Data Mining Strategies Research Articles

Survival-Critical Genes Associated with Copy Number Alterations in Lung Adenocarcinoma.

Simple SummaryGenomic instability affects cancer evolution and impacts carcinogenesis, therapy response, recurrence/prognosis, thus overall clinical outcomes. To comprehensively identify genes and pathways affecting genomic instability, we employed a novel data-mining strategy (Gene Expression to Copy Number Alterations; “GE-CNA” approach) and identified 1578 genes whose expression associates with Copy Number Alterations in human lung adenocarcinoma. Among the 1578 genes, we identified 39 as survival-critical. They represent potential targets for therapy development.Chromosome Instability (CIN) in tumors affects carcinogenesis, drug resistance, and recurrence/prognosis. Thus, it has a high impact on outcomes in clinic. However, how CIN occurs in human tumors remains elusive. Although cells with CIN (i.e., pre/early cancer cells) are proposed to be removed by apoptosis and/or a surveillance mechanism, this surveillance mechanism is poorly understood. Here we employed a novel data-mining strategy (Gene Expression to Copy Number Alterations [CNA]; “GE-CNA”) to comprehensively identify 1578 genes that associate with CIN, indicated by genomic CNA as its surrogate marker, in human lung adenocarcinoma. We found that (a) amplification/insertion CNA is facilitated by over-expressions of DNA replication stressor and suppressed by a broad range of immune cells (T-, B-, NK-cells, leukocytes), and (b) deletion CNA is facilitated by over-expressions of mitotic regulator genes and suppressed predominantly by leukocytes guided by leukocyte extravasation signaling. Among the 39 CNA- and survival-associated genes, the purine metabolism (PPAT, PAICS), immune-regulating CD4-LCK-MEC2C and CCL14-CCR1 axes, and ALOX5 emerged as survival-critical pathways. These findings revealed a broad role of the immune system in suppressing CIN/CNA and cancer development in lung, and identified components representing potential targets for future chemotherapy, chemoprevention, and immunomodulation approaches for lung adenocarcinoma.

Preliminary Analysis of Structured Reporting in the HiGHmed Use Case Cardiology: Challenges and Measures.

The HiGHmed consortium aims to create a shared information governance framework to integrate clinical routine data. One challenge is the replacement of unstructured reporting (e.g. doctoral letters) with structured reporting in clinical routine. The Heidelberg cardiology department evaluates dynamic PDF forms for structured data reporting of heart failure (HF) patients. In this use case, we aim to identify potential caveats or shortcomings in data processing at an early stage. We employed data mining strategies to detect patterns related to incomplete or false data, which we found to be present among all data types. We then discuss the characteristics of the baseline patient cohort in Heidelberg to find out about specific peculiarities and potential biases, which may be site-specific. Briefly, our patient population is predominantly male (67%), NYHA I & II are the most common severity classes, NYHA IV is missing entirely. Most patients have a dilated cardiomyopathy (DCM) or coronary heart disease (CHD) diagnosed as their cause of HF. Finally, we also analyzed how comorbidities and risk factors relate to specific disease entities of heart failure patients. Family anamnesis was more frequent among cardiomyopathy patients than among CHD patients, who show a more dominating presence of dyslipidemia instead. Generally, the most dominant risk factor was arterial hypertension, while at the other end of the scale alcoholism appears to be underreported.

An unsupervised data mining strategy for performance evaluation of ground source heat pump systems

This paper presents an efficient data mining strategy to reveal the operational problems of ground source heat pump (GSHP) systems. Symbolic Aggregate approXimation was employed to identify typical daily load patterns and provide a reference for data partition. Kernel Density Estimation was used to evaluate overall system performance in different operation patterns identified. To find the root causes of inefficient operations, a customized association rule mining model was developed to discover the associations among different attributes. Lastly, the inference tree technique was applied to demonstrate the discovered associations for better comparative analysis. This strategy was evaluated using one-year operational data of a GSHP system. It was found that only 25% of the operations of this GSHP system in cooling seasons during 00:00–06:00 were considered as energy efficient, while above 79% of the operations in heating seasons were considered as energy efficient. Excessive power consumption of the water pumps due to improper control resulted in poor system COP (i.e. less than 2.0 or even 1.4 in cooling seasons and less than 2.1 in heating seasons). The results showed that this strategy can efficiently discover useful information from the operational data and identify energy conservation opportunities of GSHP systems.

