Biomedical Data Mining Research Articles

A RECENT SURVEY ON TEXT MINING TOOLS & TECHNIQUES IN THE BIO-MEDICAL DOMAIN

Text mining in the biomedical domain has emerged as a crucial technique that capitalizes on the advancements of natural language processing and machine learning methodologies to extract valuable insights from the biomedical texts available to us from different sources. This research paper explores the methods and recent advancements in text mining techniques for the biomedical field. We analyze various approaches, including Named Entity Recognition (NER), information retrieval, and machine learning algorithms, focusing on their application to biomedical data.Biomedical text mining aims to extract valuable information from a vast and diverse array of unstructured medical text data available from different sources, which can significantly contribute to the advancements in medical research and healthcare improvement. This research paper reflects a comprehensive exploration of fundamental concepts of biomedical textual data mining, its techniques, software, applications of biomedical textual data mining, a literature survey on clinical text mining, and its key challenges. It examines the effectiveness of these techniques in identifying and categorizing biomedical entities like genes, proteins, diseases, and drugs. Through case studies and empirical evaluations, we demonstrate how text mining contributes to knowledge discovery, improves data management, and supports decision-making in healthcare and research. This study aims to provide a detailed overview of state-of-the-art biomedical text mining, offering insights into future directions and potential improvements in this rapidly evolving field.

A new hybrid algorithm for three-stage gene selection based on whale optimization

In biomedical data mining, the gene dimension is often much larger than the sample size. To solve this problem, we need to use a feature selection algorithm to select feature gene subsets with a strong correlation with phenotype to ensure the accuracy of subsequent analysis. This paper presents a new three-stage hybrid feature gene selection method, that combines a variance filter, extremely randomized tree, and whale optimization algorithm. First, a variance filter is used to reduce the dimension of the feature gene space, and an extremely randomized tree is used to further reduce the feature gene set. Finally, the whale optimization algorithm is used to select the optimal feature gene subset. We evaluate the proposed method with three different classifiers in seven published gene expression profile datasets and compare it with other advanced feature selection algorithms. The results show that the proposed method has significant advantages in a variety of evaluation indicators.

The Scope, Methods and Applications of Biomedical Data Mining

Most literature assumptions have been drawn from public databases e.g. NHANES (National Health and Nutrition Examination Survey). Nonetheless, the sets of data are typically featured by high-dimensional timeliness, heterogeneity, characteristics and irregularity, hence amounting to valuation of these databases not being applied completely. Data Mining (DM) technologies have been the frontiers domains in biomedical studies, as it shows smart routine in assessing patients’ risks and aiding in the process of biomedical research and decision-making in developing disease-forecasting frameworks. In that case, DM has novel merits in biomedical Big Data (BD) studies, mostly in large-scale biomedical datasets. In this paper, a description of DM techniques alongside their fundamental practical applications will be provided. The objectives of this study are to help biomedical researchers to attain intuitive and clear appreciative of the applications of data-mining technologies on biomedical BD to enhance to creation of biomedical results, which are relevant in a biomedical setting.

A Practical Guide to Integrating Multimodal Machine Learning and Metabolic Modeling.

Complex, distributed, and dynamic sets of clinical biomedical data are collectively referred to as multimodal clinical data. In order to accommodate the volume and heterogeneity of such diverse data types and aid in their interpretation when they are combined with a multi-scale predictive model, machine learning is a useful tool that can be wielded to deconstruct biological complexity and extract relevant outputs. Additionally, genome-scale metabolic models (GSMMs) are one of the main frameworks striving to bridge the gap between genotype and phenotype by incorporating prior biological knowledge into mechanistic models. Consequently, the utilization of GSMMs as a foundation for the integration of multi-omic data originating from different domains is a valuable pursuit towards refining predictions. In this chapter, we show how cancer multi-omic data can be analyzed via multimodal machine learning and metabolic modeling. Firstly, we focus on the merits of adopting an integrative systems biology led approach to biomedical data mining. Following this, we propose how constraint-based metabolic models can provide a stable yet adaptable foundation for the integration of multimodal data with machine learning. Finally, we provide a step-by-step tutorial for the combination of machine learning and GSMMs, which includes: (i) tissue-specific constraint-based modeling; (ii) survival analysis using time-to-event prediction for cancer; and (iii) classification and regression approaches for multimodal machine learning. The code associated with the tutorial can be found at https://github.com/Angione-Lab/Tutorials_Combining_ML_and_GSMM .

