero,classified,especies,muestra) %>%
filter(muestra == 'Unde') %>%
filter(especies != 'nd') %>%
filter(classified == 'root') %>%
summarize(total_numeros = sum(numero, na.rm = TRUE))
total_Und$total_numeros ## [1] 2141108total_V169 <-tabla.kaiju %>%
select(numero,classified,especies,muestra) %>%
filter(muestra == 'V169') %>%
filter(especies != 'nd') %>%
filter(classified == 'root') %>%
summarize(total_numeros = sum(numero, na.rm = TRUE))
total_V169$total_numeros ## [1] 9298332total_V292 <-tabla.kaiju %>%
select(numero,classified,especies,muestra) %>%
filter(muestra == 'V292') %>%
filter(especies != 'nd') %>%
filter(classified == 'root') %>%
summarize(total_numeros = sum(numero, na.rm = TRUE))
total_V292$total_numeros ## [1] 25706725Crear los nuevos dataframes
p.146V <- tabla.kaiju %>%
select(numero,classified,especies,muestra) %>%
filter(muestra == '146V') %>%
filter(especies != 'nd') %>%
filter(classified == 'root') %>%
group_by(especies) %>%
summarise(porcentaje = 100*sum(numero)/total_146V) %>%
mutate(codigo = '146V') %>%
arrange(desc(porcentaje)) %>%
filter(porcentaje$total_numeros > 10)
p.171V <-tabla.kaiju %>%
select(numero,classified,especies,muestra) %>%
filter(muestra == '171V') %>%
filter(especies != 'nd') %>%
filter(classified == 'root') %>%
group_by(especies) %>%
summarise(porcentaje = 100*sum(numero)/total_171V) %>%
mutate(codigo = '171V') %>%
arrange(desc(porcentaje)) %>%
filter(porcentaje$total_numeros > 10)
p.273V <-tabla.kaiju %>%
select(numero,classified,especies,muestra) %>%
filter(muestra == '273V') %>%
filter(especies != 'nd') %>%
filter(classified == 'root') %>%
group_by(especies) %>%
summarise(porcentaje = 100*sum(numero)/total_273V) %>%
mutate(codigo = '273V') %>%
arrange(desc(porcentaje)) %>%
filter(porcentaje$total_numeros > 10)
p.52V <-tabla.kaiju %>%
select(numero,classified,especies,muestra) %>%
filter(muestra == '52V_') %>%
filter(especies != 'nd') %>%
filter(classified == 'root') %>%
group_by(especies) %>%
summarise(porcentaje = 100*sum(numero)/total_52V) %>%
mutate(codigo = '52V') %>%
arrange(desc(porcentaje)) %>%
filter(porcentaje$total_numeros > 10)
p.53V <-tabla.kaiju %>%
select(numero,classified,especies,muestra) %>%
filter(muestra == '53V_') %>%
filter(especies != 'nd') %>%
filter(classified == 'root') %>%
group_by(especies) %>%
summarise(porcentaje = 100*sum(numero)/total_53V) %>%
mutate(codigo = '53V') %>%
arrange(desc(porcentaje)) %>%
filter(porcentaje$total_numeros > 10)
p.Und <-tabla.kaiju %>%
select(numero,classified,especies,muestra) %>%
filter(muestra == 'Unde') %>%
filter(especies != 'nd') %>%
filter(classified == 'root') %>%
group_by(especies) %>%
summarise(porcentaje = 100*sum(numero)/total_Und) %>%
mutate(codigo = 'Und') %>%
arrange(desc(porcentaje)) %>%
filter(porcentaje$total_numeros > 10) %>%
arrange(desc(porcentaje))
p.V169 <-tabla.kaiju %>%
select(numero,classified,especies,muestra) %>%
filter(muestra == 'V169') %>%
filter(especies != 'nd') %>%
filter(classified == 'root') %>%
group_by(especies) %>%
summarise(porcentaje = 100*sum(numero)/total_V169) %>%
mutate(codigo = 'V169') %>%
arrange(desc(porcentaje)) %>%
filter(porcentaje$total_numeros > 10)
p.V292 <-tabla.kaiju %>%
select(numero,classified,especies,muestra) %>%
filter(muestra == 'V292') %>%
filter(especies != 'nd') %>%
filter(classified == 'root') %>%
group_by(especies) %>%
summarise(porcentaje = 100*sum(numero)/total_V292) %>%
mutate(codigo = 'V292') %>%
arrange(desc(porcentaje)) %>%
filter(porcentaje$total_numeros > 10)
print(p.146V)## # A tibble: 1 × 3
## especies porcentaje$total_numeros codigo
## <chr> <dbl> <chr>
## 1 Patois orthobunyavirus 99.9 146Vprint(p.171V)## # A tibble: 2 × 3
## especies porcentaje$total_numeros codigo
## <chr> <dbl> <chr>
## 1 Venezuelan Equine Encephalitis virus 53.9 171V
## 2 Marituba orthobunyavirus 17.9 171Vprint(p.273V)## # A tibble: 1 × 3
## especies porcentaje$total_numeros codigo
## <chr> <dbl> <chr>
## 1 Patois orthobunyavirus 99.9 273Vprint(p.52V)## # A tibble: 1 × 3
## especies porcentaje$total_numeros codigo
## <chr> <dbl> <chr>
## 1 Patois orthobunyavirus 99.2 52Vprint(p.53V)## # A tibble: 1 × 3
## especies porcentaje$total_numeros codigo
## <chr> <dbl> <chr>
## 1 Patois orthobunyavirus 99.3 53Vprint(p.Und)## # A tibble: 2 × 3
## especies porcentaje$total_numeros codigo
## <chr> <dbl> <chr>
## 1 Patois orthobunyavirus 59.5 Und
## 2 Venezuelan Equine Encephalitis virus 27.5 Undprint(p.V169)## # A tibble: 1 × 3
## especies porcentaje$total_numeros codigo
## <chr> <dbl> <chr>
## 1 Venezuelan Equine Encephalitis virus 85.1 V169print(p.V292)## # A tibble: 2 × 3
## especies porcentaje$total_numeros codigo
## <chr> <dbl> <chr>
## 1 Venezuelan Equine Encephalitis virus 84.9 V292
## 2 Cabassou virus 10.5 V292combined_Kaiju <- rbind(p.146V, p.171V, p.273V, p.52V, p.53V, p.Und, p.V169, p.V292)
View(combined_Kaiju)
str(combined_Kaiju)## tibble [11 × 3] (S3: tbl_df/tbl/data.frame)
## $ especies : chr [1:11] "Patois orthobunyavirus" "Venezuelan Equine Encephalitis virus" "Marituba orthobunyavirus" "Patois orthobunyavirus" ...
## $ porcentaje:'data.frame': 11 obs. of 1 variable:
## ..$ total_numeros: num [1:11] 99.9 53.9 17.9 99.9 99.2 ...
## $ codigo : chr [1:11] "146V" "171V" "171V" "273V" ...porcentaje<-as.data.frame(combined_Kaiju$porcentaje$total_numeros)
str(porcentaje)## 'data.frame': 11 obs. of 1 variable:
## $ combined_Kaiju$porcentaje$total_numeros: num 99.9 53.9 17.9 99.9 99.2 ...names(porcentaje)<-c("porcentaje")
porcentaje<-porcentaje$porcentaje
porcentaje## [1] 99.871751996910916205 53.862124947599554048 17.913037541978816591
## [4] 99.917008614023217206 99.214409610561077102 99.291019222908232678
## [7] 59.520024211763256972 27.470636698382332241 85.122923122125556006
## [10] 84.882154377891382069 10.459154170747149593especies<-combined_Kaiju$especies
especies## [1] "Patois orthobunyavirus"
## [2] "Venezuelan Equine Encephalitis virus"
## [3] "Marituba orthobunyavirus"
## [4] "Patois orthobunyavirus"
## [5] "Patois orthobunyavirus"
## [6] "Patois orthobunyavirus"
## [7] "Patois orthobunyavirus"
## [8] "Venezuelan Equine Encephalitis virus"
## [9] "Venezuelan Equine Encephalitis virus"
## [10] "Venezuelan Equine Encephalitis virus"
## [11] "Cabassou virus"muestra<-combined_Kaiju$codigo
muestra## [1] "146V" "171V" "171V" "273V" "52V" "53V" "Und" "Und" "V169" "V292"
## [11] "V292"combined_Kaiju <- as.data.frame(cbind(porcentaje, especies, muestra))
combined_Kaiju## porcentaje especies muestra
## 1 99.8717519969109 Patois orthobunyavirus 146V
## 2 53.8621249475996 Venezuelan Equine Encephalitis virus 171V
## 3 17.9130375419788 Marituba orthobunyavirus 171V
## 4 99.9170086140232 Patois orthobunyavirus 273V
## 5 99.2144096105611 Patois orthobunyavirus 52V
## 6 99.2910192229082 Patois orthobunyavirus 53V
## 7 59.5200242117633 Patois orthobunyavirus Und
## 8 27.4706366983823 Venezuelan Equine Encephalitis virus Und
## 9 85.1229231221256 Venezuelan Equine Encephalitis virus V169
## 10 84.8821543778914 Venezuelan Equine Encephalitis virus V292
## 11 10.4591541707471 Cabassou virus V292str(combined_Kaiju)## 'data.frame': 11 obs. of 3 variables:
## $ porcentaje: chr "99.8717519969109" "53.8621249475996" "17.9130375419788" "99.9170086140232" ...
## $ especies : chr "Patois orthobunyavirus" "Venezuelan Equine Encephalitis virus" "Marituba orthobunyavirus" "Patois orthobunyavirus" ...
