Application of interpretable machine learning algorithms to predict distant metastasis in ovarian clear cell carcinoma.

BACKGROUND: Ovarian clear cell carcinoma (OCCC) represents a subtype of ovarian epithelial carcinoma (OEC) known for its limited responsiveness to chemotherapy, and the onset of distant metastasis significantly impacts patient prognoses. This study aimed to identify potential risk factors contributing to the occurrence of distant metastasis in OCCC. METHODS: Utilizing the Surveillance, Epidemiology, and End Results (SEER) database, we identified patients diagnosed with OCCC between 2004 and 2015. The most influential factors were selected through the application of Gaussian Naive Bayes (GNB) and Adaboost machine learning algorithms, employing a Venn test for further refinement. Subsequently, six machine learning (ML) techniques, namely XGBoost, LightGBM, Random Forest (RF), Adaptive Boosting (Adaboost), Support Vector Machine (SVM), and Multilayer Perceptron (MLP), were employed to construct predictive models for distant metastasis. Shapley Additive Interpretation (SHAP) analysis facilitated a visual interpretation for individual patient. Model validity was assessed using accuracy, sensitivity, specificity, positive predictive value, negative predictive value, F1 score, and the area under the receiver operating characteristic curve (AUC). RESULTS: In the realm of predicting distant metastasis, the Random Forest (RF) model outperformed the other five machine learning algorithms. The RF model demonstrated accuracy, sensitivity, specificity, positive predictive value, negative predictive value, F1 score, and AUC (95% CI) values of 0.792 (0.762-0.823), 0.904 (0.835-0.973), 0.759 (0.731-0.787), 0.221 (0.186-0.256), 0.974 (0.967-0.982), 0.353 (0.306-0.399), and 0.834 (0.696-0.967), respectively, surpassing the performance of other models. Additionally, the calibration curve's Brier Score (95%) for the RF model reached the minimum value of 0.06256 (0.05753-0.06759). SHAP analysis provided independent explanations, reaffirming the critical clinical factors associated with the risk of metastasis in OCCC patients. CONCLUSIONS: This study successfully established a precise predictive model for OCCC patient metastasis using machine learning techniques, offering valuable support to clinicians in making informed clinical decisions.

Identification of a circulating three-miRNA panel for the diagnosis of primary open angle glaucoma.

PURPOSE: Conventional diagnosis of primary open angle glaucoma (POAG) needs a combination of ophthalmic examinations. An efficient assay is urgently needed for a timely POAG diagnosis. We aim to explore differential expressions of circulating microRNAs (miRNA) and provide novel miRNA biomarkers for POAG diagnosis. METHODS: A total of 180 POAG patients and 210 age-related cataract (ARC) patients were enrolled. We collected aqueous humor (AH) and plasma samples from the recruited patients. The expressions of candidate miRNAs were measured using quantitative real time polymerase chain reaction. The diagnostic ability of candidate miRNAs was analyzed by receiver operating characteristic curve. RESULTS: The expressions of miR-21-5p and miR-29b-3p were downregulated significantly in AH and plasma of POAG and miR-24-3p expression was significantly increased in AH and plasma of POAG, comparing with those of ARC. A three-miRNA panel was constructed by a binary logistic regression. And the panel could differentiate between POAG and ARC with an area under the curve of 0.8867 (sensitivity = 78.0%, specificity = 83.3%) in aqueous humor and 0.7547 (sensitivity = 73.8%, specificity = 81.2%) in plasma. Next, we verified the three-miRNA panel working as a potential diagnostic biomarker stable and reliable. At last, we identified related function and regulation pathways in vitro. CONCLUSIONS: In conclusion, we built and identified a circulating three-miRNA panel as a potential diagnostic biomarker for POAG. It may be developed into an efficient assay and help improve the POAG diagnosis in the future.

Thiostrepton suppresses triple-negative breast cancer through downregulating c-FLIP/SMAD2/3 signaling pathway.

