Soy Protein Isolate Gel Subjected to Freezing Treatment: Influence of Methylcellulose and Sodium Hexametaphosphate on Gel Stability, Texture and Structure.

Freezing affects texture and induces the loss of gel quality. This study investigated the effects of methylcellulose (MC) (0.2%, 0.4%, 0.6%) and sodium hexametaphosphate (SHMP) (0.15%, 0.3%) on the gel textural and structural properties of SPI gels before and after freezing, and explores the synergistic enhancement of gel texture and the underlying mechanisms resulting from the simultaneous addition of SHMP and MC to SPI gels. It was revealed that MC improved the strength of SPI gels through its thickening properties, but it could not inhibit the reduction of SPI gels after freezing. The 0.4% MC-SPI gel exhibited the best gel strength (193.2 ± 2.4 g). SHMP inhibited gel reduction during freezing through hydrogen bonding and ionic interactions; it enhanced the freezing stability of SPI gels. The addition of 0.15% SHMP made the water-holding capacity in SPI gels reach the highest score after freezing (58.2 ± 0.32%). The synergistic effect of MC and SHMP could improve the strength and the freezing stability of SPI gels. MC facilitated the release of ionizable groups within SPI, causing negatively charged SHMP groups to aggregate on the SPI and inhibit the freezing aggregation of proteins. These results provide a strong basis for the improvement of cryogenic soy protein gel performance by SHMP and MC.

Parametric and non-parametric Poisson regression for modelling of the arterial input function in positron emission tomography.

Full quantification of Positron Emission Tomography (PET) requires an arterial input function (AIF) for measurement of certain targets, or using particular radiotracers, or for the quantification of specific outcome measures. The AIF represents the measurement of radiotracer concentrations in the arterial blood plasma over the course of the PET examination. Measurement of the AIF is prone to error as it is a composite measure created from the combination of multiple measurements of different samples with different equipment, each of which can be sources of measurement error. Moreover, its measurement requires a high degree of temporal granularity for early time points, which necessitates a compromise between quality and quantity of recorded samples. For these reasons, it is often desirable to fit models to this data in order to improve its quality before using it for quantification of radiotracer binding in the tissue. The raw observations of radioactivity in arterial blood and plasma samples are derived from radioactive decay, which is measured as a number of recorded counts. Count data have several specific properties, including the fact that they cannot be negative as well as a particular mean-variance relationship. Poisson regression is the most principled modelling strategy for working with count data, as it both incorporates and exploits these properties. However, no previous studies to our knowledge have taken this approach, despite the advantages of greater efficiency and accuracy which result from using the appropriate distributional assumptions. Here, we implement a Poisson regression modelling approach for the AIF as proof-of-concept of its application. We applied both parametric and non-parametric models for the input function curve. We show that a negative binomial distribution is a more appropriate error distribution for handling overdispersion. Furthermore, we extend this approach to a hierarchical non-parametric model which is shown to be highly resilient to missing data. We thus demonstrate that Poisson regression is both feasible and effective when applied to AIF data, and propose that this is a promising strategy for modelling blood count data for PET in future.

Effect of Na+ and Ca2+ on the texture, structure and microstructure of composite protein gel of mung bean protein and wheat gluten.

To investigate the change of ionic strength on the gel characteristics during the processing of mung bean protein-based foods, the effects of NaCl and CaCl2 at different concentrations (0-0.005 g/mL) on the properties of mung bean protein (MBP) and wheat gluten (WG) composite protein gel were studied. The results showed that low concentration (0.001-0.002 g/mL) could significantly improve the water holding capacity (WHC), storage modulus (G') and texture properties of composite protein gel (MBP/WG), while the surface hydrophobicity (H0) and solubility were significantly decreased (P < 0.05). With the increase of ion concentration, the secondary structures of MBP/WG shifted from α-helix to ß-sheet, and the fluorescence spectra also showed fluorescence quenching phenomenon. By analyzing the intermolecular forces of MBP/WG, it was found that with the addition of salt ions, the hydrogen bonds was weakened and the electrostatic interactions, hydrophobic interactions and disulfide bonds were enhanced, which in turn the aggregation behavior of MBP/WG composite protein gel was affected and larger aggregates between the proteins were formed. It could be also demonstrated that the gel network was denser due to the addition of these large aggregates, thus the gel properties of MBP/WG was improved. However, too many salt ions could disrupt the stable network structure of protein gel. This study can provide theoretical support to expand the development of new mung bean protein products.