Use of Data Mining Technologies in an English Online Test Results Management System

The systematic management of English online test results can ensure the fairness of the test, guarantee the accuracy and safety of the test results, and reduce the consumption of manpower and materials. Unfortunately, the existing data mining and management strategy for learner scores cannot track the learning process or score change of learners. This paper innovatively applies the trajectory data mining technology to the design of an English online process test results management system. After analyzing the functional requirements of the system, four basic information lists were constructed in SQL Server 2005. Then, an improved k-means clustering algorithm and the trajectory frequent pattern mining algorithm were combined to cluster the test results and analyze the learning trajectory deviation of the learners. Next, the four system functions were detailed, including login, entry of test results, trajectory setting, and deviation analysis. The effectiveness of our algorithm, and the performance of our system were fully verified through experiments.

The rapid identification of chemical constituents in Fufang Xiling Jiedu capsule, a modern Chinese medicine, by ultra-performance liquid chromatography coupled with quadrupole-time-of-flight tandem mass spectrometry and data mining strategy.

Fufang Xiling Jiedu capsule is an effective Chinese medicine widely used for the treatment of cold and influenza. However, its chemical constituents had not been determined, which entailed a huge obstacle to further pharmacological studies, clinical-safe medication administration, and quality evaluation. To identify the chemical constituents in Fufang Xiling Jiedu capsule, an efficient and systematic approach using ultra-high-performance liquid chromatography coupled with a quadrupole time-of-flight mass spectrometry in conjunction with a data mining strategy was adopted in this study. As a result, 145 compounds were qualitatively identified, including 26 phenolic acids, 46 flavonoids, 39 triterpenes, and 34 other compounds, among which 6 were potentially new and 144 were being reported from Fufang Xiling Jiedu capsule for the first time. This research not only provides useful information for quality control of Fufang Xiling Jiedu capsule and its involved single herbs but also serve as basis data for further study of Fufang Xiling Jiedu capsule in vivo. Moreover, it provides a reference for the characterization of the chemical constituents of other Chinese medicine preparations.

Security and Privacy Protection in Datamining

Security and Privacy protection have been a public approach worry for quite a long time. Notwithstanding, quick innovative changes, the fast development of the internet and electronic business, and the improvement of more modern techniques for gathering, investigating, and utilizing individual information have made privacy a significant public and government issues. The field of data mining is acquiring importance acknowledgment to the accessibility of a lot of data, effortlessly gathered and put away through PC systems. Data mining procedures, while permitting the people to remove shrouded information on one hand, present various privacy dangers then again. In this paper, we concentrate a portion of these issues alongside an itemized conversation on the utilizations of different data mining strategies for giving security. This paper gives an outline of data mining field and security information event management system. We will perceive how different data

Data Mining Techniques Based Diabetes Prediction

Data mining plays an important part in the healthcare sector disease prediction. Techniques of data mining are commonly used in early disease detection. Diabetes is one of the world’s greatest health challenges. A widespread chronic condition is a diabetes. Diabetes prediction is a science that is increasingly growing. Diabetes prediction at an early stage will lead to better therapy. It is necessary to avoid, monitor and increase diabetes consciousness because it causes other health issues. Diabetes of type 1 or type 2 can lead to heart disorders, kidney diseases or complications with the eye. This survey paper reflects on numerous approaches and data mining strategies used to forecast multiple diabetes disorders at an early stage. Become a chronic disease because of diabetes. The patient lives will be spared by an early prediction of this disease. By the use of data mining tools and processes, diabetes is avoided and treatment rates are reduced. The association rule mining, classification, clustering, Random Forest, Prediction as well as the Artificial Neural Network (ANN) are among the most common and important data mining technology. Different data mining methods are available to avoid diseases such as cardiac disease, cancer including kidney etc. This study examines the use of data mining methods to predict multiple disease types.

