Elemental profiling of shoot tissue collected from 12 different Arabidopsis accessions, including Col-0, Cvi-0, Est-1, Kas-2, Mrk-0, Mt-0, Se-0, Ts-1, Van-0, Nd-1, Tsu-1, and Ler-2, revealed that Ts-1 and Tsu-1 (Figure 1A) accumulate higher levels of Na⁺ than Col-0 and all other accessions tested when propagated in soil with low levels of NaCl under controlled growth conditions (Figure 1B). Interestingly, the Ts-1 and Tsu-1 accessions were collected from the coastal regions of Spain (Tossa del Mar) and Japan (Tsu), respectively. Besides being annotated as having different geographical origins, Ts-1 and Tsu-1 have different physical appearances (Figure 1A). Moreover, based on a genome-scale DNA polymorphism analysis involving 96 Arabidopsis accessions, these two accessions appeared to be genetically distinct [21]. The Ts-1 and Tsu-1 accessions can also be distinguished based on the fact that Ts-1 accumulates elevated concentrations of cobalt (+55%) in shoot tissue compared to Col-0, while Tsu-1 has lower levels of Co. A complete set of the elemental profiling data summarized here can be obtained at the open access Purdue Ionomics Information Management System (PiiMS) at http://www.purdue.edu/dp/ionomics.

To determine the feasibility of using natural variation to identify individual loci regulating ionomic variation, we attempted to map the locus responsible for elevated Na⁺ in Ts-1 and Tsu-1. Both accessions were crossed to Col-0, and the shoot concentrations of Na⁺ were measured in the F1 hybrid plants (Figure 1C). The concentration of Na⁺ was not significantly different from Col-0, suggesting that the loci controlling Na⁺ accumulation in Ts-1 and Tsu-1 are recessive in both cases. Analysis of the segregating F2 plants from either cross revealed a pattern consistent with 3:1 segregation ratio of Col-0 × Ts-1 (Figure 2A) and Col-0 × Tsu-1 (Figure 2B) for shoot Na⁺ concentrations. Therefore, we conclude that the high Na⁺ phenotype observed in both Ts-1 and Tsu-1 segregates as a monogenic recessive trait. We further used the complementation test to demonstrate that the loci driving elevated shoot Na⁺ in Ts-1 and Tsu-1 are allelic to each other, showing that the F1 plants from Tsu-1 × Ts-1 have shoot Na⁺ levels that are similar to each parent (Figure 1D). Based on this evidence, DNA microarray-based BSA [12,13] was used to map the locus responsible for elevated Na⁺ in both Ts-1 and Tsu-1. From the Ts-1 × Col-0 F2 population represented in Figure 2A, two pools of DNA were prepared, one containing genomic DNA from 30 plants with Na⁺ levels similar to Col-0, constituting the “control” pool, and another with DNA from 30 plants with the highest Na⁺ levels, similar to those of the Ts-1 parent, constituting the “high Na⁺” pool. Single feature polymorphisms (SFPs) were identified for Col-0 and Ts-1 by comparing the hybridization of genomic DNA isolated from the parental Col-0 and Ts-1 accessions to the Affymetrix Arabidopsis ATH1 microarrays. The frequency of these SFPs in the DNA from the pool of F2 progeny plants with high Na⁺ levels, and in the pool with control Na⁺ levels, was scored by hybridization of genomic DNA to ATH1 microarrays. The DNA microarray-based BSA revealed a strong peak and therefore enrichment in Ts-1 SFPs linked to the locus causing elevated shoot Na⁺ in Ts-1 at 6.6 Mbp on Chromosome IV (Figure 2C). Similarly, a strong peak at 6.4 Mbp in Chromosome IV was obtained when the hybridization was performed using DNA pools from the Tsu-1 × Col-0 F2 population (Figure 2C). Approximately 513 genes (corresponding to 23 BAC clones) are contained within the confidence interval of 5.525 to 7.475 Mbp on Chromosome IV. The confidence interval was derived using previously published simulations [12]. One of the genes in BAC clone F24G24 (at 6.39 Mb), At4g10310, named AtHKT1, stands out as a very strong candidate because it has been previously identified as a Na⁺ transporter [15], which when disrupted causes elevated shoot Na⁺ [3,17,18]. The shoot Na⁺ concentrations in the hkt1–1 null mutant are significantly higher than Col-0 in leaves at all stages of development, with Na⁺ accumulation generally increasing with leaf age (Figure S1A). When grown under the same conditions, the Ts-1 and Tsu-1 accessions also show increased Na⁺ accumulation compared to Col-0 in leaves at all stages of development. However, Na⁺ accumulation in Ts-1 and Tsu-1 is lower than that observed for hkt1–1 (Figure S1A).

