The Atlas genome assembly system

Abstract

Atlas is a suite of programs developed for assembly of genomes by a "combined approach" that uses DNA sequence reads from both BACs and whole-genome shotgun (WGS) libraries. The BAC clones afford advantages of localized assembly with reduced computational load, and provide a robust method for dealing with repeated sequences. Inclusion of WGS sequences facilitates use of different clone insert sizes and reduces data production costs. A core function of Atlas software is recruitment of WGS sequences into appropriate BACs based on sequence overlaps. Because construction of consensus sequences is from local assembly of these reads, only small (<0.1%) units of the genome are assembled at a time. Once assembled, each BAC is used to derive a genomic layout. This "sequence-based" growth of the genome map has greater precision than with non-sequence-based methods. Use of BACs allows correction of artifacts due to repeats at each stage of the process. This is aided by ancillary data such as BAC fingerprint, other genomic maps, and syntenic relations with other genomes. Atlas was used to assemble a draft DNA sequence of the rat genome; its major components including overlapper and split-scaffold are also being used in pure WGS projects.

Figure 1

Steps in the Atlas Assembly System. (1) Trim off vector and low-quality portions of reads. (2) Count k-mers in WGS reads, saving the overall distribution plus specific counts for k-mers with copy number above a threshold. (3) Align BAC and WGS reads sharing rare k-mers and save overlap edges for high-quality end-to-end alignments. (4) Enrich each BAC read set with overlapping WGS reads and their mates, assemble using Phrap, scaffold and check for consistent assembly. (5) Arrange BACs into contiguous sets (bactigs) and flag problem BACs for closer quality checking. (6) Assemble bactigs in waves designed to limit the number of BACs that are input to Phrap. (7) Treating each bactig scaffold as a unit, rescaffold to produce superbactigs, detecting problem joins and missed merges between bactigs. (8) Link superbactigs together into ultrabactigs based on remaining (single) mate-pair links, fingerprint contigs, markers and synteny with human and mouse genomes. (9) Format chromosome files with contigs separated by strings of Ns representing gaps. Quality-control feedback steps include (10) examining coassembly scores of problem BACs and removing foreign trays of reads; (11) resolving superbactig conflicts by modifying bactigs and possibly flagging BACs for closer checking; and (12) resolving ultrabactig and mapping conflicts in collaboration with research groups that generated FPC and marker information.

Figure 2

Read trimming method. A simplified version of the trimming method is shown, with a window size of 4 and a minimum boundary quality of 2. The actual trimming of the rat genome reads used a window size of 50, a minimum boundary quality of 20, and also imposed other requirements on passing windows and regions.

Figure 3

k-mer analysis of WGS reads in the RGSP. The frequency distribution of distinct 32-mer oligonucleotides is shown. The observed distribution is shown as a blue line, and the predicted Poisson distribution of unique 32-mers at 4 × shotgun sequencing coverage is shown as the green line. Models for unique 32-mers resulting from sequencing errors, 32-mers in duplicated regions, and the total 32-mer distribution from these models are shown as orange, pink, and dotted lines.

Figure 4

Recruitment of WGS reads into eBACs with increasing BAC skim coverage. Twelve BACs were selected randomly from different chromosomes and used to BAC-Fish WGS reads from a pool representing ∼4 × sequence coverage of the genome. Progressively larger subsets of BAC reads were used to obtain the curves.

Figure 5

False clone overlaps caused by repeated sequences. Each thin line represents a BAC clone, and clones with the same color are true overlapping pairs. False overlaps between clones (lines with different colors) are due to highly repeated sequences as well as duplications of small and large regions. Overlaps from highly repetitious sequences are largely dealt with by the overlapper and binner steps and further dealt with at the overlapping BAC detection step. The second and the third situations are dealt with at the bactig linearization step because conflicts can be detected between BACs. For example, in the second case, A/D and B/D clone pairs should overlap based on the clone layout, but this will not be validated.

Figure 6

The rolling-phrap process limits the scope of reads presented to Phrap in each wave. All reads for an eBAC are added in the first wave including that eBAC. Contigs are recorded in an .ace file, and the corresponding reads are removed from the Phrap input, until a contig contains (almost) no reads from eBACs overlapping the next wave. (1) First wave containing all eBACs overlapping leftmost eBAC (arrow); (2) emit pure leftmost-eBAC contigs (not overlapping and therefore not merged with any other eBAC); (3) second wave containing all eBACs overlapping next leftmost eBAC contributing new sequences; (4) emit contigs solely from first-wave eBAC regions; (5) third wave containing all eBACs overlapping next leftmost eBAC contributing new sequences; (6) emit new contigs solely from first and second-wave eBAC regions; (7) fourth wave; (8) emit remaining contigs.