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.

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.

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.

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.

A gender specific risk assessment of coronary heart disease based on physical examination data.

Large-scale screening for the risk of coronary heart disease (CHD) is crucial for its prevention and management. Physical examination data has the advantages of wide coverage, large capacity, and easy collection. Therefore, here we report a gender-specific cascading system for risk assessment of CHD based on physical examination data. The dataset consists of 39,538 CHD patients and 640,465 healthy individuals from the Luzhou Health Commission in Sichuan, China. Fifty physical examination characteristics were considered, and after feature screening, ten risk factors were identified. To facilitate large-scale CHD risk screening, a CHD risk model was developed using a fully connected network (FCN). For males, the model achieves AUCs of 0.8671 and 0.8659, respectively on the independent test set and the external validation set. For females, the AUCs of the model are 0.8991 and 0.9006, respectively on the independent test set and the external validation set. Furthermore, to enhance the convenience and flexibility of the model in clinical and real-life scenarios, we established a CHD risk scorecard base on logistic regression (LR). The results show that, for both males and females, the AUCs of the scorecard on the independent test set and the external verification set are only slightly lower (<0.05) than those of the corresponding prediction model, indicating that the scorecard construction does not result in a significant loss of information. To promote CHD personal lifestyle management, an online CHD risk assessment system has been established, which can be freely accessed at http://lin-group.cn/server/CHD/index.html .

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.

Bitter-RF: A random forest machine model for recognizing bitter peptides.

Introduction: Bitter peptides are short peptides with potential medical applications. The huge potential behind its bitter taste remains to be tapped. To better explore the value of bitter peptides in practice, we need a more effective classification method for identifying bitter peptides. Methods: In this study, we developed a Random forest (RF)-based model, called Bitter-RF, using sequence information of the bitter peptide. Bitter-RF covers more comprehensive and extensive information by integrating 10 features extracted from the bitter peptides and achieves better results than the latest generation model on independent validation set. Results: The proposed model can improve the accurate classification of bitter peptides (AUROC = 0.98 on independent set test) and enrich the practical application of RF method in protein classification tasks which has not been used to build a prediction model for bitter peptides. Discussion: We hope the Bitter-RF could provide more conveniences to scholars for bitter peptide research.

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.

Risk prediction of diabetes and pre-diabetes based on physical examination data.

Diabetes is a metabolic disorder caused by insufficient insulin secretion and insulin secretion disorders. From health to diabetes, there are generally three stages: health, pre-diabetes and type 2 diabetes. Early diagnosis of diabetes is the most effective way to prevent and control diabetes and its complications. In this work, we collected the physical examination data from Beijing Physical Examination Center from January 2006 to December 2017, and divided the population into three groups according to the WHO (1999) Diabetes Diagnostic Standards: normal fasting plasma glucose (NFG) (FPG < 6.1 mmol/L), mildly impaired fasting plasma glucose (IFG) (6.1 mmol/L ≤ FPG < 7.0 mmol/L) and type 2 diabetes (T2DM) (FPG > 7.0 mmol/L). Finally, we obtained1,221,598 NFG samples, 285,965 IFG samples and 387,076 T2DM samples, with a total of 15 physical examination indexes. Furthermore, taking eXtreme Gradient Boosting (XGBoost), random forest (RF), Logistic Regression (LR), and Fully connected neural network (FCN) as classifiers, four models were constructed to distinguish NFG, IFG and T2DM. The comparison results show that XGBoost has the best performance, with AUC (macro) of 0.7874 and AUC (micro) of 0.8633. In addition, based on the XGBoost classifier, three binary classification models were also established to discriminate NFG from IFG, NFG from T2DM, IFG from T2DM. On the independent dataset, the AUCs were 0.7808, 0.8687, 0.7067, respectively. Finally, we analyzed the importance of the features and identified the risk factors associated with diabetes.

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.

[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.

iBLP: An XGBoost-Based Predictor for Identifying Bioluminescent Proteins.

Bioluminescent proteins (BLPs) are a class of proteins that widely distributed in many living organisms with various mechanisms of light emission including bioluminescence and chemiluminescence from luminous organisms. Bioluminescence has been commonly used in various analytical research methods of cellular processes, such as gene expression analysis, drug discovery, cellular imaging, and toxicity determination. However, the identification of bioluminescent proteins is challenging as they share poor sequence similarities among them. In this paper, we briefly reviewed the development of the computational identification of BLPs and subsequently proposed a novel predicting framework for identifying BLPs based on eXtreme gradient boosting algorithm (XGBoost) and using sequence-derived features. To train the models, we collected BLP data from bacteria, eukaryote, and archaea. Then, for getting more effective prediction models, we examined the performances of different feature extraction methods and their combinations as well as classification algorithms. Finally, based on the optimal model, a novel predictor named iBLP was constructed to identify BLPs. The robustness of iBLP has been proved by experiments on training and independent datasets. Comparison with other published method further demonstrated that the proposed method is powerful and could provide good performance for BLP identification. The webserver and software package for BLP identification are freely available at http://lin-group.cn/server/iBLP.