Triple-negative breast cancer (TNBC) is an aggressive subtype with poor prognosis of breast cancer. Thiostrepton exerts anti-tumor activities against several cancers including TNBC. Herein we discussed the new molecular mechanisms of thiostrepton in TNBC. Thiostrepton inhibited MDA-MB-231 cell viability, accompanied by a decrease of c-FLIP and p-SMAD2/3. c-FLIP overexpression reduced the sensitivity of MDA-MB-231 cells to thiostrepton, while SMAD2/3 knockdown increased the sensitivity of MDA-MB-231 cells to thiostrepton. Moreover, c-FLIP overexpression significantly increased the expression and phosphorylation of SMAD2/3 proteins and vice versa. In conclusion, our study reveals c-FLIP/SMAD2/3 signaling pathway as a novel mechanism of antitumor activity of thiostrepton.

MHESMMR: a multilevel model for predicting the regulation of miRNAs expression by small molecules.

According to the expression of miRNA in pathological processes, miRNAs can be divided into oncogenes or tumor suppressors. Prediction of the regulation relations between miRNAs and small molecules (SMs) becomes a vital goal for miRNA-target therapy. But traditional biological approaches are laborious and expensive. Thus, there is an urgent need to develop a computational model. In this study, we proposed a computational model to predict whether the regulatory relationship between miRNAs and SMs is up-regulated or down-regulated. Specifically, we first use the Large-scale Information Network Embedding (LINE) algorithm to construct the node features from the self-similarity networks, then use the General Attributed Multiplex Heterogeneous Network Embedding (GATNE) algorithm to extract the topological information from the attribute network, and finally utilize the Light Gradient Boosting Machine (LightGBM) algorithm to predict the regulatory relationship between miRNAs and SMs. In the fivefold cross-validation experiment, the average accuracies of the proposed model on the SM2miR dataset reached 79.59% and 80.37% for up-regulation pairs and down-regulation pairs, respectively. In addition, we compared our model with another published model. Moreover, in the case study for 5-FU, 7 of 10 candidate miRNAs are confirmed by related literature. Therefore, we believe that our model can promote the research of miRNA-targeted therapy.

Clinical nursing value of predictive nursing in reducing complications of pregnant women undergoing short-term massive blood transfusion during cesarean section.

BACKGROUND: Cesarean hemorrhage is one of the serious complications, and short-term massive blood transfusion can easily cause postoperative infection and physical stress response. However, predictive nursing intervention has important clinical significance for it. AIM: To explore the effect of predictive nursing intervention on the stress response and complications of women undergoing short-term mass blood transfusion during cesarean section (CS). METHODS: A clinical medical record of 100 pregnant women undergoing rapid mass blood transfusion during sections from June 2019 to June 2021. According to the different nursing methods, patients divided into control group (n = 50) and observation group (n = 50). Among them, the control group implemented routine nursing, and the observation group implemented predictive nursing intervention based on the control group. Moreover, compared the differences in stress response, complications, and pain scores before and after the nursing of pregnant women undergoing rapid mass blood transfusion during CS. RESULTS: The anxiety and depression scores of pregnant women in the two groups were significantly improved after nursing, and the psychological stress response of the observation group was significantly lower than that of the control group (P < 0.05). The heart rate and mean arterial pressure (MAP) of the observation group during delivery were lower than those of the control group, and the MAP at the end of delivery was lower than that of the control group (P < 0.05). Moreover, different pain scores improved significantly in both groups, with the observation group considerably less than the control group (P < 0.05). After nursing, complications such as skin rash, urinary retention, chills, diarrhea, and anaphylactic shock in the observation group were 18%, which significantly higher than in the control group (4%) (P < 0.05). CONCLUSION: Predictive nursing intervention can effectively relieve the pain, reduce the incidence of complications, improve mood and stress response, and serve as a reference value for the nursing of women undergoing rapid mass transfusion during CS.

Unravelling hidden threats of water disinfection: Toxicity evaluation and toxic products identification during diclofenac degradation.

