An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

The Self-Organizing Map

Globally, there is a huge unmet need for effective treatments for neurodegenerative diseases. The complexity of the molecular mechanisms underlying neuronal degeneration and the heterogeneity of the patient population present massive challenges to the development of early diagnostic tools and effective treatments for these diseases. Machine learning, a subfield of artificial intelligence, is enabling scientists, clinicians and patients to address some of these challenges. In this Review, we discuss how machine learning can aid early diagnosis and interpretation of medical images as well as the discovery and development of new therapies. A unifying theme of the different applications of machine learning is the integration of multiple high-dimensional sources of data, which all provide a different view on disease, and the automated derivation of actionable insights.

/pdf/applications-of-machine-learning-to-diagnosis-and-treatment-4ayj9iduxu.pdf

Applications of machine learning to diagnosis and treatment of neurodegenerative diseases

Data uncertainty is an inherent property in various applications due to reasons such as outdated sources or imprecise measurement. When data mining techniques are applied to these data, their uncertainty has to be considered to obtain high quality results. We present UK-means clustering, an algorithm that enhances the K-means algorithm to handle data uncertainty. We apply UK-means to the particular pattern of moving-object uncertainty. Experimental results show that by considering uncertainty, a clustering algorithm can produce more accurate results.

Uncertain data mining : An example in clustering location data

A comprehensive survey of clustering algorithms: State-of-the-art machine learning applications, taxonomy, challenges, and future research prospects

Clustering is central to many data-driven bioinformatics research and serves a powerful computational method. In particular, clustering helps at analyzing unstructured and high-dimensional data in the form of sequences, expressions, texts and images. Further, clustering is used to gain insights into biological processes in the genomics level, e.g. clustering of gene expressions provides insights on the natural structure inherent in the data, understanding gene functions, cellular processes, subtypes of cells and understanding gene regulations. Subsequently, clustering approaches, including hierarchical, centroid-based, distribution-based, density-based and self-organizing maps, have long been studied and used in classical machine learning settings. In contrast, deep learning (DL)-based representation and feature learning for clustering have not been reviewed and employed extensively. Since the quality of clustering is not only dependent on the distribution of data points but also on the learned representation, deep neural networks can be effective means to transform mappings from a high-dimensional data space into a lower-dimensional feature space, leading to improved clustering results. In this paper, we review state-of-the-art DL-based approaches for cluster analysis that are based on representation learning, which we hope to be useful, particularly for bioinformatics research. Further, we explore in detail the training procedures of DL-based clustering algorithms, point out different clustering quality metrics and evaluate several DL-based approaches on three bioinformatics use cases, including bioimaging, cancer genomics and biomedical text mining. We believe this review and the evaluation results will provide valuable insights and serve a starting point for researchers wanting to apply DL-based unsupervised methods to solve emerging bioinformatics research problems.

/pdf/deep-learning-based-clustering-approaches-for-bioinformatics-3069wbfrjk.pdf

Deep learning-based clustering approaches for bioinformatics

Gene expression data hide vital information required to understand the biological process that takes place in a particular organism in relation to its environment. Deciphering the hidden patterns in gene expression data proffers a prodigious preference to strengthen the understanding of functional genomics. The complexity of biological networks and the volume of genes present increase the challenges of comprehending and interpretation of the resulting mass of data, which consists of millions of measurements; these data also inhibit vagueness, imprecision, and noise. Therefore, the use of clustering techniques is a first step toward addressing these challenges, which is essential in the data mining process to reveal natural structures and identify interesting patterns in the underlying data. The clustering of gene expression data has been proven to be useful in making known the natural structure inherent in gene expression data, understanding gene functions, cellular processes, and subtypes of cells, mining useful information from noisy data, and understanding gene regulation. The other benefit of clustering gene expression data is the identification of homology, which is very important in vaccine design. This review examines the various clustering algorithms applicable to the gene expression data in order to discover and provide useful knowledge of the appropriate clustering technique that will guarantee stability and high degree of accuracy in its analysis procedure.

Clustering Algorithms: Their Application to Gene Expression Data

Data is useless if information or knowledge that can be used for further reasoning cannot be inferred from it. Cluster analysis, based on some criteria, shares data into important, practical or both categories (clusters) based on shared common characteristics. In research, clustering and classification have been used to analyze data, in the field of machine learning, bioinformatics, statistics, pattern recognition to mention a few. Different methods of clustering include Partitioning (K-means), Hierarchical (AGNES), Density-based (DBSCAN), Grid-based (STING), Soft clustering (FANNY), Model-based (SOM) and Ensemble clustering. Challenges and problems in clustering arise from large datasets, misinterpretation of results and efficiency/performance of clustering algorithms, which is necessary for choosing clustering algorithms. In this paper, application of data clustering was systematically discussed in view of the characteristics of the different clustering techniques that make them better suited or biased when applied to several types of data, such as uncertain data, multimedia data, graph data, biological data, stream data, text data, time series data, categorical data and big data. The suitability of the available clustering algorithms to different application areas was presented. Also investigated were some existing cluster validity methods used to evaluate the goodness of the clusters produced by the clustering algorithms.

