Plants are exposed to a variety of disease causing organisms, including viruses, bacteria, fungi, oomycetes, nematodes, insects, and parasitic plants [1], [2]. Yet, one concept in plant pathology is that in general plants are resistant to most pathogens. Plants have evolved a defense system that enables them to produce compounds that affect microbes in various ways. Some of these compounds are broad spectrum, whereas others are not. Among such defence compounds are phytoalexins, which are antimicrobial specialized metabolites that are induced under stress conditions or upon infection by a pathogen [3]–[5]. The spectrum of action of phytoalexins remains poorly understood and, surprisingly, their contribution to species-level (also known as nonhost) resistance is not always fully appreciated.

One well-studied phytoalexin is capsidiol, which is produced by the solanaceous plants Capsicum annuum (pepper) or Nicotiana tabacum (tobacco) after infection by pathogens such as the oomycete Phytophthora capsici [6], [7]. Remarkably, capsidiol affects diverse pathogens such as fungi and oomycetes. [3]–[6], [8]–[11]. Capsidiol is a bicyclic sesquiterpenoid compound and member of the isoprenoid class of phytoalexins. Like all sesquiterpenes, capsidiol derives from a common substrate farnesyl diphosphate (FPP) [12]. Two key enzymes are responsible for the biosynthesis of capsidiol. 5-epi-aristolochene synthase (EAS) catalyzes the cyclization of FPP to the intermediate 5-epi-aristolochene, then 5-epi-aristolochene dihydroxylase (EAH) mediates the two hydroxylation steps at positions C-1 and C-3 of 5-epi-aristolochene to yield capsidiol [13]. The dihydroxylase works in parallel with a cytochrome P450 reductase (CPR; NADPH-ferrihemoprotein reductase), which transfers electron equivalents for EAH reactions.

The oomycete genus Phytophthora includes some of the most destructive plant pathogens [14]. Several Phytophthora spp. infect solanaceous plants, including important crops like potato, tomato and pepper. Two of the most notorious species are the potato and tomato late blight pathogen Phytophthora infestans and the vegetable pathogen P. capsici. Both P. infestans and P. capsici have emerged as model systems to study oomycete pathogens and they have been extensively studied at the genomic level [15]–[19]. These species follow a hemibiotrophic life style and adopt two separate phases during infection. In the early stage of infection, both pathogens need living host cells. This biotrophic phase is followed by extensive necrosis of host tissue (necrotrophic phase) [20]. The host range of P. infestans is limited to solanaceous plants, particularly potato and tomato, whereas P. capsici affects a wide range of hosts in the Cucurbitaceae, Fabaceae, and Solanaceae families [14]. Although these two Phytophthora species share a common host in tomato, P. infestans cannot infect several host plants of P. capsici, notably pepper. Nonhost resistance to P. infestans is associated with a plant localized cell death response also known as the hypersensitive response (HR) [21].

The molecular basis of host-specificity of Phytophthora species, such as P. infestans and P. capsici is unknown. Although disease resistance genes that operate at the nonhost level are likely to be implicated [22], early work has also suggested a role for phytoalexins. For example, in the 1970s, several studies have shown that capsidiol has differential activity against P. infestans and P. capsici [4], [5]. Jones et al. showed that P. infestans is more sensitive (∼10 fold) to capsidiol than P. capsici, both in spore germination and growth assays [4]. Jones et al. also showed that, below a certain threshold, capsidiol has a reversible effect on both Phytophthora species [4]. This level of capsidiol is only reached in vivo in pepper varieties that are resistant to P. capsici, which led the authors to suggest sensitivity to capsidiol and differential accumulation of this phytoalexin might determine host susceptibility [23]. Apart from these pioneering studies that date back to the 1970s, only few publications have examined the role of capsidiol in Phytophthora pathosystems except to use it as a marker for defense [6], [8], [10], [24]. Nonetheless, Shibata et al. showed that silencing of NbEAS and NbEAH, two ethylene-regulated genes for capsidiol biosynthesis, negatively impact the resistance of Nicotiana benthamiana against P. infestans suggesting a positive role of capsidiol in this interaction [25], [26].