Diclofenac (DCF) is a widely-used nonsteroidal anti-inflammatory drug that is routinely found in surface water bodies. While ozonation and ultraviolet (UV) radiation are commonly employed as disinfection methods in water treatment processes, the degradation of DCF in these processes occurs due to the strong oxidizing activity of the reactive oxygen species produced during both ozonation and UV radiation. Despite extensive studies reporting the removal and transformation of DCF through ozone and UV treatments, the potential hidden hazards of toxicity arising from these processes as well as the identification of the toxic transformation products have often been overlooked. In this study, various toxicities including microtoxicity, genotoxicity and antiestrogenicity were evaluated using multiple in-vitro bioassays. The transformation products were identified via ultra-performance liquid chromatography equipped with mass spectrometry (UPLC-MS). Correlation analysis was employed to gain deeper insight into the contributions of degradation products to overall toxicity. The results revealed that DCF possessed significant genotoxic and antiestrogenic effects, but displayed minimal microtoxicity. Microtoxic products such as those containing carbazole were generated during DCF degradation with ozone, UVA and UVC. Antiestrogenic products with dichloroaniline structures were observed in DCF ozonation but not in photodegradation by UVA and UVC. These findings highlighted the hidden risks associated with the disinfection of water containing micropollutants such as DCF.

SiSGC: A Drug Repositioning Prediction Model Based on Heterogeneous Simplifying Graph Convolution.

Drug repositioning plays a key role in disease treatment. With the large-scale chemical data increasing, many computational methods are utilized for drug-disease association prediction. However, most of the existing models neglect the positive influence of non-Euclidean data and multisource information, and there is still a critical issue for graph neural networks regarding how to set the feature diffuse distance. To solve the problems, we proposed SiSGC, which makes full use of the biological knowledge information as initial features and learns the structure information from the constructed heterogeneous graph with the adaptive selection of the information diffuse distance. Then, the structural features are fused with the denoised similarity information and fed to the advanced classifier of CatBoost to make predictions. Three different data sets are used to confirm the robustness and generalization of SiSGC under two splitting strategies. Experiment results demonstrate that the proposed model achieves superior performance compared with the six leading methods and four variants. Our case study on breast neoplasms further indicates that SiSGC is trustworthy and robust yet simple. We also present four drugs for breast cancer treatment with high confidence and further give an explanation for demonstrating the rationality. There is no doubt that SiSGC can be used as a beneficial supplement for drug repositioning.

ITRAQ-based proteomics analysis of human ectopic endometrial stromal cells treated by Maqian essential oil.

BACKGROUND: Endometriosis is a common and complex syndrome characterized by the presence of endometrial-like tissue outside the uterus. Chinese medicine has been recently found to show good efficacy in treating endometriosis. Our previous results revealed that Maqian fruit essential oil (MQEO) could inhibit the proliferation and induce apoptosis of ectopic endometrial stromal cells (EESCs), but the mechanisms remain unclear. In this study, we aim to explore the molecular mechanism of MQEO's specific effects in EESCs. METHODS: We conducted a quantitative proteomics analysis by iTRAQ on EESCs treated with MQEO or DMSO. Then deep analysis was performed based on differentially expressed proteins, including Gene Ontology enrichment analysis, pathway enrichment analysis and protein interaction analysis. Candidate protein targets were subsequently verified by western blotting. RESULTS: Among 6575 identified proteins, 435 proteins exhibited altered expression levels in MQEO-treated EESCs. Of these proteins, most were distributed in signal transduction as well as immune system and the most significantly altered pathway was complement and coagulation cascades. Moreover, two differentially expressed proteins (Heme oxygenase 1 and Acyl-CoA 6-desaturase) were verified and they can be potential biomarkers for endometriosis treatment. CONCLUSIONS: Our proteomic analysis revealed distinct protein expression patterns induced by MQEO treatment in EESCs, highlighting the potential of MQEO for endometriosis treatment and biomarker discovery.

