Search

Accurately predicting three dimensional protein structures from sequences would present us with targets for drugs via molecular dynamics that would treat cancer, viral infections, and neurological diseases. These treatments would have a far reaching impact to our economy, quality of life, and society. The goal of this research was to build a data mining framework to predict cysteine connectivity in proteins from the sequence and oxidation state of cysteines. Accurately predicting the cysteine bonding configuration improves the TM-Score, a quantitative measurement of protein structure prediction accuracy. We provided state of the art $\mathrm{Q}_{{\mathrm{p}}}$ Q p and $\mathrm{Q}_{{\mathrm{c}}}$ Q c on the PDBCYS and IVD-54 Datasets. Furthermore, we have produced a Local Similarity Matrix that compares favorably to the default PSSMs generated from PSI-Blast in a statistically significant way. Our $\mathrm{Q}_{{\mathrm{p}}}$ Q p for SP39, PDBCYS, and IVD-54 were 90.6, 80.6, and 68.5, respectively.

Free radicals that form from reactive species of nitrogen and oxygen can react dangerously with cellular components and are involved with the pathogenesis of diabetes, cancer, Parkinson's, and heart disease. Cysteine amino acids, due to their reactive nature, are prone to oxidation by these free radicals. Determining which cysteines oxidize within proteins is crucial to our understanding of these chronic diseases. Wet lab techniques, like differential alkylation, to determine which cysteines oxidize are often expensive and time-consuming. We utilize machine learning as a fast and inexpensive approach to identifying cysteines with oxidative capabilities. We created the original features RAMmod and RAMseq for use in classification. We also incorporated well-known features such as PROPKA, SASA, PSS, and PSSM. Our algorithm requires only the protein sequence to operate; however, we do use template matching by MODELLER to acquire 3D coordinates for additional feature extraction. There was a mean improvement of RAM over N6C by 22.04% MCC. It was statistically significant with a p-value of 0.015. RAM provided a significant increase over PSSM with a p-value of 0.040 and an average 70.09% improvement MCC., Graphical Abstract Unlabelled Image

Ovarian cancer is one of the prime causes of mortality in women. Diagnosis of ovarian cancer using ultrasonography is tedious as ovarian tumors exhibit minute clinical and structural differences between the suspicious and non-suspicious classes. Early prediction of ovarian cancer will reduce its growth rate and may save many lives. Computer-aided diagnosis (CAD) is a noninvasive method for finding ovarian cancer in its early stage which can avoid patient anxiety and unnecessary biopsy. This study investigates the efficacy of a novel CAD tool to characterize suspicious ovarian cancer using Radon-transformed nonlinear features. The obtained dimension of the extracted features is reduced using Relief-F feature selection method. In this study, we have employed the fuzzy forest-based ensemble classifier in contrast to the known crisp rule-based classifiers. The proposed method is evaluated using 469 (non-suspicious: 238, suspicious: 231) subjects and achieved a maximum 80.60 ± 0.5% accuracy, 81.40% sensitivity, 76.30% specificity with fuzzy forest, an ensemble fuzzy classifier using thirty-nine features. The proposed method is robust and reproducible as it uses maximum number subjects (469) as compared to state-of-the-art techniques. Hence, it can be used as an assisting tool by gynecologists during their routine screening.

Total of 242 benign and malignant thyroid nodules are classified.Various entropies are extracted from Gabor transformed images.These features are subjected to LSDA and ranked by Relief-F method.Various sampling strategies are used to balance the classification data.Obtained classification accuracy of 94.3% with C4.5 decision tree classifier. Thyroid cancer commences from an atypical growth of thyroid tissue at the edge of the thyroid gland. Initially, it forms a lump in the throat and an over-growth of this tissue leads to the formation of benign or malignant thyroid nodules. Blood test and biopsies are the standard techniques used to diagnose the presence of thyroid nodules. But imaging modalities can improve the diagnosis and are marked as cost-effective, non-invasive and risk-free to identify the stages of thyroid cancer. This study proposes a novel automated system for classification of benign and malignant thyroid nodules. Raw images of thyroid nodules recorded using high resolution ultrasound (HRUS) are subjected to Gabor transform. Various entropy features are extracted from these transformed images and these features are reduced by locality sensitive discriminant analysis (LSDA) and ranked by Relief-F method. Over-sampling strategies with Wilcoxon signed-rank, Friedmans and Iman-Davenport post hoc tests are used to balance the classification data and also to improve the classification performance. Classifiers such as support vector machine (SVM), k-nearest neighbour (kNN), multi-layered perceptron (MLP) and decision tree are used for the characterization of benign and malignant thyroid nodules. We have obtained a classification accuracy of 94.3% with C4.5 decision tree classifier using 242 thyroid HRUS images. Our developed system can be used to screen the thyroid automatically and assist the radiologists.

