Machine learning-based monosaccharide profiling for tissue-specific classification of Wolfiporia extensa samples.

Machine learning (ML) has been used for many clinical decision-making processes and diagnostic procedures in bioinformatics applications. We examined eight algorithms, including linear discriminant analysis (LDA), logistic regression (LR), k-nearest neighbor (KNN), random forest (RF), gradient boosting machine (GBM), support vector machine (SVM), Naïve Bayes classifier (NB), and artificial neural network (ANN) models, to evaluate their classification and prediction capabilities for four tissue types in Wolfiporia extensa using their monosaccharide composition profiles. All 8 ML-based models were assessed as exemplary models with AUC exceeding 0.8. Five models, namely LDA, KNN, RF, GBM, and ANN, performed excellently in the four-tissue-type classification (AUC > 0.9). Additionally, all eight models were evaluated as good predictive models with AUC value > 0.8 in the three-tissue-type classification. Notably, all 8 ML-based methods outperformed the single linear discriminant analysis (LDA) plotting method. For large sample sizes, the ML-based methods perform better than traditional regression techniques and could potentially increase the accuracy in identifying tissue samples of W. extensa.

Structures of the xyloglucans in the monocotyledon family Araceae (aroids).

MAIN CONCLUSION: The xyloglucans of all aquatic Araceae species examined had unusual structures compared with those of other non-commelinid monocotyledon families previously examined. The aquatic Araceae species Lemna minor was earlier shown to have xyloglucans with a different structure from the fucogalactoxyloglucans of other non-commelinid monocotyledons. We investigated 26 Araceae species (including L. minor), from five of the seven subfamilies. All seven aquatic species examined had xyloglucans that were unusual in having one or two of three features: < 77% XXXG core motif [L. minor (Lemnoideae) and Orontium aquaticum (Orontioideae)]; no fucosylation [L. minor (Lemnoideae), Cryptocoryne aponogetonifolia, and Lagenandra ovata (Aroideae, Rheophytes clade)]; and > 14% oligosaccharide units with S or D side chains [Spirodela polyrhiza and Landoltia punctata (Lemnoideae) and Pistia stratiotes (Aroideae, Dracunculus clade)]. Orontioideae and Lemnoideae are the two most basal subfamilies, with all species being aquatic, and Aroideae is the most derived. Two terrestrial species [Dieffenbachia seguine and Spathicarpa hastifolia (Aroideae, Zantedeschia clade)] also had xyloglucans without fucose indicating this feature was not unique to aquatic species.

Structural compositions and biological activities of cell wall polysaccharides in the rhizome, stem, and leaf of Polygonatum odoratum (Mill.) Druce.

Polygonatum odoratum is a perennial rhizomatous medicinal plant and different plant parts have been used in the treatment of various ailments. Herein, we have investigated the structural compositions of rhizome, leaf, and stem cell walls. We found 30-44% of polysaccharides in these wall preparations were cyclohexanediaminetetraacetic acid (CDTA) extractable, the proportion of heteromannans (HMs) in the rhizome is nearly three-fold compared to that of the leave and stem. The pectic polysaccharides of the rhizome are also structurally more diverse, with arabinans and type I and type II arabinogalactans being richest as shown by linkage study of the sodium carbonate (Na2CO3) extract. In addition, the 2-linked Araf was rhizome-specific, suggesting the cell walls in the rhizome had adapted to a more complex structure compared to that of the leaf and stem. Water-soluble polysaccharide fractions were also investigated, high proportion of Man as in 4-linked Manp indicated high proportion of HMs. The 21.4 kDa pectic polysaccharides and HMs derived from rhizome cell walls induced specific immune response in mice macrophage cells producing IL-1α and hematopoietic growth factors GM-CSF and G-CSF in vitro.