Impact of Insoluble Dietary Fiber and CaCl2 on Structural Properties of Soybean Protein Isolate-Wheat Gluten Composite Gel.

The effect and mechanism of soybean insoluble dietary fiber (SIDF) (0~4%) and CaCl2 (0~0.005 M) on the properties of soybean protein isolate (SPI)-wheat gluten (WG) composite gel were studied. It was revealed that the addition of insoluble dietary fiber (1~2%) increased the strength and water-holding capacity (WHC) of the composite gel (p < 0.05) and enhanced the gel network structure compared with the control. WHC and LF-NMR showed that the water-binding ability of the gel system with only 2% SIDF was the strongest. The addition of excessive SIDF increased the distance between protein molecules, impeded the cross-linking of protein, and formed a three-dimensional network with low gel strength. The infrared spectrum and intermolecular force indicated that the interaction between SIDF and SPI were mainly physical, and the hydrophobic interaction and disulfide bond were the main forces in the gel system. The addition of CaCl2 can increase the critical content of gel texture destruction caused by SIDF, and the gel strength attained its peak at 3% SIDF, indicating that appropriate CaCl2 improved gel structure weakening caused by excessive SIDF. This study provides insights in enhancing the production of multi-component composite gel systems.

Use of soybean oil to modulate the gel properties of soybean protein isolation-wheat gluten composite with or without CaCl2.

BACKGROUND: Plant protein is widely used in the study of animal protein substitutes and healthy sustainable products. The gel properties are crucial for the production of plant protein foods. Therefore, the present study investigated the use of soybean oil to modulate the gel properties of soybean protein isolation-wheat gluten composite with or without CaCl2 . RESULTS: Oil droplets filled protein network pores under the addition of soybean oil (1-2%). This resulted in an enhanced gel hardness and water holding capacity. Further addition of soybean oil (3-4%), oil droplets and some protein-oil compounds increased the distance between the protein molecule chain. The results of Fourier transform infrared spectroscopy and intermolecular interaction also showed that the disulfide bond and ß-sheet ratio decreased in the gel system, which damaged the overall structure of the gel network. Compared with the addition of 0 m CaCl2 , salt ion reduced the electrostatic repulsion between proteins, and local protein cross-linking was more intense at 0.005 m CaCl2 concentration. In the present study, structural properties and rheological analysis showed that the overall strength of the gel was weakened after the addition of CaCl2 . CONCLUSION: The presence of appropriate amount of soybean oil can fill the gel pores and improve the texture properties and network structure of soy protein isolate-wheat gluten (SPI-WG) composite gel. Excessive soybean oil may hinder protein-protein interaction and adversely affect protein gel. In addition, the presence or absence of CaCl2 significantly affected the gelling properties of SPI-WG composite protein gels. © 2023 Society of Chemical Industry.

Physicochemical and functional properties of egg white peptide powders under different storage conditions.

This study aims to evaluate the effects of different storage conditions (temperature and relative humidity) on the physicochemical and functional properties of egg white peptide powders (EWPPs). The samples (EWPPs) were stored for 28 d under four conditions (4 °C, 50% RH; 4 °C, 75% RH; 25 °C, 50% RH; 25 °C, 75% RH). Results showed that storage temperature and relative humidity had a significant effect on the physicochemical and functional properties of EWPPs. The contents of antioxidant amino acids such as histidine, tyrosine, tryptophan, and lysine were reduced significantly under different storage conditions, which resulted in the decrease of the antioxidant activity of EWPPs. Circular dichroism spectroscopy analysis indicated that the secondary structure of EWPPs changed from the regular structure to the irregular coiled structure during the storage. Additionally, the hydrophobic groups of the EWPPs originally embedded inside the molecules were exposed to the surface of the molecules during the storage, which led to an aggregation of EWPPs molecule and a decrease in solubility of EWPPs. The aggregation of EWPPs molecules resulted in a decrease in emulsification, emulsification stability, foaming ability and foaming stability of the EWPPs. Therefore, different storage conditions do have an impact on the physicochemical and functional properties of EWPPs. Lower temperature and humidity storing conditions were beneficial to retain the functional property of the EWPPs.

