Mismodeled purines: implicit alternates and hidden Hoogsteens

Abstract

Hoogsteen base pairs are seen in DNA crystal structures, but only rarely. This study tests whether Hoogsteens or othersynpurines are either under-modeled or over-modeled, which are known problems for rare conformations. Candidate purines needing asyn/anti180° flip were identified by diagnostic patterns of difference electron-density peaks. Manual inspection narrowed 105 flip candidates to 20 convincing cases, all at ≤2.7 Å resolution. Rebuilding and refinement confirmed that 14 of these were authentic purine flips. Seven examples are modeled as Watson–Crick base pairs but should be Hoogsteens (commonest at duplex termini), and three had the opposite issue.Syn/antiflips were also needed for some single-stranded purines. Five of the 20 convincing cases arose from an unmodeled alternate duplex running in the opposite direction. These are in semi-palindromic DNA sequences bound by a homodimeric protein and show flipped-purine-like difference peaks at residues where the palindrome is imperfect. This study documents types of incorrect modeling which are worth avoiding. However, the primary conclusions are that such mistakes are infrequent, the bias towards fittingantipurines is very slight, and the occurrence rate of Hoogsteen base pairs in DNA crystal structures remains unchanged from earlier estimates at ∼0.3%.