Data Mining Platform Research Articles

The EPIC data analytics platform for clinical mass cytometry

Abstract Single cell technologies, such as high-dimensional cytometry, promise to enable the discovery of immune cell populations that will serve as clinical biomarkers. Recently, we reported the creation of a reference database of the healthy immune system from birth to old age and the development of the EPIC (Extended Poly-dimensional Immunome characterisation) data mining platform (Nature Biotech, accepted). Here we extend the analytics pipeline to facilitate detection of clinically stratifying cell populations in mass cytometry (CyTOF or cytometry by time-of-flight) data. Data structures called immune maps are used to integrate single cell protein expression data (over 40) of multiple samples with clinical metadata and phenotypic information inferred from automated clustering and assisted cell type annotation. Clustering is combined with batch effect correction to reduce technical while preserving biological variations. Subsequent single cell exploratory data analysis and statistical tests help to identify cell populations whose frequencies differ significantly between groups of patients. To gain further insights, users can compare their cytometry data with the healthy reference immunome by performing two types of analysis; (1) mapping to existing clusters helps obtain abundance estimates of immune cell types, (2) reclustering of uploaded data merged with reference immunomes uncovers differences to healthy immune profiles of different ages. We implemented the EPIC pipeline using R Shiny to provide interactive visualisation and an intuitive user interface. We will show examples on how the EPIC platform can characterise cellular diversity in the context of disease and the morphogenesis of the healthy immune system.

ERP Virtual Simulation Practice Platform based on Big Data

The large amount of data accumulated in the ERP practice course system of universities has an impact on the quality of teaching. And the purpose of this paper is to expound and design the intelligent ERP virtual simulation Big Data analysis and mining platform. Its principle is to explore the relationship between massive data to promote the reform of teaching programs and realize the rational use of teaching resources.

Construction of marine ship automatic identification system data mining platform based on big data

Construction of marine ship automatic identification system data mining platform based on big data

A profile of 8-oxo-dGTPase activities in the NCI-60 human cancer panel: Meta-analytic insight into the regulation and role of MTH1 (NUDT1) gene expression in carcinogenesis

We measured the specific 8-oxo-dGTPase activity profile of the NCI-60 panel of malignant cell lines, and MTH1 protein levels in a subset of 16 lines. Their 8-oxo-dGTPase activity was compared to twelve publicly accessible MTH1 mRNA expression data bases and their cross-consistency was analyzed. 8-oxo-dGTPase and MTH1 protein levels in these cell lines are generally, but not always, mainly determined by MTH1 mRNA expression levels. The aneuploidy number of MTH1 gene copies only slightly affects its mRNA expression levels. By using the data mining platforms Compare and CellMiner, our 8-oxo-dGTPase profile was compared to five global gene expression datasets to identify genes whose expression levels are directly or inversely associated with 8-oxo-dGTPase. We analyzed effects of SNP within MTH1 on MTH1 mRNA level and enzyme activity. Similar association analysis was performed for five microRNA expression datasets. We identified several proteins and microRNA which might be involved in the regulation of MTH1 expression and we discuss potential mechanisms. Comparison of chemical and natural products sensitivities of the NCI-60 panel suggests seven compounds which are directly or inversely associated with 8-oxo-dGTPase. We provide an integrated picture of MTH1 expression combined from eleven consistent MTH1 mRNA and our 8-oxo-dGTPase activity NCI-60 profiles.

Identification of pathogenic variant enriched regions across genes and gene families.