Effect of high-pressure homogenization on Ca2+ -induced gel formation of soybean 11 S globulin.

BACKGROUND: High-pressure homogenization (HPH) is commonly used as a non-thermal processing technique for soybean and soy protein products, and the preparation of soy protein gel products often requires the synergistic effect of HPH and heat treatment. The dissociative association behavior of 11 S is the key to the protein gel formation state. In this study, therefore, 11 S thermal gels were prepared by high-pressure homogenization and co-induction (90 °C, 30 min) (adding Ca2+ to promote gel formation before heat treatment), and the effects of different high-pressure homogenization pressures (0-100 MPa) and co-treatment on the dissociative association behavior of 11 S protein, gel properties, and microstructure of 11 S gels were investigated. RESULTS: The results showed that HPH at higher pressures led to the breaking of disulfide bonds of aggregates and disrupted non-covalent interactions in protein aggregates, leading to collisions between protein aggregates and the reduction of large protein aggregates. High-pressure homogenization treatment at 60 MPa improved the gel properties of 11 S more. The HPH combined with heating changed the binary and tertiary structure of 11 S soy globulin and enhanced the hydrophobic interaction between 11 S molecules, thus improving the gel properties of 11 S. The change in intermolecular forces reflected the positive effect of HPH treatment on the formation of denser and more homogeneous protein gels. CONCLUSION: In conclusion, high-pressure homogenization combined with heating can improve the properties of 11 S gels by changing the structure of 11 S protein, providing data and theoretical support for soy protein processing and its further applications. © 2022 Society of Chemical Industry.

Effect of maltodextrin on the oxidative stability of ultrasonically induced soybean oil bodies microcapsules.

Introduction: Encapsulation of soybean oil bodies (OBs) using maltodextrin (MD) can improve their stability in different environmental stresses and enhance the transport and storage performance of OBs. Methods: In this study, the effects of different MD addition ratios [OBs: MD = 1:0, 1:0.5, 1:1, 1:1.5, and 1:2 (v/v)] on the physicochemical properties and oxidative stability of freeze-dried soybean OBs microcapsules were investigated. The effect of ultrasonic power (150-250 W) on the encapsulation effect and structural properties of oil body-maltodextrin (OB-MD) microcapsules were studied. Results: The addition of MD to OBs decreased the surface oil content and improved the encapsulation efficiency and oxidative stability of OBs. Scanning electron microscopy images revealed that the sonication promoted the adsorption of MD on the surface of OBs, forming a rugged spherical structure. The oil-body-maltodextrin (OB-MD) microcapsules showed a narrower particle size distribution and a lower-potential absolute value at an MD addition ratio of 1:1.5 and ultrasonic power of 250 W (32.1 mV). At this time, MD-encapsulated OBs particles had the highest encapsulation efficiency of 85.3%. Ultrasonic treatment improved encapsulation efficiency of OBs and increased wettability and emulsifying properties of MD. The encapsulation of OBs by MD was improved, and its oxidative stability was enhanced by ultrasound treatment, showing a lower hydrogen peroxide value (3.35 meq peroxide/kg) and thiobarbituric acid value (1.65 µmol/kg). Discussion: This study showed that the encapsulation of soybean OBs by MD improved the stability of OBs microcapsules and decreased the degree of lipid oxidation during storage. Ultrasonic pretreatment further improved the encapsulation efficiency of MD on soybean OBs, and significantly enhanced its physicochemical properties and oxidative stability.

Traditional Chinese medicines and their active ingredients sensitize cancer cells to TRAIL-induced apoptosis.

