LPS consists of three functionally distinct domains (Fig 1A) [3]: the lipophilic lipid A (LA), a di-glucosamine carrying four to seven fatty acids (FAs), is linked to an oligosaccharide core region that mostly carries an O-polysaccharide (OPS) consisting of a variable number of oligosaccharide repeats. OPS composition is highly diverse among bacterial species and strains. The FA pattern on the LA, as well as phosphorylation and other modifications on the LA, core oligosaccharide, or OPS, can also differ considerably. Thus, LPS structures vary substantially between bacterial species, likely due to adaptation to different environments and lifestyles, but also a single bacterial cell envelope comprises a mixture of different LPS variants with remarkable size and structural heterogeneity (Fig 1A) [2,3]. The primary stability and barrier functions of LPS are conferred by the rather conserved inner core-LA region [2]. Cross-linking of negative residues of the inner core and LA backbone through divalent cations (Mg²⁺/Ca²⁺) facilitates tight LPS packing, which is fundamental to bacterial outer membrane (OM) rigidity and low permeability (Fig 1A) [3]. The OPS chains are involved in adhesion processes and protect bacteria from hostile environments, e.g., host antibacterial agents, thereby promoting virulence [3]. Bacteria lacking OPS or negative core charges are generally non-virulent and cannot survive within animal or plant hosts [2,4].

In mammals, all LPS domains contribute to immune recognition (Table 1). OPSs trigger antibody production in the adaptive immune system which causes a selective pressure leading to extensive OPS diversification [2]. The LA domain is recognized in picomolar concentrations as PAMP by the innate immune system through different extra- and intracellular LPS sensors and induces inflammation (Fig 1B) [7,14]. Upon LPS binding, the TLR4/MD-2 (myeloid differentiation factor-2) complex triggers expression of pro-inflammatory mediators [14–17]. LPS binding to TLR4/MD-2 is facilitated by an LPS transfer cascade involving the serum protein LPS-binding protein (LBP), which extracts LA from the bacterial membrane, and the glycoprotein CD14 [18]. CD14 can also trigger LPS signaling independent of TLR4/MD-2 [14]. Cytosolic LPS/LA is further sensed through LPS-mediated activation of non-canonical inflammatory caspases (Fig 1B) [19]. Ultimately, LPS induces an array of defense responses such as activation of phagocytes and production of pro-inflammatory cytokines and interferones and antimicrobial peptides [6,7,14]. An exaggerated immune reaction to LA, also termed endotoxin, can result in sepsis and life-threatening septic shock [3,14]. In humans, enterobacterial LPS is the most potent activator of the TLR4/MD-2 and the caspase pathway, whereas Pseudomonas LPS is only a weak agonist because of structural differences within the LA (Fig 1A) [19–21].

LPS from different bacterial species also induces defense responses in various plant species, possibly through sensing of distinct epitopes by different perception systems (Table 1) [4,22–29]. The model plant Arabidopsis thaliana, for instance, responds with nitric oxide production, defense gene expression, and induced resistance to LPS from different bacteria, including Burkholderia cepacia, Xanthomonas campestris, Pseudomonas spp., and Escherichia coli [22,26,28,29]. Studies on plant LPS responses are difficult to compare (Table 1) [4,29], as different LPS preparations were used in different concentrations on diverse plant species. LPS cannot be synthesized but is extracted from complex bacterial cultures. This raised concerns about possible highly active contaminations in LPS preparations [1]. Isolated LPS might also cause unspecific stress to plants with increasing concentrations because of its amphiphilic nature. As LPS-sensing systems in plants remained genetically unidentified, these issues could not be undoubtedly resolved. Recently, however, it was found that the RLK LORE (LipoOligosaccharide-specific Reduced Elicitation), which belongs to the plant-specific class of bulb-type lectin S-domain-1 kinases (SD-RLKs), mediates sensitive perception of Pseudomonas and Xanthomonas LPS as PAMP in the model plant A. thaliana and other crucifers triggering typical PTI responses [30]. LORE loss-of-function mutant plants are insensitive to Pseudomonas and Xanthomonas LPS and hypersusceptible to P. syringae infection. Transient expression of LORE in LPS-insensitive tobacco plants confers LPS sensitivity, demonstrating a key function for LORE in sensing LPS. Chemical isolation of LA from P. aeruginosa LPS further proved that LA alone is sufficient to induce LORE-dependent PTI [30]. If LA directly binds to LORE, however, remains yet to be shown. Perception of the membrane-embedded LA might further require disaggregation from the bacterial membrane through unidentified LPS-binding plant proteins similar to those in mammals.

LORE specifically senses Pseudomonas and Xanthomonas but not the typical enterobacterial LPS, e.g., of E. coli [30]. Thus, both mammals and plants evolved to sense LPS via its LA domain, but, apparently, the detected epitopes are structurally distinct. Future studies will reveal which structural LA features determine the specificity of LORE-mediated LPS sensing in plants. Current data hint to an important role of the LA acylation pattern and phosphorylation [26,30,31]. As LORE does not detect enterobacterial or B. cepacia LPS, previously observed responses of A. thaliana to LPS from these species [22,28,29] cannot be mediated via LORE. It will be interesting to see, in the future, if other plant LPS immune sensors also target LA or other LPS epitopes and if they show a similar LPS recognition specificity as LORE.

Interestingly, plants possess several of the canonical LPS biosynthesis genes and produce LPS precursors resembling enterobacterial LPS, but their function is yet elusive [32]. Nevertheless, this might indicate a necessity for plants to evolve perception of a different, truly microbe-specific, LPS substructure to avoid auto-immunity against endogenous LPS-like compounds. Despite conceptual analogies, LA sensing with distinct epitope specificities in animals and plants through structurally unrelated receptors [14,17,19,30] further substantiates that plant and animal PAMP sensing evolved independently but might converge on predestined PAMP targets.

Many bacterial pathogens employ LPS structure alterations, either constitutive or through dynamic modifications, to adapt to changing environments and to avoid immune recognition [33]. According to different lifestyles, LPS modifications vary greatly between bacterial species but mostly affect the LA and inner core [33]. Negative LA/core charges are crucial for OM stability and LPS-TLR4/MD-2 interactions. They are targeted by host-derived cationic antimicrobial peptides (CAMPs), an ancient defense mechanism of vertebrates and plants, to interfere with LPS cross-linking [3,20,33]. Bacteria can mask negative LA/core charges by attaching cationic moieties resulting in increased CAMP resistance and impaired TLR4/MD-2 immune sensing [33]. Thus, plant-pathogenic bacteria may also deploy LPS modifications as a virulence strategy to enhance resistance to antibacterial host compounds and to interfere with immune detection. The common sensing of PAMPs such as flagellin or LPS by plants and animals allows pathogens to deploy similar virulence strategies to colonize animal as well as plant hosts [12,34].

LPS has important functions in host–bacteria interactions, from shielding bacteria against adverse environments to host immune sensing [1,2], which are exerted by specific LPS part structures that can additionally be modified for adaptation to changing environments encountered during host colonization [20,33]. Studies on LPS structures and functions in plants, as well as the underlying genetic repertoire of plant-associated bacteria, will shed light on the evolutionary forces driving the recognition of the LA domain with distinct structural preferences as PAMP in animals and plants. On the practical side, understanding LPS immune sensing and LPS virulence functions of economically important plant pathogens, e.g., Pseudomonas, Xanthomonas, Erwinia, Ralstonia, or Xylella [35], will help to develop antibacterial tools and to improve disease resistance in crop plants in the future.