## $ muestra : chr "146V" "171V" "171V" "273V" ...combined_Kaiju$especies <- as.factor(combined_Kaiju$especies)
combined_Kaiju$muestra <- as.factor(combined_Kaiju$muestra)
combined_Kaiju$porcentaje <- as.numeric(combined_Kaiju$porcentaje)
str(combined_Kaiju)## 'data.frame': 11 obs. of 3 variables:
## $ porcentaje: num 99.9 53.9 17.9 99.9 99.2 ...
## $ especies : Factor w/ 4 levels "Cabassou virus",..: 3 4 2 3 3 3 3 4 4 4 ...
## $ muestra : Factor w/ 8 levels "146V","171V",..: 1 2 2 3 4 5 6 6 7 8 ...Añadir el porcentaje faltante
p.146V.nuevafila <- data.frame(especies = "otras",
porcentaje = (valor = 100 - sum(p.146V$porcentaje$total_numeros)),
muestra = "146V"); p.146V.nuevafila## especies porcentaje muestra
## 1 otras 0.1282480030890837952 146Vp.171V.nuevafila <- data.frame(especies = "otras",
porcentaje = (valor = 100 - sum(p.171V$porcentaje)),
muestra = "171V"); p.171V.nuevafila## especies porcentaje muestra
## 1 otras 28.224837510421622255 171Vp.273V.nuevafila <- data.frame(especies = "otras",
porcentaje = (valor = 100 - sum(p.273V$porcentaje)),
muestra = "273V"); p.273V.nuevafila## especies porcentaje muestra
## 1 otras 0.082991385976782794387 273Vp.52V.nuevafila <- data.frame(especies = "otras",
porcentaje = (valor = 100 - sum(p.52V$porcentaje)),
muestra = "52V"); p.52V.nuevafila## especies porcentaje muestra
## 1 otras 0.78559038943892289808 52Vp.53V.nuevafila <- data.frame(especies = "otras",
porcentaje = (valor = 100 - sum(p.53V$porcentaje)),
muestra = "53V"); p.53V.nuevafila## especies porcentaje muestra
## 1 otras 0.70898077709176732242 53Vp.Und.nuevafila <- data.frame(especies = "otras",
porcentaje = (valor = 100 - sum(p.Und$porcentaje)),
muestra = "Und"); p.Und.nuevafila## especies porcentaje muestra
## 1 otras 13.009339089854407234 Undp.V169.nuevafila <- data.frame(especies = "otras",
porcentaje = (valor = 100 - sum(p.V169$porcentaje)),
muestra = "V169"); p.V169.nuevafila## especies porcentaje muestra
## 1 otras 14.877076877874443994 V169p.V292.nuevafila <- data.frame(especies = "otras",
porcentaje = (valor = 100 - sum(p.V292$porcentaje)),
muestra = "V292"); p.V292.nuevafila## especies porcentaje muestra
## 1 otras 4.6586914513614630096 V292result.kaiju <- bind_rows(combined_Kaiju, p.146V.nuevafila, p.171V.nuevafila, p.273V.nuevafila,
p.52V.nuevafila, p.53V.nuevafila, p.Und.nuevafila,
p.V292.nuevafila, p.V169.nuevafila) %>%
arrange(muestra)
result.kaiju## porcentaje especies muestra
## 1 99.871751996910901993942 Patois orthobunyavirus 146V
## 2 0.128248003089083795203 otras 146V
## 3 53.862124947599596680448 Venezuelan Equine Encephalitis virus 171V
## 4 17.913037541978798827813 Marituba orthobunyavirus 171V
## 5 28.224837510421622255308 otras 171V
## 6 99.917008614023202994758 Patois orthobunyavirus 273V
## 7 0.082991385976782794387 otras 273V
## 8 99.214409610561105523630 Patois orthobunyavirus 52V
## 9 0.785590389438922898080 otras 52V
## 10 99.291019222908204255873 Patois orthobunyavirus 53V
## 11 0.708980777091767322418 otras 53V
## 12 59.520024211763299604172 Patois orthobunyavirus Und
## 13 27.470636698382300266985 Venezuelan Equine Encephalitis virus Und
## 14 13.009339089854407234270 otras Und
## 15 85.122923122125598638377 Venezuelan Equine Encephalitis virus V169
## 16 14.877076877874443994187 otras V169
## 17 84.882154377891396279665 Venezuelan Equine Encephalitis virus V292
## 18 10.459154170747099854566 Cabassou virus V292
## 19 4.658691451361463009562 otras V292Crear grafico de barras
library(ggplot2)
library(viridis)## Loading required package: viridisLite#unique(result$especies)
ggplot(result.kaiju, aes(x = muestra, y = porcentaje, fill = especies)) +
geom_col(position = "fill", width = 0.98)+
scale_fill_manual(values = c("#2271B2", "#3DB7E9", "#F0E442", "#D55E00", "#359B73")) +
xlab("Especies") +
ylab("Porcentaje") +
ggtitle("Kaiju") +
theme(plot.title = element_text(hjust = 0.5)) +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
scale_y_continuous(labels = function(x) paste0(x * 100, "%"))
Cargar resultados de Kraken2
tabla.kraken <- read.csv('/home/manuel/bioinformatica/tesisviu/compresion-kraken/tabla_final-especies.txt',
sep='\t',header=T)
tabla.kraken## Conteo Especies
## 1 18016973 Patois virus
## 2 17218450 Zegla virus
## 3 274478 Buttonwillow virus
## 4 66223 Kaeng Khoi virus
## 5 60340 Koongol virus
## 6 59569 Keystone virus
## 7 12356 Potosi virus
## 8 7264 Ilesha virus
## 9 3622 Bellavista virus
## 10 1247 Caraparu virus
## 11 454 Enseada virus
## 12 326 Jatobal virus
## 13 152 Aino virus
## 14 135 California encephalitis virus
## 15 120 Guama virus
## 16 89 Catu virus
## 17 58 Snowshoe hare virus
## 18 50 Tensaw virus
## 19 49 Bimiti virus
## 20 48 Jamestown Canyon virus
## 21 45 Leanyer virus
## 22 14 Schmallenberg virus
## 23 38 Utinga virus
## 24 29 Capim virus
## 25 24 Bozo virus
## 26 21 Marituba virus
## 27 20 Macaua virus
## 28 19 Cat Que virus
## 29 14 Madrid virus
## 30 12 Oriboca virus
## 31 12 San Angelo virus
## 32 20 Rio Preto da Eva virus
## 33 20 Beihai sesarmid crab virus 1
## 34 12 Peduovirus P22H4
## 35 126 Bracoviriform facetosae
## 36 64 BeAn 58058 virus
## 37 12 Arhar cryptic virus-I
## 38 178778 Venezuelan equine encephalitis virus comp
## 39 174147 Venezuelan equine encephalitis virus comp
## 40 171814 Venezuelan equine encephalitis virus comp
## 41 163791 Venezuelan equine encephalitis virus comp
## 42 143002 Venezuelan equine encephalitis virus comp
## 43 46527 Venezuelan equine encephalitis virus comp
## 44 3454 Venezuelan equine encephalitis virus comp
## 45 409 Highlands J virus
## 46 266 Middelburg virus
## 47 98 Venezuelan equine encephalitis virus comp
## 48 66 Onyong-nyong virus
## 49 51 Eastern equine encephalitis virus
## 50 33 Madariaga virus
## 51 170415 Marituba virus
## 52 67853 Catu virus
## 53 17070 Caraparu virus
## 54 15803 Enseada virus
## 55 7078 Serra do Navio virus
## 56 1566 Guama virus
## 57 148 Patois virus
## 58 133 Zegla virus
## 59 134 Oriboca virus
## 60 117 Batai virus
## 61 73 Brazoran virus
## 62 52 Oropouche virus
## 63 50 Bellavista virus
## 64 47 Kairi virus
## 65 39 Buttonwillow virus
## 66 38 California encephalitis virus
## 67 33 Bunyamwera virus
## 68 28 Facey's Paddock virus
## 69 21 Bimiti virus
## 70 17 Madrid virus
## 71 13 Tataguine virus
## 72 29 Abelson murine leukemia virus
## 73 145 BeAn 58058 virus
## 74 55 Escherichia phage vB_EcoM_KAW1E185
## 75 11 Papiine betaherpesvirus 3
## 76 11 Baboon cytomegalovirus OCOM4-37
## 77 36 Bracoviriform facetosae
## 78 15421814 Patois virus
## 79 9551728 Zegla virus
## 80 18909 Bimiti virus
## 81 106 Catu virus
## 82 49 Gamboa virus
## 83 39 Wolkberg virus
## 84 37 Marituba virus
## 85 19 Bellavista virus
## 86 16 Batama virus
## 87 14 Oropouche virus
## 88 13 California encephalitis virus
## 89 13 Capim virus
## 90 12 Umbre virus
## 91 11 Fort Sherman virus
## 92 90 Escherichia phage vB_EcoM_KAW1E185
## 93 68 Bracoviriform facetosae
## 94 31 BeAn 58058 virus
## 95 14 Choristoneura fumiferana granulovirus
## 96 11597150 Patois virus
## 97 10412488 Zegla virus
## 98 10745 Bellavista virus
## 99 4252 Capim virus
## 100 571 Madrid virus
## 101 49 Gamboa virus
## 102 36 Wolkberg virus
## 103 31 Koongol virus
## 104 21 Catu virus
## 105 14 Kairi virus
## 106 13 Marituba virus
## 107 12 Lumbo virus
## 108 12 Bimiti virus
## 109 55 BeAn 58058 virus
## 110 38 Bracoviriform facetosae
## 111 17 Choristoneura fumiferana granulovirus
## 112 242037 Zegla virus
## 113 151619 Patois virus
## 114 2242 Cat Que virus
## 115 112 Brazoran virus
## 116 32 Keystone virus
## 117 19 Capim virus
## 118 14 Bellavista virus
## 119 12 Potosi virus
## 120 1372 Choristoneura fumiferana granulovirus
## 121 21 Peduovirus P22H4
## 122 12 Bracoviriform facetosae
## 123 682893 Patois virus
## 124 599890 Zegla virus
## 125 4763 Buttonwillow virus
## 126 1944 Marituba virus
## 127 1908 Kaeng Khoi virus
## 128 1042 Keystone virus
## 129 1016 Koongol virus
## 130 793 Catu virus
## 131 307 Bellavista virus
## 132 242 Bimiti virus
## 133 206 Potosi virus
## 134 196 Enseada virus
## 135 178 Caraparu virus
## 136 118 Ilesha virus
## 137 96 Serra do Navio virus
## 138 52 Capim virus
## 139 36 Guama virus
## 140 33 Cat Que virus
## 141 19 California encephalitis virus
## 142 16 Madrid virus
## 143 14 Jatobal virus
## 144 15117 Venezuelan equine encephalitis virus comp
## 145 14691 Venezuelan equine encephalitis virus comp
## 146 9699 Venezuelan equine encephalitis virus comp
## 147 8113 