Development of a machine learning-based target-specific scoring function for structure-based binding affinity prediction for human dihydroorotate dehydrogenase inhibitors.

Human dihydroorotate dehydrogenase (hDHODH) is a flavin mononucleotide-dependent enzyme that can limit de novo pyrimidine synthesis, making it a therapeutic target for diseases such as autoimmune disorders and cancer. In this study, using the docking structures of complexes generated by AutoDock Vina, we integrate interaction features and ligand features, and employ support vector regression to develop a target-specific scoring function for hDHODH (TSSF-hDHODH). The Pearson correlation coefficient values of TSSF-hDHODH in the cross-validation and external validation are 0.86 and 0.74, respectively, both of which are far superior to those of classic scoring function AutoDock Vina and random forest (RF) based generic scoring function RF-Score. TSSF-hDHODH is further used for the virtual screening of potential inhibitors in the FDA-Approved & Pharmacopeia Drug Library. In conjunction with the results from molecular dynamics simulations, crizotinib is identified as a candidate for subsequent structural optimization. This study can be useful for the discovery of hDHODH inhibitors and the development of scoring functions for additional targets.

Construction of highly active and stable recombinant nattokinase by engineered bacteria and computational design.

Nattokinase (NK) is an enzyme that has been recognized as a new potential thrombolytic drug due to its strong thrombolytic activity. However, it is difficult to maintain the enzyme activity of NK during high temperature environment of industrial production. In this study, we constructed six NK mutants with potential for higher thermostability using a rational protein engineering strategy integrating free energy-based methods and molecular dynamics (MD) simulation. Then, wild-type NK and NK mutants were expressed in Escherichia coli (E. coli), and their thermostability and thrombolytic activity were tested. The results showed that, compared with wild-type NK, the mutants Y256P, Q206L and E156F all had improved thermostability. The optimal mutant Y256P showed a higher melting temperature (Tm) of 77.4 °C, an increase of 4 °C in maximum heat-resistant temperature and an increase of 51.8 % in activity at 37 °C compared with wild-type NK. Moreover, we also explored the mechanism of the increased thermostability of these mutants by analysing the MD trajectories under different simulation temperatures.

CBIL-VHPLI: a model for predicting viral-host protein-lncRNA interactions based on machine learning and transfer learning.

Virus‒host protein‒lncRNA interaction (VHPLI) predictions are critical for decoding the molecular mechanisms of viral pathogens and host immune processes. Although VHPLI interactions have been predicted in both plants and animals, they have not been extensively studied in viruses. For the first time, we propose a new deep learning-based approach that consists mainly of a convolutional neural network and bidirectional long and short-term memory network modules in combination with transfer learning named CBIL‒VHPLI to predict viral-host protein‒lncRNA interactions. The models were first trained on large and diverse datasets (including plants, animals, etc.). Protein sequence features were extracted using a k-mer method combined with the one-hot encoding and composition-transition-distribution (CTD) methods, and lncRNA sequence features were extracted using a k-mer method combined with the one-hot encoding and Z curve methods. The results obtained on three independent external validation datasets showed that the pre-trained CBIL‒VHPLI model performed the best with an accuracy of approximately 0.9. Pretraining was followed by conducting transfer learning on a viral protein-human lncRNA dataset, and the fine-tuning results showed that the accuracy of CBIL‒VHPLI was 0.946, which was significantly greater than that of the previous models. The final case study results showed that CBIL‒VHPLI achieved a prediction reproducibility rate of 91.6% for the RIP-Seq experimental screening results. This model was then used to predict the interactions between human lncRNA PIK3CD-AS2 and the nonstructural protein 1 (NS1) of the H5N1 virus, and RNA pull-down experiments were used to prove the prediction readiness of the model in terms of prediction. The source code of CBIL‒VHPLI and the datasets used in this work are available at https://github.com/Liu-Lab-Lnu/CBIL-VHPLI for academic usage.

Effects of the Nonstructural Protein-Nucleolar and Coiled-Body Phosphoprotein 1 Protein Interaction on rRNA Synthesis Through Telomeric Repeat-Binding Factor 2 Regulation Under Nucleolar Stress.

