Prediction of blood-brain barrier penetrating peptides based on data augmentation with Augur.

BACKGROUND: The blood-brain barrier serves as a critical interface between the bloodstream and brain tissue, mainly composed of pericytes, neurons, endothelial cells, and tightly connected basal membranes. It plays a pivotal role in safeguarding brain from harmful substances, thus protecting the integrity of the nervous system and preserving overall brain homeostasis. However, this remarkable selective transmission also poses a formidable challenge in the realm of central nervous system diseases treatment, hindering the delivery of large-molecule drugs into the brain. In response to this challenge, many researchers have devoted themselves to developing drug delivery systems capable of breaching the blood-brain barrier. Among these, blood-brain barrier penetrating peptides have emerged as promising candidates. These peptides had the advantages of high biosafety, ease of synthesis, and exceptional penetration efficiency, making them an effective drug delivery solution. While previous studies have developed a few prediction models for blood-brain barrier penetrating peptides, their performance has often been hampered by issue of limited positive data. RESULTS: In this study, we present Augur, a novel prediction model using borderline-SMOTE-based data augmentation and machine learning. we extract highly interpretable physicochemical properties of blood-brain barrier penetrating peptides while solving the issues of small sample size and imbalance of positive and negative samples. Experimental results demonstrate the superior prediction performance of Augur with an AUC value of 0.932 on the training set and 0.931 on the independent test set. CONCLUSIONS: This newly developed Augur model demonstrates superior performance in predicting blood-brain barrier penetrating peptides, offering valuable insights for drug development targeting neurological disorders. This breakthrough may enhance the efficiency of peptide-based drug discovery and pave the way for innovative treatment strategies for central nervous system diseases.

iRice-MS: An integrated XGBoost model for detecting multitype post-translational modification sites in rice.

Post-translational modification (PTM) refers to the covalent and enzymatic modification of proteins after protein biosynthesis, which orchestrates a variety of biological processes. Detecting PTM sites in proteome scale is one of the key steps to in-depth understanding their regulation mechanisms. In this study, we presented an integrated method based on eXtreme Gradient Boosting (XGBoost), called iRice-MS, to identify 2-hydroxyisobutyrylation, crotonylation, malonylation, ubiquitination, succinylation and acetylation in rice. For each PTM-specific model, we adopted eight feature encoding schemes, including sequence-based features, physicochemical property-based features and spatial mapping information-based features. The optimal feature set was identified from each encoding, and their respective models were established. Extensive experimental results show that iRice-MS always display excellent performance on 5-fold cross-validation and independent dataset test. In addition, our novel approach provides the superiority to other existing tools in terms of AUC value. Based on the proposed model, a web server named iRice-MS was established and is freely accessible at http://lin-group.cn/server/iRice-MS.

Anemoside B4, a new pyruvate carboxylase inhibitor, alleviates colitis by reprogramming macrophage function.

OBJECTIVES: Colitis is a global disease usually accompanied by intestinal epithelial damage and intestinal inflammation, and an increasing number of studies have found natural products to be highly effective in treating colitis. Anemoside B4 (AB4), an abundant saponin isolated from Pulsatilla chinensis (Bunge), which was found to have strong anti-inflammatory activity. However, the exact molecular mechanisms and direct targets of AB4 in the treatment of colitis remain to be discovered. METHODS: The anti-inflammatory activities of AB4 were verified in LPS-induced cell models and 2, 4, 6-trinitrobenzene sulfonic (TNBS) or dextran sulfate sodium (DSS)-induced colitis mice and rat models. The molecular target of AB4 was identified by affinity chromatography analysis using chemical probes derived from AB4. Experiments including proteomics, molecular docking, biotin pull-down, surface plasmon resonance (SPR), and cellular thermal shift assay (CETSA) were used to confirm the binding of AB4 to its molecular target. Overexpression of pyruvate carboxylase (PC) and PC agonist were used to study the effects of PC on the anti-inflammatory and metabolic regulation of AB4 in vitro and in vivo. RESULTS: AB4 not only significantly inhibited LPS-induced NF-κB activation and increased ROS levels in THP-1 cells, but also suppressed TNBS/DSS-induced colonic inflammation in mice and rats. The molecular target of AB4 was identified as PC, a key enzyme related to fatty acid, amino acid and tricarboxylic acid (TCA) cycle. We next demonstrated that AB4 specifically bound to the His879 site of PC and altered the protein's spatial conformation, thereby affecting the enzymatic activity of PC. LPS activated NF-κB pathway and increased PC activity, which caused metabolic reprogramming, while AB4 reversed this phenomenon by inhibiting the PC activity. In vivo studies showed that diisopropylamine dichloroacetate (DADA), a PC agonist, eliminated the therapeutic effects of AB4 by changing the metabolic rearrangement of intestinal tissues in colitis mice. CONCLUSION: We identified PC as a direct cellular target of AB4 in the modulation of inflammation, especially colitis. Moreover, PC/pyruvate metabolism/NF-κB is crucial for LPS-driven inflammation and oxidative stress. These findings shed more light on the possibilities of PC as a potential new target for treating colitis.