The rapidly developing resistance of cancers to chemotherapy agents and the severe cytotoxicity of such agents to normal cells are major stumbling blocks in current cancer treatments. Most current chemotherapy agents have significant cytotoxicity, which leads to devastating adverse effects and results in a substandard quality of life, including increased daily morbidity and premature mortality. The death receptor of tumor necrosis factor-related apoptosis-inducing ligand (TRAIL) can sidestep p53-dependent pathways to induce tumor cell apoptosis without damaging most normal cells. However, various cancer cells can develop resistance to TRAIL-induced apoptosis via different pathways. Therefore, it is critical to find an efficient TRAIL sensitizer to reverse the resistance of tumor cells to TRAIL, and to reinforce TRAIL's ability to induce tumor cell apoptosis. In recent years, traditional Chinese medicines and their active ingredients have shown great potential to trigger apoptotic cell death in TRAIL-resistant cancer cell lines. This review aims to collate information about Chinese medicines that can effectively reverse the resistance of tumor cells to TRAIL and enhance TRAIL's ability to induce apoptosis. We explore the therapeutic potential of TRAIL and provide new ideas for the development of TRAIL therapy and the generation of new anti-cancer drugs for human cancer treatment. This study involved an extensive review of studies obtained from literature searches of electronic databases such as Google Scholar and PubMed. "TRAIL sensitize" and "Chinese medicine" were the search keywords. We then isolated newly published studies on the mechanisms of TRAIL-induced apoptosis. The name of each plant was validated using certified databases such as The Plant List. This study indicates that TRAIL can be combined with different Chinese medicine components through intrinsic or extrinsic pathways to promote cancer cell apoptosis. It also demonstrates that the active ingredients of traditional Chinese medicines enhance the sensitivity of cancer cells to TRAIL-mediated apoptosis. This provides useful information regarding traditional Chinese medicine treatment, the development of TRAIL-based therapies, and the treatment of cancer.

Ultrasound-Assisted Mild Heating Treatment Improves the Emulsifying Properties of 11S Globulins.

Ultrasonic technology is often used to modify proteins. Here, we investigated the effects of ultrasound alone or in combination with other heating methods on emulsifying properties and structure of glycinin (11S globulin). Structural alterations were assessed with Sodium dodecyl sulphate-polyacrylamide gel electrophoresis (SDS-PAGE), intrinsic fluorescence spectroscopy, ultraviolet (UV) absorption spectroscopy, and Fourier transform infrared (FTIR) spectroscopy. The size distribution and zeta-potential of 11S globulin were evaluated with a particle size analyzer. An SDS-PAGE analysis showed no remarkable changes in the primary structure of 11S globulin. Ultrasound treatment disrupted the 11S globulin aggregates into small particles with uniform size, narrowed their distribution and increased their surface charge density. Fluorescent spectroscopy and second-derivative UV spectroscopy revealed that ultrasound coupled with heating induced partial unfolding of 11S globulin, increasing its flexibility and hydrophobicity. FTIR further showed that the random coil and α-helix contents were higher while ß-turn and ß-sheet contents were lower in ultrasound combined with heating group compared to the control group. Consequently, the oil-water interface entirely distributed protein and reduced the surface tension. Moreover, ultrasound combined with heating at 60 °C increased the emulsifying activity index and emulsifying stability index of 11S globulins by 6.49-folds and 2.90-folds, respectively. These findings suggest that ultrasound combined with mild heating modifies the emulsification properties of 11S globulin.

Impact of statistical reconstruction and compressed sensing algorithms on projection data elimination during X-ray CT image reconstruction.

