Search

Objective: To determine whether the introducer curving technique is useful in decreasing the degree of tilting of transfemoral Tulip filters., Materials and Methods: The study sample group consisted of 108 patients with deep vein thrombosis who were enrolled and planned to undergo thrombolysis, and who accepted transfemoral Tulip filter insertion procedure. The patients were randomly divided into Group C and Group T. The introducer curving technique was Adopted in Group T. The post-implantation filter tilting angle (ACF) was measured in an anteroposterior projection. The retrieval hook adhering to the vascular wall was measured via tangential cavogram during retrieval., Results: The overall average ACF was 5.8 ± 4.14 degrees. In Group C, the average ACF was 7.1 ± 4.52 degrees. In Group T, the average ACF was 4.4 ± 3.20 degrees. The groups displayed a statistically significant difference (t = 3.573, p = 0.001) in ACF. Additionally, the difference of ACF between the left and right approaches turned out to be statistically significant (7.1 ± 4.59 vs. 5.1 ± 3.82, t = 2.301, p = 0.023). The proportion of severe tilt (ACF ≥ 10°) in Group T was significantly lower than that in Group C (9.3% vs. 24.1%, χ(2) = 4.267, p = 0.039). Between the groups, the difference in the rate of the retrieval hook adhering to the vascular wall was also statistically significant (2.9% vs. 24.2%, χ(2) = 5.030, p = 0.025)., Conclusion: The introducer curving technique appears to minimize the incidence and extent of transfemoral Tulip filter tilting.

Anticancer drugs such as biological therapeutic proteins and peptides are used for treatment of a variety of tumors. However, their wider use has been hindered by their poor bioavailability and the uncontrollable sites of action in vivo. Cancer nano-therapeutics is rapidly progressing, which is being applied for solving some limitations of conventional drug delivery systems. To improve the bio-distribution of anticancer drugs, carbon nanotubes have been used as one of the most effective drug carriers. This review discusses the carbon nanotubes-mediated methods for the delivery of anticancer drugs, with emphasis on the radiation-induced drug-targeted releasing and selective photo-thermal cancer therapy.

Objective: To study the efficacy and safety of 125I particle implantation in the treatment of rhabdomysarcoma (RMS) of the head and neck in children., Methods: Eight children (four males and four females) with RMS of the head and neck received 125I particle implantation targeted to the primary lesion area. The primary lesions were noted in eyelids or eyes in two children, in the orbit in four children, and in the nasal cavity or nasal wing in two children. Treatment outcomes and side effects were observed., Results: The follow-up visits averaged 45±17 months (median 43 months) in the eight children receiving 125I particle implantation. Five children achieved a complete remission, 2 children achieved a complete remission and 1 child died. The total survival rate was 88% in the 8 children. Local pigmentation was observed in all eight children (100%). Nubecula (one case), eyeball pain (one case), serious blurred vision (one case), cornea ulcer and blindness (one case) and bleeding of the nasal cavity (one case) were also observed. Except for nubecula and blindness, these side effects were improved by symptomatic treatment., Conclusions: 125I particle implantation appears to be effective in the treatment of RMS of the head and neck in children. Most treatment-related side effects can be improved by symptomatic treatment.

Background: Protein-protein interactions (PPIs) play crucial roles in virtually every aspect of cellular function within an organism. Over the last decade, the development of novel high-throughput techniques has resulted in enormous amounts of data and provided valuable resources for studying protein interactions. However, these high-throughput protein interaction data are often associated with high false positive and false negative rates. It is therefore highly desirable to develop scalable methods to identify these errors from the computational perspective., Results: We have developed a robust computational technique for assessing the reliability of interactions and predicting new interactions by combining manifold embedding with multiple information integration. Validation of the proposed method was performed with extensive experiments on densely-connected and sparse PPI networks of yeast respectively. Results demonstrate that the interactions ranked top by our method have high functional homogeneity and localization coherence., Conclusions: Our proposed method achieves better performances than the existing methods no matter assessing or predicting protein interactions. Furthermore, our method is general enough to work over a variety of PPI networks irrespectively of densely-connected or sparse PPI network. Therefore, the proposed algorithm is a much more promising method to detect both false positive and false negative interactions in PPI networks.

Objective: To explore the brain natriuretic peptide (BNP) on prognostic value in patients with viral myocarditis., Methods: A total of 48 patients with viral myocarditis and 42 healthy people were enrolled and followed up for two years. The NYHA class and LVEF were recorded and the concentration of BNP were measured., Results: The concentration of BNP were higher and EF were lower in patients with viral myocarditis (P < 0.01) than contrast people. Higher levels of plasma BNP were related to higher mortality., Conclusion: Levels of brain natriuretic peptide measured in the plasma could be a useful biochemical marker for the myocarditis, and high concentration of BNP may correlate with poor prognosis in patients with myocarditis.

Background: The purpose of this study was to assess the efficacy of interventional therapy for peripheral arterial occlusive disease and the difference between diabetic patients and non-diabetic patients., Methods: 139 consecutive patients between September 2006 and September 2010 who underwent percutaneous lower extremity revascularization for arterial lesions were divided into diabetes group (n = 62) and non-diabetes group (n = 77). Before intervention, rest ankle brachial indexes and three dimensional computed tomography angiography from abdominal aorta to tiptoe were performed. The interventional treatments included angioplasty with or without stenting. The clinical outcomes included rest ankle-brachial indexes, primary patency rates, secondary patency rates and limb-salvage rates for 6-month, 12-month, 24-month and 36-month after treatment. The primary and secondary patency rates of all interventions and the limb-salvage rates of the patients are illustrated by Kaplan-Meier curves and compared by log-rank analysis., Results: The interventional operation success rates were 98.4% (61/62) in diabetes group and 100% (77/77) in non-diabetes group. The re-interventional operation success rates were 85.7% (18/21) in diabetes group and 76.9% (20/26) in non-diabetes group. The mean value of ankle brachial indexes was significantly increased after intervention (0.397 ± 0.125 versus 0.779 ± 0.137, t = -25.780, P < 0.001) in diabetes group and (0.406 ± 0.101 versus 0.786 ± 0.121, t = -37.221, P < 0.001) in non-diabetes group. Perioperative 30-day mortality was 0%. Major complications included groin hematoma in 7.2%, and pseudoaneurysm formation 2.2%. In diabetes group, 6, 12, 24, and 36-month primary patency rates were 88.7% ± 4.0%, 62.3% ± 6.6%, 55.3% ± 7.0%, and 46.5% ± 7.5%; secondary patency rates were 93.5% ± 3.1%, 82.3% ± 5.1%, 70.8% ± 6.5%, and 65.7% ± 7%; limb-salvage rates were 95.2% ± 2.7%, 87.7% ± 4.4%, 85.5% ± 4.8%, and 81.9% ± 5.8%. In non-diabetes group, 6, 12, 24, and 36-month primary patency rates were 90.9% ± 3.3%, 71.8% ± 5.4%, 71.8% ± 5.4%, and 60.9% ± 6.2%; secondary patency rates were 96.1% ± 2.2%, 91.6% ± 3.3%, 82.7% ± 4.8%, and 71.8% ± 6.2%; limb-salvage rates were 97.4% ± 1.8%, 94.4% ± 2.7%, 90.6% ± 3.7%, and 83.1% ± 5.4%. The differences between two groups were not significant (P > 0.05)., Conclusion: With a low risk of morbidity and mortality, the percutaneous revascularization accepted by patients does not affect ultimate necessary surgical revascularization and consequently should be considered as the preferred therapy for chronic lower extremity ischemia. The efficacy and prognosis of interventional therapy in diabetic patients is similar that in non-diabetic patients.

