Deep Augmented Metric Learning Network for Prostate Cancer Classification in Ultrasound Images.

Prostate cancer screening often relies on cost-intensive MRIs and invasive needle biopsies. Transrectal ultrasound imaging, as a more affordable and non-invasive alternative, faces the challenge of high inter-class similarity and intra-class variability between benign and malignant prostate cancers. This complexity requires more stringent differentiation of subtle features for accurate auxiliary diagnosis. In response, we introduce the novel Deep Augmented Metric Learning (DAML) network, specifically tailored for ultrasound-based prostate cancer classification. The DAML network represents a significant innovation in the metric learning space, introducing the Semantic Differences Mining Strategy (SDMS) to effectively discern and represent subtle differences in prostate ultrasound images, thereby enhancing tumor classification accuracy. Additionally, the DAML network strategically addresses class variability and limited sample sizes by combining the Linear Interpolation Augmentation Strategy (LIAS) and Permutation-Aided Reconstruction Loss (PARL). This approach enriches feature representation and introduces variability with straightforward structures, mirroring the efficacy of advanced sample generation techniques. We carried out comprehensive empirical assessments of the DAML model by testing its key components against a range of models, ensuring its effectiveness. Our results demonstrate the enhanced performance of the DAML model, achieving classification accuracies of 0.857 and 0.888 for benign and malignant cancers, respectively, underscoring its effectiveness in prostate cancer classification via medical imaging.

Utilization of the waste aqueous phase from tea residue hydrothermal carbonization for preparing active food packaging films.

Hydrothermal carbonization (HTC) is an effective strategy for high-value utilization of tea residue (TR), and it was noticed the aqueous phase (AP) has not been extensively studied. This study aimed to investigate the chemical components and characteristics of the AP, and applied it in active food packaging films. The results showed that the total phenolic content of AP was 1.86 mg GAE/mL, and the main compounds in AP were organic acids, alcohols, and amino acids. The AP showed excellent antibacterial activity and antioxidant capacity. The active films were prepared using the casting method. The 4:7-AP/PVA film showed outstanding mechanical properties (tensile strength = 34.18 MPa, elongation at break = 458.67%), antioxidant ability (DPPH scavenging capacity 92.01%), antibacterial activity, water resistance and biocompatibility. The banana preservation test showed the AP/PVA films could successfully prolong the shelf-life of bananas and have the potential to be food packaging films.

The characterization and analysis of the compound hemostatic cotton based on Ca2+/poly (vinyl alcohol)/soluble starch-fish skin collagen.

Accidental bleeding is an unavoidable problem in daily life. To avoid the risk of excessive blood loss, it is urgent to design a functional material that can quickly stop bleeding. In this study, an efficient wound dressing for hemostasis was investigated. Based on the characteristics that Ca2+ and fish skin collagen (FSC) could activate the coagulation mechanism, hemostatic cotton was prepared by solvent replacement method using CaCl2, FSC, soluble starch (SS), and polyvinyl alcohol (PVA) as raw materials. The cytotoxicity test showed the Ca2+PVA/FSC-SS hemostatic cottons had good biocompatibility. The activated partial thromboplastin time (APTT) of Ca2+PVA/FSC-SS(4) was 35.34 s, which was 22.07 s faster than that of PVA/FSC-SS, indicating Ca2+PVA/FSC-SS mediated the endogenous coagulation system. In vitro coagulation test, Ca2+PVA/FSC-SS(4) could stop bleeding rapidly within 39.60 ± 5.16 s, and the ability of wound healing was higher than commercial product (Celox). This study developed a rapid procoagulant and hemostatic material, which had a promising application in a variety of environments.

RFEM: A framework for essential microRNA identification in mice based on rotation forest and multiple feature fusion.