Data Mining Techniques Based Diabetes Prediction

Data mining plays an important part in the healthcare sector disease prediction. Techniques of data mining are commonly used in early disease detection. Diabetes is one of the world's greatest health challenges. A widespread chronic condition is a diabetes. Diabetes prediction is a science that is increasingly growing. Diabetes prediction at an early stage will lead to better therapy. It is necessary to avoid, monitor and increase diabetes consciousness because it causes other health issues. Diabetes of type 1 or type 2 can lead to heart disorders, kidney diseases or complications with the eye. This survey paper reflects on numerous approaches and data mining strategies used to forecast multiple diabetes disorders at an early stage. Become a chronic disease because of diabetes. The patient lives will be spared by an early prediction of this disease. By the use of data mining tools and processes, diabetes is avoided and treatment rates are reduced. The association rule mining, classification, clustering, Random Forest, Prediction as well as the Artificial Neural Network (ANN) are among the most common and important data mining technology. Different data mining methods are available to avoid diseases such as cardiac disease, cancer including kidney etc. This study examines the use of data mining methods to predict multiple disease types.

Surrogate-guided multi-objective optimization (SGMOO) using an efficient online sampling strategy

In this paper, we present a new multi-objective global optimization algorithm SGMOO for computationally expensive black-box problems, where Radial basis functions are used to build dynamically updated surrogate models for each objective. Moreover, an efficient online sampling strategy that includes three infilling criteria “Multi-objective-based exploitation on RBF, Single-objective-based exploitation on RBF, and Evolutionary-computation-based exploration” is presented to capture promising samples in each cycle. In the first criterion, a distance-based data mining strategy is proposed to pick out the valuable samples from the predicted Pareto solution set, speeding up the convergence to the true Pareto frontier. In the second criterion, single-objective surrogate-based sampling approach is used to enhance the local infilling performance at the bounds of Pareto frontier. Furthermore, the dynamically updated expensive sample set is regarded as a population to generate offspring by non-dominated sorting, and a novel prescreening operator considering hypervolume and space infilling performance is presented to select elite individuals in the third infilling criterion. With the help of the cooperation of the three infilling criteria, SGMOO builds a reasonable balance between global exploration and local exploitation. Compared with 4 well-known multi-objective algorithms, SGMOO has more stable and impressive performance on 25 benchmark cases and the shape optimization design of a blended-wing-body underwater glider.

Prediction of Presence of Breast Cancer Disease in the Patient using Machine Learning Algorithms and SFS

Breast cancer disease is recognized as the common extensive malignant tumor in between women. Identification of the initial stage of malignant growth may treatment of this disease. Early treatment helps to alleviate the disease and helps anticipate its recurrence in women. Experts have used some fact checks and different medical methods or equipment to improve the accuracy of conclusions in clinical medical service management. In this article, it extensively discussed the implementation of data mining strategies to detection as well as prediction of breast malignant tumors, including random forest (RF), support vector classifier (SVC), k-nearest neighbors (KNN), linear discriminant analysis (LDA), Gradient Boosting Classifier (GBC), Decision Tree (DT) In addition, principal component analysis (PCA) to underline changes and show strong patterns in the informational index. The connection framework is likewise used to show the level of close relationship between attributes. The sequential feature selection (SFS) method is used for comparing the accuracy of a data set with all features and the accuracy of a classifier with selected features. The results show that RF_sfs, KNN_sfs, SVC_rbf and SVC_sfs have the highest and equal accuracy, which is 97.66%. They perform well and can predict the growth of harmful malignant tumors.

