Attention mechanism-enhanced graph convolutional neural network for unbalanced lithology identification.

In this study, we propose a novel method for identifying lithology using an attention mechanism-enhanced graph convolutional neural network (AGCN). The aim of this method is to address the limitations of traditional approaches that evaluate unbalanced lithology by improving the identification of thin layers and small samples, while providing reliable data support for reservoir evaluation. To achieve this goal, we begin by using Principal Component Analysis (PCA) with maximum and minimum distance clustering (Max-min-distance) to correct the logging curves, which compensates for the low resolution of thin layers and enhances the accuracy of stratigraphic representation. Subsequently, we transform the logging data into graph-structured data by connecting distance similarity points and feature similarity points of the logging samples. We then use the graph convolutional network (GCN) to identify lithology, leveraging both labeled and unlabeled data to enhance the ability to identify lithology in small sample datasets. Additionally, our model incorporates a channel and spatial attention mechanism that assigns weights to the graph structure during lithology identification, improving the model's capability to discern differences across samples. To evaluate the performance of our model, we constructed a lithology dataset comprising five wells and conducted experiments. The results indicate that our approach achieves a maximum accuracy of 97.67%, surpassing the performance of a singlestructure model in lithology identification. In conclusion, our proposed method provides a promising and effective approach for unbalanced lithology identification, significantly improving accuracy levels.

Cloning, Yeast Expression, and Characterization of a ß-Amyrin C-28 Oxidase (CYP716A249) Involved in Triterpenoid Biosynthesis in Polygala tenuifolia.

Polygala tenuifolia Willd. is a traditional Chinese herbal medicine that is widely used in treating nervous system disorders. Triterpene saponins in P. tenuifolia (polygala saponins) have excellent biological activity. As a precursor for the synthesis of presenegin, oleanolic acid (OA) plays an important role in the biosynthesis of polygala saponins. However, the mechanism behind the biosynthesis of polygala saponins remains to be elucidated. In this study, we found that CYP716A249 (GenBank: ASB17946) oxidized the C-28 position of ß-amyrin to produce OA. Using quantitative real-time PCR, we observed that CYP716A249 had the highest expression in the roots of 2-year-old P. tenuifolia, which provided a basis for the selection of samples for gene cloning. To identify the function of CYP716A249, the strain R-BE-20 was constructed by expressing ß-amyrin synthase in yeast. Then, CYP716A249 was co-expressed with ß-amyrin synthase to construct the strain R-BPE-20 by using the lithium acetate method. Finally, we detected ß-amyrin and OA by ultra-HPLC-Q Exactive hybrid quadrupole-Orbitrap high-resolution accurate mass spectrometry and GC-MS. The results of this study provide insights into the biosynthesis pathway of polygala saponins.

[Analysis of influencing factors of secondary metabolites contents in cultivated Polygala tenuifolia].

This work was launched to explore the effect of habitat and growth year on the secondary metabolites contents of cultivated Polygala tenuifolia. The samples of cultivated P. tenuifolia were analyzed by ultra-high performance liquid chromatography(UPLC)-quadrupole time-of-flight mass spectrometry(Q-TOF MS), and the obtained data were analyzed using multiple statistical analysis and cluster analysis. The results showed that compared with growth year, habitat is a main influencing factor which affected the secondary metabolites contents of P. tenuifolia. The contents of sucrose esters and oligosacchride multi-esters are greatly dependent on the habitat (the sample-AG with high levels of components of tenuifoliside B and tenuifoliside C, and the sample-FY with high levels of 3,6'-disinapoyl sucrose, tenuifoliose S, tenuifoliose L, and tenuifoliose V). There is no obvious effect of habitat and growth year on xanthone. The contents of triterpene saponins are greatly dependent on the growth year, and the content of parts of triterpene saponins increased as time goes on.The result indicated that the effect of habitat and growth year on different types of secondary metabolites is not completely equivalent. This study will contribute to the breeding of P. tenuifolia and amendment of current commodity criteria.

Utilization of UPLC/Q-TOF-MS-Based Metabolomics and AFLP-Based Marker-Assisted Selection to Facilitate/Assist Conventional Breeding of Polygala tenuifolia.

As one of the most important traditional Chinese medicine, the quality of Polygala tenuifolia is difficult to control and a new method must be established to facilitate/assist the breeding of P. tenuifolia. In this study, UPLC/Q-TOF-MS-based metabolomics analysis was performed to determine the chemical composition and screen metabolite biomarkers according to agronomic traits. A total of 29 compounds and 18 metabolite biomarkers were found. AFLP-based marker-assisted selection (MAS) was used to identify molecular marker bands and screen characteristic bands associated with specific agronomic traits. 184 bands and 76 characteristic AFLP bands were found. The correlation network between compounds and characteristic AFLP bands was built, so we may directly breed certain P. tenuifolia herbs with special agronomic traits (or characteristic AFLP bands), which exhibit specific pharmacological functions depending on the content of the active compounds. The proposed method of metabolomics coupled with MAS could facilitate/assist the breeding of P. tenuifolia.

[Rationality of commodity criteria and traditional breeding of Polygala tenuifolia based on agronomic traits and determination of chemical components].