With the increasing number of microRNAs (miRNAs), identifying essential miRNAs has become an important task that needs to be solved urgently. However, there are few computational methods for essential miRNA identification. Here, we proposed a novel framework called Rotation Forest for Essential MicroRNA identification (RFEM) to predict the essentiality of miRNAs in mice. We first constructed 1,264 miRNA features of all miRNA samples by fusing 38 miRNA features obtained from the PESM paper and 1,226 miRNA functional features calculated based on miRNA-target gene interactions. Then, we employed 182 training samples with 1,264 features to train the rotation forest model, which was applied to compute the essentiality scores of the candidate samples. The main innovations of RFEM were as follows: 1) miRNA functional features were introduced to enrich the diversity of miRNA features; 2) the rotation forest model used decision tree as the base classifier and could increase the difference among base classifiers through feature transformation to achieve better ensemble results. Experimental results show that RFEM significantly outperformed two previous models with the AUC (AUPR) of 0.942 (0.944) in three comparison experiments under 5-fold cross validation, which proved the model's reliable performance. Moreover, ablation study was further conducted to demonstrate the effectiveness of the novel miRNA functional features. Additionally, in the case studies of assessing the essentiality of unlabeled miRNAs, experimental literature confirmed that 7 of the top 10 predicted miRNAs have crucial biological functions in mice. Therefore, RFEM would be a reliable tool for identifying essential miRNAs.

Effects of Intestinal Microbiota on the Biological Transformation of Arsenic in Zebrafish: Contribution and Mechanism.

Both the gut microbiome and their host participate in arsenic (As) biotransformation, while their exact roles and mechanisms in vivo remain unclear and unquantified. In this study, as3mt-/- zebrafish were treated with tetracycline (TET, 100 mg/L) and arsenite (iAsIII) exposure for 30 days and treated with probiotic Lactobacillus rhamnosus GG (LGG, 1 × 108 cfu/g) and iAsIII exposure for 15 days, respectively. Structural equation modeling analysis revealed that the contribution rates of the intestinal microbiome to the total arsenic (tAs) and inorganic As (iAs) metabolism approached 44.0 and 18.4%, respectively. Compared with wild-type, in as3mt-/- zebrafish, microbial richness and structure were more significantly correlated with tAs and iAs, and more differential microbes and microbial metabolic pathways significantly correlated with arsenic metabolites (P < 0.05). LGG supplement influenced the microbial communities, significantly up-regulated the expressions of genes related to As biotransformation (gss and gst) in the liver, down-regulated the expressions of oxidative stress genes (sod1, sod2, and cat) in the intestine, and increased arsenobetaine concentration (P < 0.05). Therefore, gut microbiome promotes As transformation and relieves As accumulation, playing more active roles under iAs stress when the host lacks key arsenic detoxification enzymes. LGG can promote As biotransformation and relieve oxidative stress under As exposure.

GPCNDTA: Prediction of drug-target binding affinity through cross-attention networks augmented with graph features and pharmacophores.

Drug-target affinity prediction is a challenging task in drug discovery. The latest computational models have limitations in mining edge information in molecule graphs, accessing to knowledge in pharmacophores, integrating multimodal data of the same biomolecule and realizing effective interactions between two different biomolecules. To solve these problems, we proposed a method called Graph features and Pharmacophores augmented Cross-attention Networks based Drug-Target binding Affinity prediction (GPCNDTA). First, we utilized the GNN module, the linear projection unit and self-attention layer to correspondingly extract features of drugs and proteins. Second, we devised intramolecular and intermolecular cross-attention to respectively fuse and interact features of drugs and proteins. Finally, the linear projection unit was applied to gain final features of drugs and proteins, and the Multi-Layer Perceptron was employed to predict drug-target binding affinity. Three major innovations of GPCNDTA are as follows: (i) developing the residual CensNet and the residual EW-GCN to correspondingly extract features of drug and protein graphs, (ii) regarding pharmacophores as a new type of priors to heighten drug-target affinity prediction performance, and (iii) devising intramolecular and intermolecular cross-attention, in which the intramolecular cross-attention realizes the effective fusion of different modal data related to the same biomolecule, and the intermolecular cross-attention fulfills the information interaction between two different biomolecules in attention space. The test results on five benchmark datasets imply that GPCNDTA achieves the best performance compared with state-of-the-art computational models. Besides, relying on ablation experiments, we proved effectiveness of GNN modules, pharmacophores and two cross-attention strategies in improving the prediction accuracy, stability and reliability of GPCNDA. In case studies, we applied GPCNDTA to predict binding affinities between 3C-like proteinase and 185 drugs, and observed that most binding affinities predicted by GPCNDTA are close to corresponding experimental measurements.

