Machine learning and comparative genomics approaches for the discovery of xylose transporters in yeast

Abstract

Background: The need to mitigate and substitute the use of fossil fuels as the main energy matrix has led to the study and development of biofuels as an alternative. Second-generation (2G) ethanol arises as one biofuel with great potential, due to not only maintaining food security, but also as a product from economically interesting crops such as energy-cane. One of the main challenges of 2G ethanol is the inefficient uptake of pentose sugars by industrial yeast Saccharomyces cerevisiae, the main organism used for ethanol production. Understanding the main drivers for xylose assimilation and identify novel and efficient transporters is a key step to make the 2G process economically viable.

Results: By implementing a strategy of searching for present motifs that may be responsible for xylose transport and past adaptations of sugar transporters in xylose fermenting species, we obtained a classifying model which was successfully used to select four different candidate transporters for evaluation in the S. cerevisiae hxt-null strain, EBY.VW4000, harbouring the xylose consumption pathway. Yeast cells expressing the transporters SpX, SpH and SpG showed a superior uptake performance in xylose compared to traditional literature control Gxf1.

Conclusions: Modelling xylose transport with the small data available for yeast and bacteria proved a challenge that was overcome through different statistical strategies. Through this strategy, we present four novel xylose transporters which expands the repertoire of candidates targeting yeast genetic engineering for industrial fermentation. The repeated use of the model for characterizing new transporters will be useful both into finding the best candidates for industrial utilization and to increase the model's predictive capabilities.

Keywords: Feature selection; Industrial biotechnology; Machine learning; Pentose metabolism; Xylose; Xylose transporter.

Fig. 1

Graphical representations of machine learning model against the dataset. a Force-plot of most important features as calculated by Recursive Feature Elimination by Cross-Validation with XGBoost. Features highlighted in red are responsible for driving the final prediction of a sample into the positive category (A probable xylose transporter) while features in blue drive the prediction into the negative category (A non-xylose transporter). The base value represents the average prediction for the samples, while the size of the feature represents its impact (higher or lower importance). b Common metrics used to evaluate a model, the grey values correspond to the base threshold model and blue to the altered threshold. c Confusion matrix showing the results of predictions against the test data

Fig. 2

Snippet of fam10 phylogeny transformed into a cladogram for visualization purposes, coupled with the alignment around the site found under positive selection by MEME. In red are the transporters chosen for further characterization. Bootstraps are not shown as all of them on these clades were over 80

Fig. 3

Spot-assay of EBY_Xyl1 carrying each of the indicated transporters and growing in a different sugars and b different concentrations of xylose. Initial OD₆₀₀ was settled at 1 before the tenfold serial dilution. Plates were incubated in 30 °C. All experiments were performed in triplicate

Fig. 4

Comparative fermentation assays of EBY_Xyl1 expressing different transporters in xylose (full lines) or glucose (dashed lines). a Growth of EBY_Xyl1 during xylose fermentation. b Xylose consumption of EBY_Xyl1 cells expressing the transporters over time. Note that SpX does not appear clearly as it overlaps with SpG. c Growth of EBY_Xyl1 expressing SuL, GXF1 as positive control and pRS426 (empty vector) as negative control during xylose/glucose co-fermentation and d sugar consumption of EBY_Xyl1 expressing SuL, GXF1 as positive control and pRS426 (empty vector) as negative control during xylose/glucose co-fermentation (note that SuL glucose fermentation overlaps with GXF1)

Fig. 5

Superimposed structures of xylE coupled with xylose (blue) and predicted structures for the four xylose transporters and GXF1 (pink tones). The 2D representations show the probable interactions between xylose and amino acids in the binding site for each transporter