OBJECTIVES: To examine the effect of incomplete, or total elimination of, projection data on computed tomography (CT) images subjected to statistical reconstruction and/or compressed sensing algorithms. METHODS: Multidetector row CT images were used. The algebraic reconstruction technique (ART) and the maximum likelihood-expectation maximization (ML-EM) method were compared with filtered back-projection (FBP). Effects on reconstructed images were studied when the projection data of 360° (360 projections) were decreased to 180 or 90 projections by reducing the collection angle or thinning the image data. The total variation (TV) regularization method using compressed sensing was applied to images processed by the ART. Image noise was subjectively evaluated using the root-mean-square error and signal-to-noise ratio. RESULTS: When projection data were reduced by one-half or three-quarters, ART and ML-EM produced better image quality than FBP. Both ART and ML-EM resulted in high quality at a spread of 90 projections over 180° rotation. Computational loading was high for statistical reconstruction, but not for ML-EM, compared with the ART. TV regularization made it possible to use only 36 projections while still achieving acceptable image quality. CONCLUSIONS: Incomplete projection data-accomplished by reducing the angle to collect image data or thinning the projection data without reducing the angle of rotation over which it is collected-made it possible to reduce the radiation dose while retaining image quality with statistical reconstruction algorithms and/or compressed sensing. Despite heavier computational calculation loading, these methods should be considered for reducing radiation doses.

TGF-ß1/Smad3 Signaling Pathway Mediates T-2 Toxin-Induced Decrease of Type II Collagen in Cultured Rat Chondrocytes.

T-2 toxin can cause damage to the articular cartilage, but the molecular mechanism remains unclear. By employing the culture of rat chondrocytes, we investigated the effect of the TGF-ß1/Smad3 signaling pathway on the damage to chondrocytes induced by T-2 toxin. It was found that T-2 toxin could reduce cell viability and increased the number of apoptotic cells when compared with the control group. After the addition of the T-2 toxin, the production of type II collagen was reduced at mRNA and protein levels, while the levels of TGF-ß1, Smad3, ALK5, and MMP13 were upregulated. The production of the P-Smad3 protein was also increased. Inhibitors of TGF-ß1 and Smad3 were able to reverse the effect of the T-2 toxin on the protein level of above-mentioned signaling molecules. The T-2 toxin could promote the level of MMP13 via the stimulation of TGF-ß1 signaling in chondrocytes, resulting in the downregulation of type II collagen and chondrocyte damage. Smad3 may be involved in the degradation of type II collagen, but the Smad3 has no connection with the regulation of MMP13 level. This study provides a new clue to elucidate the mechanism of T-2 toxin-induced chondrocyte damage.

CancerSubtypes: an R/Bioconductor package for molecular cancer subtype identification, validation and visualization.

SUMMARY: Identifying molecular cancer subtypes from multi-omics data is an important step in the personalized medicine. We introduce CancerSubtypes, an R package for identifying cancer subtypes using multi-omics data, including gene expression, miRNA expression and DNA methylation data. CancerSubtypes integrates four main computational methods which are highly cited for cancer subtype identification and provides a standardized framework for data pre-processing, feature selection, and result follow-up analyses, including results computing, biology validation and visualization. The input and output of each step in the framework are packaged in the same data format, making it convenience to compare different methods. The package is useful for inferring cancer subtypes from an input genomic dataset, comparing the predictions from different well-known methods and testing new subtype discovery methods, as shown with different application scenarios in the Supplementary Material. AVAILABILITY AND IMPLEMENTATION: The package is implemented in R and available under GPL-2 license from the Bioconductor website (http://bioconductor.org/packages/CancerSubtypes/). CONTACT: thuc.le@unisa.edu.au or jiuyong.li@unisa.edu.au. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Identifying Cancer Subtypes from miRNA-TF-mRNA Regulatory Networks and Expression Data.