Novel pH-responsive indicator films based on bromothymol blue-anchored chitin for shrimp freshness monitoring.

The cellulose nanofibers (CNFs) based pH-sensitive indicator films were developed by mixing guar gum (GG) with bromothymol blue-anchored chitin (BTB-Chitin) as an indicator to monitor shrimp freshness. The BTB-Chitin was prepared by grafting hydroxypropyltriethylamine groups (HPTA) to chitin first, then anchoring bromothymol blue (BTB) to prepare intelligent pH response BTB-Chitin. The 0.08 BTB-Chitin films had a good tensile strength of 11.76 MPa and the water contact angle values were 125°, which displayed obvious color response to pH buffers and acid base volatile gas. Besides, the homogeneous and flexible composite films showed good color stability and reversibility. The released amount of BTB was very low from the BTB-Chitin films in heptane and corn oil. The composite films had been degraded completely in 15 days in soil. The pH and volatile base nitrogen were measured to determine the degree decay of shrimp (Litopenaeus vannamei), and the prepared pH-sensitive films changed from yellow (fresh) to cyan (spoiled) with the freshness of shrimp decreased, indicating the BTB-Chitin films could detect the shrimp freshness in real-time and high visibility.

MCFF-MTDDI: multi-channel feature fusion for multi-typed drug-drug interaction prediction.

Adverse drug-drug interactions (DDIs) have become an increasingly serious problem in the medical and health system. Recently, the effective application of deep learning and biomedical knowledge graphs (KGs) have improved the DDI prediction performance of computational models. However, the problems of feature redundancy and KG noise also arise, bringing new challenges for researchers. To overcome these challenges, we proposed a Multi-Channel Feature Fusion model for multi-typed DDI prediction (MCFF-MTDDI). Specifically, we first extracted drug chemical structure features, drug pairs' extra label features, and KG features of drugs. Then, these different features were effectively fused by a multi-channel feature fusion module. Finally, multi-typed DDIs were predicted through the fully connected neural network. To our knowledge, we are the first to integrate the extra label information into KG-based multi-typed DDI prediction; besides, we innovatively proposed a novel KG feature learning method and a State Encoder to obtain target drug pairs' KG-based features which contained more abundant and more key drug-related KG information with less noise; furthermore, a Gated Recurrent Unit-based multi-channel feature fusion module was proposed in an innovative way to yield more comprehensive feature information about drug pairs, effectively alleviating the problem of feature redundancy. We experimented with four datasets in the multi-class and the multi-label prediction tasks to comprehensively evaluate the performance of MCFF-MTDDI for predicting interactions of known-known drugs, known-new drugs and new-new drugs. In addition, we further conducted ablation studies and case studies. All the results fully demonstrated the effectiveness of MCFF-MTDDI.

Development of the Emoji Faces Pain Scale and Its Validation on Mobile Devices in Adult Surgery Patients: Longitudinal Observational Study.

