Get duplicate ids from fasta files

# /data4/bio/runs-danio/PLANT/Compare/Brass/BN
# В консоли делаем
# grep '>' *.fasta | sed 's/:/\t/' | sed 's/>//' > ../ids_BN.fasta

ids <- read.delim("../ids_BN.fasta", head = F)
colnames(ids) <- c("file", "id")
ids <- unique(ids)
ids <- ids[ids$file != "BN_all.fasta", ]
ids$file <- gsub(".fasta", "", ids$file)
id.counts <- as.data.frame(table(ids$id))
colnames(id.counts) <- c("id", "count")
agg <- aggregate(ids$file, by = list(ids$id), paste, collapse = ",")
colnames(agg) <- c("id", "files")
id.counts <- merge(id.counts, agg)
id.counts <- id.counts[order(id.counts$count, decreasing = T), ]
nrow(id.counts[id.counts$count > 1, ])
write.table(id.counts, "../ids_BN_counts.txt", row.names = F,
            sep = "\t", quote = F)