BACKGROUND: Identifying cancer subtypes is an important component of the personalised medicine framework. An increasing number of computational methods have been developed to identify cancer subtypes. However, existing methods rarely use information from gene regulatory networks to facilitate the subtype identification. It is widely accepted that gene regulatory networks play crucial roles in understanding the mechanisms of diseases. Different cancer subtypes are likely caused by different regulatory mechanisms. Therefore, there are great opportunities for developing methods that can utilise network information in identifying cancer subtypes. RESULTS: In this paper, we propose a method, weighted similarity network fusion (WSNF), to utilise the information in the complex miRNA-TF-mRNA regulatory network in identifying cancer subtypes. We firstly build the regulatory network where the nodes represent the features, i.e. the microRNAs (miRNAs), transcription factors (TFs) and messenger RNAs (mRNAs) and the edges indicate the interactions between the features. The interactions are retrieved from various interatomic databases. We then use the network information and the expression data of the miRNAs, TFs and mRNAs to calculate the weight of the features, representing the level of importance of the features. The feature weight is then integrated into a network fusion approach to cluster the samples (patients) and thus to identify cancer subtypes. We applied our method to the TCGA breast invasive carcinoma (BRCA) and glioblastoma multiforme (GBM) datasets. The experimental results show that WSNF performs better than the other commonly used computational methods, and the information from miRNA-TF-mRNA regulatory network contributes to the performance improvement. The WSNF method successfully identified five breast cancer subtypes and three GBM subtypes which show significantly different survival patterns. We observed that the expression patterns of the features in some miRNA-TF-mRNA sub-networks vary across different identified subtypes. In addition, pathway enrichment analyses show that the top pathways involving the most differentially expressed genes in each of the identified subtypes are different. The results would provide valuable information for understanding the mechanisms characterising different cancer subtypes and assist the design of treatment therapies. All datasets and the R scripts to reproduce the results are available online at the website: http://nugget.unisa.edu.au/Thuc/cancersubtypes/.

Inferring microRNA-mRNA causal regulatory relationships from expression data.

MOTIVATION: microRNAs (miRNAs) are known to play an essential role in the post-transcriptional gene regulation in plants and animals. Currently, several computational approaches have been developed with a shared aim to elucidate miRNA-mRNA regulatory relationships. Although these existing computational methods discover the statistical relationships, such as correlations and associations between miRNAs and mRNAs at data level, such statistical relationships are not necessarily the real causal regulatory relationships that would ultimately provide useful insights into the causes of gene regulations. The standard method for determining causal relationships is randomized controlled perturbation experiments. In practice, however, such experiments are expensive and time consuming. Our motivation for this study is to discover the miRNA-mRNA causal regulatory relationships from observational data. RESULTS: We present a causality discovery-based method to uncover the causal regulatory relationship between miRNAs and mRNAs, using expression profiles of miRNAs and mRNAs without taking into consideration the previous target information. We apply this method to the epithelial-to-mesenchymal transition (EMT) datasets and validate the computational discoveries by a controlled biological experiment for the miR-200 family. A significant portion of the regulatory relationships discovered in data is consistent with those identified by experiments. In addition, the top genes that are causally regulated by miRNAs are highly relevant to the biological conditions of the datasets. The results indicate that the causal discovery method effectively discovers miRNA regulatory relationships in data. Although computational predictions may not completely replace intervention experiments, the accurate and reliable discoveries in data are cost effective for the design of miRNA experiments and the understanding of miRNA-mRNA regulatory relationships.

Eight-signature classifier for prediction of nasopharyngeal [corrected] carcinoma survival.

PURPOSE: Currently, nasopharyngeal carcinoma (NPC) prognosis evaluation is based primarily on the TNM staging system. This study aims to identify prognostic markers for NPC. PATIENTS AND METHODS: We detected expression of 18 biomarkers by immunohistochemistry in NPC tumors from 209 patients and evaluated the association between gene expression level and disease-specific survival (DSS). We used support vector machine (SVM)--based methods to develop a prognostic classifier for NPC (NPC-SVM classifier). Further validation of the NPC-SVM classifier was performed in an independent cohort of 1,059 patients. RESULTS: The NPC-SVM classifier integrated patient sex and the protein expression level of seven genes, including Epstein-Barr virus latency membrane protein 1, CD147, caveolin-1, phospho-P70S6 kinase, matrix metalloproteinase 11, survivin, and secreted protein acidic and rich in cysteine. The NPC-SVM classifier distinguished patients with NPC into low- and high-risk groups with significant differences in 5-year DSS in the evaluated patients (87% v 37.7%; P < .001) in the validation cohort. In multivariate analysis adjusted for age, TNM stage, and histologic subtype, the NPC-SVM classifier was an independent predictor of 5-year DSS in the evaluated patients (hazard ratio, 4.9; 95% CI, 3.0 to 7.9) in the validation cohort. CONCLUSION: As a powerful predictor of 5-year DSS among patients with NPC, the newly developed NPC-SVM classifier based on tumor-associated biomarkers will facilitate patient counseling and individualize management of patients with NPC.