BACKGROUND: Measuring pain on digital devices using classic unidimensional pain scales such as the visual analog scale (VAS), numerical rating scale (NRS), and faces pain scale (FPS) has been proven to be reliable and valid. Emoji are pictographs designed in colorful form following the Unicode standard. It could be more beneficial to use emoji as faces of FPS on digital devices because emoji can easily fit on most devices and emoji are open-source so no approval would be needed before use. With a concise and user-friendly design, the emoji faces pain scale (Emoji-FPS) might be more generalizable to a wider population and more preferred by digital device users. OBJECTIVE: This study was designed to develop an Emoji-FPS as well as to evaluate its reliability, validity, and preference on mobile devices in adult patients who underwent surgery. METHODS: A modified Delphi technique with 2 rounds of web-based surveys was applied to obtain panelists' consensus on the sequence of emoji that can best represent 6 levels of pain. The initial candidate sequences of emoji for the Delphi process were constructed referring to 2 well-validated FPSs (Wong-Baker FACES pain rating scale [Wong-Baker FACES] and faces pain scale-revised [FPS-R]). Then, a prospective cohort of patients scheduled to receive perianal surgery was recruited and asked to complete a web-based questionnaire on a mobile device at 5 time points (before surgery [T1], wake up after surgery [T2], 4 hours after surgery [T3], the second day after surgery [T4], and 15 minutes after T4 [T5]). The 4 well-validated pain scales (NRS, VAS, Wong-Baker FACES, and FPS-R) were used as reference scales. RESULTS: After 2 rounds of surveys on 40 Delphi panelists, an Emoji-FPS was finally determined to represent 6 pain levels (0, 2, 4, 6, 8, and 10) from "no hurt" to "hurts worst." For validation, 300 patients were recruited and 299 were analyzed, the mean age of whom was 38.5 (SD 10.5) years, and 106 (35.5%) were women. For concurrent validity, the Emoji-FPS was highly correlated with 4 reference scales with Spearman correlation coefficient ρ ranging from 0.91 to 0.95. Excellent agreements were observed between 4 versions of Emoji-FPS (iOS, Android, Microsoft, and OpenMoji), with weighted κ coefficients ranging from 0.96 to 0.97. For discriminant validity, patients' mean preoperative Emoji-FPS score (T1) was significantly higher than their postoperative Emoji-FPS score (T4) with a difference of 1.4 (95% CI 1.3-1.6; P<.001). For test-retest reliability, Emoji-FPS scores measured at T4 and T5 were highly correlated with a ρ of 0.91. The Emoji-FPS was mostly preferred, followed by the Wong-Baker FACES, FPS-R, NRS, and VAS. CONCLUSIONS: The Emoji-FPS is reliable and valid compared with traditional pain scales in adult surgery patients.

SNRMPACDC: computational model focused on Siamese network and random matrix projection for anticancer synergistic drug combination prediction.

Synergistic drug combinations can improve the therapeutic effect and reduce the drug dosage to avoid toxicity. In previous years, an in vitro approach was utilized to screen synergistic drug combinations. However, the in vitro method is time-consuming and expensive. With the rapid growth of high-throughput data, computational methods are becoming efficient tools to predict potential synergistic drug combinations. Considering the limitations of the previous computational methods, we developed a new model named Siamese Network and Random Matrix Projection for AntiCancer Drug Combination prediction (SNRMPACDC). Firstly, the Siamese convolutional network and random matrix projection were used to process the features of the two drugs into drug combination features. Then, the features of the cancer cell line were processed through the convolutional network. Finally, the processed features were integrated and input into the multi-layer perceptron network to get the predicted score. Compared with the traditional method of splicing drug features into drug combination features, SNRMPACDC improved the interpretability of drug combination features to a certain extent. In addition, the introduction of convolutional networks can better extract the potential information in the features. SNRMPACDC achieved the root mean-squared error of 15.01 and the Pearson correlation coefficient of 0.75 in 5-fold cross-validation of regression prediction for response data. In addition, SNRMPACDC achieved the AUC of 0.91 ± 0.03 and the AUPR of 0.62 ± 0.05 in 5-fold cross-validation of classification prediction of synergistic or not. These results are almost better than all the previous models. SNRMPACDC would be an effective approach to infer potential anticancer synergistic drug combinations.

A novel S-scheme heterojunction of Cd0.5Zn0.5S/BiOCl with oxygen defects for antibiotic norfloxacin photodegradation: Performance, mechanism, and intermediates toxicity evaluation.