Data Clustering: Algorithms and Its Applications

Malaria is an infectious disease that affects close to half a million individuals every year and Plasmodium falciparum is a major cause of malaria. The treatment of this disease could be done effectively if the essential enzymes of this parasite are specifically targeted. Nevertheless, the development of the parasite in resisting existing drugs now makes discovering new drugs a core responsibility. In this study, a novel computational model that makes the prediction of new and validated antimalarial drug target cheaper, easier, and faster has been developed. We have identified new essential reactions as potential targets for drugs in the metabolic network of the parasite. Among the top seven (7) predicted essential reactions, four (4) have been previously identified in earlier studies with biological evidence and one (1) has been with computational evidence. The results from our study were compared with an extensive list of seventy-seven (77) essential reactions with biological evidence from a previous study. We present a list of thirty-one (31) potential candidates for drug targets in Plasmodium falciparum which includes twenty-four (24) new potential candidates for drug targets.

/pdf/in-silico-knockout-screening-of-plasmodium-falciparum-4qtxxnibbw.pdf

In Silico Knockout Screening of Plasmodium falciparum Reactions and Prediction of Novel Essential Reactions by Analysing the Metabolic Network.

Plasmodium falciparum, a malaria pathogen, has shown substantial resistance to treatment coupled with poor response to some vaccines thereby requiring urgent, holistic, and broad approach to prevent this endemic disease. Understanding the biology of the malaria parasite has been identified as a vital approach to overcome the threat of malaria. This study is aimed at identifying essential proteins unique to malaria parasites using a reconstructed iPfa genome-scale metabolic model (GEM) of the 3D7 strain of Plasmodium falciparum by filling gaps in the model with nineteen (19) metabolites and twenty-three (23) reactions obtained from the MetaCyc database. Twenty (20) currency metabolites were removed from the network because they have been identified to produce shortcuts that are biologically infeasible. The resulting modified iPfa GEM was a model using the - shortest path algorithm to identify possible alternative metabolic pathways in glycolysis and pentose phosphate pathways of Plasmodium falciparum. Heuristic function was introduced for the optimal performance of the algorithm. To validate the prediction, the essentiality of the reactions in the reconstructed network was evaluated using betweenness centrality measure, which was applied to every reaction within the pathways considered in this study. Thirty-two (32) essential reactions were predicted among which our method validated fourteen (14) enzymes already predicted in the literature. The enzymatic proteins that catalyze these essential reactions were checked for homology with the host genome, and two (2) showed insignificant similarity, making them possible drug targets. In conclusion, the application of the intelligent search technique to the metabolic network of P. falciparum predicts potential biologically relevant alternative pathways using graph theory-based approach.

/pdf/computational-identification-of-metabolic-pathways-of-1n7jw1wp1q.pdf

Computational Identification of Metabolic Pathways of Plasmodium falciparum using the -Shortest Path Algorithm

Plasmodium falciparum are instrumental in causing malaria and have developed complex life cycles, thus, it becomes very possible for the malaria parasite to take advantage of the uniqueness of its pathways to design therapeutic strategies. Despite the colossal efforts put in to fight malaria the disease still affects up to over 200 million people every year amongst which close to half a million dies. The treatment of the disease, could be done successfully if the essential enzymes of this parasite is precisely targeted. Nevertheless, the development of the parasite to resisting existing drugs now makes it a core responsibility to discover novel drugs. In this study, existing essential reactions from different literature are considered and evaluated to determine reactions that are common in all literature and evaluated to determine their essentiality level. This study evaluates essential reactions that has been predicted in literature computationally and validates its essentiality based on the reconstructed metabolic network and identifies 10 essential reactions that are common to all existing literature of which all this reaction were validated to be essential by our method. This study has established a simple novel in-silico method that validates predicted essential reactions in a metabolic network which makes validation of predicted anti-malarial drug target cheaper, easier and faster. This study in-silico model serves as a valuable tool for validation of Plasmodium falciparum metabolic states under various perturbations.

Efosa Uwoghiren

Papers

Clustering Algorithms: Their Application to Gene Expression Data

Data Clustering: Algorithms and Its Applications

In Silico Knockout Screening of Plasmodium falciparum Reactions and Prediction of Novel Essential Reactions by Analysing the Metabolic Network.

Computational Identification of Metabolic Pathways of Plasmodium falciparum using the -Shortest Path Algorithm

In-silicoValidation of the Essentiality of Reactions in Plasmodium Falciparum Metabolic Network