Objective: With the background of aging population in China and advances in clinical medicine, the amount of operations on old patients increases correspondingly, which imposes increasing challenges to critical care medicine and geriatrics. The study was designed to describe information on the length of ICU stay from a single institution experience of old critically ill gastric cancer patients after surgery and the framework of incorporating data-mining techniques into the prediction., Methods: A retrospective design was adopted to collect the consecutive data about patients aged 60 or over with a gastric cancer diagnosis after surgery in an adult intensive care unit in a medical university hospital in Shenyang, China, from January 2010 to March 2011. Characteristics of patients and the length their ICU stay were gathered for analysis by univariate and multivariate Cox regression to examine the relationship with potential candidate factors. A regression tree was constructed to predict the length of ICU stay and explore the important indicators., Results: Multivariate Cox analysis found that shock and nutrition support need were statistically significant risk factors for prolonged length of ICU stay. Altogether, seven variables entered the regression model, including age, APACHE II score, SOFA score, shock, respiratory system dysfunction, circulation system dysfunction, diabetes and nutrition support need. The regression tree indicated comorbidity of two or more kinds of shock as the most important factor for prolonged length of ICU stay in the studied sample., Conclusions: Comorbidity of two or more kinds of shock is the most important factor of length of ICU stay in the studied sample. Since there are differences of ICU patient characteristics between wards and hospitals, consideration of the data-mining technique should be given by the intensivists as a length of ICU stay prediction tool.

Tumor classification based on gene expression profiles, which is of great benefit to the accurate diagnosis and personalized treatment for different types of tumor, has drawn a great attention in recent years. This paper proposes a novel tumor classification method based on correlation filters to identify the overall pattern of tumor subtype hidden in differentially expressed genes. Concretely, two correlation filters, i.e., Minimum Average Correlation Energy (MACE) and Optimal Tradeoff Synthetic Discriminant Function (OTSDF), are introduced to determine whether a test sample matches the templates synthesized for each subclass. The experiments on six publicly available datasets indicate that the proposed method is robust to noise, and can more effectively avoid the effects of dimensionality curse. Compared with many model-based methods, the correlation filter based method can achieve better performance when balanced training sets are exploited to synthesize the templates. Particularly, the proposed method can detect the similarity of overall pattern while ignoring small mismatches between test sample and the synthesized template. And it performs well even if only few training samples are available. More importantly, the experimental results can be visually represented, which is helpful for the further analysis of results.

A reliable and precise identification of the type of tumors is crucial to the effective treatment of cancer. With the rapid development of microarray technologies, tumor clustering based on gene expression data is becoming a powerful approach to cancer class discovery. In this paper, we apply the penalized matrix decomposition (PMD) to gene expression data to extract metasamples for clustering. The extracted metasamples capture the inherent structures of samples belong to the same class. At the same time, the PMD factors of a sample over the metasamples can be used as its class indicator in return. Compared with the conventional methods such as hierarchical clustering (HC), self-organizing maps (SOM), affinity propagation (AP) and nonnegative matrix factorization (NMF), the proposed method can identify the samples with complex classes. Moreover, the factor of PMD can be used as an index to determine the cluster number. The proposed method provides a reasonable explanation of the inconsistent classifications made by the conventional methods. In addition, it is able to discover the modules in gene expression data of conterminous developmental stages. Experiments on two representative problems show that the proposed PMD-based method is very promising to discover biological phenotypes.

Objective: To determine whether the matrix metalloproteinase 9 gene (MMP9) polymorphism is associated with the onset or progression of adolescent idiopathic scoliosis (AIS) in Chinese Han female., Methods: Three single nucleotide polymorphisms (SNPs) (rs17576, rs2250889, rs1805088) were genotyped through TaqMan-based real-time PCR assay in 190 AIS patients and 190 controls, all of whom were females from Chinese Han population with matched age. Analyses performed included Hardy Weinberg equilibrium test, Pearson chi-square test, Logistic regression analysis, linkage disequilibrium analysis and haplotype analysis. The mean maximum Cobb angles with different genotypes in case-only dataset were also compared., Results: All 3 SNPs have reached Hardy-Weinberg equilibrium in the controls. Genotype and allele frequencies of all SNPs were found similar between cases and controls by Pearson chi-square test and Logistic regression. Genotype-phenotype analysis showed that patients with CC genotype in rs2250889 featured larger maximum Cobb angles., Conclusion: MMP9 may not be a predisposition gene of AIS in Han female. However, homozygous mutation in rs2250889 can render scoliosis more severe, implying that MMP9 defect may result in deterioration of AIS.

A reliable and accurate identification of the type of tumors is crucial to the proper treatment of cancers. In recent years, it has been shown that sparse representation (SR) by l1-norm minimization is robust to noise, outliers and even incomplete measurements, and SR has been successfully used for classification. This paper presents a new SR-based method for tumor classification using gene expression data. A set of metasamples are extracted from the training samples, and then an input testing sample is represented as the linear combination of these metasamples by l1-regularized least square method. Classification is achieved by using a discriminating function defined on the representation coefficients. Since l1-norm minimization leads to a sparse solution, the proposed method is called metasample-based SR classification (MSRC). Extensive experiments on publicly available gene expression data sets show that MSRC is efficient for tumor classification, achieving higher accuracy than many existing representative schemes.