Production of herbicide-resistant medicinal plant Salvia miltiorrhiza transformed with the bar gene.

In this study, we successfully performed Agrobacterium-mediated genetic transformation of Salvia miltiorrhiza and produced herbicide-resistant transformants. Leaf discs of S. miltiorrhiza were infected with Agrobacterium tumefaciens EHA105 harboring pCAMBIA 3301. The pCAMBIA 3301 includes an intron-containing gus reporter and a bar selection marker. To increase stable transformation efficiency, a two-step selection was employed which consists of herbicide resistance and gus expression. Here, we put more attention to the screening step of herbicide resistance. The current study provides an efficient screening system for the transformed plant of S. miltiorrhiza harboring bar gene. To determine the most suitable phosphinothricin concentration for plant selection, non-transformed leaf discs were grown on selection media containing six different phosphinothricin concentrations (0, 0.2, 0.4, 0.6, 0.8, and 1.0 mg/l). Based on the above results of non-transformed calluses, the sensitivity of phosphinothricin (0, 0.4, 0.8, 1.2, 1.6 mg/l) was tested in the screening of transgenic S. miltiorrhiza. We identified that 0.6 mg/l phosphinothricin should be suitable for selecting putatively transformed callus because non-transformed callus growth was effectively inhibited under this concentrations. When sprayed with Basta, the transgenic S. miltiorrhiza plants were tolerant to the herbicide. Hence, we report successful transformation of the bar gene conferring herbicide resistance to S. miltiorrhiza.

The prediction of protein structural class using averaged chemical shifts.

Knowledge of protein structural class can provide important information about its folding patterns. Many approaches have been developed for the prediction of protein structural classes. However, the information used by these approaches is primarily based on amino acid sequences. In this study, a novel method is presented to predict protein structural classes by use of chemical shift (CS) information derived from nuclear magnetic resonance spectra. Firstly, 399 non-homologue (about 15% identity) proteins were constructed to investigate the distribution of averaged CS values of six nuclei ((13)CO, (13)Cα, (13)Cß, (1)HN, (1)Hα and (15)N) in three protein structural classes. Subsequently, support vector machine was proposed to predict three protein structural classes by using averaged CS information of six nuclei. Overall accuracy of jackknife cross-validation achieves 87.0%. Finally, the feature selection technique is applied to exclude redundant information and find out an optimized feature set. Results show that the overall accuracy increased to 88.0% by using the averaged CSs of (13)CO, (1)Hα and (15)N. The proposed approach outperformed other state-of-the-art methods in terms of predictive accuracy in particular for low-similarity protein data. We expect that our proposed approach will be an excellent alternative to traditional methods for protein structural class prediction.

Antioxidant activities of Dracocephalum tanguticum maxim extract and its up-regulation on the expression of neurotrophic factors in a rat model of permanent focal cerebral ischemia.

The aim of this study was to investigate the effect of a BuOH-soluble fraction from Dracocephalum tanguticum Maxim (DME), which contained 52% of total flavonoid, on the cerebral ischemia injury induced by permanent middle cerebral artery occlusion (pMCAO) in rats. RT-PCR and Western blot analysis showed that DME (30 mg/kg/day for seven days) by intragastric administration modulated the mRNA expression and protein synthesis of two neurotrophic factors: brain-derived neurotrophic factor (BDNF) and neurotrophin 3 (NT-3). DME was effective in stimulating BDNF mRNA expression and protein synthesis in the ipsilateral frontal cortex (IFC) of both the sham-operated and pMCAO rats and this effect was also observed in the hippocampus of the pMCAO rats. DME significantly increased NT-3 mRNA expression and protein synthesis in the IFC and hippocampus of the pMCAO rats, although it had no effect on NT-3 expression in the sham-operated groups. Meanwhile, DME also decreased the malondialdehyde contents in the hippocampus of the sham-operated and pMCAO groups, and significantly attenuated the decrease of endogenous antioxidant (superoxide dismutase, glutathione peroxidase and catalase) activities in both the IFC and hippocampus of the rats after ischemia insult injury. Moreover, DME facilitated the neurobehavioral recovery after the cerebral ischemia. These findings suggested that DME has potential for treatment of ischemia-induced brain damage through stimulation of antioxidant activity and neurotrophic factor synthesis.

[Identification, characterization and utilization of simple sequence repeat markers derived from Salvia miltiorrhiza expressed sequence tags].

