Bio Microbiome Amplicon Processing

Quality Filtering and Trimming

filtFs <- file.path('filtered', paste0(sample_names, '_F_filt.fastq.gz'))
filtRs <- file.path('filtered', paste0(sample_names, '_R_filt.fastq.gz'))
names(filtFs) <- sample_names
names(filtRs) <- sample_names

# Filter parameters depend on amplicon region and read length
out <- filterAndTrim(fnFs, filtFs, fnRs, filtRs,
                     truncLen = c(240, 160),      # Trim to quality scores
                     maxN = 0,                     # No ambiguous bases
                     maxEE = c(2, 2),              # Max expected errors
                     truncQ = 2,                   # Truncate at first Q <= 2
                     rm.phix = TRUE,               # Remove PhiX
                     compress = TRUE,
                     multithread = TRUE)

Error Rate Learning

errF <- learnErrors(filtFs, multithread = TRUE)
errR <- learnErrors(filtRs, multithread = TRUE)

# Visualize error rates
plotErrors(errF, nominalQ = TRUE)

Sample Inference (Denoising)

dadaFs <- dada(filtFs, err = errF, multithread = TRUE)
dadaRs <- dada(filtRs, err = errR, multithread = TRUE)

# Check results
dadaFs[[1]]

Merge Paired Reads

mergers <- mergePairs(dadaFs, filtFs, dadaRs, filtRs, verbose = TRUE)

# Check merge success
head(mergers[[1]])

Construct Sequence Table

seqtab <- makeSequenceTable(mergers)
dim(seqtab)

# Check length distribution
table(nchar(getSequences(seqtab)))

Remove Chimeras

seqtab_nochim <- removeBimeraDenovo(seqtab, method = 'consensus',
                                     multithread = TRUE, verbose = TRUE)

# Percentage retained
sum(seqtab_nochim) / sum(seqtab)

Track Reads Through Pipeline

Goal: Generate a per-sample summary table showing how many reads survived each DADA2 processing step for quality assessment.

Approach: Extract read counts from each pipeline stage (filtering, denoising, merging, chimera removal) and combine into a single tracking matrix.

getN <- function(x) sum(getUniques(x))
track <- cbind(out, sapply(dadaFs, getN), sapply(dadaRs, getN),
               sapply(mergers, getN), rowSums(seqtab_nochim))
colnames(track) <- c('input', 'filtered', 'denoisedF', 'denoisedR', 'merged', 'nonchim')
rownames(track) <- sample_names
track

ITS-Specific Processing

# For ITS, use cutadapt to remove primers first (variable length amplicons)
# Then skip truncLen (don't truncate ITS to fixed length)

out_its <- filterAndTrim(fnFs, filtFs, fnRs, filtRs,
                         maxN = 0, maxEE = c(2, 2), truncQ = 2,
                         minLen = 50,  # Minimum length
                         rm.phix = TRUE, compress = TRUE, multithread = TRUE)

Related Skills

• taxonomy-assignment - Assign taxonomy to ASVs
• read-qc/quality-reports - Pre-DADA2 quality assessment
• diversity-analysis - Analyze ASV table