Research on Bitter Peptides in the Field of Bioinformatics: A Comprehensive Review.

Bitter peptides are small molecular peptides produced by the hydrolysis of proteins under acidic, alkaline, or enzymatic conditions. These peptides can enhance food flavor and offer various health benefits, with attributes such as antihypertensive, antidiabetic, antioxidant, antibacterial, and immune-regulating properties. They show significant potential in the development of functional foods and the prevention and treatment of diseases. This review introduces the diverse sources of bitter peptides and discusses the mechanisms of bitterness generation and their physiological functions in the taste system. Additionally, it emphasizes the application of bioinformatics in bitter peptide research, including the establishment and improvement of bitter peptide databases, the use of quantitative structure-activity relationship (QSAR) models to predict bitterness thresholds, and the latest advancements in classification prediction models built using machine learning and deep learning algorithms for bitter peptide identification. Future research directions include enhancing databases, diversifying models, and applying generative models to advance bitter peptide research towards deepening and discovering more practical applications.

iPADD: A Computational Tool for Predicting Potential Antidiabetic Drugs Using Machine Learning Algorithms.

Diabetes mellitus is a chronic metabolic disease, which causes an imbalance in blood glucose homeostasis and further leads to severe complications. With the increasing population of diabetes, there is an urgent need to develop drugs to treat diabetes. The development of artificial intelligence provides a powerful tool for accelerating the discovery of antidiabetic drugs. This work aims to establish a predictor called iPADD for discovering potential antidiabetic drugs. In the predictor, we used four kinds of molecular fingerprints and their combinations to encode the drugs and then adopted minimum-redundancy-maximum-relevance (mRMR) combined with an incremental feature selection strategy to screen optimal features. Based on the optimal feature subset, eight machine learning algorithms were applied to train models by using 5-fold cross-validation. The best model could produce an accuracy (Acc) of 0.983 with the area under the receiver operating characteristic curve (auROC) value of 0.989 on an independent test set. To further validate the performance of iPADD, we selected 65 natural products for case analysis, including 13 natural products in clinical trials as positive samples and 52 natural products as negative samples. Except for abscisic acid, our model can give correct prediction results. Molecular docking illustrated that quercetin and resveratrol stably bound with the diabetes target NR1I2. These results are consistent with the model prediction results of iPADD, indicating that the machine learning model has a strong generalization ability. The source code of iPADD is available at https://github.com/llllxw/iPADD.

Identification of adaptor proteins using the ANOVA feature selection technique.

The adaptor proteins play a crucially important role in regulating lymphocyte activation. Rapid and efficient identification of adaptor proteins is essential for understanding their functions. However, biochemical methods require not only expensive experimental costs, but also long experiment cycles and more personnel. Therefore, a computational method that could accurately identify adaptor proteins is urgently needed. To solve this issue, we developed a classifier that combined the support vector machine (SVM) with the composition of k-Spaced Amino Acid Pairs (CKSAAP) and the amino acid composition (AAC) to identify adaptor proteins. Analysis of variance (ANOVA) was used to select the optimized features which could generate the maximum prediction performance. By examining the proposed model on independent data, we found that the 447 optimized features could achieve an accuracy of 92.39% with an AUC of 0.9766, demonstrating the powerful capabilities of our model. We hope that the proposed model could provide more clues for studying adaptor proteins.

