ParaCPI: A Parallel Graph Convolutional Network for Compound-Protein Interaction Prediction.

Identifying compound-protein interactions (CPIs) is critical in drug discovery, as accurate prediction of CPIs can remarkably reduce the time and cost of new drug development. The rapid growth of existing biological knowledge has opened up possibilities for leveraging known biological knowledge to predict unknown CPIs. However, existing CPI prediction models still fall short of meeting the needs of practical drug discovery applications. A novel parallel graph convolutional network model for CPI prediction (ParaCPI) is proposed in this study. This model constructs feature representation of compounds using a unique approach to predict unknown CPIs from known CPI data more effectively. Experiments are conducted on five public datasets, and the results are compared with current state-of-the-art (SOTA) models under three different experimental settings to evaluate the model's performance. In the three cold-start settings, ParaCPI achieves an average performance gain of 26.75%, 23.84%, and 14.68% in terms of area under the curve compared with the other SOTA models. In addition, the results of the experiments in the case study show ParaCPI's superior ability to predict unknown CPIs based on known data, with higher accuracy and stronger generalization compared with the SOTA models. Researchers can leverage ParaCPI to accelerate the drug discovery process.

MTTLm6A: A multi-task transfer learning approach for base-resolution mRNA m6A site prediction based on an improved transformer.

N6-methyladenosine (m6A) is a crucial RNA modification involved in various biological activities. Computational methods have been developed for the detection of m6A sites in Saccharomyces cerevisiae at base-resolution due to their cost-effectiveness and efficiency. However, the generalization of these methods has been hindered by limited base-resolution datasets. Additionally, RMBase contains a vast number of low-resolution m6A sites for Saccharomyces cerevisiae, and base-resolution sites are often inferred from these low-resolution results through post-calibration. We propose MTTLm6A, a multi-task transfer learning approach for base-resolution mRNA m6A site prediction based on an improved transformer. First, the RNA sequences are encoded by using one-hot encoding. Then, we construct a multi-task model that combines a convolutional neural network with a multi-head-attention deep framework. This model not only detects low-resolution m6A sites, it also assigns reasonable probabilities to the predicted sites. Finally, we employ transfer learning to predict base-resolution m6A sites based on the low-resolution m6A sites. Experimental results on Saccharomyces cerevisiae m6A and Homo sapiens m1A data demonstrate that MTTLm6A respectively achieved area under the receiver operating characteristic (AUROC) values of 77.13% and 92.9%, outperforming the state-of-the-art models. At the same time, it shows that the model has strong generalization ability. To enhance user convenience, we have made a user-friendly web server for MTTLm6A publicly available at http://47.242.23.141/MTTLm6A/index.php.

MSCAN: multi-scale self- and cross-attention network for RNA methylation site prediction.

BACKGROUND: Epi-transcriptome regulation through post-transcriptional RNA modifications is essential for all RNA types. Precise recognition of RNA modifications is critical for understanding their functions and regulatory mechanisms. However, wet experimental methods are often costly and time-consuming, limiting their wide range of applications. Therefore, recent research has focused on developing computational methods, particularly deep learning (DL). Bidirectional long short-term memory (BiLSTM), convolutional neural network (CNN), and the transformer have demonstrated achievements in modification site prediction. However, BiLSTM cannot achieve parallel computation, leading to a long training time, CNN cannot learn the dependencies of the long distance of the sequence, and the Transformer lacks information interaction with sequences at different scales. This insight underscores the necessity for continued research and development in natural language processing (NLP) and DL to devise an enhanced prediction framework that can effectively address the challenges presented. RESULTS: This study presents a multi-scale self- and cross-attention network (MSCAN) to identify the RNA methylation site using an NLP and DL way. Experiment results on twelve RNA modification sites (m6A, m1A, m5C, m5U, m6Am, m7G, Ψ, I, Am, Cm, Gm, and Um) reveal that the area under the receiver operating characteristic of MSCAN obtains respectively 98.34%, 85.41%, 97.29%, 96.74%, 99.04%, 79.94%, 76.22%, 65.69%, 92.92%, 92.03%, 95.77%, 89.66%, which is better than the state-of-the-art prediction model. This indicates that the model has strong generalization capabilities. Furthermore, MSCAN reveals a strong association among different types of RNA modifications from an experimental perspective. A user-friendly web server for predicting twelve widely occurring human RNA modification sites (m6A, m1A, m5C, m5U, m6Am, m7G, Ψ, I, Am, Cm, Gm, and Um) is available at http://47.242.23.141/MSCAN/index.php . CONCLUSIONS: A predictor framework has been developed through binary classification to predict RNA methylation sites.

Characterization of metabolites of sweroside in rat urine using ultra-high-performance liquid chromatography combined with electrospray ionization quadrupole time-of-flight tandem mass spectrometry and NMR spectroscopy.