Abstract PS18-31: Identification of cell surface proteins in triple negative breast cancer for the development of novel targeted therapies

Abstract Triple negative breast cancer (TNBC) stands out due to its aggressive course and high metastatic rates. No consistent protein biomarker has been described for TNBC, resulting in a scarcity of adjuvant therapies for the afflicted patients. Hence, there is an urgent need to determine novel TNBC-associated proteins for the development of new therapeutics and the identification of novel molecular mechanisms driving this malignancy. Cell surface proteins represent attractive targets for novel therapies, due to their easily accessible localization and their involvement in essential signaling pathways. Objectives: We aimed to uncover novel TNBC-associated cell surface proteins involved in carcinogenesis and metastasis for the development of novel targeted therapeutics. Rationale: Taking advantage of the fact that cell surface proteins are often N-glycosylated, we employed hydrazide chemistry to isolate N-glycopeptides. The glycoproteome of six immortalized TNBC cell lines and five ‘healthy’ controls (HC) (the immortalized cell line MCF10A and four patient-derived human mammary epithelial cell lines) was analyzed using LC-MS/MS and label-free quantification. A data mining strategy was employed to select candidates of interest. We knocked-down (k.d.) the top five candidates of interest (using siRNA technology) and evaluated cell growth using growth-curve analysis. Plexin B3 (PLXNB3) was selected for subsequent functional validations. The effects of PLXNB3 k.d. (using siRNA and CRISPR technology) on cancer cell growth, apoptosis and adhesion were interrogated using western blotting and standard cell biology protocols.Results: The N-glycoproteomics approach led to the identification of 1044 glycoproteins, with over 70% described as plasma membrane/secreted proteins. Gene Ontology analysis revealed that the TNBC-associated glycoproteome was enriched in biological processes such as: mesenchyme development, MAPK signaling, positive regulation of proliferation and regulation of neuron projection development. Candidates of interest were selected from our list by focusing on those plasma membrane proteins that were enriched in TNBC cells compared to HC according to our label-free quantified proteomics data, and that showed limited expression in healthy tissues according to the Human Protein Atlas. We further restricted the list of candidates to those proteins whose k.d. impaired cancer cell growth, with little effect on the HC. PLXNB3, an understudied protein typically expressed in healthy neuronal tissues, was selected for in depth functional analysis. Elevated mRNA PLXNB3 levels in breast cancer patients is associated with poorer overall survival compared to low mRNA expression (Integrated TCGA Pan-Cancer Clinical Data Resource, 2018). PLXNB3 k.d. (using siRNA and CRISPR technologies) impaired TNBC cell growth (in both adherent and spheroid cultures) and was associated with elevated levels of cleaved-caspase 3 and cleaved-caspase 7 compared to scrambled controls. Furthermore, PLXNB3 k.d. negatively impacted TNBC cell adhesion to extracellular matrixes compared to scrambled controls. Subsequent tests will evaluate PLXNB3’s role in tumor growth and metastasis in vivo, using orthotopic tumor models in immunocompromised mice. Citation Format: Laura Kuhlmann, Ankit Sinha, Vladimir Ignatchenko, Andrew Macklin, Lydia Liu, Meinusha Govindarajan, Amanda Khoo, Salvador Mejia-Guerrero, Jennifer Cruickshank, Hal Berman, Thomas Kislinger. Identification of cell surface proteins in triple negative breast cancer for the development of novel targeted therapies [abstract]. In: Proceedings of the 2020 San Antonio Breast Cancer Virtual Symposium; 2020 Dec 8-11; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2021;81(4 Suppl):Abstract nr PS18-31.

Prediction of Students Performance using Machine learning

An enormous measure of computerized information is being produced over a wide assortment in the field of data mining strategies. The creation of student achievement prediction models to predict student performance in academic institutions is a key area of the development of Education Data Mining. A prediction system has been proposed by using their 10th, 12th and previous semester marks. The study is evaluated using Binomial logical regression, Decision tree, and Entropy and KNN classifier. In order to attain their higher score, this framework would assist the student to recognize their final grade and improve their academic conduct.

Investigation and identification of the multiple components of Rheum officinale Baill. using ultra-high-performance liquid chromatography coupled with quadrupole-time-of-flight tandem mass spectrometry and data mining strategy.