[Exploration on rationality evaluation approach of drug combination medication based on sequential analysis and machine learning].

Drug combination is a common clinical phenomenon. However, the scientific implementation of drug combination is li-mited by the weak rational evaluation that reflects its clinical characteristics. In order to break through the limitations of existing evaluation tools, examining drug-to-drug and drug-to-target action characteristics is proposed from the physical, chemical and biological perspectives, combining clinical multicenter case resources, domestic and international drug interaction public facilities with the aim of discovering the common rules of drug combination. Machine learning technology is employed to build a system for evaluating and predicting the rationality of clinical drug combinations based on "drug characteristics-repository information-artificial intelligence" strategy, which will be debugged and validated in multi-center clinical practice, with a view to providing new ideas and technical references for the safety and efficacy of clinical drug use.

Identification of Antifungal Bisphosphocholines from Medicinal Gentiana Species.

Gentiana species including G. crassicaulis, G. macrophylla, G. dahurica, and G. straminea are used in traditional Chinese medicine as "Qinjiao" for the treatment of rheumatism, hepatitis, and pain. Four antifungal bisphosphocholines [irlbacholine (2) and three new analogues, gentianalines A-C (1, 3, and 4)] were identified from G. crassicaulis by a bioassay-guided fractionation and structure elucidation approach. Subsequent chemical analysis of 56 "Qinjiao" samples (45 from G. crassicaulis, five from G. macrophylla, three from G. dahurica, and three from G. straminea) showed that bisphosphocholines were present in all four Gentiana species, with irlbacholine as the major compound ranging from 2.0 to 6.2 mg per gram of dried material. Irlbacholine exhibited potent in vitro antifungal activity against Cryptococcus neoformans, Aspergillus fumigatus, Candida albicans, and Candida glabrata with minimum inhibitory concentration (MIC) values of 0.63, 1.25, 10.0, and 5.0 µg/mL, respectively. Identification of the bisphosphocholines, a rare class of antifungal natural products, in these medicinal plants provides scientific evidence to complement their medicinal use. The bisphosphocholines carrying a long aliphatic chain possess amphiphilic molecule-like properties with a tendency of retention in both normal and reversed-phase silica gel column chromatography and thereby may be neglected in natural products discovery. This report may stimulate interest in this class of compounds, which warrant the further study of other biological activities as well.

Application of CRISPR-Cas12a temperature sensitivity for improved genome editing in rice, maize, and Arabidopsis.

BACKGROUND: CRISPR-Cas12a (formerly Cpf1) is an RNA-guided endonuclease with distinct features that have expanded genome editing capabilities. Cas12a-mediated genome editing is temperature sensitive in plants, but a lack of a comprehensive understanding on Cas12a temperature sensitivity in plant cells has hampered effective application of Cas12a nucleases in plant genome editing. RESULTS: We compared AsCas12a, FnCas12a, and LbCas12a for their editing efficiencies and non-homologous end joining (NHEJ) repair profiles at four different temperatures in rice. We found that AsCas12a is more sensitive to temperature and that it requires a temperature of over 28 °C for high activity. Each Cas12a nuclease exhibited distinct indel mutation profiles which were not affected by temperatures. For the first time, we successfully applied AsCas12a for generating rice mutants with high frequencies up to 93% among T0 lines. We next pursued editing in the dicot model plant Arabidopsis, for which Cas12a-based genome editing has not been previously demonstrated. While LbCas12a barely showed any editing activity at 22 °C, its editing activity was rescued by growing the transgenic plants at 29 °C. With an early high-temperature treatment regime, we successfully achieved germline editing at the two target genes, GL2 and TT4, in Arabidopsis transgenic lines. We then used high-temperature treatment to improve Cas12a-mediated genome editing in maize. By growing LbCas12a T0 maize lines at 28 °C, we obtained Cas12a-edited mutants at frequencies up to 100% in the T1 generation. Finally, we demonstrated DNA binding of Cas12a was not abolished at lower temperatures by using a dCas12a-SRDX-based transcriptional repression system in Arabidopsis. CONCLUSION: Our study demonstrates the use of high-temperature regimes to achieve high editing efficiencies with Cas12a systems in rice, Arabidopsis, and maize and sheds light on the mechanism of temperature sensitivity for Cas12a in plants.