Missense variant interpretation is challenging. Essential regions for protein function are conserved among gene-family members, and genetic variants within these regions are potentially more likely to confer risk to disease. Here, we generated 2871 gene-family protein sequence alignments involving 9990 genes and performed missense variant burden analyses to identify novel essential protein regions. We mapped 2,219,811 variants from the general population into these alignments and compared their distribution with 76,153 missense variants from patients. With this gene-family approach, we identified 465 regions enriched for patient variants spanning 41,463 amino acids in 1252 genes. As a comparison, by testing the same genes individually, we identified fewer patient variant enriched regions, involving only 2639 amino acids and 215 genes. Next, we selected de novo variants from 6753 patients with neurodevelopmental disorders and 1911 unaffected siblings and observed an 8.33-fold enrichment of patient variants in our identified regions (95% C.I. = 3.90-Inf, P-value = 2.72 × 10−11). By using the complete ClinVar variant set, we found that missense variants inside the identified regions are 106-fold more likely to be classified as pathogenic in comparison to benign classification (OR = 106.15, 95% C.I = 70.66-Inf, P-value < 2.2 × 10−16). All pathogenic variant enriched regions (PERs) identified are available online through “PER viewer,” a user-friendly online platform for interactive data mining, visualization, and download. In summary, our gene-family burden analysis approach identified novel PERs in protein sequences. This annotation can empower variant interpretation.

MitoXplorer, a visual data mining platform to systematically analyze and visualize mitochondrial expression dynamics and mutations.

Mitochondria participate in metabolism and signaling. They adapt to the requirements of various cell types. Publicly available expression data permit to study expression dynamics of genes with mitochondrial function (mito-genes) in various cell types, conditions and organisms. Yet, we lack an easy way of extracting these data for mito-genes. Here, we introduce the visual data mining platform mitoXplorer, which integrates expression and mutation data of mito-genes with a manually curated mitochondrial interactome containing ∼1200 genes grouped in 38 mitochondrial processes. User-friendly analysis and visualization tools allow to mine mitochondrial expression dynamics and mutations across various datasets from four model species including human. To test the predictive power of mitoXplorer, we quantify mito-gene expression dynamics in trisomy 21 cells, as mitochondrial defects are frequent in trisomy 21. We uncover remarkable differences in the regulation of the mitochondrial transcriptome and proteome in one of the trisomy 21 cell lines, caused by dysregulation of the mitochondrial ribosome and resulting in severe defects in oxidative phosphorylation. With the newly developed Fiji plugin mitoMorph, we identify mild changes in mitochondrial morphology in trisomy 21. Taken together, mitoXplorer (http://mitoxplorer.ibdm.univ-mrs.fr) is a user-friendly, web-based and freely accessible software, aiding experimental scientists to quantify mitochondrial expression dynamics.

Developing a customized web mining system with PHP language: A case of Kaohsiung Land administration website data

With the growth of WWW, the unstructured data of web is full of useable information. But these available data are not easy to collect, access, and handle of large scale. Each company, it crawls the available data of site-specific Official or e-Commerce websites and storage huge number of data to progress the analysis of big data. But, here is a difficult question that needs to construct a data mining platform on Web server for companies. In this paper, we use PHP Language to develop a customized web mining system, taking a case of Kaohsiung Land Administration Website Data, defining a novel framework of web mining system, which can reduce cost of constructed platform and enhance efficient of Web crawler.

Augmented intelligence in educational data mining

Educational data mining (EDM) processes have shifted towards open-ended processes with visualizations and parameter and predictive model adjusting. Data and models in hyperdimensions can be visualized for end-users with popular data mining platforms such as Weka and RapidMiner. Multiple studies have shown how the adjusting and even creating the decision tree classifiers help EDM end-users to better comprehend the dataset and the context where the data has been collected. To harness the power of such open-ended approach in EDM, we introduce a novel Augmented Intelligence method and a cluster analysis algorithm Neural N-Tree. These contributions allow EDM end-users to analyze educational data in an iterative process where the knowledge discovery and the accuracy of the predictive model generated by the algorithm increases over time through the interactions between the models and the end-users. In contrast to other similar approaches, the key in our method is in the model adjusting and not in parameter tuning. We report a study where the potential EDM end-users clustered data from an education setting and interacted with Neural N-Tree models by following Augmented Intelligence method. The findings of the study suggest that the accuracy of the models evolve over time and especially the end-users who have a adequate level of knowledge from data mining benefit from the method. Moreover, the study indicates that the knowledge discovery is possible through AUI.