S-scheme heterojunction structure can endow the photocatalysts with high-performance photo-degradation of pharmaceuticals and personal care products (PPCPs) since it can remain the photogenerated electrons/holes with stronger redox ability. Herein, an integrative S-scheme heterojunction photocatalyst building from Cd0.5Zn0.5S nanoparticles and BiOCl microflowers with oxygen vacancies (OVs) was developed. Moreover, the in-situ grown process ensures the firm contact and intense electron coupling between BiOCl and Cd0.5Zn0.5S. As a result, Cd0.5Zn0.5S/BiOCl exhibited a significant reinforcement of photo-activity and stability for the abatement of antibiotic norfloxacin, manifesting a 2.8-fold or 9.6-fold enhancement compared to pristine Cd0.5Zn0.5S or BiOCl. Cd0.5Zn0.5S/BiOCl also shows good resistance to alkaline, sodium salts and humic acid. The performance of Cd0.5Zn0.5S/BiOCl to photocatalytically degrade other PPCPs with different molecular structures was further confirmed. At last, the ability of Cd0.5Zn0.5S/BiOCl for PPCPs de-toxicity was verified by evaluating the toxicity of norfloxacin and its degradation intermediate. This study demonstrates a new S-scheme heterojunction photocatalyt for efficient removal of PPCPs as well as provides some insights into developing high-performance metal sulfide solid-solution-based S-scheme heterojunctions for water decontamination.

Predicting drug-target binding affinity through molecule representation block based on multi-head attention and skip connection.

Exiting computational models for drug-target binding affinity prediction have much room for improvement in prediction accuracy, robustness and generalization ability. Most deep learning models lack interpretability analysis and few studies provide application examples. Based on these observations, we presented a novel model named Molecule Representation Block-based Drug-Target binding Affinity prediction (MRBDTA). MRBDTA is composed of embedding and positional encoding, molecule representation block and interaction learning module. The advantages of MRBDTA are reflected in three aspects: (i) developing Trans block to extract molecule features through improving the encoder of transformer, (ii) introducing skip connection at encoder level in Trans block and (iii) enhancing the ability to capture interaction sites between proteins and drugs. The test results on two benchmark datasets manifest that MRBDTA achieves the best performance compared with 11 state-of-the-art models. Besides, through replacing Trans block with single Trans encoder and removing skip connection in Trans block, we verified that Trans block and skip connection could effectively improve the prediction accuracy and reliability of MRBDTA. Then, relying on multi-head attention mechanism, we performed interpretability analysis to illustrate that MRBDTA can correctly capture part of interaction sites between proteins and drugs. In case studies, we firstly employed MRBDTA to predict binding affinities between Food and Drug Administration-approved drugs and severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) replication-related proteins. Secondly, we compared true binding affinities between 3C-like proteinase and 185 drugs with those predicted by MRBDTA. The final results of case studies reveal reliable performance of MRBDTA in drug design for SARS-CoV-2.

Claudin-5a is essential for the functional formation of both zebrafish blood-brain barrier and blood-cerebrospinal fluid barrier.

BACKGROUND: Mammalian Claudin-5 is the main endothelial tight junction component maintaining blood-brain barrier (BBB) permeability, while Claudin-1 and -3 seal the paracellular space of choroid plexus (CP) epithelial cells contributing to the blood-cerebrospinal fluid barrier (BCSFB). In zebrafish, two paralogs of claudin-5a and -5b are expressed while their roles in the formation of BBB and BCSFB are unclear. METHODS: The expression patterns of Claudin-5a and -5b in zebrafish brains were systematically analyzed by immunofluorescence (IF) assay. The developmental functions of Claudin-5a and -5b were characterized by generating of claudin-5a and -5b mutants respectively. Meanwhile, the cerebral inflammation and cell apoptosis in claudin-5a-/- were assessed by live imaging of transgenic zebrafish, RT-qPCR, IF, and TUNEL assay. The integrity of BBB and BCSFB was evaluated by in vivo angiographic and dye permeation assay. Finally, RT-qPCR, whole-mount RNA in situ hybridization (WISH), and transmission electron microscopy (TEM) analyses were performed to investigate the development of cerebral vessels and choroid plexus. RESULTS: We showed that Claudin-5a and -5b are both expressed in zebrafish cerebrovascular endothelial cells (ECs). In addition, Claudin-5a was strongly expressed in CP epithelial cells. Loss of Claudin-5b showed no effect on zebrafish vasculogenesis or BBB function. In contrast, the knockout of claudin-5a caused a lethal phenotype of severe whole-brain oedema, ventricular dilatation, and cerebral hernia in zebrafish larvae, although the cerebral vasculogenesis and the development of CP were not altered. In claudin-5a-/- , although ultrastructural analysis of CP and cerebral capillary showed intact integrity of epithelial and endothelial tight junctions, permeability assay indicated a disruption of both BBB and BCSFB functions. On the molecular level, it was found that ZO-1 was upregulated in the CP epithelium of claudin-5a-/-, while the notch and shh pathway responsible for CP development was not affected due to loss of Claudin-5a. CONCLUSIONS: Our findings verified a non-functional role of zebrafish Claudin-5b in the BBB and identified Claudin-5a as the ortholog of mammalian Claudin-5, contributing to the development and the functional maintenance of both BBB and BCSFB.