Multiplex QTL editing of grain-related genes improves yield in elite rice varieties.

KEY MESSAGE: Significant yield increase has been achieved by simultaneous introduction of three trait-related QTLs in three rice varieties with multiplex editing by CRISPR-Cas9. Using traditional breeding approaches to develop new elite rice varieties with high yield and superior quality is challenging. It usually requires introduction of multiple trait-related quantitative trait loci (QTLs) into an elite background through multiple rounds of crossing and selection. CRISPR-Cas9-based multiplex editing of QTLs represents a new breeding strategy that is straightforward and cost effective. To test this approach, we simultaneously targeted three yield-related QTLs for editing in three elite rice varieties, namely J809, L237 and CNXJ. The chosen yield-related QTL genes are OsGS3, OsGW2 and OsGn1a, which have been identified to negatively regulate the grain size, width and weight, and number, respectively. Our approach rapidly generated all seven combinations of single, double and triple mutants for the target genes in elite backgrounds. Detailed analysis of these mutants revealed differential contributions of QTL mutations to yield performance such as grain length, width, number and 1000-grain weight. Overall, the contributions are additive, resulting in 68 and 30% yield per panicle increase in triple mutants of J809 and L237, respectively. Our data hence demonstrates a promising genome editing approach for rapid breeding of QTLs in elite crop varieties.

Comparative Transcriptome Analyses Reveal Potential Mechanisms of Enhanced Drought Tolerance in Transgenic Salvia Miltiorrhiza Plants Expressing AtDREB1A from Arabidopsis.

In our previous study, drought-resistant transgenic plants of Salvia miltiorrhiza were produced via overexpression of the transcription factor AtDREB1A. To unravel the molecular mechanisms underpinning elevated drought tolerance in transgenic plants, in the present study we compared the global transcriptional profiles of wild-type (WT) and AtDREB1A-expressing transgenic plants using RNA-sequencing (RNA-seq). Using cluster analysis, we identified 3904 differentially expressed genes (DEGs). Compared with WT plants, 423 unigenes were up-regulated in pRD29A::AtDREB1A-31 before drought treatment, while 936 were down-regulated and 1580 and 1313 unigenes were up- and down-regulated after six days of drought. COG analysis revealed that the 'signal transduction mechanisms' category was highly enriched among these DEGs both before and after drought stress. Based on the Kyoto Encyclopedia of Genes and Genomes (KEGG) annotation, DEGs associated with "ribosome", "plant hormone signal transduction", photosynthesis", "plant-pathogen interaction", "glycolysis/gluconeogenesis" and "carbon fixation" are hypothesized to perform major functions in drought resistance in AtDREB1A-expressing transgenic plants. Furthermore, the number of DEGs associated with different transcription factors increased significantly after drought stress, especially the AP2/ERF, bZIP and MYB protein families. Taken together, this study substantially expands the transcriptomic information for S. miltiorrhiza and provides valuable clues for elucidating the mechanism of AtDREB1A-mediated drought tolerance in transgenic plants.

Ectopic Expression of DREB Transcription Factor, AtDREB1A, Confers Tolerance to Drought in Transgenic Salvia miltiorrhiza.