Combined feature selection and cancer prognosis using support vector machine regression.

Prognostic prediction is important in medical domain, because it can be used to select an appropriate treatment for a patient by predicting the patient's clinical outcomes. For high-dimensional data, a normal prognostic method undergoes two steps: feature selection and prognosis analysis. Recently, the L1-L2-norm Support Vector Machine (L1-L2 SVM) has been developed as an effective classification technique and shown good classification performance with automatic feature selection. In this paper, we extend L1-L2 SVM for regression analysis with automatic feature selection. We further improve the L1-L2 SVM for prognostic prediction by utilizing the information of censored data as constraints. We design an efficient solution to the new optimization problem. The proposed method is compared with other seven prognostic prediction methods on three realworld data sets. The experimental results show that the proposed method performs consistently better than the medium performance. It is more efficient than other algorithms with the similar performance.

Feature fusion using locally linear embedding for classification.

In most complex classification problems, many types of features have been captured or extracted. Feature fusion is used to combine features for better classification and to reduce data dimensionality. Kernel-based feature fusion methods are very effective for classification, but they do not reduce data dimensionality. In this brief, we propose an effective feature fusion method using locally linear embedding (LLE). The proposed method overcomes the limitations of LLE, which could not handle different types of features and is inefficient for classification. We propose an efficient algorithm to solve the optimization problem in obtaining weights of different features, and design an efficient method for LLE-based classification. In comparison to other kernel-based feature fusion methods, the proposed method fuses features to a significantly lower dimensional feature space with the same discriminant power. We have conducted experiments to demonstrate the effectiveness of the proposed feature fusion method.

Three immunomarker support vector machines-based prognostic classifiers for stage IB non-small-cell lung cancer.

PURPOSE: Approximately 30% of patients with stage IB non-small-cell lung cancer (NSCLC) die within 5 years after surgery. Current staging methods are inadequate for predicting the prognosis of this particular subgroup. This study identifies prognostic markers for NSCLC. PATIENTS AND METHODS: We used computer-generated random numbers to study 148 paraffin-embedded specimens for immunohistochemical analysis. We studied gene expression in paraffin-embedded specimens of lung cancer tissue from 73 randomly selected patients with stage IB NSCLC who had undergone radical surgical resection and evaluated the association between the level of expression and survival. We used support vector machines (SVM)-based methods to develop three immunomarker-SVM-based prognostic classifiers for stage IB NSCLC. For validation, we used randomly assigned specimens from 75 other patients. RESULTS: We devised three immunomarker-SVM-based prognostic classifiers, including SVM1, SVM2, and SVM3, to refine prognosis of stage IB NSCLC successfully. The SVM1 model integrates age, cancer cell type, and five markers, including CD34MVD, EMA, p21ras, p21WAF1, and tissue inhibitors of metalloproteinases (TIMP) -2. The SVM2 model integrates age, cancer cell type, and 19 markers, including BCL2, caspase-9, CD34MVD, low-molecular-weight cytokeratin, high-molecular-weight cytokeratin, cyclo-oxygenase-2, EMA, HER2, matrix metalloproteinases (MMP) -2, MMP-9, p16, p21ras, p21WAF1, p27kip1, p53, TIMP-1, TIMP-2, vascular endothelial growth factor (VEGF), and beta-catenin. The SVM3 model consists of SVM1 and SVM2. The three models were independent predictors of overall survival. We validated the classifiers with data from an independent cohort of 75 patients with stage IB NSCLC. CONCLUSION: The three immunomarker-SVM-based prognostic characteristics are closely associated with overall survival among patients with stage IB NSCLC.