A Comprehensive Survey on Cloud Data Mining (CDM) Frameworks and Algorithms

Data mining is used for finding meaningful information out of a vast expanse of data. With the advent of Big Data concept, data mining has come to much more prominence. Discovering knowledge out of a gigantic volume of data efficiently is a major concern as the resources are limited. Cloud computing plays a major role in such a situation. Cloud data mining fuses the applicability of classical data mining with the promises of cloud computing. This allows it to perform knowledge discovery out of huge volumes of data with efficiency. This article presents the existing frameworks, services, platforms, and algorithms for cloud data mining. The frameworks and platforms are compared among each other based on similarity, data mining task support, parallelism, distribution, streaming data processing support, fault tolerance, security, memory types, storage systems, and others. Similarly, the algorithms are grouped on the basis of parallelism type, scalability, streaming data mining support, and types of data managed. We have also provided taxonomies on the basis of data mining techniques such as clustering, classification, and association rule mining. We also have attempted to discuss and identify the major applications of cloud data mining. The various taxonomies for cloud data mining frameworks, platforms, and algorithms have been identified. This article aims at gaining better insight into the present research realm and directing the future research toward efficient cloud data mining in future cloud systems.

A hybrid Forecast Cost Benefit Classification of diabetes mellitus prevalence based on epidemiological study on Real-life patient\u2019s data

The increasing ratio of diabetes is found risky across the planet. Therefore, the diagnosis is important in population with extreme risk of diabetes. In this study, a decision-making classifier (J48) is applied over a data-mining platform (Weka) to measure accuracy and linear regression on classification results to forecast cost/benefit ratio in diabetes mellitus patients along with prevalence. In total 108 invasive and non-invasive medical features are considered from 251 patients for assessment, and the real-time data are gathered from Pakistan over a time span of June 2017 to April 2018. The results indicate that J48 classifiers achieved the best accuracy of (99.28%), whereas, error rate (0.08%), Kappa stats, PRC, and MCC are (0.98%), precision, recall, and F-matrix are (0.99%). In addition, true positive rate is (0.99%) and false positive is (0.08%). The regression forecast decision indicates blood pressure and glucose level are key features for diabetes. The cost/benefit matrix indicates two predictions for positive test with accuracy (66.68%) and (30.60%), and key attributes with total Gain (118.13%). The study confirmed the proposed prediction is practical for screening of diabetes mellitus patients at the initial stage without invasive medical tests and found effectual in the early diagnosis of diabetes.

MON-332 ADVANCING SYSTEMS-BIOLOGY FOCUSED, GLOMERULAR DISEASE RESEARCH THROUGH PUBLIC-PRIVATE PARTNERSHIPS

The landscape of renal research is changing with the adoption of large-scale data set analysis as a driver of science in both academia and in the private sector. Traditionally, research in academia emphasized publication, not rapid drug development. By working cooperatively, both the public and private sectors can successfully share responsibility in the drug development process. Academia can offset long-term challenges that the private sector may not be set up to sustain, while the private sector may keep critical, translational projects on track through targeted support. Thus, research performed in the public sector can more quickly benefit patients through partnership with private entities. Numerous models exist to achieve successful public-private partnership in nephrology. Software tools are developed that increase universal access to publicly-available, large-scale data; contractual arrangements expedite data-mining and analysis, and bilateral collaborations between the academic and pharmaceutical sector enhance understanding of analytical results. New models of partnership between the public and private sectors within a pre-competitive space integrate complimentary approaches in research direction and priorities. These efforts center around enriching the renal therapeutic target pool by identifying (via systems-biology approaches) key molecular pathways, expediting detection of high-value targets for therapeutic development, and establishing publicly-available resources that enhance understanding of kidney disease for researchers, clinicians and patients. Additionally, publicly-funded consortiums can assist in facilitating a framework, platform and infrastructure for molecularly-targeted clinical trials. Critical success factors of these arrangements are based on the establishment of a research space that allows partners to engage in a mutually-supportive environment. Our group has established one such space via NephroSeq and partnership-specific instances of the open-source datamining and datasharing platform, tranSMART. It is equally important to define expectations on data transparency and sharing from the outset. Exquisite attention to contractual details for research direction, work scope, intellectual property protection, data sharing, publication rights, and project governance are key operational aspects; this is particularly important when accessing resources generated with public funding. Finally, meticulous project management, and effective communication between participating parties can lead to progress across kidney research fields for all stakeholders and, most importantly, benefit patients suffering from kidney disease. By linking public and private entities through partnership at all phases of the translational research process, academic labs can expand the potential of medical research and significantly accelerate the drug development pipeline.