Venezuelan equine encephalitis virus comp
## 148 6075 Venezuelan equine encephalitis virus comp
## 149 2870 Venezuelan equine encephalitis virus comp
## 150 326 Venezuelan equine encephalitis virus comp
## 151 61 Middelburg virus
## 152 47 Venezuelan equine encephalitis virus comp
## 153 12 Highlands J virus
## 154 107968 Sinsheimervirus phiX174
## 155 107968 Escherichia phage phiX174
## 156 22 Inovirus M13
## 157 13 Adeno-associated dependoparvovirus A
## 158 408 Human mastadenovirus C
## 159 225 Punavirus P1
## 160 225 Enterobacteria phage P7
## 161 50 Escherichia phage DE3
## 162 25 Escherichia phage ev017
## 163 28 Human betaherpesvirus 5
## 164 38 Choristoneura fumiferana granulovirus
## 165 194730 Venezuelan equine encephalitis virus comp
## 166 150940 Venezuelan equine encephalitis virus comp
## 167 132091 Venezuelan equine encephalitis virus comp
## 168 123318 Venezuelan equine encephalitis virus comp
## 169 60264 Venezuelan equine encephalitis virus comp
## 170 19479 Venezuelan equine encephalitis virus comp
## 171 1651 Venezuelan equine encephalitis virus comp
## 172 441 Middelburg virus
## 173 135 Highlands J virus
## 174 114 Venezuelan equine encephalitis virus comp
## 175 41 Onyong-nyong virus
## 176 13 Eastern equine encephalitis virus
## 177 13 Madariaga virus
## 178 73 Escherichia phage ev017
## 179 648037 Venezuelan equine encephalitis virus comp
## 180 534047 Venezuelan equine encephalitis virus comp
## 181 298149 Venezuelan equine encephalitis virus comp
## 182 276896 Venezuelan equine encephalitis virus comp
## 183 175955 Venezuelan equine encephalitis virus comp
## 184 87993 Venezuelan equine encephalitis virus comp
## 185 10718 Venezuelan equine encephalitis virus comp
## 186 1060 Middelburg virus
## 187 665 Highlands J virus
## 188 491 Venezuelan equine encephalitis virus comp
## 189 60 Eastern equine encephalitis virus
## 190 60 Madariaga virus
## 191 21 Barmah Forest virus
## 192 12 Onyong-nyong virus
## 193 15 Patois virus
## 194 33 Peduovirus P22H4
## Complejo Muestras
## 1 146V
## 2 146V
## 3 146V
## 4 146V
## 5 146V
## 6 146V
## 7 146V
## 8 146V
## 9 146V
## 10 146V
## 11 146V
## 12 146V
## 13 146V
## 14 146V
## 15 146V
## 16 146V
## 17 146V
## 18 146V
## 19 146V
## 20 146V
## 21 146V
## 22 146V
## 23 146V
## 24 146V
## 25 146V
## 26 146V
## 27 146V
## 28 146V
## 29 146V
## 30 146V
## 31 146V
## 32 146V
## 33 146V
## 34 146V
## 35 146V
## 36 146V
## 37 146V
## 38 Rio Negro virus 171V
## 39 Cabassou virus 171V
## 40 Pixuna virus 171V
## 41 Everglades virus 171V
## 42 Venezuelan equine encephalitis virus 171V
## 43 Tonate virus 171V
## 44 Mucambo virus 171V
## 45 171V
## 46 171V
## 47 Mosso das Pedras virus 171V
## 48 171V
## 49 171V
## 50 171V
## 51 171V
## 52 171V
## 53 171V
## 54 171V
## 55 171V
## 56 171V
## 57 171V
## 58 171V
## 59 171V
## 60 171V
## 61 171V
## 62 171V
## 63 171V
## 64 171V
## 65 171V
## 66 171V
## 67 171V
## 68 171V
## 69 171V
## 70 171V
## 71 171V
## 72 171V
## 73 171V
## 74 171V
## 75 171V
## 76 171V
## 77 171V
## 78 273V
## 79 273V
## 80 273V
## 81 273V
## 82 273V
## 83 273V
## 84 273V
## 85 273V
## 86 273V
## 87 273V
## 88 273V
## 89 273V
## 90 273V
## 91 273V
## 92 273V
## 93 273V
## 94 273V
## 95 273V
## 96 52V_
## 97 52V_
## 98 52V_
## 99 52V_
## 100 52V_
## 101 52V_
## 102 52V_
## 103 52V_
## 104 52V_
## 105 52V_
## 106 52V_
## 107 52V_
## 108 52V_
## 109 52V_
## 110 52V_
## 111 52V_
## 112 53V_
## 113 53V_
## 114 53V_
## 115 53V_
## 116 53V_
## 117 53V_
## 118 53V_
## 119 53V_
## 120 53V_
## 121 53V_
## 122 53V_
## 123 Unde
## 124 Unde
## 125 Unde
## 126 Unde
## 127 Unde
## 128 Unde
## 129 Unde
## 130 Unde
## 131 Unde
## 132 Unde
## 133 Unde
## 134 Unde
## 135 Unde
## 136 Unde
## 137 Unde
## 138 Unde
## 139 Unde
## 140 Unde
## 141 Unde
## 142 Unde
## 143 Unde
## 144 Pixuna virus Unde
## 145 Rio Negro virus Unde
## 146 Everglades virus Unde
## 147 Venezuelan equine encephalitis virus Unde
## 148 Cabassou virus Unde
## 149 Tonate virus Unde
## 150 Mucambo virus Unde
## 151 Unde
## 152 Mosso das Pedras virus Unde
## 153 Unde
## 154 Unde
## 155 Unde
## 156 Unde
## 157 Unde
## 158 Unde
## 159 Unde
## 160 Unde
## 161 Unde
## 162 Unde
## 163 Unde
## 164 Unde
## 165 Pixuna virus V169
## 166 Rio Negro virus V169
## 167 Everglades virus V169
## 168 Venezuelan equine encephalitis virus V169
## 169 Cabassou virus V169
## 170 Tonate virus V169
## 171 Mucambo virus V169
## 172 V169
## 173 V169
## 174 Mosso das Pedras virus V169
## 175 V169
## 176 V169
## 177 V169
## 178 V169
## 179 Pixuna virus V292
## 180 Rio Negro virus V292
## 181 Everglades virus V292
## 182 Venezuelan equine encephalitis virus V292
## 183 Cabassou virus V292
## 184 Tonate virus V292
## 185 Mucambo virus V292
## 186 V292
## 187 V292
## 188 Mosso das Pedras virus V292
## 189 V292
## 190 V292
## 191 V292
## 192 V292
## 193 V292
## 194 V292result.kraken <-tabla.kraken %>% filter(!grepl("unclassified|root|Viruses|viria|virae|
|viricota|viricotina|viricetes|virales|
|viridae|avirus", Especies)) %>%
arrange(Muestras)
str(result.kraken)## 'data.frame': 193 obs. of 4 variables:
## $ Conteo : int 18016973 17218450 274478 66223 60340 59569 12356 7264 3622 1247 ...
## $ Especies: chr "Patois virus" "Zegla virus" "Buttonwillow virus" "Kaeng Khoi virus" ...
## $ Complejo: chr "" "" "" "" ...
## $ Muestras: chr "146V" "146V" "146V" "146V" ...result.kraken <-result.kraken %>%
rename(Muestra = Muestras)
result.kraken## Conteo Especies
## 1 18016973 Patois virus
## 2 17218450 Zegla virus
## 3 274478 Buttonwillow virus
## 4 66223 Kaeng Khoi virus
## 5 60340 Koongol virus
## 6 59569 Keystone virus
## 7 12356 Potosi virus
## 8 7264 Ilesha virus
## 9 3622 Bellavista virus
## 10 1247 Caraparu virus
## 11 454 Enseada virus
## 12 326 Jatobal virus
## 13 152 Aino virus
## 14 135 California encephalitis virus
## 15 120 Guama virus
## 16 89 Catu virus
## 17 58 Snowshoe hare virus
## 18 50 Tensaw virus
## 19 49 Bimiti virus
## 20 48 Jamestown Canyon virus
## 21 45 Leanyer virus
## 22 14 Schmallenberg virus
## 23 38 Utinga virus
## 24 29 Capim virus
## 25 24 Bozo virus
## 26 21 Marituba virus
## 27 20 Macaua virus
## 28 19 Cat Que virus
## 29 14 Madrid virus
## 30 12 Oriboca virus
## 31 12 San Angelo virus
## 32 20 Rio Preto da Eva virus
## 33 20 Beihai sesarmid crab virus 1
## 34 12 Peduovirus P22H4
## 35 126 Bracoviriform facetosae
## 36 64 BeAn 58058 virus
## 37 12 Arhar cryptic virus-I
## 38 178778 Venezuelan equine encephalitis virus comp
## 39 174147 Venezuelan equine encephalitis virus comp
## 40 171814 Venezuelan equine encephalitis virus comp
## 41 163791 Venezuelan equine encephalitis virus comp
## 42 143002 Venezuelan equine encephalitis virus comp
## 43 46527 Venezuelan equine encephalitis virus comp
## 44 3454 Venezuelan equine encephalitis virus comp
## 45 409 Highlands J virus
## 46 266 Middelburg virus
## 47 98 Venezuelan equine encephalitis virus comp
## 48 66 Onyong-nyong virus
## 49 51 Eastern equine encephalitis virus
## 50 33 Madariaga virus
## 51 170415 Marituba virus
## 52 67853 Catu virus
## 53 17070 Caraparu virus
## 54 15803 Enseada virus
## 55 7078 Serra do Navio virus
## 56 1566 Guama virus
## 57 148 Patois virus
## 58 133 Zegla virus
## 59 134 Oriboca virus
## 60 117 Batai virus
## 61 73 Brazoran virus
## 62 52 Oropouche virus
## 63 50 Bellavista virus
## 64 47 Kairi virus
## 65 39 Buttonwillow virus
## 66 38 California encephalitis virus
## 67 33 Bunyamwera virus
## 68 28 Facey's Paddock virus
## 69 21 Bimiti virus
## 70 17 Madrid virus
## 71 13 Tataguine virus
## 72 29 Abelson murine leukemia virus
## 73 145 BeAn 58058 virus
## 74 55 Escherichia phage vB_EcoM_KAW1E185
## 75 11 Papiine betaherpesvirus 3
## 76 11 Baboon cytomegalovirus OCOM4-37
## 77 36 Bracoviriform facetosae
## 78 15421814 Patois virus
## 79 9551728 Zegla virus
## 80 18909 Bimiti virus
## 81 106 Catu virus
## 82 49 Gamboa virus
## 83 39 Wolkberg virus
## 84 37 Marituba virus
## 85 19 Bellavista virus
## 86 16 Batama virus
## 87 14 Oropouche virus
## 88 13 California encephalitis virus
## 89 13 Capim virus
## 90 12 Umbre virus
## 91 11 Fort Sherman virus
## 92 90 Escherichia phage vB_EcoM_KAW1E185
## 93 68 Bracoviriform facetosae
## 94 31 BeAn 58058 virus
## 95 14 Choristoneura fumiferana granulovirus
## 96 11597150 Patois virus
## 97 10412488 Zegla virus
## 98 10745 Bellavista virus
## 99 4252 Capim virus
## 100 571 Madrid virus
## 101 49 Gamboa virus
## 102 36 Wolkberg virus
## 103 31 Koongol virus
## 104 21 Catu