BCMCMI: A Fusion Model for Predicting circRNA-miRNA Interactions Combining Semantic and Meta-path.

More and more evidence suggests that circRNA plays a vital role in generating and treating diseases by interacting with miRNA. Therefore, accurate prediction of potential circRNA-miRNA interaction (CMI) has become urgent. However, traditional wet experiments are time-consuming and costly, and the results will be affected by objective factors. In this paper, we propose a computational model BCMCMI, which combines three features to predict CMI. Specifically, BCMCMI utilizes the bidirectional encoding capability of the BERT algorithm to extract sequence features from the semantic information of circRNA and miRNA. Then, a heterogeneous network is constructed based on cosine similarity and known CMI information. The Metapath2vec is employed to conduct random walks following meta-paths in the network to capture topological features, including similarity features. Finally, potential CMIs are predicted using the XGBoost classifier. BCMCMI achieves superior results compared to other state-of-the-art models on two benchmark datasets for CMI prediction. We also utilize t-SNE to visually observe the distribution of the extracted features on a randomly selected dataset. The remarkable prediction results show that BCMCMI can serve as a valuable complement to the wet experiment process.

mTORC2 acts as a gatekeeper for mTORC1 deficiency-mediated impairments in ILC3 development.

Group 3 innate lymphoid cells (ILC3s) are mediators of intestinal immunity and barrier function. Recent studies have investigated the role of the mammalian target of rapamycin complex (mTOR) in ILC3s, whereas the mTORC1-related mechanisms and crosstalk between mTORC1 and mTORC2 involved in regulating ILC3 homeostasis remain unknown. In this study, we found that mTORC1 but not mTORC2 was critical in ILC3 development, IL-22 production, and ILC3-mediated intestinal homeostasis. Single-cell RNA sequencing revealed that mTORC1 deficiency led to disruption of ILC3 heterogeneity, showing an increase in differentiation into ILC1-like phenotypes. Mechanistically, mTORC1 deficiency decreased the expression of NFIL3, which is a critical transcription factor responsible for ILC3 development. The activities of both mTORC1 and mTORC2 were increased in wild-type ILC3s after activation by IL-23, whereas inhibition of mTORC1 by Raptor deletion or rapamycin treatment resulted in increased mTORC2 activity. Previous studies have demonstrated that S6K, the main downstream target of mTORC1, can directly phosphorylate Rictor to dampen mTORC2 activity. Our data found that inhibition of mTORC1 activity by rapamycin reduced Rictor phosphorylation in ILC3s. Reversing the increased mTORC2 activity via heterozygous or homozygous knockout of Rictor in Raptor-deleted ILC3s resulted in severe ILC3 loss and complete susceptibility to intestinal infection in mice with mTORC1 deficiency (100% mortality). Thus, mTORC1 acts as a rheostat of ILC3 heterogeneity, and mTORC2 protects ILC3s from severe loss of cells and immune activity against intestinal infection when mTORC1 activity is diminished.

Panax notoginseng alleviates oxidative stress through miRNA regulations based on systems biology approach.

BACKGROUND: Herbal medicine Sanqi (SQ), the dried root or stem of Panax notoginseng (PNS), has been reported to have anti-diabetic and anti-obesity effects and is usually administered as a decoction for Chinese medicine. Alternative to utilizing PNS pure compound for treatment, we are motivated to propose an unconventional scheme to investigate the functions of PNS mixture. However, studies providing a detailed overview of the transcriptomics-based signaling network in response to PNS are seldom available. METHODS: To explore the reasoning of PNS in treating metabolic disorders such as insulin resistance, we implemented a systems biology-based approach with RNA sequencing (RNA-seq) and miRNA sequencing data to elucidate key pathways, genes and miRNAs involved. RESULTS: Functional enrichment analysis revealed PNS up-regulating oxidative stress-related pathways and down-regulating insulin and fatty acid metabolism. Superoxide dismutase 1 (SOD1), peroxiredoxin 1 (PRDX1), heme oxygenase-1 (Hmox1) and glutamate cysteine ligase (GCLc) mRNA and protein levels, as well as related miRNA levels, were measured in PNS treated rat pancreatic ß cells (INS-1). PNS treatment up-regulated Hmox1, SOD1 and GCLc expression while down-regulating miR-24-3p and miR-139-5p to suppress oxidative stress. Furthermore, we verified the novel interactions between miR-139-5p and miR-24-3p with GCLc and SOD1. CONCLUSION: This work has demonstrated the mechanism of how PNS regulates cellular molecules in metabolic disorders. Therefore, combining omics data with a systems biology strategy could be a practical means to explore the potential function and molecular mechanisms of Chinese herbal medicine in the treatment of metabolic disorders.