Aseptic joint loosening is a key factor that reduces the life span of arthroplasty. There are currently few effective treatments for joint loosening except surgical revision. We explored the inhibitory effects of tumor necrosis factor (TNF)-alpha-targeted small interfering RNA (siRNA) on particle-induced inflammatory cytokine expression in the murine macrophage cell line, RAW264.7. siRNA targeting TNF-alpha was chemically synthesized and transfected into RAW264.7 cells by cationic liposomes. Ceramic, titanium, and polyethylene particles of different sizes (0.2-1.2 µm and 1.2-10 µm) were prepared to stimulate cells 24 h after siRNA transfection. The down-regulation of TNF-alpha mRNA and protein levels was quantitatively determined using real-time polymerase chain reaction (PCR) and enzyme-linked immunosorbent assay (ELISA), respectively, at different time intervals. Fluorescence microscopy showed that the siRNA transfection efficiency was 85.2% ± 3.5%. Real-time PCR showed that the levels of TNF-alpha mRNA in the particle stimulation plus RNA interference (RNAi) groups were significantly lower compared with the particle stimulation-only groups 3 h after stimulation (P < 0.05). Similarly, ELISA essays showed that the protein levels of TNF-alpha in the RNAi-treated groups were significantly decreased 24 h after transfection (P < 0.05). There were no significant differences in the inhibitory effect among the groups stimulated by different particle types or particle sizes (P > 0.05). Our results indicated that siRNA targeting TNF-alpha can inhibit TNF-alpha release from RAW264.7 cells when stimulated by ceramic, titanium, and polyethylene particles of different sizes and that the inhibitory effects were not related to the type or size of particle., (© 2011, Copyright the Authors. Artificial Organs © 2011, International Center for Artificial Organs and Transplantation and Wiley Periodicals, Inc.)

Hepatocellular carcinoma (HCC) is one of the most common cancers worldwide, and is characterized by a high degree of malignancy and a low survival rate. Most HCCs express insulin-like growth factors and their receptors (IGF-IR), which mediate signaling, promote survival and invasion, and prevent apoptosis. Thus, they may be potential targets for the treatment of HCCs. In the present study, the potential therapeutic effect of Tyrphostin AG1024 in HCC was examined. After treatment with various concentrations of AG1024 (one selective inhibitor of IGF-IR), AG1024 not only dose-dependently inhibited the proliferation of HCC cells and induced apoptosis, but also markedly inhibited invasion ability. Expression of proteins detected by Western blot analysis revealed that AG1024 dose-dependently increased the expression of cytochrome C, while procaspase-3 and phospho-ERK were down-regulated. Thus, IGF-IR inhibition may be a promising novel approach to the treatment of HCC.

Objective: Autologous peripheral blood stem cell transplantation (APBSCT) is an important method for treatment of malignant solid tumors in children. The mobilization and collection of blood stem cells is crucial for APBSCT. This study aimed to evaluate the clinical efficacy of mobilization and collection of blood stem cells by CIE or IEV chemotherapy protocol in APBSCT in children with neuroblastoma (NB) or rhabdomyosarcoma., Methods: The protocols of CIE (cisplatin, etoposide) and IEV (vincristine, dosfamide, etoposide) were used as mobilization chemotherapy in 8 cases of NB with stage IV and 3 cases of rhabdomysacoma with stage III, respectively. The results of the mobilization of blood stem cells were observed., Results: Of the 11 cases, mononuclear cells (MNC) and CD34+ cells were successfully collected and the volume of MNC and CD34 averaged (5.55 ± 1.43)× 10(8)/kg and (4.88 ± 2.48) × 10(6)/kg, respectively. No severe complications were observed during the mobilization and collection. A rapid hemopoietic reconstitution was observed in 10 children after APBSCT. One with NB out of the 10 children died of left heart failure 32 days after APBSCT. Others (9 cases) showed a nearly normal result of routine peripheral blood test 60 days after APBSCT., Conclusions: CIE or IEV protocol is effective and safe for the mobilization and collection of peripheral blood stem cells in children with NB or rhabdomysacoma.

Sipjeondaebo-tang (SDT, Juzen-taiho-to in Japanese), a traditional Korean herbal medicine, is used as a supplemental treatment for the adverse effects of chemotherapy, radiation therapy, and surgical treatment. However, limited information is available about the long-term safety of SDT. Therefore, we evaluated the potential adverse effects of SDT in Sprague-Dawley rats over a period of 13-weeks. The SDT was administered once daily by gavage to male and female rats at dose levels of 0, 250, 500, 1000 and 2000 mg/kg/day for 13 weeks. The SDT treatment did not result in any toxicologically significant changes in mortality, clinical signs, body weights, food and water consumption, ophthalmoscopy, urinalysis, hematology, serum biochemistry, gross findings, organ weights, histopathology, estrus cycle, serum testosterone levels and sperm analysis. We concluded that the 13-week repeated oral administration of SDT did not cause any adverse effects in rats at dose levels of ≤ 2000 mg/kg/day. Under these experimental conditions, the no-observed-adverse-effect level (NOAEL) was more than 2000 mg/kg/day for both genders. Here, we demonstrated the safety of a 13-week repeated oral dose and considered that it is a safe herbal medicine for human consumption., (Copyright © 2011. Published by Elsevier Inc.)

Background: StentBoost (SB) is a novel angiographic technique which can enhance stent visualization and improve detection of inadequate stent expansion. Studies of SB that compare it with intravascular ultrasound (IVUS), which is the current gold standard for detection of stent underexpansion, remain inadequate. This study aimed to test the correlation of IVUS and SB, and to evaluate the effect of SB guiding the stent postdilatation., Methods: From March 2009 to June 2010, 52 patients were analyzed using quantitative coronary angiography (QCA), IVUS, and SB. They included 37 patients (54 stents) with postdilatation and 15 patients (21 stents) without postdilatation. Correlations of stent diameter between the three modalities were determined., Results: The minimum diameter, maximum diameter and average diameter of postdilatation obtained by QCA, IVUS, SB were significantly larger than that of poststenting, and the ratio (maximum stent diameter (MaxLD)-minimum stent diameter (MinLD))/MaxLD of postdilatation was smaller. Correlations of MinLD were the highest between IVUS and SB (r = 0.979, P < 0.0001) when compared with QCA and SB (r = 0.973, P < 0.0001), and QCA and IVUS (r = 0.964, P < 0.0001)., Conclusions: SB has superior correlations for stent expansion measured by IVUS when compared with QCA. In addition, there is an important advantage for SB in guiding the stent postdilatation.