virus
## 105 14 Kairi virus
## 106 13 Marituba virus
## 107 12 Lumbo virus
## 108 12 Bimiti virus
## 109 55 BeAn 58058 virus
## 110 38 Bracoviriform facetosae
## 111 17 Choristoneura fumiferana granulovirus
## 112 242037 Zegla virus
## 113 151619 Patois virus
## 114 2242 Cat Que virus
## 115 112 Brazoran virus
## 116 32 Keystone virus
## 117 19 Capim virus
## 118 14 Bellavista virus
## 119 12 Potosi virus
## 120 1372 Choristoneura fumiferana granulovirus
## 121 21 Peduovirus P22H4
## 122 12 Bracoviriform facetosae
## 123 682893 Patois virus
## 124 599890 Zegla virus
## 125 4763 Buttonwillow virus
## 126 1944 Marituba virus
## 127 1908 Kaeng Khoi virus
## 128 1042 Keystone virus
## 129 1016 Koongol virus
## 130 793 Catu virus
## 131 307 Bellavista virus
## 132 242 Bimiti virus
## 133 206 Potosi virus
## 134 196 Enseada virus
## 135 178 Caraparu virus
## 136 118 Ilesha virus
## 137 96 Serra do Navio virus
## 138 52 Capim virus
## 139 36 Guama virus
## 140 33 Cat Que virus
## 141 19 California encephalitis virus
## 142 16 Madrid virus
## 143 14 Jatobal virus
## 144 15117 Venezuelan equine encephalitis virus comp
## 145 14691 Venezuelan equine encephalitis virus comp
## 146 9699 Venezuelan equine encephalitis virus comp
## 147 8113 Venezuelan equine encephalitis virus comp
## 148 6075 Venezuelan equine encephalitis virus comp
## 149 2870 Venezuelan equine encephalitis virus comp
## 150 326 Venezuelan equine encephalitis virus comp
## 151 61 Middelburg virus
## 152 47 Venezuelan equine encephalitis virus comp
## 153 12 Highlands J virus
## 154 107968 Sinsheimervirus phiX174
## 155 107968 Escherichia phage phiX174
## 156 22 Inovirus M13
## 157 13 Adeno-associated dependoparvovirus A
## 158 408 Human mastadenovirus C
## 159 225 Enterobacteria phage P7
## 160 50 Escherichia phage DE3
## 161 25 Escherichia phage ev017
## 162 28 Human betaherpesvirus 5
## 163 38 Choristoneura fumiferana granulovirus
## 164 194730 Venezuelan equine encephalitis virus comp
## 165 150940 Venezuelan equine encephalitis virus comp
## 166 132091 Venezuelan equine encephalitis virus comp
## 167 123318 Venezuelan equine encephalitis virus comp
## 168 60264 Venezuelan equine encephalitis virus comp
## 169 19479 Venezuelan equine encephalitis virus comp
## 170 1651 Venezuelan equine encephalitis virus comp
## 171 441 Middelburg virus
## 172 135 Highlands J virus
## 173 114 Venezuelan equine encephalitis virus comp
## 174 41 Onyong-nyong virus
## 175 13 Eastern equine encephalitis virus
## 176 13 Madariaga virus
## 177 73 Escherichia phage ev017
## 178 648037 Venezuelan equine encephalitis virus comp
## 179 534047 Venezuelan equine encephalitis virus comp
## 180 298149 Venezuelan equine encephalitis virus comp
## 181 276896 Venezuelan equine encephalitis virus comp
## 182 175955 Venezuelan equine encephalitis virus comp
## 183 87993 Venezuelan equine encephalitis virus comp
## 184 10718 Venezuelan equine encephalitis virus comp
## 185 1060 Middelburg virus
## 186 665 Highlands J virus
## 187 491 Venezuelan equine encephalitis virus comp
## 188 60 Eastern equine encephalitis virus
## 189 60 Madariaga virus
## 190 21 Barmah Forest virus
## 191 12 Onyong-nyong virus
## 192 15 Patois virus
## 193 33 Peduovirus P22H4
## Complejo Muestra
## 1 146V
## 2 146V
## 3 146V
## 4 146V
## 5 146V
## 6 146V
## 7 146V
## 8 146V
## 9 146V
## 10 146V
## 11 146V
## 12 146V
## 13 146V
## 14 146V
## 15 146V
## 16 146V
## 17 146V
## 18 146V
## 19 146V
## 20 146V
## 21 146V
## 22 146V
## 23 146V
## 24 146V
## 25 146V
## 26 146V
## 27 146V
## 28 146V
## 29 146V
## 30 146V
## 31 146V
## 32 146V
## 33 146V
## 34 146V
## 35 146V
## 36 146V
## 37 146V
## 38 Rio Negro virus 171V
## 39 Cabassou virus 171V
## 40 Pixuna virus 171V
## 41 Everglades virus 171V
## 42 Venezuelan equine encephalitis virus 171V
## 43 Tonate virus 171V
## 44 Mucambo virus 171V
## 45 171V
## 46 171V
## 47 Mosso das Pedras virus 171V
## 48 171V
## 49 171V
## 50 171V
## 51 171V
## 52 171V
## 53 171V
## 54 171V
## 55 171V
## 56 171V
## 57 171V
## 58 171V
## 59 171V
## 60 171V
## 61 171V
## 62 171V
## 63 171V
## 64 171V
## 65 171V
## 66 171V
## 67 171V
## 68 171V
## 69 171V
## 70 171V
## 71 171V
## 72 171V
## 73 171V
## 74 171V
## 75 171V
## 76 171V
## 77 171V
## 78 273V
## 79 273V
## 80 273V
## 81 273V
## 82 273V
## 83 273V
## 84 273V
## 85 273V
## 86 273V
## 87 273V
## 88 273V
## 89 273V
## 90 273V
## 91 273V
## 92 273V
## 93 273V
## 94 273V
## 95 273V
## 96 52V_
## 97 52V_
## 98 52V_
## 99 52V_
## 100 52V_
## 101 52V_
## 102 52V_
## 103 52V_
## 104 52V_
## 105 52V_
## 106 52V_
## 107 52V_
## 108 52V_
## 109 52V_
## 110 52V_
## 111 52V_
## 112 53V_
## 113 53V_
## 114 53V_
## 115 53V_
## 116 53V_
## 117 53V_
## 118 53V_
## 119 53V_
## 120 53V_
## 121 53V_
## 122 53V_
## 123 Unde
## 124 Unde
## 125 Unde
## 126 Unde
## 127 Unde
## 128 Unde
## 129 Unde
## 130 Unde
## 131 Unde
## 132 Unde
## 133 Unde
## 134 Unde
## 135 Unde
## 136 Unde
## 137 Unde
## 138 Unde
## 139 Unde
## 140 Unde
## 141 Unde
## 142 Unde
## 143 Unde
## 144 Pixuna virus Unde
## 145 Rio Negro virus Unde
## 146 Everglades virus Unde
## 147 Venezuelan equine encephalitis virus Unde
## 148 Cabassou virus Unde
## 149 Tonate virus Unde
## 150 Mucambo virus Unde
## 151 Unde
## 152 Mosso das Pedras virus Unde
## 153 Unde
## 154 Unde
## 155 Unde
## 156 Unde
## 157 Unde
## 158 Unde
## 159 Unde
## 160 Unde
## 161 Unde
## 162 Unde
## 163 Unde
## 164 Pixuna virus V169
## 165 Rio Negro virus V169
## 166 Everglades virus V169
## 167 Venezuelan equine encephalitis virus V169
## 168 Cabassou virus V169
## 169 Tonate virus V169
## 170 Mucambo virus V169
## 171 V169
## 172 V169
## 173 Mosso das Pedras virus V169
## 174 V169
## 175 V169
## 176 V169
## 177 V169
## 178 Pixuna virus V292
## 179 Rio Negro virus V292
## 180 Everglades virus V292
## 181 Venezuelan equine encephalitis virus V292
## 182 Cabassou virus V292
## 183 Tonate virus V292
## 184 Mucambo virus V292
## 185 V292
## 186 V292
## 187 Mosso das Pedras virus V292
## 188 V292
## 189 V292
## 190 V292
## 191 V292
## 192 V292
## 193 V292names(result.kraken) ## [1] "Conteo" "Especies" "Complejo" "Muestra"Obener los totales
total_146V.kraken <-result.kraken %>%
filter(Muestra == '146V') %>%
summarize(Conteo = sum(Conteo, na.rm = TRUE))
total_146V.kraken## Conteo
## 1 35722505total_171V.kraken <-result.kraken %>%
filter(Muestra == '171V') %>%
summarize(Conteo = sum(Conteo, na.rm = TRUE))
total_171V.kraken## Conteo
## 1 1163451total_273V.kraken <-result.kraken %>%
filter(Muestra == '273V') %>%
summarize(Conteo = sum(Conteo, na.rm = TRUE))
total_273V.kraken## Conteo
## 1 24992983total_52V.kraken <-result.kraken %>%
filter(Muestra == '52V_') %>%
summarize(Conteo = sum(Conteo, na.rm = TRUE))
total_52V.kraken## Conteo
## 1 22025504total_53V.kraken <-result.kraken %>%
filter(Muestra == '53V_') %>%
summarize(Conteo = sum(Conteo, na.rm = TRUE))
total_53V.kraken## Conteo
## 1 397492total_Und.kraken <-result.kraken %>%
filter(Muestra == 'Unde') %>%
summarize(Conteo = sum(Conteo, na.rm = TRUE))
total_Und.kraken## Conteo
## 1 1569518total_V169.kraken <-result.kraken %>%
filter(Muestra == 'V169') %>%
summarize(Conteo = sum(Conteo, na.rm = TRUE))
total_V169.kraken## Conteo
## 1 683303total_V292.kraken <-result.kraken %>%
filter(Muestra == 'V292') %>%
summarize(Conteo = sum(Conteo, na.rm = TRUE))
total_V292.kraken## Conteo
## 1 2034212crear los nuevos dataframes
names(result.kraken)## [1] "Conteo" "Especies" "Complejo" "Muestra"print(result.kraken)## Conteo Especies