Rheum officinale Baill. is a traditional Chinese medicine that has long been used for eliminating body heat, cooling and detoxifying blood, removing blood stasis and promoting menstruation, and clearing away heat-dampness to eliminate jaundice. Comprehensive and systematic structural identification of the components of Rheum officinale Baill. remains a challenge. An appropriate analytical method needs to be established for the comprehensive investigation and identification of the chemical constituents in Rheum officinale Baill. extract. In this study, a new systematic approach using ultra high performance liquid chromatography with quadrupole time-of-flight mass spectrometry in conjunction with a data mining strategy was developed to screen the targeted and nontargeted components of Rheum officinale Baill. A total of 124 compounds were identified in the Rheum officinale Baill. extract including 31 acylglucosides, 9 phenolic acids, 26 tannins, 53 anthraquinones, and 5 other compounds. Note that 55 of these compounds were reported for the first time here. In conclusion, in this study, we devised an efficient and systematic method for detecting complex compounds and have used it here to provide a foundation for future research into bioactive ingredients and quality control of Rheum officinale Baill. extract.

Transcriptome analysis of IPF fibroblastic foci identifies key pathways involved in fibrogenesis

IntroductionFibroblastic foci represent the cardinal pathogenic lesion in idiopathic pulmonary fibrosis (IPF) and comprise activated fibroblasts and myofibroblasts, the key effector cells responsible for dysregulated extracellular matrix deposition in multiple...

Analysis of chemical variations between raw and wine-processed Ligustri Lucidi Fructus by ultra-high-performance liquid chromatography-Q-Exactive Orbitrap/MS combined with multivariate statistical analysis approach.

Ligustri Lucidi Fructus (LLF) is the dried and mature fruit of Ligubtrum lucidum Ait., which has the effect of nourishing the liver and kidney, brightening the eyes and promoting the growth of black hair. Wine-processed LLF is commonly used in traditional Chinese medicine; however, the processing mechanisms are still unclear. Herein, a system data acquisition and mining strategy was designed to investigate the chemical profile differences between the raw and wine-processed LLF, based on high-performance liquid chromatography-Orbitrap high resolution mass spectrometry coupled with multivariate statistical analysis including principal component analysis and partial least square analysis. Afterwars, a total of 55 components were found to be the main contributors to the significant difference between raw and wine-processed LLF by comparison with chromatographic behaviors, intact precursor ions, and characteristic MS fragmentation patterns. In addition, 10 main constituents of raw and wine-processed LLF were simultaneously determined by UHPLC-MS/MS for analyzing the content variations. Some structural transformation mechanisms during wine processing were deduced from the results. The results may provide a scientific foundation for deeply elucidating the wine-processing mechanism of LLF.

Integrative public data-mining pipeline for thevalidation of novel independent prognostic biomarkers for lung adenocarcinoma.

Aim: We aimed to develop a candidate-based integrative public data mining strategy for validation of novel prognostic markers in lung adenocarcinoma. Materials & methods: An insilico approach integrating meta-analyses of publicly available clinical information linked RNA expression, gene copy number and mutation datasets combined with independent immunohistochemistry and survival datasets. Results: After validation of pipeline integrity utilizing data from the well-characterized prognostic factor Ki-67, prognostic impact of the calcium-andintegrin-binding protein, CIB1, was analyzed. CIB1 was overexpressed in lung adenocarcinoma which correlated with pathological tumor andpathological lymph node status and impaired overall/progression-free survival. In multivariate analyses, CIB1 emerged as UICC stage-independent risk factor for impaired survival. Conclusion: Our pipeline holds promise to facilitate further identification and validation of novel lung cancer-associated prognostic markers.

Three-dimensional reconstruction of laryngeal cancer with whole organ serial immunohistochemical sections

Three-dimensional (3D) image reconstruction of tumors based on serial histological sectioning is one of the most powerful methods for accurate high-resolution visualization of tumor structures. However, 3D histological reconstruction of whole tumor has not yet been achieved. We established a high-resolution 3D model of molecular marked whole laryngeal cancer by optimizing the currently available techniques. A series of 5,388 HE stained or immunohistochemically stained whole light microscopic images (200 ×) were acquired (15.61 TB).The data set of block-face images (96.2 GB) was also captured. Direct volume rendering of serial 6.25 × light microscopy images did not demonstrate the major characteristics of the laryngeal cancer as expected. Based on fusion of two datasets, the accurate boundary of laryngeal tumor bulk was visualized in an anatomically realistic context. In the regions of interest, micro tumor structure, budding, cell proliferation and tumor lymph vessels were well represented in 3D after segmentation, which highlighted the advantages of 3D reconstruction of light microscopy images. In conclusion, generating 3D digital histopathological images of a whole solid tumor based on current technology is feasible. However, data mining strategy should be developed for complete utilization of the large amount of data generated.