Sweroside, a major active iridoid in Swertia pseudochinensis Hara, is recognized as an effective agent in the treatment of liver injury. Based on previous reports, the relatively short half-life (64 min) and poor bioavailability (approximately 0.31%) in rats suggested that not only sweroside itself but also its metabolites could be responsible for the observed hepato-protective effect. However, few studies have been carried out on the metabolism of sweroside. Therefore, the present study aimed at identifying the metabolites of sweroside in rat urine after a single oral dose (100 mg/kg). With ultra-high-performance liquid chromatography coupled with electrospray ionization quadrupole time-of-flight tandem mass spectrometry (UHPLC/Q-TOF-MS), the metabolic profile revealed 11 metabolites in rat urine, including phase I, phase II and aglycone-related products. The chemical structures of metabolites were proposed based on accurate mass measurements of protonated or deprotonated molecules and their fragmentation patterns. Our findings showed that the aglycone of sweroside (M05) and its glucuronide conjugate (M06) were principal circulating metabolites in rats. While several other metabolic transformations, occurring via reduction, N-heterocyclization and N-acetylation after deglycosylation, were also observed. Two metabolites (M05 and M06) were isolated from the rat urine for structural elucidation and identifcation of reaction sites. Both M05 and M06 were characterized by (1)H, (13)C and two-dimensional nuclear magnetic resonance (NMR) spectroscopy. UHPLC/Q-TOF-MS analysis has provided an important analytical platform to gather metabolic profile of sweroside.

Microbial biotransformation of gentiopicroside by the endophytic fungus Penicillium crustosum 2T01Y01.

Endophytic fungi are symbiotic with plants and possess multienzyme systems showing promising metabolite potency with region selectivity and stereoselectivity. The aim of this study was to use these special microorganisms as an in vitro model to mimic the potential mammalian metabolites of a natural iridoid gentiopicroside (GPS, compound 1). The fungi isolated from a medicinal plant, Dendrobium candidum Wall. ex Lindl., were screened for their biotransformation abilities with GPS as the substrate, and one strain with high converting potency was identified as Penicillium crustosum 2T01Y01 on the basis of the sequence of the internal transcribed spacer of the ribosomal DNA region. Upon the optimized incubation of P. crustosum 2T01Y01 with the substrate, seven deglycosylated metabolites were detected by ultraperformance liquid chromatography/quadrupole time of flight mass spectrometry (UPLC/Q-TOF MS). Preparative-scale biotransformation with whole cells of the endophytic fungus resulted in the production of five metabolites, including three novel ones, 5α-(hydroxymethyl)-6ß-methyl-3,4,5,6-tetrahydropyrano[3,4-c]pyran-1(8H)-one (compound 2), (Z)-4-(1-hydroxybut-3-en-2-yl)-5,6-dihydropyran-2-one (compound 3), and (E)-4-(1-hydroxybut-3-en-2-yl)-5,6-dihydropyran-2-one (compound 4), along with two known ones, 5α-(hydroxymethyl)-6ß-methyl-1H,3H-5,6-dihydropyrano[3,4-c]pyran-1(3H)-one (compound 5) and 5α-(hydroxymethyl)-6α-methyl-5,6-dihydropyrano[3,4-c]pyran-1(3H)-one (compound 6), aided by nuclear magnetic resonance and high-resolution mass spectral analyses. The other two metabolites were tentatively identified by online UPLC/Q-TOF MS as 5-hydroxymethyl-5,6-dihydroisochromen-1-one (compound 7) and 5-hydroxymethyl-3,4,5,6-tetrahydroisochromen-1-one (compound 8), and compound 8 is a new metabolite. To test the metabolic mechanism, the ß-glucosidase activity of the fungus P. crustosum 2T01Y01 was assayed with ρ-nitrophenyl-ß-d-glucopyranoside as a probe substrate, and the pathway of GPS biotransformation by strain 2T01Y01 is proposed. In addition, the hepatoprotective activities of GPS and metabolite compounds 2, 5, and 6 against human hepatocyte line HL-7702 injury induced by hydrogen peroxide were evaluated.

Identification of bio-active metabolites of gentiopicroside by UPLC/Q-TOF MS and NMR.

Gentiopicroside (GPS), the main bioactive component in Gentiana scabra Bge., has attracted our attention owing to its high bioactivity, especially the treatment of hepatobiliary disorders. The aglycone form of GPS, a typical secoiridoid glycoside, is considered to be more readily absorbed than its parent drug. This study aimed to identify and characterize the metabolites after GPS incubated with ß-glucosidase in buffer solution at 37°C. Samples of biotransformed solution were collected and analyzed by ultraperformance liquid chromatography (UPLC)/quadrupole-time-of-flight mass spectrometry (Q-TOF MS). A total of four metabolites were detected: two were isolated and elucidated by preparative-HPLC and NMR techniques, and one of those four is reported for the first time. The mass spectral fragmentation pattern and accurate masses of metabolites were established on the basis of UPLC/Q-TOF MS analysis. Structure elucidation of metabolites was achieved by comparing their fragmentation pattern with that of the parent drug. A fairly possible metabolic pathway of GPS by ß-glucosidase was proposed. The hepatoprotective activities of metabolites M1 and M2 were investigated and the results showed that their hepatoprotective activities were higher than that of parent drug. Our results provided a meaningful basis for discovering lead compounds from biotransformation related to G. scabra Bge. in traditional Chinese medicine.