Drought decreases crop productivity more than any other type of environmental stress. Transcription factors (TFs) play crucial roles in regulating plant abiotic stress responses. The Arabidopsis thaliana gene DREB1A/CBF3, encoding a stress-inducible TF, was introduced into Salvia miltiorrhiza Ectopic expression of AtDREB1A resulted in increased drought tolerance, and transgenic lines had higher relative water content and Chl content, and exhibited an increased photosynthetic rate when subjected to drought stress. AtDREB1A transgenic plants generally displayed lower malondialdehyde (MDA), but higher superoxide dismutase (SOD), catalase (CAT) and peroxidase (POD) activities under drought stress. In particular, plants with ectopic AtDREB1A expression under the control of the stress-induced RD29A promoter exhibited more tolerance to drought compared with p35S::AtDREB1A transgenic plants, without growth inhibition or phenotypic aberrations. Differential gene expression profiling of wild-type and pRD29A::AtDREB1A transgenic plants following drought stress revealed that the expression levels of various genes associated with the stress response, photosynthesis, signaling, carbohydrate metabolism and protein protection were substantially higher in transgenic plants. In addition, the amount of salvianolic acids and tanshinones was significantly elevated in AtDREB1A transgenic S. miltiorrhiza roots, and most of the genes in the related biosynthetic pathways were up-regulated. Together, these results demonstrated that inducing the expression of a TF can effectively regulate multiple genes in the stress response pathways and significantly improve the resistance of plants to abiotic stresses. Our results also suggest that genetic manipulation of a TF can improve production of valuable secondary metabolites by regulating genes in associated pathways.

Effective screen of CRISPR/Cas9-induced mutants in rice by single-strand conformation polymorphism.

KEY MESSAGE: A method based on DNA single-strand conformation polymorphism is demonstrated for effective genotyping of CRISPR/Cas9-induced mutants in rice. Clustered regularly interspaced short palindromic repeats (CRISPR)/CRISPR-associated 9 (Cas9) has been widely adopted for genome editing in many organisms. A large proportion of mutations generated by CRISPR/Cas9 are very small insertions and deletions (indels), presumably because Cas9 generates blunt-ended double-strand breaks which are subsequently repaired without extensive end-processing. CRISPR/Cas9 is highly effective for targeted mutagenesis in the important crop, rice. For example, homozygous mutant seedlings are commonly recovered from CRISPR/Cas9-treated calli. However, many current mutation detection methods are not very suitable for screening homozygous mutants that typically carry small indels. In this study, we tested a mutation detection method based on single-strand conformational polymorphism (SSCP). We found it can effectively detect small indels in pilot experiments. By applying the SSCP method for CRISRP-Cas9-mediated targeted mutagenesis in rice, we successfully identified multiple mutants of OsROC5 and OsDEP1. In conclusion, the SSCP analysis will be a useful genotyping method for rapid identification of CRISPR/Cas9-induced mutants, including the most desirable homozygous mutants. The method also has high potential for similar applications in other plant species.

Promoter analysis of the sweet potato ADP-glucose pyrophosphorylase gene IbAGP1 in Nicotiana tabacum.

KEY MESSAGE: The IbAGP1 gene of sweet potato ( Ipomoea batatas ) encodes the sucrose-inducible small subunit of ADP-glucose pyrophosphorylase. Through expression analysis of 5'-truncations and synthetic forms of the IbAGP1 promoter in transgenic tobacco, we show that SURE-Like elements and W-box elements of the promoter contribute to the sucrose inducibility of this gene. Sweet potato (Ipomoea batatas) contains two genes (IbAGP1 and IbAGP2) encoding the catalytically active small subunits of ADP-glucose pyrophosphorylase, an enzyme with an important role in regulating starch synthesis in higher plants. Previous studies have shown that IbAGP1 is expressed in the storage roots, leaves, and stem tissues of sweet potato, and its transcript is strongly induced by applying sucrose exogenously to detached leaves. To investigate the tissue-specific expression of the IbAGP1 promoter, a series of 5'-truncated promoters extending from bases -1913, -1598, -1298, -1053, -716, and -286 to base +75 were used to drive the expression of the ß-glucuronidase reporter gene (GUS) in tobacco plants (Nicotiana tabacum). Histochemical and fluorometric GUS assays showed that (1) GUS expression driven by the longest fragment (1989 bp) of the IbAGP1 promoter was detected in vegetative tissues (roots, stems, leaves), (2) fragments extending to -1053 or beyond retained strong GUS expression in roots, stems, and leaves, whereas further 5'-deletions resulted in considerable reduction in GUS activity, and (3) the series of 5'-truncated promoters responded differently to exogenously applied sucrose. The 1989-bp IbAGP1 promoter contains five sequences (two AATAAAA, one AATAAAAAA, and two AATAAATAAA) that are similar to sucrose-responsive elements (SURE). These SURE-Like sequences are found at nucleotide positions -1273, -1239, -681, -610, and -189. Moreover, putative W-box elements are found at positions -1985, -1434, -750, and -578. Synthetic promoters containing tandem repeats of the 4X SURE-Like or 4X W-box upstream from a minimal CaMV35S promoter-GUS fusion showed significant expression in transgenic tobacco in response to exogenous sucrose. These results show that SURE-Like elements and W-box elements of the IbAGP1 promoter contribute to the sucrose inducibility of this gene.