Designing oxygen vacancy mediated bismuth molybdate (Bi2MoO6)/N-rich carbon nitride (C3N5) S-scheme heterojunctions for boosted photocatalytic removal of tetracycline antibiotic and Cr(VI): Intermediate toxicity and mechanism insight.

Polymeric N-rich carbon nitride of C3N5 is being utilized as a new visible-light-driven catalyst due to its narrower bandgap (∼2.0 eV). Building step-scheme (S-scheme) heterojunction by coupling with other semiconductors especially those own oxygen vacancies (OVs) can further upgrade the photocatalytic performance of C3N5-based photocatalysts. Herein, a novel S-scheme heterojunction of OVs mediated Bi2MoO6/C3N5 was fabricated by in-situ growing Bi2MoO6 nanoparticles with OVs on C3N5 nanosheets. Benefiting from the efficient separation and transfer of high energetic charge carriers by S-scheme charge migration, enriched structural defects, as well as the close contact by the in-situ growth, the heterojunction exhibited superior visible-light photocatalytic performance toward the removal of tetracycline (TC) and Cr(VI) than C3N5, Bi2MoO6, and their mechanical mixture under visible light. The TC degradation routes and the bio-toxicity evolution of TC were explored. Moreover, the photocatalytic mechanism for TC decomposition and Cr(VI) reduction over Bi2MoO6/C3N5 with OVs were elucidated. This work presents a newfangled vision for designing promising C3N5-based S-scheme heterojunction photocatalysts for pollution control.

Rationally designed tetra (4-carboxyphenyl) porphyrin/graphene quantum dots/bismuth molybdate Z-scheme heterojunction for tetracycline degradation and Cr(VI) reduction: Performance, mechanism, intermediate toxicity appraisement.

Constructing novel Z-scheme heterojunctions is an effective strategy for obtaining high-performance photocatalysts. Herein, tetra (4-carboxyphenyl) porphyrin (TCPP) and graphene quantum dots (GQDs) were loaded on the surface of Bi2MoO6 (BMO) to fabricate novel Z-scheme heterojunctions of TCPP/G/BMO. Especially, TCPP/G/BMO-2 showed an exceptional visible-light photoactivity for tetracycline (TC) degradation (81.0%, 40 min) and Cr(VI) reduction (90.7%, 60 min), respectively by 2.38 folds and 2.96 folds enhancement compared to sole Bi2MoO6. The substantial enhancement of activity is attributed to the synergy effect of the Z-scheme charge transfer mechanism and the improved light absorption. The degradation pathways of TC were inferred by determining the generated intermediates using high performance liquid chromatography-mass spectrometry (HPLC-MS), and the toxicity of the transformation products was assessed by Toxicity Estimation Software Tool (T.E.S.T). Overall, on the basis of trapping experiments and electron spin resonance spectra (ESR) analysis, the photocatalytic mechanisms of Cr(VI) reduction and TC degradation by the TCPP/G/BMO Z-scheme heterojunction was proposed. This work indicates TCPP/G/BMO could be a promising photocatalyst for wastewater treatment.

Molecular Characterization of a New Tetrodotoxin-Binding Protein, Peroxiredoxin-1, from Takifugu bimaculatus.

