to use with rcbL sequencing data from Santa Ana River, 7/27/26

library(knitr)
library(readxl)
#detach(package:plyr)
library(dplyr)
library(ggplot2)
library(reshape2)
library(kableExtra)
library(ggh4x)
library(stringr)
library(seqinr)
library(palettetown)
library(phyloseq)
set.seed(100)
path<-
"/Users/kylielanglois/SCCWRP/KL data - General/sequencing/data/SAR_072726"

d<-read.csv(file.path(path, "BIO_SAR_rcbL_072726_merger_V2_6_table.csv"))

tax<-read.delim(file.path(
  path, "BIO_SAR_rcbL_072726_merger_V2_6_repset_diat.rcbL.v12_NB_tax.tsv"))
tax1<-tax[, !grepl("Conf", colnames(tax))]

tr<-read.csv(file.path(
  path, "BIO_SAR_rcbL_072726_fastqc_multiqc_dada2_filteronly_results_V2.csv"))

map.in<-read_excel("/Users/kylielanglois/SCCWRP/eDNA Sample Management - eDNA/SANTA_ANA/eDNAMasterFile_inventory_extraction_SANTA_ANA.xlsx", sheet = 1)
colnames(map.in)<-map.in[1, ]
map.in<-map.in[-1, ]

map.ex<-read_excel("/Users/kylielanglois/SCCWRP/eDNA Sample Management - eDNA/SANTA_ANA/eDNAMasterFile_inventory_extraction_SANTA_ANA.xlsx", sheet = 2)
colnames(map.ex)<-map.ex[1, ]
map.ex<-map.ex[-1, ]

map<-merge(map.in, map.ex, by="SCCWRP_ID", all = T)
colnames(map)<-gsub("\r\n", "\\.", colnames(map)) 
#turn "new line" in excel format to period
colnames(map)<-gsub(" ", "\\.", colnames(map))

get dada2 stats

get basic stats

## [1] "# of ASV: 221"
## [1] "total # of seqs: 395109"

plot taxonomy