Target DNA chromatinization modulates nicking by L1 endonuclease

Abstract

L1 elements are human transposons which replicate via an RNA intermediate. At least 15% of the human genome is composed of L1 sequence. An important initial step in the transposition reaction is nicking of the genomic DNA by L1 endonuclease (L1 EN). In vivo much of the genome exists in the form of chromatin or is undergoing biochemical transactions such as transcription, replication or repair, which may alter the accessibility of the L1 transposition machinery to DNA. To investigate this possibility we have examined the effect of substrate chromatinization on the ability of L1 EN to nick DNA. We find that DNA incorporated into nucleosomes is generally refractory to nicking by L1 EN. Interestingly, nicking of a minority of DNA sequences is enhanced when included in chromatin. Thus, dynamic epigenetic factors such as chromatinization are likely to influence the relatively permanent placement of L1 and other retroelements in the human genome.

Figure 1

The human L1 retrotransposon. EN, endonuclease domain; RT, reverse transcriptase; ZN, putative zinc finger; vTSD, variable target site duplication. The 5′-UTR contains an internal promoter (black arrow), the 3′-UTR a poly(A) sequence.

Figure 2

L1 endonuclease nicking is repressed by chromatin. (A) Nicking on free and nucleosomal DNA. The boundary of the nucleosome is indicated by the bars to the right of the gels. Sites repressed when nucleosomal are numbered with black arrowheads; nucleosome-specific enhancements are annotated with letters and grey arrowheads. –, no L1 EN; G, guanosine-specific Maxam–Gilbert sequencing ladder; R, cleavage of the nucleosomal substrate with hydroxyl radicals. (B) As (A) but with substrate 2.

Figure 3

Sites and quantitation of L1 EN nicking repression and enhancement. Listed are the sequences of the major L1 EN nicking sites from Figure 2A and B. Upper black arrowheads, nicked bond; lower grey arrowheads, nucleosome-specific enhancements. Bands from the lane containing the third EN concentration were used for quantitation. Background intensities at the appropriate position in lanes lacking EN were subtracted from the signal prior to comparison. When the background was equal to or greater than the signal the fold repression or enhancement was calculated without background subtraction and listed with a preceding >. The general consensus sequence for L1 EN nicking is TTTTAA, with nicking occurring at the TpA bond.

Figure 4

Densitometric traces of hydroxyl radical and L1 EN nicking. Upper black arrowheads, sites of nicking repression; lower grey arrowheads, sites of nicking enhancement; light grey lines, divisions of 10 bp periodicity. The traces are from Figure 2A and correspond to dilution 3 (Free) and dilution 5 (Nucleosomal). These lanes were chosen for maximal clarity of presentation and are not intended to be quantitatively accurate.

Figure 5

Nucleosome-mediated repression of L1 EN occurs only in cis. (A) Naked supercoiled Bluescript DNA was mixed with the chromatinized DNA and assayed for nicking. Lanes 2 and 7, no L1 EN; lanes 3–6 and 8–11, increasing 2-fold concentrations of L1 EN. s.c., supercoiled; o.c., open circle. DNA from the chromatin fragment is not visible as it has been electrophoresed off the gel in order to resolve the relatively large plasmids.

Figure 6

A model for L1 EN nicking of nucleosomal DNA. (A) DNA wrapped around the histone octamer. (B) Repression of L1 EN. Nicking at the center exposed minor groove requires extensive minor groove recognition up to 4–5 bp 5′, an interaction which is blocked by the histone octamer. (C) Enhancement of nicking. Recognition of the minor groove is unimpeded by the octamer. Either the active site of L1 EN is flexible enough to access the relatively protected cleaved phosphodiester or L1 EN binding initiates a change in the rotational position of the DNA within the nucleosome (not shown).