AdapterRemoval v2: rapid adapter trimming, identification, and read merging

Abstract

Background: As high-throughput sequencing platforms produce longer and longer reads, sequences generated from short inserts, such as those obtained from fossil and degraded material, are increasingly expected to contain adapter sequences. Efficient adapter trimming algorithms are also needed to process the growing amount of data generated per sequencing run.

Findings: We introduce AdapterRemoval v2, a major revision of AdapterRemoval v1, which introduces (i) striking improvements in throughput, through the use of single instruction, multiple data (SIMD; SSE1 and SSE2) instructions and multi-threading support, (ii) the ability to handle datasets containing reads or read-pairs with different adapters or adapter pairs, (iii) simultaneous demultiplexing and adapter trimming, (iv) the ability to reconstruct adapter sequences from paired-end reads for poorly documented data sets, and (v) native gzip and bzip2 support.

Conclusions: We show that AdapterRemoval v2 compares favorably with existing tools, while offering superior throughput to most alternatives examined here, both for single and multi-threaded operations.

Fig. 1

Adapter-trimming and read-merging performance. Performance metrics for trimming of single adapter-pairs, multiple adapter-pairs, and merging of overlapping read pairs

Fig. 2

Adapter-trimming and read-merging throughput. Throughput is reported on the y-axis as thousands of FASTQ reads processed per second. Results are grouped on the x-axis firstly per program, secondly by read length (100 or 200 bp), and thirdly by the number of threads used (1–4). For programs that do not support multi-threaded operation, only columns corresponding to one thread are shown. Note that multi-threaded trimming of single-end reads using Trimmomatic was excluded, due to erratic behavior on the test machine. Benchmarking was carried out on an otherwise idle Intel^® Core™ i7-4790 K 4 × 4.00 GHz, with 8 GB of DDR3-2133 RAM, on an ext4 partition on a Samsung SSD 840 EVO 750 GB drive

Fig. 3

Fidelity of adapter sequence reconstruction from paired-end reads. The x-axis represents the mean insert size of simulated, paired-end reads in bp, with a standard deviation of 75 bp. The y-axis represents the number of bases before first mistake in the (best) recovered adapter sequence for the mate 1 adapter sequence