Deciphering the photolysis products and biological concerns of triclosan under UVC and UVA.

Triclosan (TCS) is omnipresent in the environment and has drawn increasing attention due to its potential adverse effects on human health. Direct photolysis of TCS readily occurs, especially in the surface layers of waters that receive abundant ultraviolet radiation during the daytime. However, biological concerns and the identification of toxic products during TCS photolysis have been explored limitedly. Therefore, in the present work, the structural characterization of the photolysis products by UVC and UVA were performed based on the mass spectra and fragmental ions. The results displayed that TCS was more readily eliminated by UVC than UVA, and the product species were completely different when TCS was degraded by UVC and UVA, respectively. Two products, m/z 235 and m/z 252, were produced via reductive dechlorination and nucleophilic substitution with UVC, while three dioxin-like isomer products were generated by dechlorination, cyclization and hydroxylation. Furthermore, the results of biological concerns suggested that the elimination of TCS did not represent the disappearance of biological risks. Specifically, more hazardous and photolysis products were formed during TCS photolysis with ultraviolets. For instance, the dioxin-like isomer products were highly microtoxic and genotoxic, and mildly antiestrogenic. The positive findings highlighted the biological concerns of TCS photolysis by ultraviolet radiation in the aquatic environment.

The impact of hospital-family integrated continuation nursing based on information technology on patients unhealthy mood, family function and sexual function after cervical cancer surgery.

The objective of this study was to explore the impact on hospital-family integrated continuation care based on information technology on the negative emotions, family function, and sexual function of patients after cervical cancer surgery. The clinical case data onto 114 postoperative cervical cancer patients who were nursing in our hospital from July 2019 to July 2021 were selected and were divided into a control group and an observation group. The control group used routine nursing care, and on this basis, the observation group used information technology as the basis for hospital-family integrated continuation care, and we observed and compared the differences in the 2 groups of patients bad mood, family function, and sexual function. The score of anxiety (P = .017), depression (P = .009), fatigue rating (P = .012), and anger (P < .001) in the observation group after care were significantly lower than those in the control group. Problem solving, role, emotional response, emotional involvement, and family function total score in the observation group after care was significantly lower than those in the control group (P < .05). Sexual desire score, sexual arousal score, vaginal lubrication score, orgasm score, sexual satisfaction score, dyspareunia score, and Female Sexual Function Inventory total scores in the observation and control groups after care were significantly higher than those before care (P < .05). The sexual function scores in the observation group after care was significantly higher than those in the control group (P < .05). The hospital-family integrated continuation care based on information technology is more effective than conventional nursing care for patients after cervical cancer surgery.

A feature extraction method based on noise reduction for circRNA-miRNA interaction prediction combining multi-structure features in the association networks.