To investigate the effects and underlying molecular mechanisms of the interaction between the non-structural protein 1 (NS1) and nucleolar and coiled-body phosphoprotein 1 (NOLC1) on rRNA synthesis through nucleolar telomeric repeat-binding factor 2 (TRF2) under nucleolar stress in avian influenza A virus infection. The analysis of TRF2 ties into the exploration of ribosomal protein L11 (RPL11) and mouse double minute 2 (MDM2) because TRF2 has been found to interact with NOLC1, and the RPL11-MDM2 pathway plays an important role in nucleolar regulation and cellular processes. Both human embryonic kidney 293T cells and human lung adenocarcinoma A549 cells were transfected with the plasmids pCAGGS-HA and pCAGGS-HA-NS1, respectively. In addition, A549 cells were transfected with the plasmids pEGFP-N1, pEGFP-N1-NS1, and pDsRed2-N1-TRF2. The cell cycle was detected by flow cytometry, and coimmunoprecipitation was applied to examine the interactions between different proteins. The effect of NS1 on TRF2 was detected by immunoprecipitation, and the colocalization of NOLC1 and TRF2 or NS1 and TRF2 was visualized by immunofluorescence. Quantitative real-time PCR was conducted to detect the expression of the TRF2 and p21. There is a strong interaction between NOLC1 and TRF2, and the colocalization of NOLC1 and TRF2 in the nucleus. The protein expression of NOLC1 in A549-HA-NS1 cells was lower than that in A549-HA cells, which was accompanied by the upregulated protein expression of p53 in A549-HA-NS1 cells (all p < .05). TRF2 was scattered throughout the nucleus without clear nucleolar aggregation. RPL11 specifically interacted with MDM2 in the NS1 group, and expression of the p21 gene was significantly increased in the HA-NS1 group compared with the HA group (p < .01). NS1 protein can lead to the reduced aggregation of TRF2 in the nucleolus, inhibition of rRNA expression, and cell cycle blockade by interfering with the NOLC1 protein and generating nucleolar stress.

Study on the transport and internalisation mechanism of dietary supplement nattokinase in the small intestine using animal and Caco-2 cell monolayer models.

Maintaining proper blood flow is critical to promoting good health. Nattokinase is a serine protease from Bacillus subtilis that has significant in vitro thrombolytic activity, but its mechanism as a dietary supplement to prevent thrombosis through intestinal absorption and transport is still unclear.The purpose of this study is to study the transport and internalisation mechanism of NK in the small intestine using animal models and Caco-2 cell monolayer models.This study first evaluated the preventive effect of supplementing low dose (4000 FU (Fibrin Unit)/kg, n = 6), medium dose (8000 FU/kg, n = 6), and high dose (12000 FU/kg, n = 6) of nattokinase on carrageenan induced thrombosis in mice. Subsequently, we used the rat gut sac model, ligated intestinal loop model, and Caco-2 cell uptake model to study the intestinal transport mechanism of NK.Results indicate that NK is a moderately absorbed biomolecule whose transport through enterocytes is energy- and time-dependent. Chlorpromazine, nystatin and EIPA all inhibited the endocytosis of NK to varying degrees, indicating that the endocytosis of NK in Caco-2 cells involves macropinocytosis, clathrin-mediated and caveolae-mediated pathway. These findings offer a theoretical basis for investigating the mechanism of oral NK supplementation in greater depth.

Construction of an oxidative stress-related lncRNAs signature to predict prognosis and the immune response in gastric cancer.

Oxidative stress, as a characteristic of cellular aerobic metabolism, plays a crucial regulatory role in the development and metastasis of gastric cancer (GC). Long noncoding RNAs (lncRNAs) are important regulators in GC development. However, research on the prognostic patterns of oxidative stress-related lncRNAs (OSRLs) and their functions in the immune microenvironment is currently insufficient. We identified the OSRLs signature (DIP2A-IT1, DUXAP8, TP53TG1, SNHG5, AC091057.1, AL355001.1, ARRDC1-AS1, and COLCA1) from 185 oxidative stress-related genes in The Cancer Genome Atlas (TCGA) cohort via random survival forest and Cox analyses, and the results were subsequently validated in the Gene Expression Omnibus (GEO) dataset. The patients were divided into high- and low-risk groups by the risk score of the OSRLs signature. Longer overall survival was detected in the low-risk group than in the high-risk group in both the TCGA cohort (P < 0. 001, HR = 0.43, 95% CI 0.31-0.62) and the GEO cohort (P = 0.014, HR = 0.67, 95% CI 0.48-0.93). Next, multivariate Cox analysis identified that the risk model was an independent prognostic characteristic (HR > 1, P = 0.005), and time-dependent receiver operating characteristic (ROC) curve analysis and nomogram analysis were utilized to evaluate the predictive ability of the risk model. Next, gene set enrichment analysis revealed that the immune-related pathway, Wnt/[Formula: see text]-catenin signature, mammalian target of rapamycin complex 1 signature, and cytokine‒cytokine receptor interaction was enriched. High-risk patients were more responsive to CD200, TNFSF4, TNFSF9, and BTNL2 immune checkpoint blockade. The results of qRT‒PCR further proved the accuracy of our bioinformatic analysis. Overall, our study identified a novel OSRLs signature that can serve as a promising biomarker and prognostic indicator, which provides a personalized predictive approach for patient prognosis evaluation and treatment.