Social networks are defined as a graphical data structure, which captures complex social interactions between users of a social network. Signed social networks are weighted representations of the social network with the emphasis of capturing both positive and negative interactions (edges) between actors of the network. Ad-hoc communities in a social network, as a corollary can be treated as the logical grouping of social actors that share common interests, ideas, or beliefs. In this work, we leverage these known constructs in social networks to effectively identify influencers (i.e. a subset of actors that exert their influence over a community), aka, seeds. Traditional approaches largely rely on degree of connectivity in identifying influencers of a community. We hypothesize that there are other measures to identify influences. In this work, our objective is therefore to explore and propose a technique using Principal Component Analysis (PCA) to identify the smallest set of influencers with increasing the possibility of adopting a product. Furthermore, we validate our finding by evaluating the potential of these influencers to identify positive communities in a social network. We believe our approach is novel in choosing our influencers (seeds) and thus by using these seeds, positive and negative edges are established. We exploit resulting positive and negative edges to mine ad-hoc communities of interest.

Texture features within images are actively pursued for accurate and efficient glaucoma classification. Energy distribution over wavelet subbands is applied to find these important texture features. In this paper, we investigate the discriminatory potential of wavelet features obtained from the daubechies (db3), symlets (sym3), and biorthogonal (bio3.3, bio3.5, and bio3.7) wavelet filters. We propose a novel technique to extract energy signatures obtained using 2-D discrete wavelet transform, and subject these signatures to different feature ranking and feature selection strategies. We have gauged the effectiveness of the resultant ranked and selected subsets of features using a support vector machine, sequential minimal optimization, random forest, and naïve Bayes classification strategies. We observed an accuracy of around 93% using tenfold cross validations to demonstrate the effectiveness of these methods.

Edge detection in medical images has generated significant interest in the medical informatics community, especially in recent years. With the advent of imaging technology in biomedical and clinical domains, the growth in medical digital images has exceeded our capacity to analyze and store them for efficient representation and retrieval, especially for data mining applications. Medical decision support applications frequently demand the ability to identify and locate sharp discontinuities in an image for feature extraction and interpretation of image content, which can then be exploited for decision support analysis. However, due to the inherent high dimensional nature of the image content and the presence of ill-defined edges, edge detection using classical procedures is difficult, if not impossible, for sensitive and specific medical informatics-based discovery. In this paper, we propose a new edge detection technique based on the regional recursive hierarchical decomposition using quadtree and post-filtration of edges using a finite difference operator. We show that in medical images of common origin, focal and/or penumbral blurred edges can be characterized by an estimable intensity gradient. This gradient can further be used for dismissing false alarms. A detailed validation and comparison with related works on diabetic retinopathy images and CT scan images show that the proposed approach is efficient and accurate.

Protein folding is frequently guided by local residue interactions that form clusters in the protein core. The interactions between residue clusters serve as potential nucleation sites in the folding process. Evidence postulates that the residue interactions are governed by the hydrophobic propensities that the residues possess. An array of hydrophobicity scales has been developed to determine the hydrophobic propensities of residues under different environmental conditions. In this work, we propose a graph-theory-based data mining framework to extract and isolate protein structural features that sustain invariance in evolutionary-related proteins, through the integrated analysis of five well-known hydrophobicity scales over the 3D structure of proteins. We hypothesize that proteins of the same homology contain conserved hydrophobic residues and exhibit analogous residue interaction patterns in the folded state. The results obtained demonstrate that discriminatory residue interaction patterns shared among proteins of the same family can be employed for both the structural and the functional annotation of proteins. We obtained on the average 90 percent accuracy in protein classification with a significantly small feature vector compared to previous results in the area. This work presents an elaborate study, as well as validation evidence, to illustrate the efficacy of the method and the correctness of results reported.

Prolonged diabetes retinopathy leads to diabetes maculopathy, which causes gradual and irreversible loss of vision. It is important for physicians to have a decision system that detects the early symptoms of the disease. This can be achieved by building a classification model using machine learning algorithms. Fuzzy logic classifiers group data elements with a degree of membership in multiple classes by defining membership functions for each attribute. Various methods have been proposed to determine the partitioning of membership functions in a fuzzy logic inference system. A clustering method partitions the membership functions by grouping data that have high similarity into clusters, while an equalized universe method partitions data into predefined equal clusters. The distribution of each attribute determines its partitioning as fine or coarse. A simple grid partitioning partitions each attribute equally and is therefore not effective in handling varying distribution amongst the attributes. A data-adaptive method uses a data frequency-driven approach to partition each attribute based on the distribution of data in that attribute. A data-adaptive neuro-fuzzy inference system creates corresponding rules for both finely distributed and coarsely distributed attributes. This method produced more useful rules and a more effective classification system. We obtained an overall accuracy of 98.55 %.

Healthcare informatics, a multi-disciplinary field has become synonymous with the technological advancements and big data challenges. With the need to reduce healthcare costs and the movement towards personalized healthcare, the healthcare industry faces changes in three core areas namely, electronic record management, data integration, and computer aided diagnoses. Machine learning a complex field in itself offers a wide range of tools, techniques, and frameworks that can be exploited to address these challenges. This chapter elaborates on the intricacies of data handling the data rich filed of healthcare informatics, and the potential role of machine learning to mitigate the challenges faced.