MOTIVATION: A large number of studies have shown that circular RNA (circRNA) affects biological processes by competitively binding miRNA, providing a new perspective for the diagnosis, and treatment of human diseases. Therefore, exploring the potential circRNA-miRNA interactions (CMIs) is an important and urgent task at present. Although some computational methods have been tried, their performance is limited by the incompleteness of feature extraction in sparse networks and the low computational efficiency of lengthy data. RESULTS: In this paper, we proposed JSNDCMI, which combines the multi-structure feature extraction framework and Denoising Autoencoder (DAE) to meet the challenge of CMI prediction in sparse networks. In detail, JSNDCMI integrates functional similarity and local topological structure similarity in the CMI network through the multi-structure feature extraction framework, then forces the neural network to learn the robust representation of features through DAE and finally uses the Gradient Boosting Decision Tree classifier to predict the potential CMIs. JSNDCMI produces the best performance in the 5-fold cross-validation of all data sets. In the case study, seven of the top 10 CMIs with the highest score were verified in PubMed. AVAILABILITY: The data and source code can be found at https://github.com/1axin/JSNDCMI.

Ciprofloxacin degradation performances and mechanisms by the heterogeneous electro-Fenton with flocculated fermentation biochar.

Antibiotic fermentation residue flocculated by polymeric ferric sulfate (PFS) has been classified as a "hazardous waste" in China. In this study, it was recycled into antibiotic fermentation residue biochar (AFRB) by pyrolysis and used as a heterogeneous electro-Fenton (EF) catalyst for ciprofloxacin (CIP) degradation. The results show that PFS was reduced to Fe0 and FeS during pyrolysis, which was beneficial for the EF process. The AFRB with mesoporous structures exhibited soft magnetic features, which were convenient for separation. CIP was completely degraded within 10 min by the AFRB-EF process at an initial concentration of 20 mg/L. Increasing the working current and catalyst dosage within a certain range could improve the degradation rate. ·OH and O2·- were the dominant reactive oxygen species that played critical roles for CIP degradation. The antibacterial groups of CIP have been destroyed by the heterogeneous electro-Fenton process and its toxicity was negligible. The AFRB showed satisfactory performance, even though it was recycled five times. This study provide new insights into the resourceful treatment of antibiotic fermentation residues.

LPIH2V: LncRNA-protein interactions prediction using HIN2Vec based on heterogeneous networks model.

LncRNA-protein interaction plays an important role in the development and treatment of many human diseases. As the experimental approaches to determine lncRNA-protein interactions are expensive and time-consuming, considering that there are few calculation methods, therefore, it is urgent to develop efficient and accurate methods to predict lncRNA-protein interactions. In this work, a model for heterogeneous network embedding based on meta-path, namely LPIH2V, is proposed. The heterogeneous network is composed of lncRNA similarity networks, protein similarity networks, and known lncRNA-protein interaction networks. The behavioral features are extracted in a heterogeneous network using the HIN2Vec method of network embedding. The results showed that LPIH2V obtains an AUC of 0.97 and ACC of 0.95 in the 5-fold cross-validation test. The model successfully showed superiority and good generalization ability. Compared to other models, LPIH2V not only extracts attribute characteristics by similarity, but also acquires behavior properties by meta-path wandering in heterogeneous networks. LPIH2V would be beneficial in forecasting interactions between lncRNA and protein.

Combining K Nearest Neighbor With Nonnegative Matrix Factorization for Predicting Circrna-Disease Associations.

Accumulating evidences show that circular RNAs (circRNAs) play an important role in regulating gene expression, and involve in many complex human diseases. Identifying associations of circRNA with disease helps to understand the pathogenesis, treatment and diagnosis of complex diseases. Since inferring circRNA-disease associations by biological experiments is costly and time-consuming, there is an urgently need to develop a computational model to identify the association between them. In this paper, we proposed a novel method named KNN-NMF, which combines K nearest neighbors with nonnegative matrix factorization to infer associations between circRNA and disease (KNN-NMF). Frist, we compute the Gaussian Interaction Profile (GIP) kernel similarity of circRNA and disease, the semantic similarity of disease, respectively. Then, the circRNA-disease new interaction profiles are established using weight K nearest neighbors to reduce the false negative association impact on prediction performance. Finally, Nonnegative Matrix Factorization is implemented to predict associations of circRNA with disease. The experiment results indicate that the prediction performance of KNN-NMF outperforms the competing methods under five-fold cross-validation. Moreover, case studies of two common diseases further show that KNN-NMF can identify potential circRNA-disease associations effectively.