Comparative transcriptome analysis to reveal genes involved in wheat hybrid necrosis.

Wheat hybrid necrosis is an interesting genetic phenomenon that is found frequently and results in gradual death or loss of productivity of wheat. However, the molecular basis and mechanisms of this genetic phenomenon are still not well understood. In this study, the transcriptomes of wheat hybrid necrosis F1 and its parents (Neimai 8 and II469) were investigated using digital gene expression (DGE). A total of 1300 differentially expressed genes were identified, indicating that the response to hybrid necrosis in wheat is complicated. The assignments of the annotated genes based on Gene Ontology (GO) revealed that most of the up-regulated genes belong to "universal stress related", "DNA/RNA binding", "protein degradation" functional groups, while the down-regulated genes belong to "carbohydrate metabolism" and "translation regulation" functional groups. These findings suggest that these pathways were affected by hybrid necrosis. Our results provide preliminarily new insight into the underlying molecular mechanisms of hybrid necrosis and will help to identify important candidate genes involved in wheat hybrid necrosis.

Comprehensive untargeted lipidomics study of black morel (Morchella sextelata) at different growth stages.

The black morel (Morchella sextelata) is a valuable edible and medicinal mushroom appreciated worldwide. Here, lipidomic profiles and lipid dynamic changes during the growth of M. sexletata were analyzed using ultra-performance liquid chromatography coupled with mass spectrometry. 203 lipid molecules, including four categories and fourteen subclasses, were identified in mature fruiting bodies, with triacylglycerol being the most abundant (37.00 %). Fatty acid composition analysis revealed that linoleic acid was the major fatty acid among the free fatty acids, glycerolipids and glycerophospholipids. The relative concentration of lipids in M. sextelata changed significantly during its growth, from which 12 and 29 differential lipid molecules were screened out, respectively. Pathway analysis based on these differential lipids showed that glycerophospholipid metabolism was the major pathway involved in the growth of M. sextelata. Our study provides a comprehensive understanding of the lipids in M. sextelata and will facilitate the development and utilization of M. sextelata.

Predicting the role of the human gut microbiome in type 1 diabetes using machine-learning methods.

Gut microbes is a crucial factor in the pathogenesis of type 1 diabetes (T1D). However, it is still unclear which gut microbiota are the key factors affecting T1D and their influence on the development and progression of the disease. To fill these knowledge gaps, we constructed a model to find biomarker from gut microbiota in patients with T1D. We first identified microbial markers using Linear discriminant analysis Effect Size (LEfSe) and random forest (RF) methods. Furthermore, by constructing co-occurrence networks for gut microbes in T1D, we aimed to reveal all gut microbial interactions as well as major beneficial and pathogenic bacteria in healthy populations and type 1 diabetic patients. Finally, PICRUST2 was used to predict Kyoto Encyclopedia of Genes and Genomes (KEGG) functional pathways and KO gene levels of microbial markers to investigate the biological role. Our study revealed that 21 identified microbial genera are important biomarker for T1D. Their AUC values are 0.962 and 0.745 on discovery set and validation set. Functional analysis showed that 10 microbial genera were significantly positively associated with D-arginine and D-ornithine metabolism, spliceosome in transcription, steroid hormone biosynthesis and glycosaminoglycan degradation. These genera were significantly negatively correlated with steroid biosynthesis, cyanoamino acid metabolism and drug metabolism. The other 11 genera displayed an inverse correlation. In summary, our research identified a comprehensive set of T1D gut biomarkers with universal applicability and have revealed the biological consequences of alterations in gut microbiota and their interplay. These findings offer significant prospects for individualized management and treatment of T1D.