As diabetic maculopathy (DM) is a prevalent cause of blindness in the world, it is increasingly important to use automated techniques for the early detection of the disease. In this paper, we propose a decision system to classify DM fundus images into normal, clinically significant macular edema (CMSE), and non-clinically significant macular edema (non-CMSE) classes. The objective of the proposed decision system is three fold namely, to automatically extract textural features (both region specific and global), to effectively choose subset of discriminatory features, and to classify DM fundus images to their corresponding class of disease severity. The system uses a gamut of textural features and an ensemble classifier derived from four popular classifiers such as the hidden naive Bayes, naive Bayes, sequential minimal optimization (SMO), and the tree-based J48 classifiers. We achieved an average classification accuracy of 96.7% using five-fold cross validation.

The endeavor to decipher the structure and function of a protein from its amino acid sequence has provided an enduringly interesting challenge. Due to the sheer quantity of existing protein data, this challenge naturally presents itself as a complex computational problem requiring the deployment of novel data mining techniques. We hypothesize that the hydrophobic moment (HM) is important in the folding and the formation of secondary structures, and is evolutionarily retained in structurally related proteins. We propose the use of magnitude-squared spectral coherence (MSC) to capture HM of a sequence using selected hydrophobicity scales for effective structural and fold classification of protein sequences. Extensive experimentation on PDBselect dataset demonstrates overall success rates of 77.4% and 63.4% for structural and fold classification. The comparative results show that spectral coherence between the hydrophobic and hydrophilic representations of a sequence effectively captures periodic hydrophobic variations over the length of the sequence that corresponds to HM.

Alzheimer’s disease (AD) is a complex disease where the analysis of gene expression patterns relies on computational techniques to understand the cause and progression of the disease. Evidence postulates that the complexity of AD stems from the overlap of early-stage markers with normal aging. Furthermore, there is increasing evidence suggesting that gene co-regulation in AD plays a vital role in the progression of the disease. The aim of this work is to identify and track co-regulated genes from incipient to severe cases of AD i.e. samples that exhibited progression of AD. We hypothesize that co-expressed genes associated with two markers of AD (the cognitive marker-mini mental state examination (MMSE) and the pathological marker Neurofibrillary Tangles (NFT)), are conserved across AD progression. For our analysis we used the Blalock dataset and the prominent tool weighted correlation network analysis (WGCNA). Through our analysis we observed that genes GNA11 and MAP2K2 were consistently ranked through the progression of AD. The functional analysis of the identified co-regulated genes at the incipient stages of AD includes RNA and cofactor binding. Through this exploratory study we conclude that from incipient to severe stages of AD the gamut of co-regulated genes vary rather than being conserved across disease severity.

Multi-domain proteins result from the duplication and combination of complex but limited number of domains. The ability to distinguish multi-domain homologs from unrelated pairs that share a domain is essential to genomic analysis. Heuristics based on sequence similarity and alignment coverage have been proposed to screen out domain insertions but have met with limited success. In this paper we propose a unique protein classification schema for multi-domain protein superfamilies. Segmented profiles of physico-chemical properties and amino acid composition are created for vector quantization based dimensionality reduction to create a feature profile for rule-discovery and classification. Association rules are mined to identify isomorphic relationships that govern the formation of domains between proteins to correctly predict homologous pairs and reject unrelated pairs, including those that share domains. Our results demonstrate that effective classification of conserved domain classes can be performed using these feature profiles, and the classifier is not susceptible to class imbalances frequently encountered in these databases.

Identification of genes expressed in a cell-cycle-specific periodical manner is of importance and has attracted significant interest recently. However, the identification of cell cycle regulated genes by microarray gene analysis is complicated by both synchronization loss and the presence of noise, and remains an interesting challenge. It is known that periodicity and regulation are two vital components observed in popularly used synchronization experiments-alpha arrest, cdc15, and cdc28. We hypothesize that an integrated analysis of aligned synchronization experiments can improve the identification of cell-cyclic genes of the Saccharomyces cerevisiae (budding yeast) data set. In this paper, we propose a unique ranking scheme based on an integrated analysis of two synchronization experiments (cdc15 and cdc28) for a gene using Pearson correlation coefficients and principle component analysis (PCA). Skewness and kurtosis based features vectors are also discovered for the correlated information space. Genetic algorithm based classification employed for the identification of known cell cycle genes from the discovered features of the ranked genes results in higher degrees of accuracy.

Gene array experiments are progressively conducted. However, the biological functional interpretation has not kept pace with this rapid escalation. Functional genomics using data mining methods potentially offers precise, objective, and more reliable gene identification. Our work creates a gene-ranking scheme by integrating gene expression profile phase information with protein similarity to identify cell-cyclic genes. We present a unique schema to enable integration by employing QR-factorisation from the pair-wise similarity matrix formulation. Angular coefficients are derived and consequently employed for integrated gene ranking. Experimental results on an independent benchmark dataset signify the efficacy of the method.