To establish if a different allele of AtHKT1 is present in Ts-1 and Tsu-1, the nucleotide sequence was determined for the AtHKT1 locus in both accessions. The sequenced region comprises 5,456 bp upstream (363 bp downstream of the previous gene At4g10300) of AtHKT1 translational start codon that includes the promoter to 386 bp downstream of the AtHKT1 stop codon. Several polymorphisms were identified both in the coding region and in the upstream and downstream regions of the AtHKT1 gene. In the coding region, no nonsense mutation was recognized and 19 single nucleotide polymorphisms (SNPs) were identified in both Ts-1 and Tsu-1 (Figure S2A), seven of which result in the amino acid changes R3I, K10N, V66L, C134Y, E385G, V453L, and F477L. None of the amino acid changes are located in the three relatively highly conserved regions identified by Uozumi et al. [15], and none of them affect the first serine residue at position 68 of P-loop A that has been implicated in the Na⁺ specificity of the transporter [22]. One of the amino acid changes, valine to leucine in position 453 (V453L), was also found in the Ler AtHKT1 allele published by Uozumi et al. [15].

In the upstream region, which includes the promoter of AtHKT1, four major polymorphisms were identified between Ts-1, Tsu-1, and Col-0 (Figure S2B). The most upstream polymorphism affects two repeated units of 681 and 673 bp, linked by a 34-bp sequence (Figure S2B). These two repeated units are localized 5,320 to 3,933 bp upstream of the AtHKT1 start codon and are 97% identical to each other in Col-0. In Ts-1 and Tsu-1, we identified a 725- and 687-bp deletion, respectively, which removes the end of the first of these repeated units, the beginning of the second unit, and the 34-bp junction sequence. Consequently, only one of the repeated units is present in Ts-1 and Tsu-1. The second major polymorphism identified in this region, about 3,100 bp upstream of the start codon, is an insertion of 13 bp in the sequence of Ts-1 as well as Tsu-1, resulting in the duplication of a 10-bp sequence (AATGTGTTAT) in Ts-1 and Tsu-1 that is present only once in Col-0. Similarly, 1,210 bp upstream of the start codon, a 14-bp insertion results in a duplicated 10-bp sequence (TCATTGCAAA) in Ts-1 and Tsu-1. The last major polymorphism in the promoter region is localized 148 to 98 bp upstream of the translational start codon. Compared to Col-0, these sequence polymorphisms found in both Ts-1 and Tsu-1 abolish the first of the two putative CAAT boxes suggested by Uozumi et al. [15].

Polymorphisms have also been found in the two introns of AtHKT1, mainly SNPs. We have been unable to sequence the last 157 bp of the second intron of the Ts-1 and Tsu-1 alleles, which according to the published Col-0 sequence is enriched in [TA] repeats. Finally, major differences in the sequence between Col-0 and Ts-1 and Tsu-1 occur in the sequence downstream of the stop codon, including the 3′-untranslated region. Several SNPs, as well as deletions in Ts-1 and Tsu-1, result in a sequence of 246 and 140 bp shorter than the 386-bp sequence found in Col-0.