In this study, we revisited the effect of capsidiol on P. infestans and P. capsici, and the variation in sensitivity to this phytoalexin. Compared to the earlier studies [4], [11], [23], [27] we used highly pure preparations obtained from yeast engineered to express the capsidiol biosynthetic pathway [28]. We also assayed the effect of capsidiol on both mycelial growth and zoospores, using a novel fluorescence-based assay taking advantage of transgenic Phytophthora strains expressing fluorescent markers for biomass quantification. We confirmed major differences in capsidiol sensitivity between P. infestans and P. capsici. We also showed that capsidiol alters the growth behaviour of both Phytophthora species. Finally, we monitored the intraspecific variation within P. infestans isolates to capsidiol.

In this work, we developed new assays to examine the effect of the phytoalexin capsidiol on two Phytophthora species with differing host ranges. Our results are overall consistent with a 1975 report [4] that P. infestans is more sensitive to capsidiol than P. capsici using highly pure preparations of capsidiol. A major (>10-fold) differential effect of capsidiol between species was noted using both mycelial and zoospore assays. Considering that this phytoalexin is produced by pepper but not potato, our findings are consistent with the hypothesis that capsidiol contributes to nonhost resistance of pepper to P. infestans.

Previous studies used capsidiol purified from pepper fruits or tobacco cell cultures [4], [11], [23], [27]. We used a recently developed method to produce highly pure capsidiol synthesized in yeast [28]. This reduced the likelihood that contaminating phytochemicals may have affected the experiments. It allowed us to directly test the effect of capsidiol on Phytophthora species and helped us to more accurately estimate the inhibitory doses of capsidiol on Phytophthora growth. Furthermore, we took advantage of fluorescently labelled Phytophthora strains to measure biomass and growth. Although our findings are consistent with the earlier studies, we could more accurately estimate the difference in sensitivity. We found that 120 µM of capsidiol completely inhibited growth of P. infestans both in mycelial and zoospore assays, whereas Jones et al. concluded that this effect started at 200 µM of capsidiol [4]. Furthermore, in our mycelial plug assays P. capsici was not completely inhibited even at a concentration of 2 mM capsidiol, whereas according to Jones et al. 1.5 mM is a completely inhibitory concentration [4]. However, these differences are probably due to the assays used. Our zoospore assays were more consistent with the results of Jones et al. who concluded that capsidiol has a fungistatic effect at 3.75 mM and is fungitoxic at concentrations that exceed 5 mM [4], [23]. We also found that the difference in sensitivity to capsidiol between the two Phytophthora species is approximately 13 fold, which is in agreement with earlier studies that showed P. capsici to be at least 10 times more resistant to capsidiol than P. infestans [4]. Finally we extended our studies and showed that the level of sensitivity between different P. infestans isolates varies, providing a basis for studying the underlying genetic variation.

Earlier studies have showed that similar to capsidiol, other phytoalexins show a differential toxicity to phytopathogenic fungi. Hargreaves et al. [34] showed that the major phytoalexins from Vicia faba including isoflavoinoid medicarpin and wyerone acid had a greater impact on germ tubes produced by the necrotrophic fungus Botrytis cinerea, than B. fabae. They further highlighted a differential toxicity in wyerone derivatives than medicarpin [34]. Also, another study on the effect of the phytoalexins pisatin and maackiain from garden pea and red clover, respectively, against 19 fungal species revealed that nonhost phytoalexins have a greater effect inhibiting growth of the pathogens tested than the phytoalexins naturally occurring in the host [35]. These studies point out that differential activity of phytoalexins is a common phenomenon, and highlight the importance of understanding how different pathogens have evolved to cope with them.