Three-dimensional quantitative structure-activity relationship (3D-QSAR) studies were performed on Frusectose-1, 6-bisphosphatase (FBPase) inhibitors, based on molecular docking obtained by using GOLD and comparative molecular field analysis (CoMFA). Three random splits into training and test sets had been performed and the high leave-one-out (LOO) cross-validated correlation coefficients q(2) of 0.781, 0.725 and 0.801, respectively, revealed that the models are useful tools for the prediction of test sets as well as newly designed structures against FBPase activity. The superimposed CoMFA models on the receptor site of FBPase are guiding the design of potential inhibitory structures directed against FBPase activity., (Copyright © 2011 Elsevier Masson SAS. All rights reserved.)

Ethnopharmacological Relevance: Pyungwi-san (PWS, Heii-san in Japanese) is a mixture of six herbs and is traditionally used in Northeast Asia (especially Korea and Japan) for the treatment of gastrointestinal disorder, such as dyspepsia and inappetance induced by gastric dilatation and gastrointestinal catarrh., Aim of the Study: Although PWS is a widely used herbal prescription in Korea and Japan, little information is available in the literature on the safety and toxicity of PWS. As part of a safety evaluation of PWS, the present study evaluated the potential genotoxicity of PWS using a standard battery of test., Materials and Methods: We prepared PWS using a water extraction method and simultaneously extracted three compounds from PWS using high performance liquid chromatography. The PWS extract that was obtained was assayed for genotoxicity using the standard three tests recommended by the Korea Food and Drug Administration. These tests included the bacterial reverse mutation test (Ames test), the chromosomal aberration test using China hamster lung cells, and the micronucleus test using ICR mice., Results: The Ames test showed that the PWS extract did not induce an increase in the number of revertant colonies compared with vehicle control at any dose in all of tester strains. In the micronucleus test, no significant increase was observed in micronucleated polychromatic erythrocytes (MNPCEs) at any dose of PWS extract compared with vehicle control. Conversely, chromosomal aberration test showed that the PWS extract at a dosage of 4500 μg/mL induced an increase in the number of chromosomal aberrations in the 6 h group with metabolic activation compared with the vehicle control., Conclusion: PWS extract exhibits genotoxicity, based on the results of the chromosomal aberration test. Thus, further detailed experiments will be needed to identify the ingredient responsible for inducing this genotoxicity and to determine its mechanism., (Copyright © 2010 Elsevier Ireland Ltd. All rights reserved.)

Objective: Many countries carry a high cancer burden and comprehensive cancer nursing is becoming increasingly complicated and difficult. Summarizing the recent research focus on cancer nursing may provide a snapshot of this field for those nurses or nurse educators who are in need of a quick overview of the research and its utilization., Methods: Candidate publications from January 1st 2001 to March 31st 2011 were collected by searching PubMed with the MeSH word 'oncologic nursing' and without language restriction. Bibliometric techniques used in this study included a statistical analysis of publication counts by authors, countries and journals and a co-word cluster analysis of highly-frequent MeSH words., Results: A total of 2933 publications about cancer nursing from 246 journals were indexed in PubMed, with Oncology Nursing Forum identified as the top contributing journal in the field. The United States, the United Kingdom and Canada were the largest three producer countries about cancer nursing. A total of 34 highly-frequent MeSH words for more than 100 times' occurrences in the papers about oncologic nursing were extracted for cluster analysis. These words were classified into 3 aspects: (1) nursing practice; (2) nursing evaluation and education; (3) nursing-related social support., Conclusions: Stable growth has occurred in the research field of cancer nursing. The limited amount of the publications from developing countries indicates that the field is still under-developed. Emerging topics of nurse-patient relations and social support provide some hints of the need to provide more target training for the nurses and nurse students in the field of cancer nursing.

Yukmijihwang-tang (YMJ; Liu wei di huang tang (China), Rokumigan (Japan)) has been used in the treatment of diseases including renal disorder, cognitive vitality, and diabetes mellitus. However, there is very little information regarding the toxicity of YMJ to give an assurance of safety for clinical treatment. To provide safety information for YMJ, we evaluated its acute and sub-chronic toxicity in rats. The single-dose toxicity of YMJ was examined using Sprague-Dawley rats. Rats were treated with YMJ extract orally at 0, 500, 1000, or 2000 mg/kg body weight. After a single administration, clinical signs were observed every day for two weeks, and body weights were measured five times, including an initial measurement on day 1 (the day of administration). In the sub-chronic oral toxicity study, YMJ was administered to rats at 0, 500, 1000, or 2000 mg/kg/day for 13 weeks. Mortalities, clinical signs, body weight changes, food and water consumption, ophthalmologic findings, urinalysis, hematological and biochemical parameters, gross findings, organ weights, and histological examination were monitored during the study period. We found no mortality and no abnormalities in clinical signs, body weights, and necropsy findings for any of the animals in the acute and sub-chronic studies following oral administration in the rat at up to 2000 mg/kg/day YMJ. YMJ may not have any single-dose toxicity; the LD(50) of YMJ was over 2000 mg/kg, and it is safe for rats. The no-observed-adverse-effect-level (NOAEL) was considered to be 2000 mg/kg/day.

Attention is a critical mechanism for visual scene analysis. By means of attention, it is possible to break down the analysis of a complex scene to the analysis of its parts through a selection process. Empirical studies demonstrate that attentional selection is conducted on visual objects as a whole. We present a neurocomputational model of object-based selection in the framework of oscillatory correlation. By segmenting an input scene and integrating the segments with their conspicuity obtained from a saliency map, the model selects salient objects rather than salient locations. The proposed system is composed of three modules: a saliency map providing saliency values of image locations, image segmentation for breaking the input scene into a set of objects, and object selection which allows one of the objects of the scene to be selected at a time. This object selection system has been applied to real gray-level and color images and the simulation results show the effectiveness of the system., (Copyright © 2010 Elsevier Ltd. All rights reserved.)