The preparation of polyclonal antibody against chlordimeform and establishment of detection by indirect competitive ELISA.

Objective: Chlordimeform is a chemical pesticide that is highly carcinogenic and toxic. The purpose of this study was to establish an enzyme-linked immunosorbent assay (ELISA) method for the detection of chlordimeform in aquaculture and fish farming. METHODS: Chlordimeform was coupled with bovine serum albumin (BSA) and ovalbumin (OVA) as carrier proteins. A chlordimeform-BSA conjugate was used as an immunogen, and chlordimeform-OVA was used as a coating antigen. Chlordimeform-BSA was used to immunize rabbits, and a polyclonal antibody was prepared. An indirect competitive enzyme-linked immunosorbent assay (IC-ELISA) was established to detect chlordimeform. RESULTS: The working range of the established IC-ELISA method for chlordimeform detection was 1-20 ng/mL. The IC50 was 3.126 ng/mL, and the lower limit of detection (LOD) of chlordimeform was 0.637 ng/mL. The recovery of chlordimeform from spiked water samples ranged from 81% to 107%. CONCLUSION: An anti-chlordimeform polyclonal antibody was successfully developed, and a novel IC-ELISA was established to detect chlordimeform in aquaculture.

Using Network Distance Analysis to Predict lncRNA-miRNA Interactions.

LncRNA-miRNA interactions contribute to the regulation of therapeutic targets and diagnostic biomarkers in multifarious human diseases. However, it remains difficult to experimentally identify lncRNA-miRNA associations at large scale, and computational prediction methods are limited. In this study, we developed a network distance analysis model for lncRNA-miRNA association prediction (NDALMA). Similarity networks for lncRNAs and miRNAs were calculated and integrated with Gaussian interaction profile (GIP) kernel similarity. Then, network distance analysis was applied to the integrated similarity networks, and final scores were obtained after confidence calculation and score conversion. Our model obtained satisfactory results in fivefold cross validation, achieving an AUC of 0.8810 and an AUPR of 0.8315. Moreover, NDALMA showed superior prediction performance over several other network algorithms, and we tested the suitability and flexibility of the model by comparing different types of similarity. In addition, case studies of the relationships between lncRNAs and miRNAs were conducted, which verified the reliability of our method in predicting lncRNA-miRNA associations. The datasets and source code used in this study are available at https://github.com/Liu-Lab-Lnu/NDALMA .

Prediction of the Blood-Brain Barrier (BBB) Permeability of Chemicals Based on Machine-Learning and Ensemble Methods.

The ability of chemicals to enter the blood-brain barrier (BBB) is a key factor for central nervous system (CNS) drug development. Although many models for BBB permeability prediction have been developed, they have insufficient accuracy (ACC) and sensitivity (SEN). To improve performance, ensemble models were built to predict the BBB permeability of compounds. In this study, in silico ensemble-learning models were developed using 3 machine-learning algorithms and 9 molecular fingerprints from 1757 chemicals (integrated from 2 published data sets) to predict BBB permeability. The best prediction performance of the base classifier models was achieved by a prediction model based on an random forest (RF) and a MACCS molecular fingerprint with an ACC of 0.910, an area under the receiver-operating characteristic (ROC) curve (AUC) of 0.957, a SEN of 0.927, and a specificity of 0.867 in 5-fold cross-validation. The prediction performance of the ensemble models is better than that of most of the base classifiers. The final ensemble model has also demonstrated good accuracy for an external validation and can be used for the early screening of CNS drugs.

Predicting the reproductive toxicity of chemicals using ensemble learning methods and molecular fingerprints.

Reproductive toxicity endpoints are a significant safety concern in the assessment of the adverse effects of chemicals in drug discovery. Computational models that can accurately predict a chemical's toxic potential are increasingly pursued to replace traditional animal experiments. Thus, ensemble learning models were built to predict the reproductive toxicity of compounds. Our ensemble models were developed using support vector machine, random forest, and extreme gradient boosting methods and 9 molecular fingerprints calculated for a dataset containing 1823 chemicals. The best prediction performance was achieved by the Ensemble-Top12 model, with an accuracy (ACC) of 86.33 %, a sensitivity (SEN) of 82.02 %, a specificity (SPE) of 90.19 %, and an area under the receiver operating characteristic curve (AUC) of 0.937 in 5-fold cross-validation and ACC, SEN, SPE, and AUC values of 84.38 %, 86.90 %, 90.67 %, and 0.920, respectively, in external validation. We also defined the applicability domain (AD) of the ensemble model by calculating the Tanimoto distance of the training set. Compared with models in existing literature, our ensemble model achieves relatively high ACC, SPE and AUC values. We also identified several fingerprint features related to chemical reproductive toxicity. Considering the performance of model, we recommend using the Ensemble-Top12 model to predict reproductive toxicity in early drug development.