Despite Salvia miltiorrhiza being one of the most important medicine plants in China, there is a limited availability of genomic resources, especially of the expressed sequence tag-based markers. In this study, we selected and characterized functional markers in S. miltiorrhiza, which consisted of 4,192 non-redundant expressed sequence tags (ESTs) from 10,288 identified S. miltiorrhiza ESTs in dbEST data bank. Among them, 159 simple sequence repeats (SSR) were detected, which amounted to 3.79% of the non-redundant starting sequence population. This incidence was equivalent to one EST-SSR in every 12.74 kb of S. miltiorrhiza ESTs. Among the different motifs ranging from 1 bp to 6 bp, di-nucleotide repeat motif was the most abundant (77, 48.43%), followed by tri-nucleotide (41, 25.79%), hexa-nucleotide (23, 14.47%), penta-nucleotide (12, 7.55%) and tetra-nucleotide (6, 3.77%). In 47 identified motif types, the detected frequency above 5% were GA/CT (16.35%), AG/TC (15.09%), TCA/AGT (10.69%), AT/TA (6.29%), GAAAAG/CAAAAC (6.29%) and TA/AT (5.03%). Based on flank sequence of detected SSR, a total of 83 EST-SSR primer pairs were designed and tested for the amplification efficiency, polymorphism and transferability in thirteen S. mihiorrhiza samples and other ten species from the genus Salvia. The results showed that 72 primer pairs were successfully amplified in S. miltiorrhiza samples to yield and 279 loci with an average of 3.88 loci per primer pair. The cross-transferability of S. miltiorrhiza EST-SSR markers to other ten Salvia plants was very high, ranging from 60% to 100% with an average of 85%. Further analysis of the genetic similarity based on the polymorphic bands showed the EST-SSR could detect the genetic diversity on different levels among the whole test samples and distinguish the S. miltiorrhiza from other Salvia plants effectively. It is expected that the potential markers described here would add to the repertoire of DNA markers needed for genetic analysis, linkage mapping and comparative genomics studies in S. miltiorrhiza and related Salvia genus plants.

[Identification and phylogenetic application of unique nucleotide sequence of nad7 intron2 in Rhodiola (Crassulaceae) species].

Genetic characterization of 9 populations of Rhodiola crenulata, R. fastigiata and R. sachalinensis (Crassulaceae) species from Sichuan and Jilin Provinces of China, was investigated using the conserved primer of nad7 intron 2. All PCR products about 800 bp long were shorter than other Crassulaceae plants, which were used as molecular markers to identify the Rhodiola species. The sequence of the products indicated that total exon of 53 bp and intron of 738 bp exhibit only 9 nucleotide variations. Blasting the nad7 sequences to GenBank and the phylogenetic analysis showed that the sequence of Rhodiola species was clusted independently, and the length was smaller than all the registered sequences of higher plants. The result suggests that the Rhiodola species had a unique sequence in this gene region, which might be related to the special growth condition.

[Sequence variation of chloroplast gene infA-rpl36 region occurred in some Triticeae species].

Based on the sequenced wheat chloroplast genome (cpDNA), a pair of primers in infA-rp136 region was designed and used to amplify DNA from 12 diploid or polyploid Triticeae species. The 12 PCR products were cloned and sequenced. The resulting sequences ranged from 584 to 601 bp. DNA sequence analysis revealed that variation was higher in their intergenic regions than in their coding regions. Among these 12 species, the DNA sequence of coding region of infA gene showed homology as high as 97 percent, indicating that the infA gene is highly conserved among species. However, substantial deletions and insertions were found in 5 out of 12 deduced amino acid sequences, confirming that infA is one of the most evolutionally active cpDNA genes. Whereas the low variation was observed in rp136 gene, implying that the different genes has different evolutionary speed. The constructed phylogenetic trees demonstrate that the polyploidy species Thinopyrum intermedium might have different origin of cytoplasm, and their cytoplasm origins are as complex as their nuclear genome origins.

Studies on genome relationship and species-specific PCR marker for Dasypyrum breviaristatum in Triticeae.

Dasypyrum breviaristatum and nine related species in Triticeae were analyzed using the random amplified polymorphic DNA (RAPD) technique, in order to understand the genetic relationship and to develop species specific markers. The genome relationship dendrogram shows that D. breviaristatum and D. villosum could not be grouped together, indicating that D. breviaristatum was unlikely to be directly derived from D. villosum, while D. breviaristatum was closest to Thinopyrum intermedium, which implied that they might have similar breeding behaviors when introducing their chromatins into wheat. A D. breviaristatum genome specific RAPD product of 1182bp, was cloned and designated as pDb12H. Sequence analysis revealed that pDb12H was strongly homologuos to a long terminal repeat (LTR) Sabrina retrotransposon newly reported in Hordeum. The pDb12H was converted into a PCR based marker, which allows effectively monitoring the D. breviaristatum chromatin introgression into wheat. Fluorescence in situ hybridization (FISH) suggested that pDb12H was specifically hybridized throughout all D. breviaristatum chromosomes arms except for the terminal and centromeric regions, which can be used to characterize wheat -D. breviaristatum chromosome translocation. The genomes repetitive element will also be useful to study gene interactions between the wheat and alien genomes after the polyploidization.