Objective: to explore the effect of simvastatin on alveolar epithelial cells and the expression of vascular endothelial growth factor (VEGF) in cigarette smoking-induced emphysema in rats., Methods: twenty-four, 12-week-old healthy male and female Wistar rats were randomly divided into 4 groups of 6 each: a control (W) group, a smoking (Sm) group, a simvastatin (St) group, and a smoking-simvastatin (SmSt) group. The rats were simultaneously fed, and kept in individual cages for 16 weeks. The VEGF level in lung tissue and bronchoalveolar lavage fluid (BALF) of each group was measured by ELISA. The expression of VEGF mRNA was determined by RT-PCR. The expressions of VEGF and proliferating cell nuclear antigen (PCNA) were determined by two-step immunohistochemistry assay. One-way ANOVA and LSD-t test were used for statistical analysis., Results: the percentage of PCNA-positively stained alveolar epithelial cells was significantly higher in the SmSt group [(10.3 ± 2.0)%] than in the Sm group [(4.8 ± 0.8)%]. The levels of VEGF in BALF and lung tissue homogenate of the SmSt group [(187 ± 15) ng/L and (6782 ± 50) ng/L] were similar to the W group [(200 ± 20) ng/L and (7558 ± 330) ng/L], but were significantly higher than that in the Sm group [(71 ± 16) ng/L and (4149 ± 110) ng/L]. VEGF expression in alveolar and bronchial epithelial cells of rats in the SmSt group [(67.7 ± 5.0)% and (49.0 ± 3.0)%], was similar to the W group [(68.3 ± 3.3)% and (51.3 ± 2.9)%]. But the level of VEGF expression was significantly increased as compared to that in the Sm group [(27.0 ± 5.9)% and (16.3 ± 2.7)%]. SmSt group vs Sm group t = 1.117 - 12.001, all P < 0.01., Conclusions: simvastatin ameliorated the development of cigarette smoke-induced COPD in rats, partly by promoting alveolar epithelial cell proliferation and up-regulating the expression of VEGF.

A novel method is proposed for predicting protein-protein interactions (PPIs) based on the meta approach, which predicts PPIs using support vector machine that combines results by six independent state-of-the-art predictors. Significant improvement in prediction performance is observed, when performed on Saccharomyces cerevisiae and Helicobacter pylori datasets. In addition, we used the final prediction model trained on the PPIs dataset of S. cerevisiae to predict interactions in other species. The results reveal that our meta model is also capable of performing cross-species predictions. The source code and the datasets are available at http://home.ustc.edu.cn/~jfxia/Meta&#95;PPI.html.

Motivation: High-throughput protein interaction data, with ever-increasing volume, are becoming the foundation of many biological discoveries, and thus high-quality protein-protein interaction (PPI) maps are critical for a deeper understanding of cellular processes. However, the unreliability and paucity of current available PPI data are key obstacles to the subsequent quantitative studies. It is therefore highly desirable to develop an approach to deal with these issues from the computational perspective. Most previous works for assessing and predicting protein interactions either need supporting evidences from multiple information resources or are severely impacted by the sparseness of PPI networks., Results: We developed a robust manifold embedding technique for assessing the reliability of interactions and predicting new interactions, which purely utilizes the topological information of PPI networks and can work on a sparse input protein interactome without requiring additional information types. After transforming a given PPI network into a low-dimensional metric space using manifold embedding based on isometric feature mapping (ISOMAP), the problem of assessing and predicting protein interactions is recasted into the form of measuring similarity between points of its metric space. Then a reliability index, a likelihood indicating the interaction of two proteins, is assigned to each protein pair in the PPI networks based on the similarity between the points in the embedded space. Validation of the proposed method is performed with extensive experiments on densely connected and sparse PPI network of yeast, respectively. Results demonstrate that the interactions ranked top by our method have high-functional homogeneity and localization coherence, especially our method is very efficient for large sparse PPI network with which the traditional algorithms fail. Therefore, the proposed algorithm is a much more promising method to detect both false positive and false negative interactions in PPI networks., Availability: MATLAB code implementing the algorithm is available from the web site http://home.ustc.edu.cn/∼yzh33108/Manifold.htm.

Gene expression data collected from DNA microarray are characterized by a large amount of variables (genes), but with only a small amount of observations (experiments). In this paper, manifold learning method is proposed to map the gene expression data to a low dimensional space, and then explore the intrinsic structure of the features so as to classify the microarray data more accurately. The proposed algorithm can project the gene expression data into a subspace with high intra-class compactness and inter-class separability. Experimental results on six DNA microarray datasets demonstrated that our method is efficient for discriminant feature extraction and gene expression data classification. This work is a meaningful attempt to analyze microarray data using manifold learning method; there should be much room for the application of manifold learning to bioinformatics due to its performance., (Copyright © 2010 Elsevier Ltd. All rights reserved.)

Investigation of a Chinese folk medicine, Artemisia dubia (syn. Artemisia subdigitata), has resulted in the isolation of eight new guaianolides (artemdubolides A-H, 1-8), and nineteen known sesquiterpene lactones. Their structures were elucidated primarily on the basis of spectroscopic methods, including extensive 2D NMR experiments. The cytotoxic activities of compounds 1-8 were evaluated against A549 (human lung adenocarcinoma), Colo205 (human colon carcinoma), HepG2 (human hepatoma), and MDA-MB-435 (human melanoma) cell lines. Compounds 2 and 5 showed weak cell growth inhibition of Colo205 and MDA-MB-435 cells., (© Georg Thieme Verlag KG Stuttgart · New York.)

Objective: To study the curative effect of operation to flatfoot deformity with concurrent spinal disease in children., Methods: A retrospective survey was performed in 8 flatfoot patients with concurrent spinal disease from January 2004 to January 2008. Every case received special operative treatment. After casting, achilles tendon prolongation, reefing or tendon transfer, rehabilitation therapy was performed sequentially. Radiographs and clinical outcomes were evaluated during the follow-up., Results: Six patients were followed up. There were 2 feet in 1 female and 7 feet in 5 males. The complications included tethered cord syndrome (n = 1), T12-S1 vertebral canal arachnoid cyst (n = 1), cerebral palsy and scoliosis (n = 1) and scoliosis and spinal bifida occult (n = 3). The average age was 8.4 (4 - 14) years old and the average follow-up time 22 (14 - 64) months. All cases were satisfied with the appearance and function according to Maryland foot score. Five were excellent, 2 good and 2 fair postoperatively versus 2 fair and 7 failed preoperatively. The total excellent and good rate was 77.8%. In the early stage after tendon transfer in 4 patients, the lateral view of height arch, talus-first metatarsal angle, calcaneus-navicular-first metatarsal angle and talonavicular coverage angle improved. Yet it lost the improved angle and reverted to the pre-operative state. No degenerative change was detected in tarsus joints during the long follow-up., Conclusion: The special and sequential surgical procedure may be an effective regimen in the treatment of flatfoot deformity with concurrent spinal disease in children.

