Get sequence length for all reference contigs

```{bash}

cat data/REF/reference.fasta | awk '$0 ~ ">" {print c; c=0;printf substr($0,2,100) "\t"; } $0 !~ ">" {c+=length($0);} END { print c; }' > results/fasta.length

```

Import and analyze to get summary stats

```{r}

ref_stats <- read_delim("results/fasta.length", delim = "\t",
                        col_names = c("CONTIG", "LENGTH"))

sum(ref_stats$LENGTH)

length(ref_stats$CONTIG)

mean(ref_stats$LENGTH)

Mode(ref_stats$LENGTH)

min(ref_stats$LENGTH)

```