Switching the Photoreactions of Ir(III) Diamine Complexes between C-N Coupling and Dehydrogenation under Visible Light Irradiation.

The selective photoreactions under mild conditions play an important role in synthetic chemistry. Herein, efficient and mild protocols for switching the photoreactions of Ir(III)-diamine complexes between the interligand C-N coupling and dehydrogenation are developed in the presence of O2 in EtOH solution. The photoreactions of achiral diamine complexes rac-[Ir(L)2(dm)](PF6) (L is 2-phenylquinoline or 2-(2,4-difluorophenyl)quinoline, dm is 1,2-ethylenediamine, 1,2-diaminopropane, 2-methyl-1,2-diamino-propane, or N,N'-dimethyl-1,2-ethylenediamine) are competitive in the oxidative C-N coupling and dehydrogenation at room temperature, which can be switched into the interligand C-N coupling reaction at 60 °C, affording hexadentate complexes in good to excellent yields, or the dehydrogenative reaction in the presence of a catalytic amount of TEMPO as an additive, affording imine complexes. Mechanism studies reveal that 1O2 is the major reactive oxygen species, and metal aminyl is the key intermediate in the formation of the oxidative C-N coupling and imine products in the photoreaction processes. These will provide a new and practical protocol for the synthesis of multidentate and imine ligands in situ via the postcoordinated strategy under mild conditions.

Stem Cell Therapy for Diabetic Foot Ulcers: Theory and Practice.

Diabetic foot ulcers are associated with increases in limb amputation, morbidity, and mortality. Recently, a stem cell application is emerging as promising adjuvant therapy. We presented available remedies by conducting a literature review on the application, safety, and efficacy of stem cell therapy. Relevant literature, including randomized control trials and article journals, was obtained from reputable search engines (PubMed, Scopus, and Web of Science). We analyzed five credible cohorts, with variable sources of stem cells, in a total of 216 participants, 151 males and 65 females, age (mean ± SD) of 64.5 ± 9.6 years. With an average success of 86.41% in all Wagner-II lesions, mesenchymal SCA (stem cell application) is safe and effective, hence can significantly prevent limb amputation.

Robust and accurate prediction of self-interacting proteins from protein sequence information by exploiting weighted sparse representation based classifier.

BACKGROUND: Self-interacting proteins (SIPs), two or more copies of the protein that can interact with each other expressed by one gene, play a central role in the regulation of most living cells and cellular functions. Although numerous SIPs data can be provided by using high-throughput experimental techniques, there are still several shortcomings such as in time-consuming, costly, inefficient, and inherently high in false-positive rates, for the experimental identification of SIPs even nowadays. Therefore, it is more and more significant how to develop efficient and accurate automatic approaches as a supplement of experimental methods for assisting and accelerating the study of predicting SIPs from protein sequence information. RESULTS: In this paper, we present a novel framework, termed GLCM-WSRC (gray level co-occurrence matrix-weighted sparse representation based classification), for predicting SIPs automatically based on protein evolutionary information from protein primary sequences. More specifically, we firstly convert the protein sequence into Position Specific Scoring Matrix (PSSM) containing protein sequence evolutionary information, exploiting the Position Specific Iterated BLAST (PSI-BLAST) tool. Secondly, using an efficient feature extraction approach, i.e., GLCM, we extract abstract salient and invariant feature vectors from the PSSM, and then perform a pre-processing operation, the adaptive synthetic (ADASYN) technique, to balance the SIPs dataset to generate new feature vectors for classification. Finally, we employ an efficient and reliable WSRC model to identify SIPs according to the known information of self-interacting and non-interacting proteins. CONCLUSIONS: Extensive experimental results show that the proposed approach exhibits high prediction performance with 98.10% accuracy on the yeast dataset, and 91.51% accuracy on the human dataset, which further reveals that the proposed model could be a useful tool for large-scale self-interacting protein prediction and other bioinformatics tasks detection in the future.