Background: To explore the anti-tumor effects of parthenolide in human pancreatic cancer., Methods: BxPC-3 cell, a human pancreatic cancer, was treated with parthenolide at different concentrations. The MTT assay was used to analyze cell viability. Flow cytometry and DNA fragmentation analysis were applied to evaluate apoptosis after parthenolide treatment. The wound closure and cell invasion assay were also employed in the study. Western blotting was used to demonstrate Bad, Bcl-2, Bax, caspase-9 and pro-caspase-3 expression., Results: The MTT assay indicated that the pancreatic cancer growth could be dose-dependently inhibited by parthenoolide. This phenomenon was confirmed by flow cytometry and DNA fragmentation analysis. The wound closure assay and cell invasion assay showed that BxPC-3 cell was significantly suppressed by parthenolide at 7.5 microM and 15 microM. Western Blotting demonstrated the Bcl-2 and pro-caspase-3 were down-regulated while the Bax and caspase-9 were up-regulated. No alteration in Bad expression was found after treatment., Conclusions: The parthenolide can inhibit the cell growth, migration, and induce the apoptosis in human pancreatic cancer. These findings may provide a novel approach for pancreatic cancer treatment.

Background: Genetic interaction profiles are highly informative and helpful for understanding the functional linkages between genes, and therefore have been extensively exploited for annotating gene functions and dissecting specific pathway structures. However, our understanding is rather limited to the relationship between double concurrent perturbation and various higher level phenotypic changes, e.g. those in cells, tissues or organs. Modifier screens, such as synthetic genetic arrays (SGA) can help us to understand the phenotype caused by combined gene mutations. Unfortunately, exhaustive tests on all possible combined mutations in any genome are vulnerable to combinatorial explosion and are infeasible either technically or financially. Therefore, an accurate computational approach to predict genetic interaction is highly desirable, and such methods have the potential of alleviating the bottleneck on experiment design., Results: In this work, we introduce a computational systems biology approach for the accurate prediction of pairwise synthetic genetic interactions (SGI). First, a high-coverage and high-precision functional gene network (FGN) is constructed by integrating protein-protein interaction (PPI), protein complex and gene expression data; then, a graph-based semi-supervised learning (SSL) classifier is utilized to identify SGI, where the topological properties of protein pairs in weighted FGN is used as input features of the classifier. We compare the proposed SSL method with the state-of-the-art supervised classifier, the support vector machines (SVM), on a benchmark dataset in S. cerevisiae to validate our method's ability to distinguish synthetic genetic interactions from non-interaction gene pairs. Experimental results show that the proposed method can accurately predict genetic interactions in S. cerevisiae (with a sensitivity of 92% and specificity of 91%). Noticeably, the SSL method is more efficient than SVM, especially for very small training sets and large test sets., Conclusions: We developed a graph-based SSL classifier for predicting the SGI. The classifier employs topological properties of weighted FGN as input features and simultaneously employs information induced from labelled and unlabelled data. Our analysis indicates that the topological properties of weighted FGN can be employed to accurately predict SGI. Also, the graph-based SSL method outperforms the traditional standard supervised approach, especially when used with small training sets. The proposed method can alleviate experimental burden of exhaustive test and provide a useful guide for the biologist in narrowing down the candidate gene pairs with SGI. The data and source code implementing the method are available from the website: http://home.ustc.edu.cn/~yzh33108/GeneticInterPred.htm.

Background: It is well known that most of the binding free energy of protein interaction is contributed by a few key hot spot residues. These residues are crucial for understanding the function of proteins and studying their interactions. Experimental hot spots detection methods such as alanine scanning mutagenesis are not applicable on a large scale since they are time consuming and expensive. Therefore, reliable and efficient computational methods for identifying hot spots are greatly desired and urgently required., Results: In this work, we introduce an efficient approach that uses support vector machine (SVM) to predict hot spot residues in protein interfaces. We systematically investigate a wide variety of 62 features from a combination of protein sequence and structure information. Then, to remove redundant and irrelevant features and improve the prediction performance, feature selection is employed using the F-score method. Based on the selected features, nine individual-feature based predictors are developed to identify hot spots using SVMs. Furthermore, a new ensemble classifier, namely APIS (A combined model based on Protrusion Index and Solvent accessibility), is developed to further improve the prediction accuracy. The results on two benchmark datasets, ASEdb and BID, show that this proposed method yields significantly better prediction accuracy than those previously published in the literature. In addition, we also demonstrate the predictive power of our proposed method by modelling two protein complexes: the calmodulin/myosin light chain kinase complex and the heat shock locus gene products U and V complex, which indicate that our method can identify more hot spots in these two complexes compared with other state-of-the-art methods., Conclusion: We have developed an accurate prediction model for hot spot residues, given the structure of a protein complex. A major contribution of this study is to propose several new features based on the protrusion index of amino acid residues, which has been shown to significantly improve the prediction performance of hot spots. Moreover, we identify a compact and useful feature subset that has an important implication for identifying hot spot residues. Our results indicate that these features are more effective than the conventional evolutionary conservation, pairwise residue potentials and other traditional features considered previously, and that the combination of our and traditional features may support the creation of a discriminative feature set for efficient prediction of hot spot residues. The data and source code are available on web site http://home.ustc.edu.cn/~jfxia/hotspot.html.

Objective: To investigate the efficacy of high dose chemotherapy combined with autologous peripheral blood stem cell transplantation (APBSCT) for the treatment of neural ectodermal solid tumor originated from neural crest in children., Methods: Twenty-three children at a medium age of 5.8 + or - 3.5 years with neural ectodermal solid tumor originated from neural crest were enrolled. Of the 23 children, 20 with stage IV neuroblastoma (9 were in complete remission, 7 were in partial remission and 4 were in progressive disease), 2 with stage IV primitive neuroectodermal tumor (PNET) in complete remission, and 1 with retinoblastoma in partial remission. Before APBSCT the children received 8.0 + or - 4.3 courses of chemotherapy. During chemotherapy the autologous peripheral blood stem cells were harvested and the tumor excision was performed. Then APBSCT was performed., Results: The reconstruction of the hematopoietic system was noted in 19 of 20 children with stage IV neuroblastoma 16.5 + or - 0.9 days after transplantation. A follow-up (median 15.8 months) was done in these children. The follow-up showed that the survival rate in children in complete remission before transplantation was 100%, 57% in those in partial remission, and none of children in progressive disease survived (P<0.05). The total survival rate was 67% in children with neuroblastoma. The child with retinoblastoma had complete remission in a 6-months follow-up. The tumors recurred in children with PNET 5 to 8 months after transplantation and all died within one year after transplantation., Conclusions: High dose chemotherapy combined with APBSCT can result in a good outcome in children with neural ectodermal solid tumor originated from neural crest in complete remission before transplantation and can improve the outcome in patients in partial remission before transplantation. However, the children with PNET, even in complete remission before transplantation, do not respond to the therapy.

