De novo production of the flavonoid naringenin in engineered Saccharomyces cerevisiae

Selection of naringenin biosynthetic genes from A. thaliana

As a first step towards heterologous expression of naringenin in S. cerevisiae, flavonoid biosynthetic genes were selected from A. thaliana. It has been proposed that, in plants, flavonoid biosynthetic enzymes can be organized in protein complexes, where the proteins involved in the pathway are spatially co-localized. The combination of isoenzymes in such complexes is hypothesized to facilitate the synthesis of different flavonoids [24]. In addition, complex formation might enhance pathway activity and carbon flux via metabolic channeling of intermediates [24]. Moreover, formation of toxic intermediates is kept locally and are sequentially converted [32]. Protein complex formation is likely to require specific protein-protein interactions and therefore, co-evolution of the protein structures of the enzymes that form these complexes. In A. thaliana, several isoenzymes exist for most of the reactions leading to naringenin formation (Table 1). In order to identify the best set of isoenzymes for naringenin production and maintain the potential benefit of plant-specific protein-protein interactions upon expression in S. cerevisiae, a subset of isoenzymes from one single species, A. thaliana, was identified and subsequently subjected to expression profile correlation analysis. The subset of isoenzymes was selected based on previous reports indicating either the involvement in the lignin biosynthetic pathway [33] and/or the flavonoid biosynthetic pathway (Figure 1), since these pathways share the same reactions up to the metabolic branch-point coumaroyl-CoA. The specific genes from this isoenzyme subset were then further assessed for the correlation of their expression levels in a dataset comprising 392 transcriptome studies of A. thaliana[34].

From the expression correlation analysis, using the BAR Expression Angler [35], two clear modules could be distinguished (Figure 2). The first module comprises flavonoid biosynthetic genes, including the 4-coumaric acid-CoA ligase gene (4CL3), the chalcone synthase gene (CHS3), two chalcone isomerase genes (CHI1, CHI3) and a number of genes that mediate the further modification of naringenin. The second, a lignin module, comprised two phenylalanine ammonia lyase (PAL1, PAL2) genes, the trans-cinnamate 4-monooxygenase (C4H) gene and three 4-coumaric acid-CoA ligase genes (4CL1, 4CL2, 4CL4), in addition to a number of genes known to be involved in formation of lignin and phenolic esters.

Since these results are in good agreement with a previous study on expression correlation in plants [36], the following genes for the pathway towards naringenin were selected for heterologous expression in S. cerevisiae: the flavonoid biosynthetic genes 4CL3 (at1g65060), CHS1 (at4g00040) and CHI1 (at5g05270), as well as, C4H (at2g30490) and PAL1 (at2g37040) from the lignin biosynthetic genes [37]. PAL1 and CHI1 were preferred over PAL2 and CHI3, as their expression profiles showed stronger correlations with C4H and 4CL3 respectively (Figure 2).

Construction and evaluation of a naringenin producing strain

To enable naringenin production in S. cerevisiae, one episomal and one integrative expression vector were constructed which together, harbor the five flavonoid biosynthetic genes. Additionally, activation of the cytochrome P450 C4H requires a cytochrome P450 reductase (CPR). To choose the best candidate gene, the two A. thaliana CPR variants (CPR1 or CPR2) were separately included in the pathway engineering strategy. First, the centromeric episomal plasmid pUDE172, carrying PAL1 and yeast codon-optimized versions of the A. thaliana C4H (coC4H) and CPR1 (coCPR1) genes was constructed. In a same manner, separate construct, PAL1 and coC4H were combined with the coCPR2 gene. Subsequently, the integration plasmid pUDI065 was constructed, which carried the non yeast optimized A. thaliana genes at4CL3, atCHS1 and atCHI1. Only the, C4H and CPR1 in the naringenin production pathway were codon optimized since these genes hold the majority of rare codons for yeast (8), compared to the other genes (PAL1, 4CL3, CHS3 and CHI1) (3). When coCPR2 was expressed instead of coCPR1, significantly lower naringenin titers were observed (data not shown); coCPR2 was therefore not used in further experiments. Introduction of the coCPR1 version of the centromeric expression vector and the integration vector yielded the S. cerevisiae strain IMU011. In shake-flask cultures containing synthetic medium and with glucose as the sole carbon source, this strain produced naringenin to a concentration of 5.4 μM (Figure 3A). Interestingly, naringenin was measured extracellularly, although its export mechanism has not yet been elucidated.