Assessing drug target suitability using TargetMine.

In selecting drug target candidates for pharmaceutical research, the linkage to disease and the tractability of the target are two important factors that can ultimately determine the drug efficacy. Several existing resources can provide gene-disease associations, but determining whether such a list of genes are attractive drug targets often requires further information gathering and analysis. In addition, few resources provide the information required to evaluate the tractability of a target. To address these issues, we have updated TargetMine, a data warehouse for assisting target prioritization, by integrating new data sources for gene-disease associations and enhancing functionalities for target assessment. As a data mining platform that integrates a variety of data sources, including protein structures and chemical compounds, TargetMine now offers a powerful and flexible interface for constructing queries to check genetic evidence, tractability and other relevant features for the candidate genes. We demonstrate these features by using several specific examples.

An Accurate Clinical Implication Assessment for Diabetes Mellitus Prevalence Based on a Study from Nigeria

The increasing rate of diabetes is found across the planet. Therefore, the diagnosis of pre-diabetes and diabetes is important in populations with extreme diabetes risk. In this study, a machine learning technique was implemented over a data mining platform by employing Rule classifiers (PART and Decision table) to measure the accuracy and logistic regression on the classification results for forecasting the prevalence in diabetes mellitus patients suffering simultaneously from other chronic disease symptoms. The real-life data was collected in Nigeria between December 2017 and February 2019 by applying ten non-intrusive and easily available clinical variables. The results disclosed that the Rule classifiers achieved a mean accuracy of 98.75%. The error rate, precision, recall, F-measure, and Matthew’s correlation coefficient MCC were 0.02%, 0.98%, 0.98%, 0.98%, and 0.97%, respectively. The forecast decision, achieved by employing a set of 23 decision rules (DR), indicates that age, gender, glucose level, and body mass are fundamental reasons for diabetes, followed by work stress, diet, family diabetes history, physical exercise, and cardiovascular stroke history. The study validated that the proposed set of DR is practical for quick screening of diabetes mellitus patients at the initial stage without intrusive medical tests and was found to be effective in the initial diagnosis of diabetes.

Research on Spark Big Data Recommendation Algorithm under Hadoop Platform

Hadoop is the main platform for big data mining. It can build Yarn, Mahout, Storm, Graph Lab and other frameworks on its platform. Spark framework is a common task scheduling framework, which not only has powerful processing capabilities, but also has Data processing timeliness, which integrates functions such as machine learning, graph calculation, and online learning, adopts a unified processing mechanism, and the speed is dozens or even hundreds of times that of traditional data processing methods. The paper establishes a Spark framework based on the Hadoop platform, and verifies that the Spark framework’s processing mechanism for big data can meet the speed requirements of the increasingly value-added big data applications.