Tumor classification is an important application domain of gene expression data. Because of its characteristics of high dimensionality and small sample size (SSS), and a great number of redundant genes not related to tumor phenotypes, various feature extraction or gene selection methods have been applied to gene expression data analysis. Wavelet packet transforms (WPT) and neighborhood rough sets (NRS) are effective tools to extract and select features. In this paper, a novel approach of tumor classification is proposed based on WPT and NRS. First the classification features are extracted by WPT and the decision tables are formed, then the attributes of the decision tables are reduced by NRS. Thirdly, a feature subset with few attributes and high classification ability is obtained. The experimental results on three gene expression datasets demonstrate that the proposed method is effective and feasible., (2010. Published by Elsevier Ltd.)

Agenesis of the gallbladder with normal bile ducts is a rare anomaly. More cases have been reported preoperatively because of the increased awareness of this entity. However some cases remain difficult to diagnosis. We report such a case. A symptomatic male patient (age 45) was diagnosed with chronic atrophic cholecystitis and cholecystlithiasis by ultrasonography and computed tomography scan. The images revealed solid tissue in the gallbladder fossa. However, during laparoscopic exploration no gallbladder or ectopic gallbladder was found. Only adipose tissue and the gallbladder artery were identified during the operation. Gallbladder agenesis was diagnosed postoperatively. It still remains a challenge to determine surgical intervention in these cases.

Identifying protein-protein interactions (PPIs) is critical for understanding the cellular function of the proteins and the machinery of a proteome. Data of PPIs derived from high-throughput technologies are often incomplete and noisy. Therefore, it is important to develop computational methods and high-quality interaction dataset for predicting PPIs. A sequence-based method is proposed by combining correlation coefficient (CC) transformation and support vector machine (SVM). CC transformation not only adequately considers the neighboring effect of protein sequence but describes the level of CC between two protein sequences. A gold standard positives (interacting) dataset MIPS Core and a gold standard negatives (non-interacting) dataset GO-NEG of yeast Saccharomyces cerevisiae were mined to objectively evaluate the above method and attenuate the bias. The SVM model combined with CC transformation yielded the best performance with a high accuracy of 87.94% using gold standard positives and gold standard negatives datasets. The source code of MATLAB and the datasets are available on request under smgsmg@mail.ustc.edu.cn.

Since Golub applied gene expression profiles (GEP) to the molecular classification of tumor subtypes for more accurately and reliably clinical diagnosis, a number of studies on GEP-based tumor classification have been done. However, the challenges from high dimension and small sample size of tumor dataset still exist. This paper presents a new tumor classification approach based on an ensemble of probabilistic neural network (PNN) and neighborhood rough set model based gene reduction. Informative genes were initially selected by gene ranking based on an iterative search margin algorithm and then were further refined by gene reduction to select many minimum gene subsets. Finally, the candidate base PNN classifiers trained by each of the selected gene subsets were integrated by majority voting strategy to construct an ensemble classifier. Experiments on tumor datasets showed that this approach can obtain both high and stable classification performance, which is not too sensitive to the number of initially selected genes and competitive to most existing methods. Additionally, the classification results can be cross-verified in a single biomedical experiment by the selected gene subsets, and biologically experimental results also proved that the genes included in the selected gene subsets are functionally related to carcinogenesis, indicating that the performance obtained by the proposed method is convincing., (2009. Published by Elsevier Ltd.)

We propose a sequence-based multiple classifier system, i.e., rotation forest, to infer protein-protein interactions (PPIs). Moreover, Moran autocorrelation descriptor is used to code an interaction protein pair. Experimental results on Saccharomyces cerevisiae and Helicobacter pylori datasets show that our approach outperforms those previously published in literature, which demonstrates the effectiveness of the proposed method.

Phytochemical investigation of the aerial parts of Abies chensiensis afforded two new (compounds 2 and 3) and 27 known compounds, including the related compound larixinol ( 1). The structures of spirobiflavonoids 1- 3 were established using 1D and 2D NMR spectroscopic techniques. In addition, the structure of larixinol ( 1) was confirmed by X-ray crystallographic analysis. Compounds 1- 3 were evaluated for inhibitory activities against LPS-induced NO production in macrophages. Larixinol ( 1) showed moderate effects, with an IC(50) value of 60.0 microg/mL. In addition, it did not show any cytotoxicity on RAW 264.7 macrophages at 100 microg/mL., (Georg Thieme Verlag KG Stuttgart, New York.)

Tumor clustering is becoming a powerful method in cancer class discovery. Nonnegative matrix factorization (NMF) has shown advantages over other conventional clustering techniques. Nonetheless, there is still considerable room for improving the performance of NMF. To this end, in this paper, gene selection and explicitly enforcing sparseness are introduced into the factorization process. Particularly, independent component analysis is employed to select a subset of genes so that the effect of irrelevant or noisy genes can be reduced. The NMF and its extensions, sparse NMF and NMF with sparseness constraint, are then used for tumor clustering on the selected genes. A series of elaborate experiments are performed by varying the number of clusters and the number of selected genes to evaluate the cooperation between different gene selection settings and NMF-based clustering. Finally, the experiments on three representative gene expression datasets demonstrated that the proposed scheme can achieve better clustering results.

Chitosan modified multi-walled carbon nanotube composites were synthesized under microwave irradiation. The resultant chitosan modified multi-walled carbon nanotube composites were purified by twice adjusting of pH value of the solution and centrifugating in succession. The surface functional groups of chitosan modified multi-walled carbon nanotube composites are confirmed by Fourier transform infrared spectroscopy and UV-vis spectroscopy. Transmission electron microscopic images further show the morphologic changes of the carbon nanotubes. Thermal gravimetric analysis shows that the chitosan content in the chitosan modified multi-walled carbon nanotube composites is much higher than conventional methods. The whole reaction procedure can be completed in 1 h under microwave irradiation.

Objective: Oral oestrogen has been shown to dissociate the growth hormone (GH)/insulin-like growth factor (IGF)-I axis and alter energy metabolism in postmenopausal women. This study was designed to determine whether these metabolic changes occur with short-term oral oestrogen in premenopausal women., Study Design: A double-blind placebo controlled randomised-crossover design study was performed in 12 premenopausal women. Investigations were performed after either 5 days of oral 17beta-oestradiol valerate 2mg twice daily or placebo. Outcomes included body composition measured by bio-impedance, energy metabolism measured by indirect calorimetry and blood sampling., Results: Oral oestrogen significantly suppressed IGF-I levels and increased fasting GH levels. No significant changes in energy metabolism or body composition were detected., Conclusions: Short-term oral oestrogen suppresses IGF-I and elevates GH levels in premenopausal women. No effects were seen on body composition and energy metabolism. Further research is required to determine whether metabolic effects of oral oestrogen may become apparent if longer courses of treatment were administered to premenopausal women.