Alleviation of tyrosine feedback inhibition of yeast 3-deoxy-D-arabinose-heptulosonate-7-phosphate (DAHP) synthase

Since phenylalanine is a key intermediate in naringenin biosynthesis (Figure 1), further metabolic engineering was directed at improving its intracellular availability. Aromatic amino acid biosynthesis in S. cerevisiae is subject to strong feedback inhibition by phenylalanine and tyrosine. Introduction of a tyrosine insensitive ARO4 allele (ARO4^G226S) [38,39] in conjunction with the deletion of the other allele of the 3-deoxy-d-arabinose-heptulosonate-7-phosphate (DAHP) synthase (ARO3) has previously been shown to cause a 4-fold increase in flux through the aromatic amino acid pathway [40]. To test the potential impact of this genetic intervention on naringenin synthesis, S. cerevisiae strain IMX183 (ARO4^G226Saro3Δ, atPAL1↑, coC4H↑, coCPR1↑, atCHI1↑, atCHS3↑_,at4CL3↑) was constructed. The deregulation of DAHP synthase in this strain lead to a 2-fold increase of the naringenin titer in shake flask cultures (10.4 μM) (Figure 3). However, this increase was accompanied by a strongly enhanced accumulation of phenylethanol, whose extracellular concentration was increased 100-fold to a level ca. 20 fold higher than the improved naringenin concentration (Figure 3B). Therefore, to improve further naringenin production, we adopted a strategy to reduce the diversion of aromatic amino acid biosynthesis into this byproduct.

Elimination of competing phenylpyruvate decarboxylase activity

In S. cerevisiae, phenylethanol is produced via the Ehrlich pathway. Decarboxylation of phenylpyruvate, the 2-oxo acid associated to phenylalanine, yields phenylacetaldehyde, which is subsequently reduced into phenylethanol and/or oxidized to phenylacetate [41-43]. Decarboxylation of phenylpyruvate can be catalyzed by four different thiamine pyrophosphate-dependent 2-oxo acid decarboxylases encoded by ARO10, PDC1, PDC5, and PDC6[43,44]. Recent work in our group has demonstrated that, among the four decarboxylases capable of phenylpyruvate decarboxylase, Pdc1 and Pdc6 showed a much lower affinity and decarboxylation rate of phenylpyruvate than Pdc5 and, in particular, Aro10 [44]. Since absence of all three pyruvate decarboxylase genes (PDC1, PDC5 and PDC6) abolishes growth on glucose in synthetic media, strains only retaining PDC1 (aro10Δ, pcd5Δ, pdc6Δ) were constructed [45]. The intermediate strain IMX185 (ARO4^G226S, aro3Δ, pdc5Δ, pdc6Δ) did not show a reduced phenylethanol titer compared to its ancestor IMX183 (ARO4^G226S, aro3Δ) (Figure 3B). In contrast, the naringenin producing strain IMX106 (ARO4^G226S, aro3Δ, pdc5Δ, pdc6Δ, aro10Δ) that also carries the ARO10 deletion exhibited a 22-fold lower concentration of extracellular phenylethanol (44 μM) compared to both ancestor strains IMX183 and IMX185 (955 μM). This strong reduction in phenylethanol production coincided with a 3-fold increase of extracellular naringenin (up to 46.5 μM) (Figure 3A), indicating that reduction of the flux through the Ehrlich pathway had indeed led to substantial improvement in naringenin production. Analysis of culture supernatants revealed that strain IMX106 also produced coumaric acid up to a concentration of 200 μM (Figure 4). Moreover, this strain showed increased production of another aromatic metabolite that, based on HPLC spectra and LC-MS analysis, was identified as phloretic acid (Figure 4). Production of phloretic acid was only observed in cultures that also produced coumaric acid and which expressed 4CL3 (data not shown). This suggests that phloretic acid is most likely produced from coumaroyl-CoA (Figure 4).