Pufferfish are considered a culinary delicacy but require careful preparation to avoid ingestion of the highly toxic tetrodotoxin (TTX), which accumulates in certain tissues. In this study, the tissue distribution of peroxiredoxin-1 from Takifugu bimaculatus was investigated. The peroxiredoxin-1 protein was obtained by in vitro recombinant expression and purification. The recombinant protein had a strong ability to scavenge hydroxyl radicals, protect superhelical DNA plasmids from oxidative damage, and protect L929 cells from H2O2 toxicity through in vitro antioxidant activity. In addition, we verified its ability to bind to tetrodotoxin using surface plasmon resonance techniques. Further, recombinant proteins were found to facilitate the entry of tetrodotoxin into cells. Through these analyses, we identified, for the first time, peroxiredoxin-1 protein from Takifugu bimaculatus as a potential novel tetrodotoxin-binding protein. Our findings provide a basis for further exploration of the application of peroxiredoxin-1 protein and the molecular mechanisms of tetrodotoxin enrichment in pufferfish.

Prediction of potential miRNA-disease associations based on stacked autoencoder.

In recent years, increasing biological experiments and scientific studies have demonstrated that microRNA (miRNA) plays an important role in the development of human complex diseases. Therefore, discovering miRNA-disease associations can contribute to accurate diagnosis and effective treatment of diseases. Identifying miRNA-disease associations through computational methods based on biological data has been proven to be low-cost and high-efficiency. In this study, we proposed a computational model named Stacked Autoencoder for potential MiRNA-Disease Association prediction (SAEMDA). In SAEMDA, all the miRNA-disease samples were used to pretrain a Stacked Autoencoder (SAE) in an unsupervised manner. Then, the positive samples and the same number of selected negative samples were utilized to fine-tune SAE in a supervised manner after adding an output layer with softmax classifier to the SAE. SAEMDA can make full use of the feature information of all unlabeled miRNA-disease pairs. Therefore, SAEMDA is suitable for our dataset containing small labeled samples and large unlabeled samples. As a result, SAEMDA achieved AUCs of 0.9210 and 0.8343 in global and local leave-one-out cross validation. Besides, SAEMDA obtained an average AUC and standard deviation of 0.9102 ± /-0.0029 in 100 times of 5-fold cross validation. These results were better than those of previous models. Moreover, we carried out three case studies to further demonstrate the predictive accuracy of SAEMDA. As a result, 82% (breast neoplasms), 100% (lung neoplasms) and 90% (esophageal neoplasms) of the top 50 predicted miRNAs were verified by databases. Thus, SAEMDA could be a useful and reliable model to predict potential miRNA-disease associations.

Sodium Butyrate Ameliorates Oxidative Stress-Induced Intestinal Epithelium Barrier Injury and Mitochondrial Damage through AMPK-Mitophagy Pathway.

Sodium butyrate has gained increasing attention for its vast beneficial effects. However, whether sodium butyrate could alleviate oxidative stress-induced intestinal dysfunction and mitochondrial damage of piglets and its underlying mechanism remains unclear. The present study used a hydrogen peroxide- (H2O2-) induced oxidative stress model to study whether sodium butyrate could alleviate oxidative stress, intestinal epithelium injury, and mitochondrial dysfunction of porcine intestinal epithelial cells (IPEC-J2) in AMPK-mitophagy-dependent pathway. The results indicated that sodium butyrate alleviated the H2O2-induced oxidative stress, decreased the level of reactive oxygen species (ROS), increased mitochondrial membrane potential (MMP), mitochondrial DNA (mtDNA), and mRNA expression of genes related to mitochondrial function, and inhibited the release of mitochondrial cytochrome c (Cyt c). Sodium butyrate reduced the protein expression of recombinant NLR family, pyrin domain-containing protein 3 (NLRP3) and fluorescein isothiocyanate dextran 4 kDa (FD4) permeability and increased transepithelial resistance (TER) and the protein expression of tight junction. Sodium butyrate increased the expression of light-chain-associated protein B (LC3B) and Beclin-1, reduced the expression of P62, and enhanced mitophagy. However, the use of AMPK inhibitor or mitophagy inhibitor weakened the protective effect of sodium butyrate on mitochondrial function and intestinal epithelium barrier function and suppressed the induction effect of sodium butyrate on mitophagy. In addition, we also found that after interference with AMPKα, the protective effect of sodium butyrate on IPEC-J2 cells treated with H2O2 was suppressed, indicating that AMPKα is necessary for sodium butyrate to exert its protective effect. In summary, these results revealed that sodium butyrate induced mitophagy by activating AMPK, thereby alleviating oxidative stress, intestinal epithelium barrier injury, and mitochondrial dysfunction induced by H2O2.