Influence of a combination of triptolide and ferulic acid on the activities of CYP450 enzymes and oxidative stress in HaCaT cells.

Topical administration of triptolide (TP) is effective in the treatment of rheumatoid arthritis (RA), but it can also induce skin irritation. Previous studies have used data mining strategies to analyze the application of Tripterygium wilfordii in the treatment of RA and have shown that TP and ferulic acid (FA) can be used in combination due to their component compatibility. The aims of the present study were to investigate the mechanisms underlying the effects of TP treatment and to identify its effects on metabolism and oxidative damage in the skin. MTT assay results suggested that the HaCaT cell survival rate was significantly increased when the compatibility ratio of TP to FA was 1:100. Moreover, the combination of TP with FA (TP + FA) did not significantly affect the activities of the cytochrome P40 (CYP) enzymes CYP family 1 subfamily A member 2 (CYP1A2), CYP2E1 and CYP3A4, when used as a ‘cocktail’. It was found that TP + FA significantly decreased the production levels of reactive oxygen species (ROS), superoxide dismutase and malondialdehyde in HaCaT cells, while significantly increasing levels of glutathione and catalase. In addition, TP + FA significantly increased nuclear factor erythroid 2-related factor 2 protein expression, compared with TP alone. Thus, the present results indicated that the underlying mechanism of TP + FA efficacy may be related to decreased ROS production level in HaCaT cells, increased production levels of key antioxidant factors and increased antioxidant activity of the epidermis, all of which were correlated with a protective effect against oxidative damage.

Essentials in Metagenomics (Part II)

With the development of high-throughput next generation sequencing technologies and the technical advances to generate high-quality sequencing data, the bottleneck in implementing metagenomics for economic and social purposes in Latin America has shifted from obtaining DNA sequences to post-sequencing data analysis. Latin American countries still face challenges to develop and implement strategies for local data processing and data mining due to the limited bioinformatics capacity. Although many large computing grids already exist, outsourcing analyses and computing is not always the best solution since data transfer requires significant bandwidth due to the file sizes, and more importantly, it limits the training of local researchers to perform cutting-edge bioinformatics. Therefore, developing learning material in data processing and analysis in metagenomics is critical to the formation of new highly-skilled bioinformaticians. The present document is a tutorial in essential aspects of metagenomics data processing (post- sequencing) which was structured based on an extensive literature review, with the goal of presenting the current bioinformatics tools and workflows for extracting relevant, biological information out of a large sequencing data set. This is the second of a two-part series of documents designed to provide the essential background (experimental and computational) for users to approach the field of metagenomics. Users will find an overview of the different bioinformatic analyses that are commonly performed in metagenomic studies, including quality control, decontamination, coverage estimation, assembly, recovery of MAGs (metagenome- assembled genomes), taxonomic and functional classification of reads and contigs, and strain- level comparative analysis, among many other relevant topics. Users will also find rich discussions on the advantages and limitations that the different tools and methods offer and will be provided with external links and websites where additional information can be found.

A cluster analysis of data mining studies in library and information science from 2006 to 2018

AbstractAnalyzing content from articles published in major LIS journals during the years 2006, 2012, and 2018, this study examines the use of data mining strategies in LIS research. A total of 301 articles were identified that utilized data mining strategies across the 3 years studied, with the JASIST having the most such articles with 42, with Information Processing and Management following close behind with 32. A cluster analysis performed based on word frequency in these articles abstracts identified three unique clusters associated with the topics of Publications/Citations, Consumer Behavior, and Information/Media Use. A cluster analysis of the proportion of articles indicates a shift away from Publications/Citations towards more Consumer Behavior‐based data mining studies.