Alleviate the bottleneck downstream of coumaric acid

Naringenin chalcone synthase, which catalyzes the formation of chalcone by condensing coumaroyl-CoA with three molecules of malonyl-CoA, is known to be an enzyme with low catalytic activity [46]. The transient accumulation and later reconsumption of coumaric acid in shake flask cultures suggested that reactions downstream of coumaric acid were limiting naringenin production. To test whether the capacity of chalcone synthase was indeed controlling flux through the pathway, two additional copies of the coCHS3 gene were introduced into strain IMX106 on an episomal plasmid (pUDE188), yielding strain IMX197. The two additional copies resulted in a 2.5 fold increase in naringenin accumulation (134.5 μM) in shake flask cultures (Figure 5A), indicating that coCHS3 was indeed a limiting step in the naringenin production. Additional coCHS3 copies also caused a decreased production of phloretic acid (Figure 5B), consistent with the hypothesis that phloretic acid production occurs when coumaroyl-CoA cannot be efficiently converted to naringenin.

Expression of a tyrosine ammonia lyase leads to increased naringenin synthesis

The engineered naringenin production pathway directs carbon via the aromatic amino acid phenylalanine to coumaric acid through phenylalanine ammonia lyase, trans-cinnamate 4-monooxygenase and subsequently to naringenin through the 4-coumaric acid-CoA ligase and chalcone synthase reactions (Figure 1). Deregulation of aromatic amino acid synthesis in S. cerevisiae by eliminating feed-back inhibition of DAHP synthase not only increases intracellular phenylalanine levels, but also the intracellular concentration of tyrosine [40]. Since S. cerevisiae cannot interconvert tyrosine and phenylalanine, this increased intracellular availability of tyrosine could not be exploited for naringenin production. In other organisms, deamination of tyrosine by tyrosine ammonia lyase does provide an alternative route to coumaric acid. This has previously been shown to increase naringenin production by E coli when fed with either glucose or tyrosine [18,20,47]. To investigate the added benefit of the direct conversion of tyrosine into coumaric acid in S. cerevisiae IMX197, a cotal1 gene from Rhodobacter capsulatus was expressed. This R. capsulatus gene was chosen based on its known high catalytic efficiency for tyrosine [48]. Integration of this yeast codon-optimized cotal1 gene resulted in increased naringenin production in the resulting strain IMX198 (aro3Δ ARO4^G226Saro10Δ, pdc5Δ, pdc6Δ, atPAL1↑, coC4H↑, coCPR1↑, atCHI1↑, atCHS3↑_,coCHS3↑, at4CL3↑, cotal1↑) (Figure 5B), to a titer of 200 μM in shake-flask cultures. Additionally, the phloretic acid concentrations in this strain again increased compared to the parental strain IMX197 (623,9 ± 11,4 μM and 396,1 ± 6,9 respectively), while the coumaric acid concentrations in cultures of the two strains remained the same.

Naringenin production in controlled aerobic batch cultures

To further characterize strain IMX198 (aro3Δ ARO4^G226Saro10Δ, pdc5Δ, pdc6Δ, atPAL1↑, coC4H↑, coCPR1↑, atCHI1↑, atCHS3↑_,coCHS3↑, at4CL3↑, cotal1↑) under controlled conditions, this strain was cultured in a 2L batch bioreactor with 20 g·l^-1 glucose at pH 5.0 (Figure 6A, B). When S. cerevisiae is grown aerobically in batch cultures on glucose, alcoholic fermentation is the predominant mode of glucose metabolism [49,50] and is characterized by a diauxic growth profile. During the glucose consumption phase the specific growth rate of IMX198 was 0.2 h^-1, which is approximately 50% of the specific growth rate of the reference strain S. cerevisiae CEN.PK113-7D under the same conditions [51]. Besides the expected formation of ethanol, a specific naringenin production rate of 12.545 ± 0.333 μmol^.g^-1_CDWh^-1 was obtained. After complete consumption of glucose, a naringenin titer 148.06 ± 5.67 μM at a naringenin yield on glucose of 0.002 ± 0.000 (g·g^-1) was obtained. When all the glucose was consumed, ethanol, acetate and glycerol that were produced during the first phase were subsequently consumed (Figure 6A). During this reconsumption phase, naringenin titers increased to 414.63 ± 1.60 μM, indicating that most naringenin is produced during this second phase (Figure 6B). However, it must be taken into account that during this reconsumption phase, naringenin production is also facilitated by the presence of available coumarate that was previously formed during the glucose consumption phase and also by the higher amount of biomass, compared to the glucose phase. When only calculating the product yield over the total glucose and ethanol consumption phase, a yield of 0.006 ± 0.000 (g·g^-1) was obtained, which is approximately triple of what is obtained during solely the glucose consumption phase.