MutagenPred-GCNNs: A Graph Convolutional Neural Network-Based Classification Model for Mutagenicity Prediction with Data-Driven Molecular Fingerprints.

An important task in the early stage of drug discovery is the identification of mutagenic compounds. Mutagenicity prediction models that can interpret relationships between toxicological endpoints and compound structures are especially favorable. In this research, we used an advanced graph convolutional neural network (GCNN) architecture to identify the molecular representation and develop predictive models based on these representations. The predictive model based on features extracted by GCNNs can not only predict the mutagenicity of compounds but also identify the structure alerts in compounds. In fivefold cross-validation and external validation, the highest area under the curve was 0.8782 and 0.8382, respectively; the highest accuracy (Q) was 80.98% and 76.63%, respectively; the highest sensitivity was 83.27% and 78.92%, respectively; and the highest specificity was 78.83% and 76.32%, respectively. Additionally, our model also identified some toxicophores, such as aromatic nitro, three-membered heterocycles, quinones, and nitrogen and sulfur mustard. These results indicate that GCNNs could learn the features of mutagens effectively. In summary, we developed a mutagenicity classification model with high predictive performance and interpretability based on a data-driven molecular representation trained through GCNNs.

Ensemble Learning Models Based on Noninvasive Features for Type 2 Diabetes Screening: Model Development and Validation.

BACKGROUND: Early diabetes screening can effectively reduce the burden of disease. However, natural population-based screening projects require a large number of resources. With the emergence and development of machine learning, researchers have started to pursue more flexible and efficient methods to screen or predict type 2 diabetes. OBJECTIVE: The aim of this study was to build prediction models based on the ensemble learning method for diabetes screening to further improve the health status of the population in a noninvasive and inexpensive manner. METHODS: The dataset for building and evaluating the diabetes prediction model was extracted from the National Health and Nutrition Examination Survey from 2011-2016. After data cleaning and feature selection, the dataset was split into a training set (80%, 2011-2014), test set (20%, 2011-2014) and validation set (2015-2016). Three simple machine learning methods (linear discriminant analysis, support vector machine, and random forest) and easy ensemble methods were used to build diabetes prediction models. The performance of the models was evaluated through 5-fold cross-validation and external validation. The Delong test (2-sided) was used to test the performance differences between the models. RESULTS: We selected 8057 observations and 12 attributes from the database. In the 5-fold cross-validation, the three simple methods yielded highly predictive performance models with areas under the curve (AUCs) over 0.800, wherein the ensemble methods significantly outperformed the simple methods. When we evaluated the models in the test set and validation set, the same trends were observed. The ensemble model of linear discriminant analysis yielded the best performance, with an AUC of 0.849, an accuracy of 0.730, a sensitivity of 0.819, and a specificity of 0.709 in the validation set. CONCLUSIONS: This study indicates that efficient screening using machine learning methods with noninvasive tests can be applied to a large population and achieve the objective of secondary prevention.

Interaction of avian influenza virus NS1 protein and nucleolar and coiled-body phosphoprotein 1.

Nonstructural protein 1 (NS1) is a non-structural protein of avian influenza virus. It can interact with a variety of proteins of the host cells, enhancing the expression of viral proteins and changing the growth and metabolism of the host cells, thereby enhancing the virus' pathogenicity and virulence. To investigate whether there are more host proteins that can interact with NS1 during viral infection, T7-phage display system was used to screen human lung cell cDNA library for proteins that could interact with NS1. One positive and specific clone was obtained and identified as nucleolar and coiled-body phosphoprotein 1(NOLC1). The interaction between these two proteins was further demonstrated by His-pull-down and co-immunoprecipitation experiments. Co-expression of both proteins in HeLa cell showed that NS1 and NOLC1 were co-localized in the cell's nucleus. Gene truncation experiments revealed that the effector domain of NS1 was sufficient to interact with NOLC1. The results demonstrated a positive interaction between a viral NS1 and NOLC1 of the host cells, and provided a new target for drug screening.