Application of neural network autoencoder algorithm in the cancer informatics research

Cancers have been widely recognized as highly heterogeneous diseases, and early diagnosis and prognosis of cancer types have become the focus of cancer research. In the era of big data, efficient mining of massive biomedical data has become a grand challenge for bioinformatics research. As a typical neural network model, the autoencoder is able to efficiently learn the features of input data by unsupervised training method and further help integrate and mine the biological data. In this article, the primary structure and workflow of the autoencoder model are introduced, followed by summarizing the advances of the autoencoder model in cancer informatics using various types of biomedical data. Finally, the challenges and perspectives of the autoencoder model are discussed.

BSEN: A BiSiamese Entity Normalization Method for Biomedicine

Normalization of named entities in the field of biomedicine is an important task in biomedical text data mining. Compared with other tasks in biomedical text mining research, there are relatively few researches on entities normalization. In this article, a BiSiamese entity normalization method for biomedicine (BSEN) is proposed. Firstly, the text similarity algorithm is analyzed, and an improved similarity measurement algorithm for biomedical inverse text frequency and cosine (BIC) is proposed. Secondly, the data set is trained in pairs using BiSiamese network and combined with BIC to calculate text similarity. The entity corresponding to the maximum similarity calculated in the normalization knowledge base is the normalized result obtained by the BSEN method. The verification experiments on the verification data set show that the BSEN has achieved better normalization results than the existing methods.

Biomedical Named Entity Recognition Based on Self‐supervised Deep Belief Network

Named entity recognition is a fundamental and crucial issue of biomedical data mining. For effectively solving this issue, we propose a novel approach based on Deep belief network (DBN). We select nine entity features, and construct feature vector mapping tables by the recognition contribution degree of different values of them. Using the mapping tables, we transform words in biomedical texts to feature vectors. The DBN will identify entities by reducing dimensions of vector data. The extensive experimental results reveal that the novel approach has achieved excellent recognition performance, with 69.96% maximum value of F-measure on GENIA 3.02 testing corpus. We propose a self-supervised DBN, which can decide whether to add supervised fine-tuning or not according to the recognition performance of each layer, can overcome the errors propagation problem, while the complexity of model is limited. Test analysis shows that the new DBN improves recognition performance, the F-measure increases to 72.12%.

The use or generation of biomedical data and existing medicines to discover and establish new treatments for patients with rare diseases \u2013 recommendations of the IRDiRC Data Mining and Repurposing Task Force

The number of available therapies for rare diseases remains low, as fewer than 6% of rare diseases have an approved treatment option. The International Rare Diseases Research Consortium (IRDiRC) set up the multi-stakeholder Data Mining and Repurposing (DMR) Task Force to examine the potential of applying biomedical data mining strategies to identify new opportunities to use existing pharmaceutical compounds in new ways and to accelerate the pace of drug development for rare disease patients. In reviewing past successes of data mining for drug repurposing, and planning for future biomedical research capacity, the DMR Task Force identified four strategic infrastructure investment areas to focus on in order to accelerate rare disease research productivity and drug development: (1) improving the capture and sharing of self-reported patient data, (2) better integration of existing research data, (3) increasing experimental testing capacity, and (4) sharing of rare disease research and development expertise. Additionally, the DMR Task Force also recommended a number of strategies to increase data mining and repurposing opportunities for rare diseases research as well as the development of individualized and precision medicine strategies.

Gene Selection Method for Microarray Data Classification Using Particle Swarm Optimization and Neighborhood Rough Set

Background: Mining knowledge from microarray data is one of the popular research topics in biomedical informatics. Gene selection is a significant research trend in biomedical data mining, since the accuracy of tumor identification heavily relies on the genes biologically relevant to the identified problems. Objective: In order to select a small subset of informative genes from numerous genes for tumor identification, various computational intelligence methods were presented. However, due to the high data dimensions, small sample size, and the inherent noise available, many computational methods confront challenges in selecting small gene subset. Methods: In our study, we propose a novel algorithm PSONRS_KNN for gene selection based on the particle swarm optimization (PSO) algorithm along with the neighborhood rough set (NRS) reduction model and the K-nearest neighborhood (KNN) classifier. Results: First, the top-ranked candidate genes are obtained by the GainRatioAttributeEval preselection algorithm in WEKA. Then, the minimum possible meaningful set of genes is selected by combining PSO with NRS and KNN classifier. Conclusion: Experimental results on five microarray gene expression datasets demonstrate that the performance of the proposed method is better than existing state-of-the-art methods in terms of classification accuracy and the number of selected genes.