Because the Ts-1 and Tsu-1 HKT1 alleles are recessive (Figure 1C) and the hkt1–1 null mutant, like Ts-1 and Tsu-1, shows elevated shoot Na⁺ accumulation (Figure S1), we used the deficiency complementation test to establish that AtHKT1 is the gene responsible for elevated Na⁺ in Ts-1 and Tsu-1 [23]. Both accessions, Ts-1 and Tsu-1, were crossed to the hkt1–1 T-DNA insertional mutant in the Col-0 gl1 genetic background [19]. The hkt1 null mutant accumulates higher levels of Na⁺ in the shoot and lower levels in the root than the wild-type, implicating HKT1 in the regulation of Na⁺ distribution throughout the plant [17–19]. F1 plants from the cross of hkt1–1 to Col-0 present Na⁺ levels similar to the those of the wild-type, as expected from a recessive mutation (Figure 3). However, F1 hybrid plants from the crosses of hkt1–1 (Col-0 gl1) with Ts-1 or Tsu-1 accumulate levels of Na⁺ that are intermediate between each parent and significantly higher than Col-0 (Figure 3), indicating that the Ts-1 and Tsu-1 HKT1 allele is deficient in complementing the hkt1–1 null mutation. This helps establish that elevated Na⁺ in Ts-1 and Tsu-1 is due to alterations in the AtHKT1 gene. However, the lower levels of Na⁺ in the F1 plants compared with hkt1–1 suggest that the Ts-1 and Tsu-1 alleles of AtHKT1 are not nulls but rather weak alleles, although a role of the genetic background cannot be excluded (Figure 3).

Several polymorphisms in the promoter region suggested that HKT1 in Ts-1 and Tsu-1 might have a different expression level or expression pattern compared to Col-0, which could be responsible for the high Na⁺ phenotype in Ts-1 and Tsu-1. Plants displaying elevated shoot Na⁺ accumulation, compared to Col-0, were used to determine expression levels of AtHKT1 in shoot and root tissue, using quantitative real-time PCR. As previously described [15–17], expression of AtHKT1 in Col-0 is significantly higher in roots compared to shoots (Figure 4). In the shoot, no significant differences in expression levels were found between Col-0 and Ts-1 or Tsu-1. In the root, however, the level of AtHKT1 expression in Ts-1 and Tsu-1 is approximately 10-fold lower than in Col-0 (Figure 4).

An Arabidopsis mutant (Line 1425), in the Col-0 gl1 sos3–1 background, previously identified as a weak suppressor of sos3–1 Na⁺ sensitivity (A. Rus and P. M. Hasegawa, unpublished data), was found to contain a T-DNA insertion within the tandem repeat region localized 5,320 to 3,933 bp upstream of the AtHKT1 start codon (Figure 5A), where Ts-1 and Tsu-1 also have a 725- and 687-bp deletion, respectively (Figure S2B). We observed that in Line 1425, expression of AtHKT1 in both roots and shoots is drastically reduced to levels comparable to hkt1–1 (Figure 5B). Furthermore, disruption of this tandem repeat, and elimination of AtHKT1 expression in Line 1425, leads to elevated shoot Na⁺ compared to both Col-0 and sos3–1 (Figure 5C), and this phenocopies the elevated shoot Na⁺ levels observed in both hkt1–1 and the sos3–1 hkt1–1 double mutant (Figure 5C). Such evidence strongly implicates the approximately 700-bp deletion in the tandem repeat upstream of AtHKT1 in both Ts-1 and Tsu-1 as being involved in the reduced root expression of AtHKT1 in these accessions.

The elevated shoot Na⁺ of Ts-1 and Tsu-1 that maps to the AtHKT1 locus is associated with the loss of AtHKT1 expression in roots. To address the contribution of HKT1 expression in the root to the control of Na⁺ accumulation in the shoot, we performed reciprocal grafting experiments (Figure 6). Shoots from hkt1–1 grafted onto Col-0 roots show no significant difference in shoot Na⁺ compared to Col-0 self-grafted controls, while Col-0 shoots grafted onto hkt1–1 roots accumulated Na⁺ levels similar to those observed in self-grafted hkt1–1 plants (Figure 6). This is further evidence that AtHKT1 expression in the root is the primary site for HKT1′s role in regulating shoot Na⁺.