In summary, the naringenin production of IMX198 in a well aerated and pH controlled batch bioreactor cultivation required only 38 hours and yielded more than twice the naringenin titer that was achieved in equivalent shake flasks cultivations (200 vs. 415 μM).

Strains and maintenance

All strains used in this study (Table 2) are derived from the S. cerevisiae CEN.PK strain family background [65,66]. Stock cultures were grown at 30°C in 500 ml shake flask cultures containing 100 ml synthetic medium (according to [67]) with 20 g·l^-1 glucose and appropriate growth factors to supplement the specific auxotrophic requirements of the strains [68]. After overnight growth, a final concentration of 20% glycerol was added and 1 ml aliquots were stored at -80°C.

Introduction of chromosomal gene alteration

Plasmids and oligonucleotide primers used in this study are listed in Tables 2 and 3, respectively. The geneticin (G418) resistance cassette (KanMX4) was amplified by using the pUG6 vector as the template [70]. The KanMX4 PCR product was transformed to the appropriate host (Table 2) using the lithium acetate method [76]. Synthetic medium agar plates containing 2% glucose and 200 mg·l^-1 G418 (Sigma-Aldrich, Zwijdrecht, The Netherlands) and appropriate growth factors to supplement the auxotrophic requirements of the strains, were used to select for the presence of the KanMX4 gene. The KanMX4 marker was removed by the CreloxP recombination system using the plasmid pSH47 as described previously [70].

The introduction of a feed-back-insensitive DAHP synthase activity in S.cerevisiae was accomplished in two steps. Firstly, the ARO3 allele was deleted in strain CEN.PK 2.1C using primers ARO3 KO for and ARO3 KO rev as described above. In this resulting strain, the chromosomal ARO4 allele was replaced by the feed-back-insensitive ARO4^G226S allele [38,39]. Genomic DNA of strain CEN.PK717.5A was prepared using the genomic DNA isolation kit (Zymo Research, Orange, CA), according to the manufacturer’s recommendations. The ARO4^G226S allele was then amplified using primers Aro4 for/Aro4 rev, and transformed. Selection was performed by screening for tyrosine tolerance by plating on selective agar plates containing synthetic medium, 2% glucose and 1 g·l^-1 tyrosine. The resulting strain was named IMK328 (Table 2).

Plasmid construction

Plasmid pUDE172 was obtained by transformation-associated recombination methods as described previously [29,30,77]. The backbone fragment harboring the yeast and bacterial origins of replication and markers was amplified from pAG416GPD-ccdB (Table 2) using primers FK86/87. Genes were optimized for S. cerevisiae using the JCat algorithm [78]), based on the A. thaliana gene sequence. The DNA fragments were synthesized (Life Technologies, Bleiswijk, The Netherlands) harboring the yeast codon-optimized genes (codon, promoter, terminator and 2 unique 80 bp flanks that included an EcoRV sites at each end). The codon-optimized plant genes were flanked by different promoter and terminator combinations to prevent plasmid instability due to homologous recombination. Prior to transformation-associated recombination, the synthesized fragments were digested from the cloning vector using EcoRV and gel purified. The pAG416GPD-ccdB backbone fragment and the 3 gene cassettes atPAL1, coC4H and coCPR were mixed at a ratio of 1:2:2:2 (50ng :100ng; 100ng: 100ng) and transformed to CEN.PK2-1C. Colonies were selected on glucose synthetic medium plates in the absence of uracil and checked by multiplex PCR using the primers FK105 – FK112. After plasmid isolation, retransformation to E. coli and subsequent plasmid purification, the structure of the resulting plasmid pUDE172 (Genbank accession number: JX268037) was verified using restriction analysis.