## 1 18016973 Patois virus
## 2 17218450 Zegla virus
## 3 274478 Buttonwillow virus
## 4 66223 Kaeng Khoi virus
## 5 60340 Koongol virus
## 6 59569 Keystone virus
## 7 12356 Potosi virus
## 8 7264 Ilesha virus
## 9 3622 Bellavista virus
## 10 1247 Caraparu virus
## 11 454 Enseada virus
## 12 326 Jatobal virus
## 13 152 Aino virus
## 14 135 California encephalitis virus
## 15 120 Guama virus
## 16 89 Catu virus
## 17 58 Snowshoe hare virus
## 18 50 Tensaw virus
## 19 49 Bimiti virus
## 20 48 Jamestown Canyon virus
## 21 45 Leanyer virus
## 22 14 Schmallenberg virus
## 23 38 Utinga virus
## 24 29 Capim virus
## 25 24 Bozo virus
## 26 21 Marituba virus
## 27 20 Macaua virus
## 28 19 Cat Que virus
## 29 14 Madrid virus
## 30 12 Oriboca virus
## 31 12 San Angelo virus
## 32 20 Rio Preto da Eva virus
## 33 20 Beihai sesarmid crab virus 1
## 34 12 Peduovirus P22H4
## 35 126 Bracoviriform facetosae
## 36 64 BeAn 58058 virus
## 37 12 Arhar cryptic virus-I
## 38 178778 Venezuelan equine encephalitis virus comp
## 39 174147 Venezuelan equine encephalitis virus comp
## 40 171814 Venezuelan equine encephalitis virus comp
## 41 163791 Venezuelan equine encephalitis virus comp
## 42 143002 Venezuelan equine encephalitis virus comp
## 43 46527 Venezuelan equine encephalitis virus comp
## 44 3454 Venezuelan equine encephalitis virus comp
## 45 409 Highlands J virus
## 46 266 Middelburg virus
## 47 98 Venezuelan equine encephalitis virus comp
## 48 66 Onyong-nyong virus
## 49 51 Eastern equine encephalitis virus
## 50 33 Madariaga virus
## 51 170415 Marituba virus
## 52 67853 Catu virus
## 53 17070 Caraparu virus
## 54 15803 Enseada virus
## 55 7078 Serra do Navio virus
## 56 1566 Guama virus
## 57 148 Patois virus
## 58 133 Zegla virus
## 59 134 Oriboca virus
## 60 117 Batai virus
## 61 73 Brazoran virus
## 62 52 Oropouche virus
## 63 50 Bellavista virus
## 64 47 Kairi virus
## 65 39 Buttonwillow virus
## 66 38 California encephalitis virus
## 67 33 Bunyamwera virus
## 68 28 Facey's Paddock virus
## 69 21 Bimiti virus
## 70 17 Madrid virus
## 71 13 Tataguine virus
## 72 29 Abelson murine leukemia virus
## 73 145 BeAn 58058 virus
## 74 55 Escherichia phage vB_EcoM_KAW1E185
## 75 11 Papiine betaherpesvirus 3
## 76 11 Baboon cytomegalovirus OCOM4-37
## 77 36 Bracoviriform facetosae
## 78 15421814 Patois virus
## 79 9551728 Zegla virus
## 80 18909 Bimiti virus
## 81 106 Catu virus
## 82 49 Gamboa virus
## 83 39 Wolkberg virus
## 84 37 Marituba virus
## 85 19 Bellavista virus
## 86 16 Batama virus
## 87 14 Oropouche virus
## 88 13 California encephalitis virus
## 89 13 Capim virus
## 90 12 Umbre virus
## 91 11 Fort Sherman virus
## 92 90 Escherichia phage vB_EcoM_KAW1E185
## 93 68 Bracoviriform facetosae
## 94 31 BeAn 58058 virus
## 95 14 Choristoneura fumiferana granulovirus
## 96 11597150 Patois virus
## 97 10412488 Zegla virus
## 98 10745 Bellavista virus
## 99 4252 Capim virus
## 100 571 Madrid virus
## 101 49 Gamboa virus
## 102 36 Wolkberg virus
## 103 31 Koongol virus
## 104 21 Catu virus
## 105 14 Kairi virus
## 106 13 Marituba virus
## 107 12 Lumbo virus
## 108 12 Bimiti virus
## 109 55 BeAn 58058 virus
## 110 38 Bracoviriform facetosae
## 111 17 Choristoneura fumiferana granulovirus
## 112 242037 Zegla virus
## 113 151619 Patois virus
## 114 2242 Cat Que virus
## 115 112 Brazoran virus
## 116 32 Keystone virus
## 117 19 Capim virus
## 118 14 Bellavista virus
## 119 12 Potosi virus
## 120 1372 Choristoneura fumiferana granulovirus
## 121 21 Peduovirus P22H4
## 122 12 Bracoviriform facetosae
## 123 682893 Patois virus
## 124 599890 Zegla virus
## 125 4763 Buttonwillow virus
## 126 1944 Marituba virus
## 127 1908 Kaeng Khoi virus
## 128 1042 Keystone virus
## 129 1016 Koongol virus
## 130 793 Catu virus
## 131 307 Bellavista virus
## 132 242 Bimiti virus
## 133 206 Potosi virus
## 134 196 Enseada virus
## 135 178 Caraparu virus
## 136 118 Ilesha virus
## 137 96 Serra do Navio virus
## 138 52 Capim virus
## 139 36 Guama virus
## 140 33 Cat Que virus
## 141 19 California encephalitis virus
## 142 16 Madrid virus
## 143 14 Jatobal virus
## 144 15117 Venezuelan equine encephalitis virus comp
## 145 14691 Venezuelan equine encephalitis virus comp
## 146 9699 Venezuelan equine encephalitis virus comp
## 147 8113 Venezuelan equine encephalitis virus comp
## 148 6075 Venezuelan equine encephalitis virus comp
## 149 2870 Venezuelan equine encephalitis virus comp
## 150 326 Venezuelan equine encephalitis virus comp
## 151 61 Middelburg virus
## 152 47 Venezuelan equine encephalitis virus comp
## 153 12 Highlands J virus
## 154 107968 Sinsheimervirus phiX174
## 155 107968 Escherichia phage phiX174
## 156 22 Inovirus M13
## 157 13 Adeno-associated dependoparvovirus A
## 158 408 Human mastadenovirus C
## 159 225 Enterobacteria phage P7
## 160 50 Escherichia phage DE3
## 161 25 Escherichia phage ev017
## 162 28 Human betaherpesvirus 5
## 163 38 Choristoneura fumiferana granulovirus
## 164 194730 Venezuelan equine encephalitis virus comp
## 165 150940 Venezuelan equine encephalitis virus comp
## 166 132091 Venezuelan equine encephalitis virus comp
## 167 123318 Venezuelan equine encephalitis virus comp
## 168 60264 Venezuelan equine encephalitis virus comp
## 169 19479 Venezuelan equine encephalitis virus comp
## 170 1651 Venezuelan equine encephalitis virus comp
## 171 441 Middelburg virus
## 172 135 Highlands J virus
## 173 114 Venezuelan equine encephalitis virus comp
## 174 41 Onyong-nyong virus
## 175 13 Eastern equine encephalitis virus
## 176 13 Madariaga virus
## 177 73 Escherichia phage ev017
## 178 648037 Venezuelan equine encephalitis virus comp
## 179 534047 Venezuelan equine encephalitis virus comp
## 180 298149 Venezuelan equine encephalitis virus comp
## 181 276896 Venezuelan equine encephalitis virus comp
## 182 175955 Venezuelan equine encephalitis virus comp
## 183 87993 Venezuelan equine encephalitis virus comp
## 184 10718 Venezuelan equine encephalitis virus comp
## 185 1060 Middelburg virus
## 186 665 Highlands J virus
## 187 491 Venezuelan equine encephalitis virus comp
## 188 60 Eastern equine encephalitis virus
## 189 60 Madariaga virus
## 190 21 Barmah Forest virus
## 191 12 Onyong-nyong virus
## 192 15 Patois virus
## 193 33 Peduovirus P22H4
## Complejo Muestra
## 1 146V
## 2 146V
## 3 146V
## 4 146V
## 5 146V
## 6 146V
## 7 146V
## 8 146V
## 9 146V
## 10 146V
## 11 146V
## 12 146V
## 13 146V
## 14 146V
## 15 146V
## 16 146V
## 17 146V
## 18 146V
## 19 146V
## 20 146V
## 21 146V
## 22 146V
## 23 146V
## 24 146V
## 25 146V
## 26 146V
## 27 146V
## 28 146V
## 29 146V
## 30 146V
## 31 146V
## 32 146V
## 33 146V
## 34 146V
## 35 146V
## 36 146V
## 37 146V
## 38 Rio Negro virus 171V
## 39 Cabassou virus 171V
## 40 Pixuna virus 171V
## 41 Everglades virus 171V
## 42 Venezuelan equine encephalitis virus 171V
## 43 Tonate virus 171V
## 44 Mucambo virus 171V
## 45 171V
## 46 171V
## 47 Mosso das Pedras virus 171V
## 48 171V
## 49 171V
## 50 171V
## 51 171V
## 52 171V
## 53 171V
## 54 171V
## 55 171V
## 56 171V
## 57 171V
## 58 171V
## 59 171V
## 60 171V
## 61 171V
## 62 171V
## 63 171V
## 64 171V
## 65 171V
## 66 171V
## 67 171V
## 68 171V
## 69 171V
## 70 171V
## 71 171V
## 72 171V
## 73 171V
## 74 171V
## 75 171V
## 76 171V
## 77 171V
## 78 273V
## 79 273V
## 80 273V
## 81 273V
## 82 273V
## 83 273V
## 84 273V
## 85 273V
## 86 273V
## 87 273V
## 88 273V
## 89 273V
## 90 273V
## 91 273V
## 92 273V
## 93 273V
## 94 273V
## 95 273V
## 96 52V_
## 97 52V_
## 98 52V_
## 99 52V_
## 100 52V_
## 101 52V_
## 102 52V_
## 103 52V_
## 104 52V_
## 105 52V_
## 106 52V_
## 107 52V_
## 108 52V_
## 109 52V_
## 110 52V_
## 111 52V_
## 112 53V_
## 113 53V_
## 114 53V_
## 115 53V_
## 116 53V_
## 117 53V_
## 118 53V_
## 119 53V_
## 120 53V_
## 121 53V_
## 122 53V_
## 123 Unde
## 124 Unde
## 125 Unde
## 126 Unde
## 127 Unde
## 128 Unde
## 129 Unde
## 130 Unde
## 131 Unde
## 132 Unde
## 133 Unde
## 134 Unde
## 135 Unde
## 136 Unde
## 137 Unde
## 138 Unde
## 139 Unde
## 140 Unde
## 141 Unde
## 142 Unde
## 143 Unde
## 144 Pixuna virus Unde
## 145 Rio Negro virus Unde
## 146 Everglades virus Unde
## 147 Venezuelan equine encephalitis virus Unde
## 148 Cabassou virus Unde
## 149 Tonate virus Unde
## 150 Mucambo virus Unde
## 151 Unde
## 152 Mosso das Pedras virus Unde
## 153 Unde
## 154 Unde
## 155 Unde
## 156 Unde
## 157 Unde
## 158 Unde
## 159 Unde
## 160 Unde
## 161 Unde
## 162 Unde
## 163 Unde
## 164 Pixuna virus V169
## 165 Rio Negro virus V169
## 166 Everglades virus V169
## 167 Venezuelan equine encephalitis virus V169
## 168 Cabassou virus V169
## 169 Tonate virus V169
## 170 Mucambo virus V169
## 171 V169
## 172 V169
## 173 Mosso das Pedras virus V169
## 174 V169
## 175 V169
## 176 V169
## 177 V169
## 178 Pixuna virus V292
## 179 Rio Negro virus V292
## 180 Everglades virus V292
## 181 Venezuelan equine encephalitis virus V292
## 182 Cabassou virus V292
## 183 Tonate virus V292
## 184 Mucambo virus V292
## 185 V292
## 186 V292
## 187 Mosso das Pedras virus V292
## 188 V292
## 189 V292
## 190 V292
## 191 V292
## 192 V292
## 193 V292p.146V.kraken <- result.kraken %>%
select(Conteo,Especies,Muestra) %>%
filter(Muestra == '146V')%>%
group_by(Especies) %>%
summarise(Porcentaje = 100*sum(Conteo)/total_146V.kraken) %>%
mutate(codigo = '146V') %>%
arrange(desc(Porcentaje)) %>%
filter(Porcentaje > 10) ## Warning: Using one column matrices in `filter()` was deprecated in dplyr 1.1.0.