AtHKT1 has been implicated in Arabidopsis tolerance to NaCl stress. The hkt1 null mutant is sensitive to elevated NaCl as a result of Na⁺ overaccumulation in the shoot [Figure 7A; 17–19]. Under unstressed conditions, we have established that the weaker AtHKT1 allele in Ts-1 and Tsu-1 is responsible for the elevated Na⁺ content in the shoot of these two accessions, similar to that observed in the hkt1–1 null mutant. Under high NaCl concentrations (50 and 100 mM NaCl), both Ts-1 and Tsu-1 have higher levels of Na⁺ in the shoot compared to Col-0, in all leaves at different stages of development, including the youngest ones not fully developed and localized close to the meristem (stage 1; Figure S1B and S1C). However, this elevated shoot Na does not cause increased NaCl sensitivity in Tsu-1 (Figure 7A). Given the connection between AtHKT1 expression and NaCl sensitivity, we decided to evaluate the involvement of this novel allele of AtHKT1 in NaCl tolerance by screening F2 plants from a cross between Tsu-1 × Col-0 for their capacity to survive high levels of NaCl (Figure 7). The genotyping of the F2 population from Tsu-1 × Col-0 identified 25 plants homozygous for Tsu-1-HKT1 and 50 plants heterozygous and 20 plants homozygous for the Col-0-HKT1 allele, following the expected 1:2:1 segregation ratio. The plants homozygous or heterozygous for the Tsu-1-HKT1 allele were able to survive longer in the presence of 100 mM NaCl compared to plants that were homozygous for the Col-0-HKT1 allele (Figure 7). Therefore, although this new AtHKT1 allele contributes to an increased Na⁺ accumulation in the shoot, it does not confer NaCl sensitivity but, on the contrary, appears to co-segregate with enhanced NaCl tolerance. Although currently we cannot eliminate the possibility that a second unknown gene is conferring the enhanced NaCl tolerance observed in Tsu-1, and due to a small genetic distance between AtHKT1 and this second gene they segregate together in the F2 population studied. Further transgenic studies are required to discern this.

A. thaliana Col-0, Ts-1, Tsu-1, and other accessions reported in this paper were obtained from the Arabidopsis Stock Center at the Arabidopsis Biological Resource Center. The hkt1–1 mutant [19] was from our own seed stock. For the genetic analysis, F1 and F2 plants from different crosses are as specified throughout the paper.

Plants used for elemental profiling by ICP-MS analysis were grown under unstressed conditions in a controlled environment, 8 h light:16 h dark (90 μmol • m⁻² • s⁻¹ light intensity) and 19 to 22 °C [1]. Briefly, seeds were sown onto moist soil (Sunshine Mix LB2; Carl Brehob & Son, Indianapolis, Indiana, United States) with various elements added at subtoxic concentrations (As, Cd, Co, Li, Ni, Pb, and Se [1]) and stratified at 4 °C for 3 d. Plants were bottom-watered twice per week with 0.25× Hoagland solution in which iron was replaced with 10 μM Fe-HBED [N,N′-di(2-hydroxybenzyl)ethylenediamine-N,N′-diacetic acid monohydrochloride hydrate; Strem Chemicals, Inc., http://www.strem.com). For sodium analysis after 42 d, plants were nondestructively sampled by removing one or two leaves. The plant material was rinsed with 18 MΩ water and placed into Pyrex digestion tubes.

The evaluation of the F2 population from the Tsu-1 × Col-0 cross in response to salt stress was realized in a growth chamber under controlled environmental conditions, 8 h light:16 h dark (150 μmol • m⁻² • s⁻¹ light intensity), 21 °C:19 °C (day/night) and 60% relative humidity. After stratification, F2 seeds as well as seeds from each one of the parents were sown onto moist soil (Scotts Potting Medium; Scotts-Sierra Horticultural Products Company, Marysville, Ohio, United States). About 2 wk after germination, seedlings were thinned to leave one plant per individual cell. Plants were bottom-watered twice per week with 0.5× Murashige and Skoog (MS) Macro- and Micronutrients (Caisson Laboratories, Inc., Rexburg, Idaho, United States). One month after the seeds were sewn, NaCl was added to the watering solution increasingly from 50 to 100 mM NaCl and maintained at that level until all the plants were recorded dead.