Improving the genetic bee colony optimization algorithm for efficient gene selection in microarray data

Feature selection is a very critical component in the workflow of biomedical data mining applications. In particular, there is a need for feature selection methods that can find complex relationships among genes, yet computationally efficient. Within the scope of microarray data analysis, the genetic bee colony (Gbc) algorithm is one of the best feature selection algorithms, which leverages the combination between genetic and ant colony optimization algorithms to search for the optimal solution. In this paper, we analyse in depth the fundamentals lying behind the Gbc and propose some improvements in both efficiency and accuracy, so that researchers can even take more advantage of this excellent method. By (i) replacing the filtering phase of Gbc with a more efficient technique, (ii) improving the population generation in the artificial colony algorithm used in Gbc, and (iii) improving the exploitation method in Gbc, our experiments in microarray data sets reveal that our new method Gbc+ is not only significantly more accurate, but also around ten times faster on average than the original

Benchmarking relief-based feature selection methods for bioinformatics data mining

Modern biomedical data mining requires feature selection methods that can (1) be applied to large scale feature spaces (e.g. ‘omics’ data), (2) function in noisy problems, (3) detect complex patterns of association (e.g. gene-gene interactions), (4) be flexibly adapted to various problem domains and data types (e.g. genetic variants, gene expression, and clinical data) and (5) are computationally tractable. To that end, this work examines a set of filter-style feature selection algorithms inspired by the ‘Relief’ algorithm, i.e. Relief-Based algorithms (RBAs). We implement and expand these RBAs in an open source framework called ReBATE (Relief-Based Algorithm Training Environment). We apply a comprehensive genetic simulation study comparing existing RBAs, a proposed RBA called MultiSURF, and other established feature selection methods, over a variety of problems. The results of this study (1) support the assertion that RBAs are particularly flexible, efficient, and powerful feature selection methods that differentiate relevant features having univariate, multivariate, epistatic, or heterogeneous associations, (2) confirm the efficacy of expansions for classification vs. regression, discrete vs. continuous features, missing data, multiple classes, or class imbalance, (3) identify previously unknown limitations of specific RBAs, and (4) suggest that while MultiSURF∗ performs best for explicitly identifying pure 2-way interactions, MultiSURF yields the most reliable feature selection performance across a wide range of problem types.

A filter feature selection method based on the Maximal Information Coefficient and Gram-Schmidt Orthogonalization for biomedical data mining

A filter feature selection technique has been widely used to mine biomedical data. Recently, in the classical filter method minimal-Redundancy-Maximal-Relevance (mRMR), a risk has been revealed that a specific part of the redundancy, called irrelevant redundancy, may be involved in the minimal-redundancy component of this method. Thus, a few attempts to eliminate the irrelevant redundancy by attaching additional procedures to mRMR, such as Kernel Canonical Correlation Analysis based mRMR (KCCAmRMR), have been made. In the present study, a novel filter feature selection method based on the Maximal Information Coefficient (MIC) and Gram-Schmidt Orthogonalization (GSO), named Orthogonal MIC Feature Selection (OMICFS), was proposed to solve this problem. Different from other improved approaches under the max-relevance and min-redundancy criterion, in the proposed method, the MIC is used to quantify the degree of relevance between feature variables and target variable, the GSO is devoted to calculating the orthogonalized variable of a candidate feature with respect to previously selected features, and the max-relevance and min-redundancy can be indirectly optimized by maximizing the MIC relevance between the GSO orthogonalized variable and target. This orthogonalization strategy allows OMICFS to exclude the irrelevant redundancy without any additional procedures. To verify the performance, OMICFS was compared with other filter feature selection methods in terms of both classification accuracy and computational efficiency by conducting classification experiments on two types of biomedical datasets. The results showed that OMICFS outperforms the other methods in most cases. In addition, differences between these methods were analyzed, and the application of OMICFS in the mining of high-dimensional biomedical data was discussed. The Matlab code for the proposed method is available at https://github.com/lhqxinghun/bioinformatics/tree/master/OMICFS/.

FC1000: normalized gene expression changes of systematically perturbed human cells.

The systematic study of transcriptional responses to genetic and chemical perturbations in human cells is still in its early stages. The largest available dataset to date is the newly released L1000 compendium. With its 1.3 million gene expression profiles of treated human cells it offers many opportunities for biomedical data mining, but also data normalization challenges of new dimensions. We developed a novel and practical approach to obtain accurate estimates of fold change response profiles from L1000, based on the RUV (Remove Unwanted Variation) statistical framework. Extending RUV to a big data setting, we propose an estimation procedure, in which an underlying RUV model is tuned by feedback through dataset specific statistical measures, reflecting p-value distributions and internal gene knockdown controls. Applying these metrics - termed evaluation endpoints - to disjoint data splits and integrating the results to select an optimal normalization, the procedure reduces bias and noise in the L1000 data, which in turn broadens the potential of this resource for pharmacological and functional genomic analyses. Our pipeline and normalization results are distributed as an R package (nelanderlab.org/FC1000.html).