Ensemble of kernel ridge regression-based small molecule-miRNA association prediction in human disease.

MicroRNAs (miRNAs) play crucial roles in human disease and can be targeted by small molecule (SM) drugs according to numerous studies, which shows that identifying SM-miRNA associations in human disease is important for drug development and disease treatment. We proposed the method of Ensemble of Kernel Ridge Regression-based Small Molecule-MiRNA Association prediction (EKRRSMMA) to uncover potential SM-miRNA associations by combing feature dimensionality reduction and ensemble learning. First, we constructed different feature subsets for both SMs and miRNAs. Then, we trained homogeneous base learners based on distinct feature subsets and took the average of scores obtained from these base learners as SM-miRNA association score. In EKRRSMMA, feature dimensionality reduction technology was employed in the process of construction of feature subsets to reduce the influence of noisy data. Besides, the base learner, namely KRR_avg, was the combination of two classifiers constructed under SM space and miRNA space, which could make full use of the information of SM and miRNA. To assess the prediction performance of EKRRSMMA, we conducted Leave-One-Out Cross-Validation (LOOCV), SM-fixed local LOOCV, miRNA-fixed local LOOCV and 5-fold CV based on two datasets. For Dataset 1 (Dataset 2), EKRRSMMA got the Area Under receiver operating characteristic Curves (AUCs) of 0.9793 (0.8871), 0.8071 (0.7705), 0.9732 (0.8586) and 0.9767 ± 0.0014 (0.8560 ± 0.0027). Besides, we conducted four case studies. As a result, 32 (5-Fluorouracil), 19 (17ß-Estradiol), 26 (5-Aza-2'-deoxycytidine) and 11 (cyclophosphamide) out of top 50 predicted potentially associated miRNAs were confirmed by database or experimental literature. Above evaluation results demonstrated that EKRRSMMA is reliable for predicting SM-miRNA associations.

Facile construction of novel organic-inorganic tetra (4-carboxyphenyl) porphyrin/Bi2MoO6 heterojunction for tetracycline degradation: Performance, degradation pathways, intermediate toxicity analysis and mechanism insight.

Developing durable photocatalysts with highly efficient antibiotics degradation is crucial for environment purification. Herein, tetra (4-carboxyphenyl) porphyrin (TCPP) was loaded onto the surface of Bi2MoO6 microspheres to gain hierarchical organic-inorganic TCPP/Bi2MoO6 (TCPP/BMO) heterojunctions via a facile impregnation strategy. The catalytic properties of these catalysts were comprehensively investigated through the photodegradation of tetracycline hydrochloride (TC) under visible light. Among all the TCPP/BMO heterojunctions, the highest photodegradation rate constant (0.0278 min-1) was achieved with 0.25 wt% TCPP (TCPP/BMO-2), which was approximately 1.15 folds greater than that of pristine Bi2MoO6 and far superior to pure TCPP. The extremely high photocatalytic performance is attributed to the interfacial interaction between TCPP and Bi2MoO6, which favors the efficient separation of charge carriers and the enhancement of visible-light absorbance. TCPP/BMO-2 possesses high mineralization capability and good recycling performance. Photo-induced O2-, h+, and OH were mainly responsible for the degradation of TC. The degradation pathways of TC and toxicity of degradation intermediates were analyzed based on the intermediates detected by the high performance liquid chromatography-mass spectrometer (HPLC-MS) and the toxicity assessment by the quantitative structure-activity relationship (QSAR) prediction. A possible photocatalytic mechanism over TCPP/BMO is proposed. This work offers an insight in developing the porphyrin-based organic-inorganic heterojunctions for effectively remedying pharmaceutical wastewater.