Plants from Col-0, hkt1–1, Ts-1, and Tsu-1 used to evaluate Na⁺ accumulation in the shoot in response to NaCl stress were grown under controlled growth conditions (as described above in “General plant growth conditions”) and treated with NaCl for 2 wk. NaCl treatment was started 1 mo after the seeds were sewn. Plants were watered twice weekly without or with NaCl. The NaCl treatments included plants watered with 50 mM NaCl and plants watered once with 50 mM, once with 75 mM, and twice with 100 mM NaCl. Two weeks after the beginning of the salt treatments, plants were harvested and analyzed by ICP-MS. Na⁺ was analyzed in leaves of different age throughout the shoot. The leaves were numbered from the meristem toward the outer leaf ring of the rosette. Four samples (indicated as Nos. 1, 2, 3, and 4 in the graph) were harvested per plant, with No. 1 containing leaves Nos. 4 and 5 and therefore being the youngest leaves, No. 2 containing leaf No. 8, No. 3 containing leaf No. 11, and No. 4 containing leaf No. 14 and being the oldest.

Approximately 3 mg of dry weight of each plant was sampled into Pyrex tubes (16 × 100 mm) after drying at 92 °C for 20 h. After cooling, seven of approximately 100 samples from each sample set were weighed. All samples were digested with 0.7 ml of concentrated nitric acid (OmniTrace; VWR Scientific Products; http://www.vwr.com) and diluted to 6.0 ml with 18 MΩ water. Elemental analysis was performed with an ICP-MS (Elan DRCe; PerkinElmer, http://www.perkinelmer.com) for Li, B, Na, Mg, P, K, Ca, Mn, Fe, Co, Ni, Cu, Zn, As, Se, Mo, and Cd. All samples were normalized to calculated weights, as determined with an iterative algorithm using the best-measured elements, the weights of the seven weighed samples, and the solution concentrations, implemented in Microsoft Excel (http://www.microsoft.com) [1].

DNA microarray-based BSA was realized as previously described [12,13]. Briefly, SFPs were identified between Col-0 and Ts-1 and Tsu-1 by hybridizing labeled DNA from each one of the accessions to Affymetrix ATH1 microarrays and comparing them to Col-0 hybridizations downloaded from http://www.naturalvariation.org/xam. Two genomic DNA pools from an F2 population of a cross between Ts-1 or Tsu-1 and Col-0 were created and hybridized to arrays. Each one of the pools contained plants with either levels of Na⁺ similar to Col-0 (“control” pool) or high Na⁺ levels similar to Ts-1 or Tsu-1 (“high Na^+” pool). At loci unlinked to the ionomic phenotype of interest, the pools should have equivalent amounts of each genotype, and the hybridization signal at each SFP should be intermediate between the two parent accessions, for an average difference between the two DNA microarrays of zero. At linked loci, the difference between the two DNA microarrays should be approximately two-thirds the difference between the parent accessions. By smoothing the signal across multiple SFPs, the noise is reduced and the peak of the differences in hybridization signal will correspond to the chromosomal region of the loci controlling the mapped trait. Raw hybridization data (.CEL files) for each probe on the ATH1 DNA microarrays used in these experiments have been submitted to both Natrualvariation.org (http://www.naturalvariation.org) and Gene Expression Omnibus (http://www.ncbi.nlm.nih.gov/geo) for public distribution.

To sequence the AtHKT1 gene and corresponding promoter from Ts-1 (CS1552) and Tsu-1 (CS1640), synthetic oligonucleotide primers were designed to produce overlapping amplified PCR products from 5,456 bp upstream of the AtHKT1 start codon to 386 bp downstream of the AtHKT1 stop codon, corresponding to positions 32,115 and 41,615, respectively of the BAC clone F24G24 in Chromosome IV.