A Review of Towered Big-Data Service Model for Biomedical Text-Mining Databases

The rapid growth of biomedical informatics has drawn increasing popularity and attention. The reason behind this are the advances in genomic, new molecular, biomedical approaches and various applications like protein identification, patient medical records, genome sequencing, medical imaging and a huge set of biomedical research data are being generated day to day. The increase of biomedical data consists of both structured and unstructured data. Subsequently, in a traditional database system (structured data), managing and extracting useful information from unstructured-biomedical data is a tedious job. Hence, mechanisms, tools, processes, and methods are necessary to apply on unstructured biomedical data (text) to get the useful business data. The fast development of these accumulations makes it progressively troublesome for people to get to the required information in an advantageous and viable way. Text mining can help us mine information and knowledge from a mountain of text, and is now widely applied in biomedical research. Text mining is not a new technology, but it has recently received spotlight attention due to the emergence of Big Data. The applications of text mining are diverse and span to multiple disciplines, ranging from biomedicine to legal, business intelligence and security. In this survey paper, the researcher identifies and discusses biomedical data (text) mining issues, and recommends a possible technique to cope with possible future growth.

A Optimized Binary Approach for Heart Disease Decision Model in Biomedical Data Mining

A Optimized Binary Approach for Heart Disease Decision Model in Biomedical Data Mining

An Improved Wrapper Generation Using Self Organizing Maps and Meta Heuristic Technique for Web Based Biomedical Data Mining

An Improved Wrapper Generation Using Self Organizing Maps and Meta Heuristic Technique for Web Based Biomedical Data Mining

An Improved Mining of Biomedical Data from Web Documents Using Clustering

An Improved Mining of Biomedical Data from Web Documents Using Clustering

Genomic cloud computing: legal and ethical points to consider.

The biggest challenge in twenty-first century data-intensive genomic science, is developing vast computer infrastructure and advanced software tools to perform comprehensive analyses of genomic data sets for biomedical research and clinical practice. Researchers are increasingly turning to cloud computing both as a solution to integrate data from genomics, systems biology and biomedical data mining and as an approach to analyze data to solve biomedical problems. Although cloud computing provides several benefits such as lower costs and greater efficiency, it also raises legal and ethical issues. In this article, we discuss three key ‘points to consider' (data control; data security, confidentiality and transfer; and accountability) based on a preliminary review of several publicly available cloud service providers' Terms of Service. These ‘points to consider' should be borne in mind by genomic research organizations when negotiating legal arrangements to store genomic data on a large commercial cloud service provider's servers. Diligent genomic cloud computing means leveraging security standards and evaluation processes as a means to protect data and entails many of the same good practices that researchers should always consider in securing their local infrastructure.

Editorial for International Journal of biomedical Data Mining

Copyright: © 2014 Dong G, et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. This issue of the International Journal of Biomedical Data Mining presents two contributed articles. The first article, entitled Data Inventory for Cancer Patients Receiving Radiotherapy for Outcome Analysis and Modeling, authored by Jason Vickress, Rob Barnett and Slav Yartsev, describes a database created for storing and analyzing patient specific data related to pre-treatment condition, treatment planning, and treatment outcomes, for patients receiving radiotherapy based cancer treatment. The proposed database can perform automated analysis regarding quality assurance, dose accumulation for multiple treatments on different machines and can assist physicians in choosing the optimal radiation therapy for new patients. The second article, entitled Likelihood Ratio Test of Hardy-Weinberg Equilibrium Using Uncertain Genotypes for Sibship Data, authored by Qiong Li, Helene Massam and Xin Gao, is concerned with the problem of testing for Hardy-Weinberg equilibrium of genotype frequencies in the area of population genetics. This paper develops an Expectation-Maximization algorithm to estimate the genotype frequencies for sibship data with genotype uncertainty, and develops a likelihood ratio test of HardyWeinberg equilibrium for sibships where parental genotypes are not available and where genotyping errors may exist.

Clustering cliques for graph-based summarization of the biomedical research literature.

BackgroundGraph-based notions are increasingly used in biomedical data mining and knowledge discovery tasks. In this paper, we present a clique-clustering method to automatically summarize graphs of semantic predications produced from PubMed citations (titles and abstracts).ResultsSemRep is used to extract semantic predications from the citations returned by a PubMed search. Cliques were identified from frequently occurring predications with highly connected arguments filtered by degree centrality. Themes contained in the summary were identified with a hierarchical clustering algorithm based on common arguments shared among cliques. The validity of the clusters in the summaries produced was compared to the Silhouette-generated baseline for cohesion, separation and overall validity. The theme labels were also compared to a reference standard produced with major MeSH headings.ConclusionsFor 11 topics in the testing data set, the overall validity of clusters from the system summary was 10% better than the baseline (43% versus 33%). While compared to the reference standard from MeSH headings, the results for recall, precision and F-score were 0.64, 0.65, and 0.65 respectively.