Objective: To investigate the role of B7-H1 expression in IL-10 production, the B7-H1 and IL-10 expression levels in pancreatic carcinoma tissues and to analyze the correlation between B7-H1 expression and IL-10 level., Methods: The mRNA and protein levels expressions of B7-H1 and IL-10 in 35 cases of pancreatic cancer and corresponding paracarcinoma tissues and 5 cases of normal pancreas tissues were detected by RT-PCR, Western blot and immunohistochemistry respectively., Results: The findings for the first time provided the evidences that there was a clear trend for B7-H1 and IL-10 expressions to be most highly expressed in carcinoma tissue, intermediately expressed in paracarcinoma tissue, and expressed at the lowest level in normal pancreatic tissue at mRNA and protein levels. Moreover, there were statistically significant differences in B7-H1 and IL-10 expression between pancreatic carcinoma tissues, corresponding paracarcinoma tissues and normal pancreatic tissues at mRNA and protein levels (P < 0.05). Furthermore, the immunohistochemistry indicated that there were high expression levels of B7-H1 (60.5% +/- 12.7%) and IL-10 (65.3% +/- 16.2%) in pancreatic carcinoma tissues while there were no significant expressions in normal pancreatic tissues. Meanwhile, correlation analysis revealed that B7-H1 expression was significant associated with IL-10 level in tumor tissues at mRNA (P = 0.008, r = 0.841) and protein levels (P = 0.007, r = 0.838)., Conclusions: Over-expression of B7-H1 may be responsible for the increasing IL-10 production in pancreatic cancer, which caused reduced immune response to tumor cells and contributed to pancreatic carcinoma escape from immune attack.

Background: Supervised learning and many stochastic methods for predicting protein-protein interactions require both negative and positive interactions in the training data set. Unlike positive interactions, negative interactions cannot be readily obtained from interaction data, so these must be generated. In protein-protein interactions and other molecular interactions as well, taking all non-positive interactions as negative interactions produces too many negative interactions for the positive interactions. Random selection from non-positive interactions is unsuitable, since the selected data may not reflect the original distribution of data., Results: We developed a bootstrapping algorithm for generating a negative data set of arbitrary size from protein-protein interaction data. We also developed an efficient boosting algorithm for finding interacting motif pairs in human and virus proteins. The boosting algorithm showed the best performance (84.4% sensitivity and 75.9% specificity) with balanced positive and negative data sets. The boosting algorithm was also used to find potential motif pairs in complexes of human and virus proteins, for which structural data was not used to train the algorithm. Interacting motif pairs common to multiple folds of structural data for the complexes were proven to be statistically significant. The data set for interactions between human and virus proteins was extracted from BOND and is available at http://virus.hpid.org/interactions.aspx. The complexes of human and virus proteins were extracted from PDB and their identifiers are available at http://virus.hpid.org/PDB&#95;IDs.html., Conclusion: When the positive and negative training data sets are unbalanced, the result via the prediction model tends to be biased. Bootstrapping is effective for generating a negative data set, for which the size and distribution are easily controlled. Our boosting algorithm could efficiently predict interacting motif pairs from protein interaction and sequence data, which was trained with the balanced data sets generated via the bootstrapping method.

In this paper, a novel heuristic structure optimization methodology for radial basis probabilistic neural networks (RBPNNs) is proposed. First, a minimum volume covering hyperspheres (MVCH) algorithm is proposed to select the initial hidden-layer centers of the RBPNN, and then the recursive orthogonal least square algorithm (ROLSA) combined with the particle swarm optimization (PSO) algorithm is adopted to further optimize the initial structure of the RBPNN. The proposed algorithms are evaluated through eight benchmark classification problems and two real-world application problems, a plant species identification task involving 50 plant species and a palmprint recognition task. Experimental results show that our proposed algorithm is feasible and efficient for the structure optimization of the RBPNN. The RBPNN achieves higher recognition rates and better classification efficiency than multilayer perceptron networks (MLPNs) and radial basis function neural networks (RBFNNs) in both tasks. Moreover, the experimental results illustrated that the generalization performance of the optimized RBPNN in the plant species identification task was markedly better than that of the optimized RBFNN.

We propose a new method for tumor classification from gene expression data, which mainly contains three steps. Firstly, the original DNA microarray gene expression data are modeled by independent component analysis (ICA). Secondly, the most discriminant eigenassays extracted by ICA are selected by the sequential floating forward selection technique. Finally, support vector machine is used to classify the modeling data. To show the validity of the proposed method, we applied it to classify three DNA microarray datasets involving various human normal and tumor tissue samples. The experimental results show that the method is efficient and feasible.

We address the microarray dataset based cancer classification using a newly proposed multiple classifier system (MCS), referred to as Rotation Forest. To the best of our knowledge, it is the first time that Rotation Forest has been applied to the microarray dataset classification. In the framework of Rotation Forest, a linear transformation method is required to project data into new feature space for each classifier, and then the base classifiers are trained in different new spaces so as to enhance both the accuracies of base classifiers and the diversity in the ensemble system. Principal component analysis (PCA), non-parametric discriminant analysis (NDA) and random projections (RP) were applied to feature transformation in the original Rotation Forest. In this paper, we use independent component analysis (ICA) as a new transformation method since it can better describe the property of microarray data. The breast cancer dataset and prostate dataset are deployed to validate the efficiency of Rotation Forest. In all the experiments, it can be found that Rotation Forest outperforms other MCSs, such as Bagging and Boosting. In addition, the experimental results also revealed that ICA can further improve the performance of Rotation Forest compared with the original transformation methods.

Contact map, which is important to understand and reconstruct protein's three-dimensional (3D) structure, may be helpful to solve the protein's 3D structure. This paper presents a novel approach to predict the contact map using Radial Basis Function Neural Network (RBFNN) optimised by Conformational Energy Function (CEF) based on chemico-physical knowledge of amino acids. Finally, the results are trimmed by Short-Range Contact Function (SRCF). Consequently, it can be found that our proposed method is better than the existing methods such as PROFcon and the PE-based method. Particularly, this method can accurately predict 35% of contacts at a distance cutoff of 8 A.