The A. thaliana CHI1 gene was amplified using primers FK7/8 from plasmid pUNI.U21762 (Table 2), and then agarose gel purified and digested using SpeI and SalI. The restricted fragment was ligated into an SpeI and SalI linearized pAG305-GPD-ccdB plasmid. The A. thaliana 4CL3 gene was amplified using primers FK9/10 from pDZ.4CL3, purified and then ligated into p426TEF (Table 2) using SpeI and SalI. Subsequently, the P_TEF-at4CL3-T_TEF cassette was amplified using primer FK11/12, purified and ligated into a NaeI digested and FastAP (Thermo Scientific, Etten-Leur, The Netherlands) treated pUDI053, yielding pUDI060. The A. thaliana CHS3 gene was amplified using primer FK13/14, purified and ligated into p426TPI (Table 2) using SpeI and XhoI yielding pUDE101. The P_TPI-atCHS3-T_ADH cassette was amplified using primer FK15/16, purified and digested by SacI. The resulting fragment was ligated into SacI digested and FastAP treated pUDI060 plasmid, yielding pUDI061. A fragment of the PYK2 gene (1-710bp) was amplified from the CEN.PK2-1C genome using primer FK29/30, and then purified and digested using PfoI. This fragment was ligated into pUDI061 plasmid that had been digested by PfoI and treated with alkaline phosphatase (FastAP, Thermo Scientific) yielding pUDI065 (Genbank accession number: JX268039). The resulting plasmid was linearized using NcoI and integrated into the chromosomal PYK2 locus.

The tal1 gene from R. capsulatus[48,79], was codon optimized for yeast using JCat [78], and synthesized (GeneScript, Piscataway, NJ). The synthetic cotal1 was amplified using primers FK52/53 and ligated into pAG304-ccdB using SpeI and XhoI resulting in pUDI069 (Genbank accession number: JX268036). Integration of this plasmid into the trp1 locus was preceded by linearization using EcoRV.

A DNA fragment containing the custom-synthesized, yeast codon-optimized CHS3 sequence (Life Technologies, Bleiswijk, The Netherlands) was amplified using primers FK169/170 and ligated into both a pAG325GPD-ccdB and p426TEF (Table 2) using SpeI and XhoI yielding respectively, pUDE185 and 186. Subsequently, the P_TEF-coCHS3-T_TEF cassette was amplified using primers FK 171/172 and restricted using SacI. This cassette was ligated into a SacI digested and FastAP (Thermo Scientific) treated pUDE185. Plasmids were screened for opposing gene orientation by restriction analysis, yielding pUDE188 (Genbank accession number: JX268038).

Molecular biology procedures

PCR amplification was performed using Phusion® Hot Start II High Fidelity Polymerase (Thermo Scientific) according to the manufacturer's instructions in a Biometra TGradient Thermocycler (Biometra, Gottingen, Germany). Agarose gel separation was performed using 1% (w/v) agarose (Sigma-Aldrich, Zwijdrecht, The Netherlands) gel in 1×TAE (40 mM Tris-acetate pH 8.0 and 1 mM EDTA). Isolation of agarose trapped fragments was performed using Zymoclean Gel DNA Recovery kit (Zymo Research, Orange, CA). Restriction endonucleases, DNA ligases and FastAP (Thermo Scientific) were used according to the manufacturer's instructions. Transformation and amplification of plasmids were performed in E. coli DH5α electrocompetent cells (Invitrogen, Carlsbad, CA) according to the manufacturer's instructions. Plasmids were isolated from E. coli with the Sigma GenElute Plasmid Miniprep Kit (Sigma-Aldrich). Alternatively, plasmid purification was performed using a Zymoprep™™ Yeast Plasmid Miniprep (Zymo Research). Sequencing of constructs was performed by Baseclear BV (Baseclear, Leiden, The Netherlands).

Cultivation and media

E. coli was grown at 37°C in Luria Broth medium containing the appropriate antibiotic, 100 μg·l^-1 ampicillin or 50 μg·l^-1 kanamycin (Sigma-Aldrich, Zwijndrecht, The Netherlands). S. cerevisiae was grown at 30°C in medium containing demineralized water, 20 g·l^-1 glucose, 5 g·l^-1 (NH₄)₂SO₄, 3 g·l^-1 KH₂PO₄, 0.5 g·l^-1 MgSO₄.7H₂O, vitamins and trace elements [67]. The pH of the medium was set to 6.0 using KOH. Appropriate growth factors to supplement the auxotrophic requirements of the strains were added at 150 mg·l^-1 for uracil, 500 mg·l^-1 for leucine, 75 mg·l^-1 for tryptophan and 125 mg·l^-1 for histidine [68]. Unless otherwise stated, cultures were grown in 500 ml shake flasks with 100 ml medium by adding 1 ml frozen stock culture and incubating at 30°C in an Innova incubator shaker (New Brunswick Scientific, Edison, NJ) set at 200 rpm. Controlled aerobic batch cultures were grown at 30°C in 2l bioreactors (Applikon, Schiedam, The Netherlands), using a working volume of 1l. In the bioreactor experiments, the (NH₄)₂SO₄ concentration in the synthetic medium was increased to 10 g·l^-1 to avoid nitrogen depletion towards the end of the culture. Emulsion C antifoam at 0.05% (w/v) (Sigma-Aldrich, Zwijndrecht, The Netherlands) was added separately after autoclaving. The pH was maintained at pH 5.0 by automatic addition of either 2 M KOH or 2 M H₂SO₄, the stirrer speed was fixed at 800 rpm and the aeration rate was set at 500 ml·min^-1.

