Molecular indexing of human genomic DNA

Abstract

Molecular indexing sorts DNA fragments into subsets for inter-sample comparisons. Type IIS or interrupted palindrome restriction endonucleases, which result in single-stranded ends not including the original recognition sequence of the enzyme, are used to produce the fragments. The ends can then be any sequence but will always be specific for a given fragment. Fragments with particular ends are selected by ligation to a corresponding indexing adapter. We describe iterative indexing, a new process that after an initial round of indexing uses a Type IIS restriction endonuclease to expose additional sequence for further indexing. New plasmids, pINDnn, were produced for novel use as indexing adapters. Together, the plasmids index all 16 possible dinucleotides. Their large size can be increased by dimerisation in vitro and allows the isolation of indexed material by size separation. Fragments produced from human genomic DNA by Type II restriction endonucleases were sorted using six bases in total to a possible enrichment of 1920-fold. By comparison with the public human sequence databases, fidelity of indexing was shown to be high and was tolerant of repetitive sequences. Genome-wide comparisons on a candidate or non-candidate basis are made possible by this approach.

Figure 1

Removal of the BpmI and BsrDI sites of pUC19 by recombination PCR. The indexing plasmids were created by replacing the polylinker region of pUC19 with one containing adjacent sites for BpmI and BsrDI. Sites for BpmI and BsrDI within the ampicillin gene of pUC19 were first removed. Three overlapping regions between the XmnI and AflIII sites of pUC19 were amplified using the primer pairs XmRa (5′-TCTCAACAGCGGTAAGATCC) with Bp17Fa (5′-ACGCTCACCGGCACCAGATT), Bs19Ra (5′-CCTGTAGCTATGGCAACAAC) with IXB_Fa (5′-AGTATTTGGTATCTGCGCTC) and Bs17Ra (5′-CTCGCGGTATAATTGCAGCA) with AfFa (5′-GGTAATACGGTTATCCACAG), which altered the sequence within the BpmI and BsrDI recognition sites by introducing neutral substitutions (x in figure and underline in sequence). Recombination PCR using primers XmRa and AfFa joined the amplified regions. The new region was then used to replace the original region between XmnI and AflIII of pUC19 producing plasmid pIND10. (N.B. not to scale.)

Figure 2

(A) Dimerisation of plasmid pINDnn for use in indexing. (B) Plasmid pINDnn-mediated indexing of genomic DNA.

Figure 2

(A) Dimerisation of plasmid pINDnn for use in indexing. (B) Plasmid pINDnn-mediated indexing of genomic DNA.

Figure 3

Representative example of correctly indexed genomic DNA and flanking sequences. The figure shows all possible configurations of indexing. A BpmI indexing adapter ligated to the BglII site exposes two bases for indexing which are eight bases from the end of the BglII site. The first indexer ligated at these bases contains a BpmI site which allows two more bases to be exposed for indexing 12 bases along. The BpmI site in the genomic DNA was cleaved at the first BpmI digest and exposes two bases for indexing 14 bases from the site. Restriction sites and indexed nucleotides are shown in bold.

Figure 4

Frequency distribution of sizes of original indexed fragments from the subsets F1, F2, M1 and M2. Independent clones of fragments indexed originally from human genomic DNA were sequenced and the sequences compared to the EMBL database to find the corresponding genomic human sequences. The sizes of the originally indexed fragments were determined from the positions of presumed indexed sites found in the EMBL sequences corresponding to the clones