Identification of a soybean protein that interacts with GAGA element dinucleotide repeat DNA

Abstract

Dinucleotide repeat DNA with the pattern (GA)(n)/(TC)(n), so-called GAGA elements, control gene expression in animals, and are recognized by a specific regulatory protein. Here, a yeast one-hybrid screen was used to isolate soybean (Glycine max) cDNA encoding a GAGA-binding protein (GBP) that binds to (GA)(n)/(CT)(n) DNA. Soybean GBP was dissimilar from the GAGA factor of Drosophila melanogaster. Recombinant GBP protein did not bind to dinucleotide repeat sequences other than (GA)(n)/(CT)(n). GBP bound to the promoter of the heme and chlorophyll synthesis gene Gsa1, which contains a GAGA element. Removal of that GAGA element abrogated binding of GBP to the promoter. Furthermore, insertion of the GAGA element to a nonspecific DNA conferred GBP-binding activity on that DNA. Thus, the GAGA element of the Gsa1 promoter is both necessary and sufficient for GBP binding. Gbp mRNA was expressed in leaves and was induced in symbiotic root nodules elicited by the bacterium Bradyrhizobium japonicum. In addition, Gbp transcripts were much higher in leaves of dark-treated etiolated plantlets than in those exposed to light for 24 h. Homologs of GBP were found in other dicots and in the monocot rice (Oryza sativa), as well. We suggest that interaction between GAGA elements and GBP-like proteins is a regulatory feature in plants.

Figure 1

Identification of GBP. A, Activation of lacZ by pNPGAD3 in a yeast one-hybrid system. Yeast strain YM4271(placZGAGA) harboring pNPGAD3 was spotted on a plate and grown, and then the plate was flooded with X-gal. Blue color formation (dark color in black and white image) indicates β-galactosidase activity (left spot). pNPGAD3 encodes a GAL4-GBP fusion protein, indicating that GBP binds to the GAGA element in the lacZ promoter. The vector pGAG424 did not activate the lacZ gene under the control of the GAGA element (middle spot). As a positive control, pGAD53 m, which encodes a GAL4-p53 fusion protein, was introduced into strain YM4271(p53Blue), which harbors a p53-binding site in the lacZ promoter (right spot). B, The deduced protein sequence of GBP. The underlined segment denotes a putative nuclear localization signal.

Figure 2

Interaction of GBP with dinucleotide repeat DNA. EMSA were carried out with a 54-bp double-stranded DNA comprising 27 repeating units of GA/CT (GA), TA/AT (TA), GT/CA (GT), and GC/CG (GC). The GC/CG-unbound DNA ran faster than the other unbound DNA fragments, and the image was moved for direct comparison with the other free DNAs. The DNAs were run either free (−) or with MBP-GBP fusion protein (+). The mobility of the DNAs were unaffected in the presence of MBP alone (data not shown).

Figure 3

Binding of GBP to the promoter of the Gsa1 gene. A, The promoter region of Gsa1, including the GAGA element. The underlined region was used in the gel shift assays. The bolded nucleotide shows the transcription start site determined previously (Frustaci et al., 1995). The italicized codon shows the translation start site. B, The four probes used in the analysis are as follows: I, 60-bp DNA fragment corresponding to the multiple cloning site of pBluescript SK used as a negative control; II, 60-bp DNA fragment within the Gsa1 promoter that includes the GAGA element, underlined in A; III, probe II, except that the 18-bp GAGA element was removed and replaced with an 18-bp sequence from pBluescript SK; and IV, probe I, except 18 bp was removed and replaced with the GAGA element. C, EMSA were carried out with the four probes and purified GBP. −, Free probe; +, presence of GBP in the binding reaction.

Figure 4

Northern-blot analysis of Gbp mRNA in soybean tissues. A, Gbp mRNA was analyzed in poly(A⁺) RNA from leaves (L), roots (R), and nodules (N). Ubiquitin (Ubi) was used as a control for a constitutively expressed gene. B, Leaves from illuminated (I) or dark-treated (D) etiolated plantlets were analyzed for Gbp. Cab is a control for a light-regulated gene.

Figure 5

Alignment of soybean GBP with homologs from other plants. The GBP homologs were identified by BLAST searches of databases. Arabidopsis sequences (protein identification nos. AAF63172 and AAF18588) and the rice sequence (protein identification no. AAK52535) were identified in the GenBank database using a BLAST search. Corresponding ESTs have been found for these sequences; thus, they are annotated as unknown proteins. The potato and tomato sequences were derived from EST consensus sequences found in the TIGR database (http://www.tigr.org/tdb) using a BLAST search (identification nos. TC85862 and TC23396 for tomato and potato, respectively). The sequences were aligned using Clustal W (version 1.81). The stars represent identity at that position in all six sequences. The colon represents similarity at that position.