## ℹ Please use one dimensional logical vectors instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.p.146V.kraken## # A tibble: 2 × 3
## Especies Porcentaje$Conteo codigo
## <chr> <dbl> <chr>
## 1 Patois virus 50.4 146V
## 2 Zegla virus 48.2 146Vp.171V.kraken <- result.kraken %>%
select(Conteo,Especies,Muestra) %>%
filter(Muestra == '171V') %>%
group_by(Especies) %>%
summarise(Porcentaje = 100*sum(Conteo)/total_171V.kraken) %>%
mutate(codigo = '171V') %>%
arrange(desc(Porcentaje)) %>%
filter(Porcentaje > 10)
p.171V.kraken## # A tibble: 2 × 3
## Especies Porcentaje$Conteo codigo
## <chr> <dbl> <chr>
## 1 Venezuelan equine encephalitis virus comp 75.8 171V
## 2 Marituba virus 14.6 171Vp.273V.kraken <- result.kraken %>%
select(Conteo,Especies,Muestra) %>%
filter(Muestra == '273V') %>%
group_by(Especies) %>%
summarise(Porcentaje = 100*sum(Conteo)/total_273V.kraken) %>%
mutate(codigo = '273V') %>%
arrange(desc(Porcentaje)) %>%
filter(Porcentaje > 10)
p.273V.kraken ## # A tibble: 2 × 3
## Especies Porcentaje$Conteo codigo
## <chr> <dbl> <chr>
## 1 Patois virus 61.7 273V
## 2 Zegla virus 38.2 273Vp.52V.kraken <- result.kraken %>%
select(Conteo,Especies,Muestra) %>%
filter(Muestra == '52V_') %>%
group_by(Especies) %>%
summarise(Porcentaje = 100*sum(Conteo)/total_52V.kraken) %>%
mutate(codigo = '52V') %>%
arrange(desc(Porcentaje)) %>%
filter(Porcentaje > 10)
p.52V.kraken## # A tibble: 2 × 3
## Especies Porcentaje$Conteo codigo
## <chr> <dbl> <chr>
## 1 Patois virus 52.7 52V
## 2 Zegla virus 47.3 52Vp.53V.kraken <- result.kraken %>%
select(Conteo,Especies,Muestra) %>%
filter(Muestra == '53V_') %>%
group_by(Especies) %>%
summarise(Porcentaje = 100*sum(Conteo)/total_53V.kraken) %>%
mutate(codigo = '53V') %>%
arrange(desc(Porcentaje)) %>%
filter(Porcentaje > 10)
p.53V.kraken## # A tibble: 2 × 3
## Especies Porcentaje$Conteo codigo
## <chr> <dbl> <chr>
## 1 Zegla virus 60.9 53V
## 2 Patois virus 38.1 53Vp.Und.kraken <- result.kraken %>%
select(Conteo,Especies,Muestra) %>%
filter(Muestra == 'Unde') %>%
group_by(Especies) %>%
summarise(Porcentaje = 100*sum(Conteo)/total_Und.kraken) %>%
mutate(codigo = 'Und') %>%
arrange(desc(Porcentaje)) %>%
filter(Porcentaje > 10)
p.Und.kraken## # A tibble: 2 × 3
## Especies Porcentaje$Conteo codigo
## <chr> <dbl> <chr>
## 1 Patois virus 43.5 Und
## 2 Zegla virus 38.2 Undp.V169.kraken <- result.kraken %>%
select(Conteo,Especies,Muestra) %>%
filter(Muestra == 'V169') %>%
group_by(Especies) %>%
summarise(Porcentaje = 100*sum(Conteo)/total_V169.kraken) %>%
mutate(codigo = 'V169') %>%
arrange(desc(Porcentaje)) %>%
filter(Porcentaje > 10)
p.V169.kraken## # A tibble: 1 × 3
## Especies Porcentaje$Conteo codigo
## <chr> <dbl> <chr>
## 1 Venezuelan equine encephalitis virus comp 99.9 V169p.V292.kraken <- result.kraken %>%
select(Conteo,Especies,Muestra) %>%
filter(Muestra == 'V292') %>%
group_by(Especies) %>%
summarise(Porcentaje = 100*sum(Conteo)/total_V292.kraken) %>%
mutate(codigo = 'V292') %>%
arrange(desc(Porcentaje)) %>%
filter(Porcentaje > 10)
p.V292.kraken## # A tibble: 1 × 3
## Especies Porcentaje$Conteo codigo
## <chr> <dbl> <chr>
## 1 Venezuelan equine encephalitis virus comp 99.9 V292print(p.146V.kraken)## # A tibble: 2 × 3
## Especies Porcentaje$Conteo codigo
## <chr> <dbl> <chr>
## 1 Patois virus 50.4 146V
## 2 Zegla virus 48.2 146Vprint(p.171V.kraken)## # A tibble: 2 × 3
## Especies Porcentaje$Conteo codigo
## <chr> <dbl> <chr>
## 1 Venezuelan equine encephalitis virus comp 75.8 171V
## 2 Marituba virus 14.6 171Vprint(p.273V.kraken)## # A tibble: 2 × 3
## Especies Porcentaje$Conteo codigo
## <chr> <dbl> <chr>
## 1 Patois virus 61.7 273V
## 2 Zegla virus 38.2 273Vprint(p.52V.kraken)## # A tibble: 2 × 3
## Especies Porcentaje$Conteo codigo
## <chr> <dbl> <chr>
## 1 Patois virus 52.7 52V
## 2 Zegla virus 47.3 52Vprint(p.53V.kraken)## # A tibble: 2 × 3
## Especies Porcentaje$Conteo codigo
## <chr> <dbl> <chr>
## 1 Zegla virus 60.9 53V
## 2 Patois virus 38.1 53Vprint(p.Und.kraken)## # A tibble: 2 × 3
## Especies Porcentaje$Conteo codigo
## <chr> <dbl> <chr>
## 1 Patois virus 43.5 Und
## 2 Zegla virus 38.2 Undprint(p.V169.kraken)## # A tibble: 1 × 3
## Especies Porcentaje$Conteo codigo
## <chr> <dbl> <chr>
## 1 Venezuelan equine encephalitis virus comp 99.9 V169print(p.V292.kraken)## # A tibble: 1 × 3
## Especies Porcentaje$Conteo codigo
## <chr> <dbl> <chr>
## 1 Venezuelan equine encephalitis virus comp 99.9 V292combined_Kraken <- rbind(p.146V.kraken, p.171V.kraken, p.273V.kraken,
p.52V.kraken, p.53V.kraken, p.Und.kraken,
p.V169.kraken, p.V292.kraken)
View(combined_Kraken)
str(combined_Kraken)## tibble [14 × 3] (S3: tbl_df/tbl/data.frame)
## $ Especies : chr [1:14] "Patois virus" "Zegla virus" "Venezuelan equine encephalitis virus comp" "Marituba virus" ...
## $ Porcentaje:'data.frame': 14 obs. of 1 variable:
## ..$ Conteo: num [1:14] 50.4 48.2 75.8 14.6 61.7 ...
## $ codigo : chr [1:14] "146V" "146V" "171V" "171V" ...porcentaje<-as.data.frame(combined_Kraken$Porcentaje$Conteo)
str(porcentaje)## 'data.frame': 14 obs. of 1 variable:
## $ combined_Kraken$Porcentaje$Conteo: num 50.4 48.2 75.8 14.6 61.7 ...names(porcentaje)<-c("porcentaje")### Porcentaje<-porcentaje$Conteo
porcentaje## porcentaje
## 1 50.435917078043658535
## 2 48.200567121482663424
## 3 75.775516115418696472
## 4 14.647372343141224604
## 5 61.704575240178414219
## 6 38.217638926893997109
## 7 52.653278671852412174
## 8 47.274686654162373145
## 9 60.891036800740643287
## 10 38.143912330311053438
## 11 43.509727190130981000
## 12 38.221288319089048002
## 13 99.895214860757235442
## 14 99.905319602873248641especies<-combined_Kraken$Especies
especies## [1] "Patois virus"
## [2] "Zegla virus"
## [3] "Venezuelan equine encephalitis virus comp"
## [4] "Marituba virus"
## [5] "Patois virus"
## [6] "Zegla virus"
## [7] "Patois virus"
## [8] "Zegla virus"
## [9] "Zegla virus"
## [10] "Patois virus"
## [11] "Patois virus"
## [12] "Zegla virus"
## [13] "Venezuelan equine encephalitis virus comp"
## [14] "Venezuelan equine encephalitis virus comp"muestra<-combined_Kraken$codigo
muestra## [1] "146V" "146V" "171V" "171V" "273V" "273V" "52V" "52V" "53V" "53V"
## [11] "Und" "Und" "V169" "V292"combined_Kraken2 <- as.data.frame(cbind(porcentaje, especies, muestra))
combined_Kraken2## porcentaje especies muestra
## 1 50.435917078043658535 Patois virus 146V
## 2 48.200567121482663424 Zegla virus 146V
## 3 75.775516115418696472 Venezuelan equine encephalitis virus comp 171V
## 4 14.647372343141224604 Marituba virus 171V
## 5 61.704575240178414219 Patois virus 273V
## 6 38.217638926893997109 Zegla virus 273V
## 7 52.653278671852412174 Patois virus 52V
## 8 47.274686654162373145 Zegla virus 52V
## 9 60.891036800740643287 Zegla virus 53V
## 10 38.143912330311053438 Patois virus 53V
## 11 43.509727190130981000 Patois virus Und
## 12 38.221288319089048002 Zegla virus Und
## 13 99.895214860757235442 Venezuelan equine encephalitis virus comp V169
## 14 99.905319602873248641 Venezuelan equine encephalitis virus comp V292str(combined_Kraken2)## 'data.frame': 14 obs. of 3 variables:
## $ porcentaje: num 50.4 48.2 75.8 14.6 61.7 ...
## $ especies : chr "Patois virus" "Zegla virus" "Venezuelan equine encephalitis virus comp" "Marituba virus" ...
## $ muestra : chr "146V" "146V" "171V" "171V" ...combined_Kraken2$especies <- as.factor(combined_Kraken2$especies)
combined_Kraken2$muestra <- as.factor(combined_Kraken2$muestra)
combined_Kraken2$porcentaje <- as.numeric(combined_Kraken2$porcentaje)
str(combined_Kraken2)## 'data.frame': 14 obs. of 3 variables:
## $ porcentaje: num 50.4 48.2 75.8 14.6 61.7 ...
## $ especies : Factor w/ 4 levels "Marituba virus",..: 2 4 3 1 2 4 2 4 4 2 ...
## $ muestra : Factor w/ 8 levels "146V","171V",..: 1 1 2 2 3 3 4 4 5 5 ...Anadir el porcentaje faltante
p.146V.nuevafila.kraken <- data.frame(especies = "otras",
porcentaje = (valor = 100 - sum(p.146V.kraken$Porcentaje$Conteo)),
muestra = "146V"); p.146V.nuevafila.kraken## especies porcentaje muestra
## 1 otras 1.3635158004736780413 146Vp.171V.nuevafila.kraken <- data.frame(especies = "otras",
porcentaje = (valor = 100 - sum(p.171V.kraken$Porcentaje$Conteo)),
muestra = "171V"); p.171V.nuevafila.kraken## especies porcentaje muestra
## 1 otras 9.5771115414400753707 171Vp.273V.nuevafila.kraken <- data.frame(especies = "otras",
porcentaje = (valor = 100 - sum(p.273V.kraken$Porcentaje$Conteo)),
muestra = "273V"); p.273V.nuevafila.kraken## especies porcentaje muestra
## 1 otras 0.077785832927588671737 273Vp.52V.nuevafila.kraken <- data.frame(especies = "otras",
porcentaje = (valor = 100 - sum(p.52V.kraken$Porcentaje$Conteo)),
muestra = "52V"); p.52V.nuevafila.kraken## especies porcentaje muestra
## 1 otras 0.072034673985214681124 52Vp.53V.nuevafila.kraken <- data.frame(especies = "otras",
porcentaje = (valor = 100 - sum(p.53V.kraken$Porcentaje$Conteo)),
muestra = "53V"); p.53V.nuevafila.kraken## especies porcentaje muestra
## 1 otras 0.9650508689483103808 53Vp.Und.nuevafila.kraken <- data.frame(especies = "otras",
porcentaje = (valor = 100 - sum(p.Und.kraken$Porcentaje$Conteo)),
muestra = "Und"); p.Und.nuevafila.kraken## especies porcentaje muestra
## 1 otras 18.268984490779970997 Undp.V169.nuevafila.kraken <- data.frame(especies = "otras",
porcentaje = (valor = 100 - sum(p.V169.kraken$Porcentaje$Conteo)),
muestra = "V169"); p.V169.nuevafila.kraken## especies porcentaje muestra
## 1 otras 0.10478513924276455782 V169p.V292.nuevafila.kraken <- data.frame(especies = "otras",
porcentaje = (valor = 100 - sum(p.V292.kraken$Porcentaje$Conteo)),
muestra = "V292"); p.V292.nuevafila.kraken## especies porcentaje muestra
## 1 otras 0.094680397126751358883 V292result.kraken <- bind_rows(combined_Kraken2, p.146V.nuevafila.kraken, p.171V.nuevafila.kraken, p.273V.nuevafila.kraken,
p.52V.nuevafila.kraken, p.53V.nuevafila.kraken, p.Und.nuevafila.kraken,
p.V292.nuevafila.kraken, p.V169.nuevafila.kraken)
result.kraken %>%
arrange(muestra)## porcentaje especies muestra
## 1 50.435917078043658534625 Patois virus 146V
## 2 48.200567121482663424104 Zegla virus 146V
## 3 1.363515800473678041271 otras 146V
## 4 75.775516115418696472261 Venezuelan equine encephalitis virus comp 171V
## 5 14.647372343141224604324 Marituba virus 171V
## 6 9.577111541440075370701 otras 171V
## 7 61.704575240178414219372 Patois virus 273V
## 8 38.217638926893997108891 Zegla virus 273V
## 9 0.077785832927588671737 otras 273V
## 10 52.653278671852412173848 Patois virus 52V
## 11 47.274686654162373145027 Zegla virus 52V
## 12 0.072034673985214681124 otras 52V
## 13 60.891036800740643286645 Zegla virus 53V
## 14 38.143912330311053437981 Patois virus 53V
## 15 0.965050868948310380802 otras 53V
## 16 43.509727190130981000493 Patois virus Und
## 17 38.221288319089048002297 Zegla virus Und
## 18 18.268984490779970997210 otras Und
## 19 99.895214860757235442179 Venezuelan equine encephalitis virus comp V169
## 20 0.104785139242764557821 otras V169
## 21 99.905319602873248641117 Venezuelan equine encephalitis virus comp V292
## 22 0.094680397126751358883 otras V292Crear gráfico de barras
library(ggplot2)
library(viridis)
names(result.kraken)## [1] "porcentaje" "especies" "muestra"ggplot(result.kraken, aes(x = muestra, y = porcentaje, fill = especies)) +
geom_col(position = "fill", width = 0.98)+
scale_fill_manual(values = c("#2271B2", "#3DB7E9", "#F0E442", "#D55E00", "#359B73")) +
xlab("Especies") +
ylab("Porcentaje") +
ggtitle("Kraken") +
theme(plot.title = element_text(hjust = 0.5)) +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
scale_y_continuous(labels = function(x) paste0(x * 100, "%"))
Cargar resultados de MetaPhlAn4
tabla.mpa <- read.csv('/home/manuel/bioinformatica/tesisviu/compresion-metaphlan/tabla_final-especies.txt',
sep='\t',header=T)
tabla.mpa## Especies Porcentaje
## 1 Simbu_orthobunyavirus 84.225949999999997431
## 2 Brazoran_virus 11.232549999999999812
## 3 Venezuelan_equine_encephalitis_virus 99.670439999999999259
## 4 Simbu_orthobunyavirus 99.584869999999995116
## 5 Simbu_orthobunyavirus 75.650689999999997326
## 6 Abelson_murine_leukemia_virus 11.576150000000000162
## 7 Murine_osteosarcoma_virus 10.829890000000000683
## 8 Simbu_orthobunyavirus 100.000000000000000000
## 9 Venezuelan_equine_encephalitis_virus 99.654049999999998022
## 10 Venezuelan_equine_encephalitis_virus 99.954849999999993315
## 11 Venezuelan_equine_encephalitis_virus 99.993200000000001637
## Muestra
## 1 146V_S5_L001_R1_001_mpa.txt
## 2 146V_S5_L001_R1_001_mpa.txt
## 3 171V_S6_L001_R1_001_mpa.txt
## 4 273V_S7_L001_R1_001_mpa.txt
## 5 52V_S3_L001_R1_001_mpa.txt
## 6 52V_S3_L001_R1_001_mpa.txt
## 7 52V_S3_L001_R1_001_mpa.txt
## 8 53V_S4_L001_R1_001_mpa.txt
## 9 Undetermined_S0_L001_R1_001_mpa.txt
## 10 V169_S1_L001_R1_001_mpa.txt
## 11 V292_S2_L001_R1_001_mpa.txtnames(tabla.mpa)## [1] "Especies" "Porcentaje" "Muestra"result.mpa<-tabla.mpa %>%
mutate(Muestra = gsub("L001_R1_001_mpa.txt|_S||5_|6_|7_|3_|4_|0_|1_|2_", "", Muestra)) %>%
mutate(Muestra = gsub("V29S", "V292", Muestra)) %>%
mutate(Especies = gsub("_", " ", Especies)) %>%
mutate(Muestra = gsub("etermined", "", Muestra))Obener los totales
result.mpa## Especies Porcentaje Muestra
## 1 Simbu orthobunyavirus 84.225949999999997431 146V
## 2 Brazoran virus 11.232549999999999812 146V
## 3 Venezuelan equine encephalitis virus 99.670439999999999259 171V
## 4 Simbu orthobunyavirus 99.584869999999995116 273V
## 5 Simbu orthobunyavirus 75.650689999999997326 52V
## 6 Abelson murine leukemia virus 11.576150000000000162 52V
## 7 Murine osteosarcoma virus 10.829890000000000683 52V
## 8 Simbu orthobunyavirus 100.000000000000000000 53V
## 9 Venezuelan equine encephalitis virus 99.654049999999998022 Und
## 10 Venezuelan equine encephalitis virus 99.954849999999993315 V169
## 11 Venezuelan equine encephalitis virus 99.993200000000001637 V292names(result.mpa)## [1] "Especies" "Porcentaje" "Muestra"total_146V.mpa <-result.mpa %>%
filter(Muestra == '146V') %>%
summarize(Porcentaje = sum(Porcentaje, na.rm = TRUE))
total_146V.mpa## Porcentaje
## 1 95.458500000000000796total_171V.mpa <-result.mpa %>%
filter(Muestra == '171V') %>%
summarize(Porcentaje = sum(Porcentaje, na.rm = TRUE))
total_171V.mpa## Porcentaje
## 1 99.670439999999999259total_273V.mpa <-result.mpa %>%
filter(Muestra == '273V') %>%
summarize(Porcentaje = sum(Porcentaje, na.rm = TRUE))
total_273V.mpa## Porcentaje
## 1 99.584869999999995116total_52V.mpa <-result.mpa %>%
filter(Muestra == '52V') %>%
summarize(Porcentaje = sum(Porcentaje, na.rm = TRUE))
total_52V.mpa## Porcentaje
## 1 98.056730000000001723total_53V.mpa <-result.mpa %>%
filter(Muestra == '53V') %>%
summarize(Porcentaje = sum(Porcentaje, na.rm = TRUE))
total_53V.mpa## Porcentaje
## 1 100total_Und.mpa <-result.mpa %>%
filter(Muestra == 'Und') %>%
summarize(Porcentaje = sum(Porcentaje, na.rm = TRUE))
total_Und.mpa## Porcentaje
## 1 99.654049999999998022total_V169.mpa <-result.mpa %>%
filter(Muestra == 'V169') %>%
summarize(Porcentaje = sum(Porcentaje, na.rm = TRUE))
total_V169.mpa## Porcentaje
## 1 99.954849999999993315total_V292.mpa <-result.mpa %>%
filter(Muestra == 'V292') %>%
summarize(Porcentaje = sum(Porcentaje, na.rm = TRUE))
total_V292.mpa## Porcentaje
## 1 99.993200000000001637Crear los nuevos dataframes
names(result.mpa)## [1] "Especies" "Porcentaje" "Muestra"print(result.mpa)## Especies Porcentaje Muestra
## 1 Simbu orthobunyavirus 84.225949999999997431 146V
## 2 Brazoran virus 11.232549999999999812 146V
## 3 Venezuelan equine encephalitis virus 99.670439999999999259 171V
## 4 Simbu orthobunyavirus 99.584869999999995116 273V
## 5 Simbu orthobunyavirus 75.650689999999997326 52V
## 6 Abelson murine leukemia virus 11.576150000000000162 52V
## 7 Murine osteosarcoma virus 10.829890000000000683 52V
## 8 Simbu orthobunyavirus 100.000000000000000000 53V
## 9 Venezuelan equine encephalitis virus 99.654049999999998022 Und
## 10 Venezuelan equine encephalitis virus 99.954849999999993315 V169
## 11 Venezuelan equine encephalitis virus 99.993200000000001637 V292p.146V.mpa <- result.mpa %>%
select(Porcentaje,Especies,Muestra) %>%
filter(Muestra == '146V')
p.146V.mpa## Porcentaje Especies Muestra
## 1 84.225949999999997431 Simbu orthobunyavirus 146V
## 2 11.232549999999999812 Brazoran virus 146Vp.171V.mpa <- result.mpa %>%
select(Porcentaje,Especies,Muestra) %>%
filter(Muestra == '171V')
p.171V.mpa## Porcentaje Especies Muestra
## 1 99.670439999999999259 Venezuelan equine encephalitis virus 171Vp.273V.mpa <- result.mpa %>%
select(Porcentaje,Especies,Muestra) %>%
filter(Muestra == '273V')
p.273V.mpa ## Porcentaje Especies Muestra
## 1 99.584869999999995116 Simbu orthobunyavirus 273Vp.52V.mpa <- result.mpa %>%
select(Porcentaje,Especies,Muestra) %>%
filter(Muestra == '52V')
p.52V.mpa## Porcentaje Especies Muestra
## 1 75.650689999999997326 Simbu orthobunyavirus 52V
## 2 11.576150000000000162 Abelson murine leukemia virus 52V
## 3 10.829890000000000683 Murine osteosarcoma virus 52Vp.53V.mpa <- result.mpa %>%
select(Porcentaje,Especies,Muestra) %>%
filter(Muestra == '53V')
p.53V.mpa## Porcentaje Especies Muestra
## 1 100 Simbu orthobunyavirus 53Vp.Und.mpa <- result.mpa %>%
select(Porcentaje,Especies,Muestra) %>%
filter(Muestra == 'Und')
p.Und.mpa## Porcentaje Especies Muestra
## 1 99.654049999999998022 Venezuelan equine encephalitis virus Undp.V169.mpa <- result.mpa %>%
select(Porcentaje,Especies,Muestra) %>%
filter(Muestra == 'V169')
p.V169.mpa## Porcentaje Especies Muestra
## 1 99.954849999999993315 Venezuelan equine encephalitis virus V169p.V292.mpa <- result.mpa %>%
select(Porcentaje,Especies,Muestra) %>%
filter(Muestra == 'V292')
p.V292.mpa## Porcentaje Especies Muestra
## 1 99.993200000000001637 Venezuelan equine encephalitis virus V292print(p.146V.mpa)## Porcentaje Especies Muestra
## 1 84.225949999999997431 Simbu orthobunyavirus 146V
## 2 11.232549999999999812 Brazoran virus 146Vprint(p.171V.mpa)## Porcentaje Especies Muestra
## 1 99.670439999999999259 Venezuelan equine encephalitis virus 171Vprint(p.273V.mpa)## Porcentaje Especies Muestra
## 1 99.584869999999995116 Simbu orthobunyavirus 273Vprint(p.52V.mpa)## Porcentaje Especies Muestra
## 1 75.650689999999997326 Simbu orthobunyavirus 52V
## 2 11.576150000000000162 Abelson murine leukemia virus 52V
## 3 10.829890000000000683 Murine osteosarcoma virus 52Vprint(p.53V.mpa)## Porcentaje Especies Muestra
## 1 100 Simbu orthobunyavirus 53Vprint(p.Und.mpa)## Porcentaje Especies Muestra
## 1 99.654049999999998022 Venezuelan equine encephalitis virus Undprint(p.V169.mpa)## Porcentaje Especies Muestra
## 1 99.954849999999993315 Venezuelan equine encephalitis virus V169print(p.V292.mpa)## Porcentaje Especies Muestra
## 1 99.993200000000001637 Venezuelan equine encephalitis virus V292combined_mpa <- rbind(p.146V.mpa, p.171V.mpa, p.273V.mpa,
p.52V.mpa, p.53V.mpa, p.Und.mpa,
p.V169.mpa, p.V292.mpa)
View(combined_mpa)
str(combined_mpa)## 'data.frame': 11 obs. of 3 variables:
