Linking genome content to biofuel production yields: a meta-analysis of major catabolic pathways among select H2 and ethanol-producing bacteria

Abstract

Background: Fermentative bacteria offer the potential to convert lignocellulosic waste-streams into biofuels such as hydrogen (H2) and ethanol. Current fermentative H2 and ethanol yields, however, are below theoretical maxima, vary greatly among organisms, and depend on the extent of metabolic pathways utilized. For fermentative H2 and/or ethanol production to become practical, biofuel yields must be increased. We performed a comparative meta-analysis of (i) reported end-product yields, and (ii) genes encoding pyruvate metabolism and end-product synthesis pathways to identify suitable biomarkers for screening a microorganism's potential of H2 and/or ethanol production, and to identify targets for metabolic engineering to improve biofuel yields. Our interest in H2 and/or ethanol optimization restricted our meta-analysis to organisms with sequenced genomes and limited branched end-product pathways. These included members of the Firmicutes, Euryarchaeota, and Thermotogae.

Results: Bioinformatic analysis revealed that the absence of genes encoding acetaldehyde dehydrogenase and bifunctional acetaldehyde/alcohol dehydrogenase (AdhE) in Caldicellulosiruptor, Thermococcus, Pyrococcus, and Thermotoga species coincide with high H2 yields and low ethanol production. Organisms containing genes (or activities) for both ethanol and H2 synthesis pathways (i.e. Caldanaerobacter subterraneus subsp. tengcongensis, Ethanoligenens harbinense, and Clostridium species) had relatively uniform mixed product patterns. The absence of hydrogenases in Geobacillus and Bacillus species did not confer high ethanol production, but rather high lactate production. Only Thermoanaerobacter pseudethanolicus produced relatively high ethanol and low H2 yields. This may be attributed to the presence of genes encoding proteins that promote NADH production. Lactate dehydrogenase and pyruvate:formate lyase are not conducive for ethanol and/or H2 production. While the type(s) of encoded hydrogenases appear to have little impact on H2 production in organisms that do not encode ethanol producing pathways, they do influence reduced end-product yields in those that do.

Conclusions: Here we show that composition of genes encoding pathways involved in pyruvate catabolism and end-product synthesis pathways can be used to approximate potential end-product distribution patterns. We have identified a number of genetic biomarkers for streamlining ethanol and H2 producing capabilities. By linking genome content, reaction thermodynamics, and end-product yields, we offer potential targets for optimization of either ethanol or H2 yields through metabolic engineering.

Figure 1

Comparison of putative gene products involved in pyruvate metabolism and end-product synthesis among select hydrogen and ethanol-producing species. Presence of putative gene products are indicated in matrix with respective letters corresponding to selected organism (see legend). Numbers indicate standard free energies of reaction (△G°’) corresponding to a particular enzyme. Abbreviations: PEPCK, phosphoenolpyruvate carboxykinase; OAADC, oxaloacetate decarboxylase; MDH, malate dehydrogenase; MalE, malic enzyme; PPK, pyruvate kinase; PPDK, pyruvate phosphate dikinase; LDH, lactate dehydrogenase; PFL, pyruvate formate lyase; PFOR, pyruvate:ferredoxin oxidoreductase; PDH, pyruvate dehydrogenase; ADH, alcohol dehydrogenase; ALDH, acetaldehyde dehydrogenase; AdhE, bifinctional acetaldehyde/alcohol dehydrogenase; ACK, acetate kinase; PTA, phosphotransacetylase; NFO, NADH:Fd oxidoreductase.

Figure 2

Differentiation between fermentation pathways that favor (A) hydrogen and (B) ethanol production based on comparative genomics and end-product profiles. Pathways that favor (green lines), disfavor (broken red lines), and appear to have little impact (black lines) on production of H₂ or ethanol are indicated. Correlation of reaction thermodynamics and genome content with reported end-product yields suggest that reduction, and subsequent reoxidation, of ferredoxin via PFOR and Fd-dependent (and/or bifurcating) H₂ases, respectively, support H₂ production. Alternatively, reduction, of NAD⁺ via PDH (and/or NADH generating uptake H₂ases) generate NADH conducive for ethanol production. Abbreviations (see figure 1 legend).