Table S1 provides a summary of the pairs of primers used and the size of the PCR products expected for Col-0 (based on published sequence) and obtained for Ts-1 and Tsu-1. The PCR products obtained for each one of the primer pairs were cloned using the pGEM-T Easy Vector System I according to the manufacturer's instructions (Promega, http://www.promega.com). After transformation of electrocompetent Escherichia coli cells strain DH5α and selection of transformed colonies using ampicillin, positive clones were confirmed by PCR. The plasmids containing the inserted PCR product were extracted and used to carry out the sequencing reaction in both directions using Big Dye terminator v 3.0 according to the manufacturer's instructions (Applied Biosystems, http://www.appliedbiosystems.com). The sequencing products were then analyzed at the sequencing center (Purdue University), and sequences were compared to the corresponding Col-0 sequence from the Arabidopsis database.

Plants were first analyzed by ICP-MS and further used to determine the AtHKT1 transcript levels. Shoot and root from plants grown under short-day conditions (as described above in “General plant growth conditions”) were separated and rinsed thoroughly with deionized water to remove any soil contamination. The samples were then frozen in liquid nitrogen and stored at −80 °C until extraction. Total RNA was extracted from each one of the samples using the Qiagen RNeasy Plant Mini Kit (http://www.qiagen.com), and DNase digestion was performed during the extraction procedure according to the manufacturer's instructions. Two micrograms of total RNA was used as a template to synthesize first-strand cDNA with random hexamers using SuperScript II Reverse Transcriptase (Invitrogen Life Technologies, http://www.invitrogen.com). Quantitative real-time PCR was performed with the first strand cDNA as a template on a sequence detector system (ABI Prism 7000, Applied Biosystems). For normalization across samples, the expression of the Actin 1 gene (At2g37620) was used with the following primers: CPRD66, 5′-TGG AAC TGG AAT GGT TAA GGC TG-3′ and CPRD67, TCT CCA GAG TCG AGC ACA ATA C-3′. For AtHKT1, the following primers were used: HKT-RTF, 5′-TGG GAT CTT ATA ATT CGG ACA GTT C-3′ and HKT-RTR, 5′-GAT AAG ACC CTC GCG ATA ATC AGT-3′. For each sample, the average value from triplicate real-time PCRs was used to evaluate the transcript abundance, and the relative fold induction relative to AtHKT1 expression in Col-0 shoots was calculated based on the ΔΔC_t method.

Seedlings to be grafted were germinated on 100 × 15-mm plates containing 0.5× MS Macro- and Micronutrients, 0.5× MS Vitamins (Caisson Laboratories, Inc.), 3 mg/L Benomyl [methyl 1-(butylcarbamoyl)-2-benzimidazolecarbamate; Sigma, http://www.signaaldrich.com), 0.04 mg/L BA (6-benzylaminopurine; Sigma), 0.02 mg/L IAA (indole acetic acid; Sigma), and 12 g/L agar. Hormone treatment was found to greatly improve grafting efficiency due to at least three factors: enhanced callusing at the graft union, retardation of shoot growth which maintained contact at the graft union, and an approximately 90% reduction in adventitious root formation from the graft union. Benomyl virtually eliminated fungal contamination [26]. Plates containing the stratified seeds were placed vertically under controlled environmental conditions (16 h light:8 h dark and 25 °C). Five-day-old seedlings were grafted on the plate by the 90-degree blunt end technique with a 15-degree Stab Knife (Fine Scientific Tools, North Vancouver, British Columbia, Canada) without collars [27]. The grafted seedlings remained on the plate for an addition 5 d to allow the formation of the graft union. Successfully unified seedlings were transplanted directly to soil (as described above in “General plant growth conditions”). Plants were harvested for Na⁺ analysis 4 wk after transfer to soil. Postharvest analysis of graft unions was performed under the stereoscope to identify any adventitious root formation from grafted individuals. Individuals with adventitious roots emerging at or above the graft union were eliminated from subsequent analyses.

The Arabidopsis Biological Resource Center (ABRC) (http://www.biosci.ohio-state.edu/pcmb/Facilities/abrc/abrchome.htm12) accessions used in this paper were Col-0 (CS6000), Cvi-0 (CS1096), Est-1 (CS1150), Kas-2 (CS1264), Mrk-0 (CS1374), Mt-0 (CS1380), Se-0 (CS1502), Ts-1 (CS1552), Van-0 (CS1584), Nd-1 (CS1636), Tsu-1 (CS1640), and Ler-2 (CS8581).