What could be the nature of the differential effect of capsidiol on the two Phytophthora species? Ward and Stoessl [36] argued that P. capsici detoxification of capsidiol is unlikely and instead proposed that P. capsici does not induce high enough levels of capsidiol during infection of its host plant pepper [4], [36], [37]. Detoxification would probably involve oxidation of capsidiol to a less fungitoxic ketone, capsenone, as noted in in vitro assays with the fungi Botryris cinerea and Fusarium spp. [3], [36]. Importantly, capsenone was not detected in pepper tissue infected with P. capsici indicating that the pathogen may evade the phytoalexin by limiting its induction [36]. Alternatively, ATP-binding cassette (ABC) transporters may be involved as an efflux pump. Coleman et al. showed that the rot causing ascomycete Nectria haematococca can overcome the effect of the pea phytoalexin pisatin using a specific ABC transporter, NhABC1, that enhances the fungus tolerance to the phytoalexin [38]. Since there is no evidence that P. capsici can detoxify capsidiol [36], [37], P. capsici may rely on ABC transporters to cope with capsidiol. A more recent study on the role of ABC transporters in fungicide sensitivity in P. infestans failed to show correlation between up-regulation of ABC transporter genes in strains that are less sensitive to fungicides [39]. Whether inter- or intra-specific variation in expression of ABC transporter genes explains differences in capsidiol sensitivity in Phytophthora remains to be determined.

A genetic difference in the target of capsidiol could underpin the difference in sensitivity between the P. capsici and P. infestans. De Marino et al. [40] showed that capsidiol has a bacteriostatic effect against the human gastritis pathogen Helicobacter pylori in vitro but the mode of action remains unknown. It would be interesting to identify the molecules that are targeted by capsidiol in Phytophthora. Given that the genome sequences of P. capsici and P. infestans are available [15], [41], [42], a promising approach would be to determine transcriptome dynamics in response to capsidiol. From an evolutionary perspective, it would be of great interest to examine the response of Phytophthora to other sesquiterpenes that emerged during the functional divergence of terpene synthases in solanaceous plants [43].

The differences in capsidiol sensitivity observed among various P. infestans isolates reflect the remarkable level of diversity noted in this highly adaptable plant pathogen species [18], [21]. This variation is similar to what has been noted for sensitivity to fungicides in P. infestans and other oomycetes [44]–[46]. In some cases the genetic basis of chemical sensitivity has been identified. Randall et al. determined that sequence polymorphisms in the large subunit of RNA polymerase I (RPA190) contributes to P. infestans insensitivity to the oomycete-specific control chemical Mefenoxam [44]. Also, Blum et al. demonstrated that for two oomycetes, the causal agent of downy mildew in grape, Plasmopara viticola and P. infestans, an amino acid change in a protein known to be involved in cellulose biosynthesis (PiCESA3 and PvCESA3 in the two pathogens respectively) confers insensitivity to Mandipropamide [45], [46].

We observed that sensitivity to capsidiol ranged ∼5 fold in the P. infestans isolates tested. Is there a biological significance for these differences? Although potato does not produce capsidiol, it is possible that P. infestans has evolved mechanisms to tolerate other terpenoids produced by potato, which might contribute to host immunity. Indeed, potato is known to accumulate rishitin, another bicyclic sesquiterpene phytoalexin that is related to capsidiol [22]. In the future, it would be interesting to examine whether there is any correlation between aggressiveness and tolerance to capsidiol among various P. infestans isolates.

Finally, our work points to a biotechnological approach to engineer resistance to P. infestans. Genetic manipulation of capsidiol production in Nicotiana benthamiana, a P. infestans host plant that produces capsidiol, has already indicated that this phytoalexin contributes to disease resistance [25], [26]. Interestingly, P. capsici is markedly more aggressive pathogen of N. benthamiana than P. infestans [29], possibly because it can tolerate the capsidiol produced by this plant. Ultimately, capsidiol biosynthetic genes could be transferred from pepper or tobacco to potato and tomato as a potential strategy for disease resistance against P. infestans.