## $ Porcentaje: num 84.2 11.2 99.7 99.6 75.7 ...
## $ Especies : chr "Simbu orthobunyavirus" "Brazoran virus" "Venezuelan equine encephalitis virus" "Simbu orthobunyavirus" ...
## $ Muestra : chr "146V" "146V" "171V" "273V" ...#porcentaje<-porcentaje$Conteo
combined_mpa$Especies <- as.factor(combined_mpa$Especies)
combined_mpa$Muestra <- as.factor(combined_mpa$Muestra)
combined_mpa$Porcentaje <- as.numeric(combined_mpa$Porcentaje)
str(combined_mpa)## 'data.frame': 11 obs. of 3 variables:
## $ Porcentaje: num 84.2 11.2 99.7 99.6 75.7 ...
## $ Especies : Factor w/ 5 levels "Abelson murine leukemia virus",..: 4 2 5 4 4 1 3 4 5 5 ...
## $ Muestra : Factor w/ 8 levels "146V","171V",..: 1 1 2 3 4 4 4 5 6 7 ...Anadir el porcentaje faltante
p.146V.nuevafila.mpa <- data.frame(Especies = "otras",
Porcentaje = (valor = 100 - sum(p.146V.mpa$Porcentaje)),
Muestra = "146V"); p.146V.nuevafila.mpa## Especies Porcentaje Muestra
## 1 otras 4.5414999999999992042 146Vp.171V.nuevafila.mpa <- data.frame(Especies = "otras",
Porcentaje = (valor = 100 - sum(p.171V.mpa$Porcenta)),
Muestra = "171V"); p.171V.nuevafila.mpa## Especies Porcentaje Muestra
## 1 otras 0.32956000000000074124 171Vp.273V.nuevafila.mpa <- data.frame(Especies = "otras",
Porcentaje = (valor = 100 - sum(p.273V.mpa$Porcentaje)),
Muestra = "273V"); p.273V.nuevafila.mpa## Especies Porcentaje Muestra
## 1 otras 0.41513000000000488399 273Vp.52V.nuevafila.mpa <- data.frame(Especies = "otras",
Porcentaje = (valor = 100 - sum(p.52V.mpa$Porcentaje)),
Muestra = "52V"); p.52V.nuevafila.mpa## Especies Porcentaje Muestra
## 1 otras 1.9432699999999982765 52Vp.53V.nuevafila.mpa <- data.frame(Especies = "otras",
Porcentaje = (valor = 100 - sum(p.53V.mpa$Porcentaje)),
Muestra = "53V"); p.53V.nuevafila.mpa## Especies Porcentaje Muestra
## 1 otras 0 53Vp.Und.nuevafila.mpa <- data.frame(Especies = "otras",
Porcentaje = (valor = 100 - sum(p.Und.mpa$Porcentaje)),
Muestra = "Und"); p.Und.nuevafila.mpa## Especies Porcentaje Muestra
## 1 otras 0.34595000000000197815 Undp.V169.nuevafila.mpa <- data.frame(Especies = "otras",
Porcentaje = (valor = 100 - sum(p.V169.mpa$Porcentaje)),
Muestra = "V169"); p.V169.nuevafila.mpa## Especies Porcentaje Muestra
## 1 otras 0.045150000000006684786 V169p.V292.nuevafila.mpa <- data.frame(Especies = "otras",
Porcentaje = (valor = 100 - sum(p.V292.mpa$Porcentaje)),
Muestra = "V292"); p.V292.nuevafila.mpa## Especies Porcentaje Muestra
## 1 otras 0.0067999999999983629095 V292result.mpa <- bind_rows(combined_mpa, p.146V.nuevafila.mpa, p.171V.nuevafila.mpa, p.273V.nuevafila.mpa,
p.52V.nuevafila.mpa, p.53V.nuevafila.mpa, p.Und.nuevafila.mpa,
p.V292.nuevafila.mpa, p.V169.nuevafila.mpa)
result.mpa %>%
arrange(Muestra)## Porcentaje Especies Muestra
## 1 8.4225949999999997431e+01 Simbu orthobunyavirus 146V
## 2 1.1232549999999999812e+01 Brazoran virus 146V
## 3 4.5414999999999992042e+00 otras 146V
## 4 9.9670439999999999259e+01 Venezuelan equine encephalitis virus 171V
## 5 3.2956000000000074124e-01 otras 171V
## 6 9.9584869999999995116e+01 Simbu orthobunyavirus 273V
## 7 4.1513000000000488399e-01 otras 273V
## 8 7.5650689999999997326e+01 Simbu orthobunyavirus 52V
## 9 1.1576150000000000162e+01 Abelson murine leukemia virus 52V
## 10 1.0829890000000000683e+01 Murine osteosarcoma virus 52V
## 11 1.9432699999999982765e+00 otras 52V
## 12 1.0000000000000000000e+02 Simbu orthobunyavirus 53V
## 13 0.0000000000000000000e+00 otras 53V
## 14 9.9654049999999998022e+01 Venezuelan equine encephalitis virus Und
## 15 3.4595000000000197815e-01 otras Und
## 16 9.9954849999999993315e+01 Venezuelan equine encephalitis virus V169
## 17 4.5150000000006684786e-02 otras V169
## 18 9.9993200000000001637e+01 Venezuelan equine encephalitis virus V292
## 19 6.7999999999983629095e-03 otras V292#####Crear grafico de barras####
library(ggplot2)
library(viridis)
names(result.mpa)## [1] "Porcentaje" "Especies" "Muestra"ggplot(result.mpa, aes(x = Muestra, y = Porcentaje, fill = Especies)) +
geom_col(position = "fill", width = 0.98)+
scale_fill_manual(values = c("#2271B2", "#3DB7E9", "#F0E442", "#D55E00", "#359B73", "#F748A5")) +
xlab("Especies") +
ylab("Porcentaje") +
ggtitle("mpa") +
theme(plot.title = element_text(hjust = 0.5)) +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
scale_y_continuous(labels = function(x) paste0(x * 100, "%"))
Todos los graficos
library(ggplot2)
library(viridis)
library(gridExtra)##
## Attaching package: 'gridExtra'## The following object is masked from 'package:dplyr':
##
## combinelibrary(cowplot)
#unique(result$especies)
barplot.kaiju <- ggplot(result.kaiju, aes(x = muestra, y = porcentaje, fill = especies)) +
geom_col(position = "fill", width = 0.98)+
scale_fill_manual(values = c("#2271B2", "#3DB7E9", "#F0E442", "#D55E00", "#359B73")) +
xlab("Especies") +
ylab("Porcentaje") +
ggtitle("Kaiju") +
theme(plot.title = element_text(hjust = 0.5)) +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
scale_y_continuous(labels = function(x) paste0(x * 100, "%"))
barplot.kraken <- ggplot(result.kraken, aes(x = muestra, y = porcentaje, fill = especies)) +
geom_col(position = "fill", width = 0.98)+
scale_fill_manual(values = c("#2271B2", "#3DB7E9", "#F0E442", "#D55E00", "#359B73")) +
xlab("Especies") +
ylab("Porcentaje") +
ggtitle("Kraken2") +
theme(plot.title = element_text(hjust = 0.5)) +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
scale_y_continuous(labels = function(x) paste0(x * 100, "%"))
barplot.mpa <- ggplot(result.mpa, aes(x = Muestra, y = Porcentaje, fill = Especies)) +
geom_col(position = "fill", width = 0.98)+
scale_fill_manual(values = c("#000000", "#E20134", "#F69E00", "#359B73", "#F748A5", "#D55E00")) +
xlab("Especies") +
ylab("Porcentaje") +
ggtitle("MetaPhlAn4") +
theme(plot.title = element_text(hjust = 0.5)) +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
scale_y_continuous(labels = function(x) paste0(x * 100, "%"))
plot.horizontal <- grid.arrange(barplot.kaiju, barplot.kraken, barplot.mpa, nrow = 1)
# Guardar el gráfico combinado como PNG
ggsave("plot-metagenomica.png", plot.horizontal, width = 20, height = 6, dpi = 300)