Predictive Policing and the Platformization of Police Work

Although the revolutionary potential of predictive policing has often been exaggerated, this novel policing strategy nonetheless implies something substantially new: the underlying methods of (crime) data analysis. Moreover, these police prediction tools matter not only because of their capacity to generate near-term crime predictions but also because they have the potential to generally enhance police-related data crunching, ultimately giving rise to the comprehensive datafication of police work, creating an ongoing drive for extensive data collection and, hence, surveillance. This paper argues that because of its enablement of crime data analysis in general, predictive policing software will be an important incubator for datafied police work, especially when executed via data mining platforms, because it has made police authorities aware that the massive amounts of crime data they possess are quite valuable and can now be easily analyzed. These data are perceived to be even more useful when combined with external data sets and when processed on the largest possible scale. Ultimately, significant transformative effects are to be expected for policing, especially in relation to data collection practices and surveillance imperatives.&#x0D;

Assessing drug target suitability using TargetMine

In selecting drug target candidates for pharmaceutical research, the linkage to disease and the tractability of the target are two important factors that can ultimately determine the drug efficacy. Several existing resources can provide gene-disease associations, but determining whether such a list of genes are attractive drug targets often requires further information gathering and analysis. In addition, few resources provide the information required to evaluate the tractability of a target. To address these issues, we have updated TargetMine, a data warehouse for assisting target prioritization, by integrating new data sources for gene-disease associations and enhancing functionalities for target assessment. As a data mining platform that integrates a variety of data sources, including protein structures and chemical compounds, TargetMine now offers a powerful and flexible interface for constructing queries to check genetic evidence, tractability and other relevant features for the candidate genes. We demonstrate these features by using several specific examples.

Assessing drug target suitability using TargetMine.

In selecting drug target candidates for pharmaceutical research, the linkage to disease and the tractability of the target are two important factors that can ultimately determine the drug efficacy. Several existing resources can provide gene-disease associations, but determining whether such a list of genes are attractive drug targets often requires further information gathering and analysis. In addition, few resources provide the information required to evaluate the tractability of a target. To address these issues, we have updated TargetMine, a data warehouse for assisting target prioritization, by integrating new data sources for gene-disease associations and enhancing functionalities for target assessment. As a data mining platform that integrates a variety of data sources, including protein structures and chemical compounds, TargetMine now offers a powerful and flexible interface for constructing queries to check genetic evidence, tractability and other relevant features for the candidate genes. We demonstrate these features by using several specific examples.

Model Training Task Scheduling Algorithm Based on Greedy-Genetic Algorithm for Big-Data Mining

With the coming of the big data age, data mining attracts more and more attention from all trades and professions. Due to the vast computation cost of data mining, the public service platform for big data mining has become the urgent needs, especially for the model training tasks. In this way, how to perform this kind of task scheduling becomes critical. This paper focuses on the assignment of tasks on multiple computing resources to optimize the total operation time. Firstly, a task scheduling algorithm based on the greedy and genetic algorithm is proposed to set the computation resource requirement for each task. Moreover, a greedy strategy is used to decide the task operation order and the assignment mapping between the tasks and the computation resources. Finally, the proposed algorithm proves to be efficient by several experiments.

Mining Insights From Visual Assets.

Zorroa democratizes machine learning by creating an easy to use data mining platform for visual assets.

Study of big data mining based on cloud computing

The discovery of meaningful knowledge with high level of applicability in decision making relies on the maxim of efficient information management and analysis mechanism. Since organisations are functioning in a global scenario with exponentially high data management challenges, it is an imperative for them to adapt to the emerging paradigm of 'big data processing technology'. In the recent decade, the concept of 'big data mining' has acquired greater momentum due to its credible aspects such as cloud hosting, highly indexed and optimised data structures, automatic archival and extraction capabilities, and reporting interfaces. There exists a conspicuous difference between the 'conventional data mining' and 'big data mining'. This paper is an illustration of the advancement of the 'big data mining' and its application in various contexts. The authors of this article narrate on typical data mining algorithm and in-specific the 'parallel implementation of the algorithms'. The paper also analyses the architecture of big data mining system and the framework of big data mining platform based on cloud computing, which has provided reference to the users' cognition and application of big data mining.