Antibiotic combinations prediction based on machine learning to multicentre clinical data and drug interaction correlation.

BACKGROUND: With increasing antibiotic resistance and regulation, the issue of antibiotic combination has been emphasised. However, antibiotic combination prescribing lacks a rapid identification of feasibility, while its risk of drug interactions is unclear. METHODS: We conducted statistical descriptions on 16 101 antibiotic coprescriptions for inpatients with bacterial infections from 2015 to 2023. By integrating the frequency and effectiveness of prescriptions, we formulated recommendations for the feasibility of antibiotic combinations. Initially, a machine learning algorithm was utilised to optimise grading thresholds and habits for antibiotic combinations. A feedforward neural network (FNN) algorithm was employed to develop antibiotic combination recommendation model (ACRM). To enhance interpretability, we combined sequential methods and DrugBank to explore the correlation between antibiotic combinations and drug interactions. RESULTS: A total of 55 antibiotics, covering 657 empirical clinical antibiotic combinations were used for ACRM construction. Model performance on the test dataset showed AUROCs of 0.589-0.895 for various antibiotic recommendation classes. The ACRM showed satisfactory clinical relevance with 61.54-73.33% prediction accuracy in a new independent retrospective cohort. Antibiotic interaction detection showed that the risk of drug interactions was 29.2% for strongly recommended and 43.5% for not recommended. A positive correlation was identified between the level of clinical recommendation and the risk of drug interactions. CONCLUSIONS: Machine learning modelling of retrospective antibiotic prescriptions habits has the potential to predict antibiotic combination recommendations. The ACRM plays a supporting role in reducing the incidence of drug interactions. Clinicians are encouraged to adopt such systems to improve the management of antibiotic usage and medication safety.

Predicting coronary heart disease in Chinese diabetics using machine learning.

Diabetes, a common chronic disease worldwide, can induce vascular complications, such as coronary heart disease (CHD), which is also one of the main causes of human death. It is of great significance to study the factors of diabetic patients complicated with CHD for understanding the occurrence of diabetes/CHD comorbidity. In this study, by analyzing the risk of CHD in more than 300,000 diabetes patients in southwest China, an artificial intelligence (AI) model was proposed to predict the risk of diabetes/CHD comorbidity. Firstly, we statistically analyzed the distribution of four types of features (basic demographic information, laboratory indicators, medical examination, and questionnaire) in comorbidities, and evaluated the predictive performance of three traditional machine learning methods (eXtreme Gradient Boosting, Random Forest, and Logistic regression). In addition, we have identified nine important features, including age, WHtR, BMI, stroke, smoking, chronic lung disease, drinking and MSP. Finally, the model produced an area under the receiver operating characteristic curve (AUC) of 0.701 on the test samples. These findings can provide personalized guidance for early CHD warning for diabetic populations.

Discovery of a New Anti-Inflammatory Agent from Anemoside B4 Derivatives and Its Therapeutic Effect on Colitis by Targeting Pyruvate Carboxylase.

Anemoside B4 (AB4), a triterpenoidal saponin from Pulsatilla chinensis, shows significant anti-inflammatory activity, and may be used for treating inflammatory bowel disease (IBD). Nevertheless, its application is limited due to its high molecular weight and pronounced water solubility. To discover new effective agents for treating IBD, we synthesized 28 AB4 derivatives and evaluated their cytotoxic and anti-inflammatory activities in vitro. Among them, A3-6 exhibited significantly superior anti-inflammatory activity compared to AB4. It showed a significant improvement in the symptoms of DSS-induced colitis in mice, with a notably lower oral effective dose compared to AB4. Furthermore, we discovered that A3-6 bound with pyruvate carboxylase (PC), then inhibited PC activity, reprogramming macrophage function, and alleviated colitis. These findings indicate that A3-6 is a promising therapeutic candidate for colitis, and PC may be a potential new target for treating colitis.