The agronomic traits (plant height, root diameter, root length, first lateral root height, lateral root amount, root weight) of 18 Polygala tenuifolia samples with different agronomic traits were analyzed, respectively. HPLC was used to analyze three main characteristic components including tenuifolin, polygalaxanthone Ⅲ, and 3,6'-disinapoyl sucrose. At last, the correlation between six agronomic traits and three main characteristic components were analyzed by scatter plot. We found no significant correlation between root diameter and three main characteristic components. There were no obvious correlations between tenuifolin and the remaining five agronomic traits. Short root length and first lateral root height as well as high lateral root amount resulted in high levels of polygalaxanthone Ⅲ in P. tenuifolia samples. High levels of 3,6'-disinapoyl sucrose were observed in P. tenuifolia samples with longer root. So, the current commodity criteria and traditional breeding of P. tenuifolia did not conform to pharmacopoeia standards, which excellent medicinal materials should have high contents of the main characteristic components. It was urgent to revise the current commodity criteria and breeding methods.

[Analysis of digital gene expression profiles of the cultivated Polygala tenuifolia in different phenological phases].

The content changes of chemical components in different phenological phase of the cultivated Polygala tenuifolia is one of the important factors for determination of the best harvest time in the production practice. In this study, the digital gene expression (DGE) profiles of the cultivated P. tenuifolia were analyzed in different phenological phase (flowering fruit bearing stage, wilting stage, dormancy stage). The differentially expressed genes were found in the biosynthesis of chemical composition in P. tenuifolia, and the representational ones were validated by RT-q PCR. Then, the key enzymes(CYP450s and UGTs) involved in the downstream of the triterpenoid saponins biosynthesis pathway in P. tenuifolia were predicted through the correlation analysis of gene expression. The number of down-regulated genes was more than that of up-regulated in P. tenuifolia from flowering fruit bearing stage to dormancy stage. Six differentially expressed genes (HMGS, PMK, FPPS, SQS, SE, ß-AS) and five (PAL, C4 H, 4CL, CAD, peroxidase) were annotated to the triterpenoid saponins and phenylpropanoid biosynthesis pathway in P. tenuifolia, respectively. Compared to wilting and dormancy stages, the saponins, xanthones, and lignins were largely synthesized at the flowering fruit bearing stage of P. tenuifolia. Furthermore, UGT83A1, CYP716B1, CYP98A3, CYP86B1, and CYP94A1 may be the part of key enzymes in the downstream of the triterpenoid saponins biosynthesis pathway in P. tenuifolia. This study provides evidence to support the correctness of traditional harvest time of P. tenuifolia at the level of transcription, and lays the scientific foundation for gene cloning and functional verification of CYP450 s and UGTs in the downstream of the triterpenoid saponins biosynthesis pathway in P. tenuifolia in the future.

[UPLC/Q-TOF MS-Based Metabolomics Analysis of Chemical uiterences in Different Polygala tenuifolia Varieties].

OBJECTIVE: The chemical differences of Polygala tenuifolia varieties-JinYuan 1 (JY1), FenYuan 2 (FY2) and traditional FenYang (FY) were studied, in order to provide reference for the breeding of Polygala tenuifolia. METHODS: The samples of JY1, FY2 and FY were subjected to ultra-high performance liquid chromatography (UPLC) quadrupole time-of-flight mass spectrometry (Q-TOF MS) analysis. The obtained data were analyzed using Principal Component Analysis (PCA) and other statistical analysis methods, and differential metabolites were further figured out. RESULTS: Compared with FY,sucrose esters (such as sibiricoses A5 and tenuifoliside B) and oligosaccharides (such as tenuifoliose K) in JY1 and FY2 contributed more to the separation of Polygala tenuifolia varieties in the PCA score plot. Compared with JYl, The sugar esters (such as tenuifoliside B and tenuifoliside A) and oligosaccharides( such as tenuifoliose A) in the FY2 also contributed more to the separation of Polygala tenuifolia varieties in the PCA score plot. In addition, the relative contents of sibiricaxanthone A,3,6'-disinapoly sucrose and senegin III showed significant differences among FY, JY1 and FY2. CONCLUSION: As new Polygala tenuifolia varieties, JY1 and FY2 had certain differences and respective advantages on the chemical composition compared with FY,which could provide data support for the directional breeding of Polygala tenuifolia based on the contents of some active compounds.

[Study on quality assessment of Polygalae Radix based on HPLC-DAD fingerprint].

OBJECTIVE: To establish an HPLC fingerprint to evaluate the quality of Polygalae Radix, root xylem, and those collected in different growth ages or harvest time. METHOD: Separation was performed at 30 °C on a Kromasil C18 column (4.6 mm x 250 mm, 5 µm); the mobile phases was acetonitrile and 0.05% H3PO4 water in the gradient elution; the flow rate was set at 1.0 mL · min(-1) and the detection wavelength at 314 nm; the quality discriminant analyses were accomplished by means of similarity analysis, cluster analysis, principal component analysis and neural network model. RESULT: In 26 batches of Polygalae Radix, 24 batches fingerprint similarities were above 0.8. In 5 different growth or harvest time batches, 4 batches were above 0.8; in 8 batches root xylem samples, the similarities were all above 0.875. The similarity analysis was in accord with the quality discriminant analysis of cluster analysis, principal component analysis and neural network model. CONCLUSION: Fingerprint combined with chemical pattern recognition technique can effectively evaluate the quality of Polygalae Radix. The active substance species are all similar in cultivated, wild, different growth or harvest time Polygalae Radix and polygala root xylem, but the chromatography peak areas are different. The effective material contents are similar between wild and cultivated Polygalae Radix, but each chromatographic peak area of the root xylem is much smaller than that of Polygalae Radix. The chemical substance accumulation mainly depends on harvest month, but little growth time in Polygalae Radix.