Analytical methods

Optical density was measured at 660 nm using a Libra S11 spectrophotometer (Biochrom, Cambridge, UK). Biomass dry weights were determined by filtration of 10 ml culture over dry, preweighed 0.45 μm nitrocellulose filters (Gelman Laboratory, Ann Arbor, USA). After removal of the medium, the filter was washed twice with demineralized water and dried for 20 min using a microwave set at 350 W. Glucose, ethanol, glycerol and acetate were analyzed using an Aminex HPX-87H ion exchange column (BioRad, Veenendaal, The Netherlands) operated at 60°C with 5 mM H₂SO₄ as mobile phase at a flow rate of 0.6 ml·min^-1. For measurement of phenylpropanoic compounds, culture samples were diluted with an equal volume of 100% ethanol. After vigorous mixing, cells were spun down at 13000 rpm in a Sorval Heraeus #3328 rotor for 2 min. The supernatant was analysed using HPLC. For phenylpropanoic compounds, measurements were made using a Waters 2695 separation module and a Waters 996 photodiode array detector. Phloretic acid, coumaric acid, phenyl ethanol, cinnamic acid and naringenin were measured respectively at 275, 309, 214, 277, 289 nm using an Agilent Zorbax SB-C18 Column (4.6 × 5.0, 3.5 micron) operating at 30^oC. A gradient of acetonitrile and 20 mM KH₂PO₄ (pH 2) with 1% acetonitrile was used as eluent, at a flow rate of 1 ml·min^-1, increasing from 0 to 10% acetonitrile in 6 min followed by an increase to 40% acetonitrile until 23 min. From 23 min to 27 min, the flow was set to 100% KH₂PO₄. Naringenin, coumaric acid, cinnamic acid, phloretic acid and phenylethanol standards were obtained from Sigma Aldrich (Sigma-Aldrich, Zwijndrecht, The Netherlands).

For analysis of carbon dioxide production in bioreactor cultures, the off-gas was first cooled in a condenser (2°C) and dried with a Perma Pure Dryer (Permapure, Toms River, NJ). CO₂ concentrations in the off-gas were then measured with a NGA 2000 Rosemount gas analyzer (Rosemount Analytical, Orrville,OH).

Identification of phenylpropanoid intermediates and naringenin was performed using liquid chromatography coupled to both photodiode-array detection and accurate mass quadrupole time-of-flight mass spectrometry (LC–PDA-QTOF MS) was performed using a Waters Alliance 2795 HPLC connected to a Waters 2996 PDA detector and subsequently a QTOF Ultima V4.00.00 mass spectrometer (Waters, MS technologies, UK) operating in negative ionization mode, an analytical column (Luna 3 μ C18/2 100A; 2.0 × 150 mm) attached to a C18 pre-column (2.0 × 4 mm; AJO-4286; both Phenomenex, USA). Eluents A (ultrapure water:formic acid (1000:1, v/v) ) and B (acetonitrile : formic acid (1000 : 1, v/v) ) were used at 0.19 ml.min. The gradient started at 5% B and increased linearly to 35% B in 45 min, after which the column was washed and equilibrated for 15 min before the next injection. The injection volume was 5 μl. Leucine enkephalin ([M-H]- = 554.2620) was used as a lock mass for on-line accurate mass correction [80]. Data were recorded using MassLynx 4.0 software (Waters).

Co-expression correlation analysis of naringenin biosynthetic genes in A. thaliana

Expression correlation analysis was performed using the BAR Expression Angler [35]. Each candidate gene listed in Table 1 was used as “bait”, and expression was correlated over a set of 392 micro-array experiments generated using the ATH1 Affymetrix Whole Genome GeneChip, from the Nottingham Arabidopsis Stock Centre's microarray database [34]. Correlations between expression levels of genes from Table 1 were recorded when the Pearson correlation coefficient was above 0.6.