Increasing Data Dimensionality Research Articles

Fuzzy Adaptive Knowledge-Based Inference Neural Networks: Design and Analysis.

A novel fuzzy adaptive knowledge-based inference neural network (FAKINN) is proposed in this study. Conventional fuzzy cluster-based neural networks (FCBNNs) suffer from the challenge of a direct extraction of fuzzy rules that can capture and represent the interclass heterogeneity and intraclass homogeneity when the data possess complex structures. Moreover, the capability of the cluster-based rule generator in FCBNNs may decrease with the increase of data dimensionality. These drawbacks impede the generation of desired fuzzy rules, and affect the inference results depending on the fuzzy rules, thereby limiting their generalization ability. To address these drawbacks, an adaptive knowledge generator (AKG), consisting of the observation paradigm (OP) and clustering strategy (CS), is effectively designed to improve the generalization ability in FAKINN. The OP distills the characteristic information (CI) from data to highlight the homogeneity and heterogeneity of objects, and the CS, viz., the weighted condition-driven fuzzy clustering method (WCFCM), is proposed to summarize the CI to construct fuzzy rules. Moreover, the feedback between the OP and CS can control the dimensionality of CI, which endows FAKINN with the potential to tackle high-dimensional data. The main originality of the study focuses on the AKG and WCFCM that are proposed to develop the structural design methodology of FNNs. The performance of FAKINN is evaluated on various benchmarks with 27 comparative methods, and two real-world problems are adopted to validate its effectiveness. Experimental results show that FAKINN outperforms the comparison methods.

High-dimensional control charts with application to surveillance of grease damage in bearings of wind turbines

ABSTRACT High-dimensional data, characterized by having more attributes or variables than observations, presents unique challenges in industrial operations surveillance. Traditional multivariate control charts, like Hotelling’s T 2 chart, perform adequately with lower-dimensional data. However, they often fail to detect variations in process means as data dimensionality increases. This research proposes new control charts designed to enhance the detection of mean variations in both high and low-dimensional data. Specifically, Srivastava-Du (SD), Bai-Saranadasa (BS) and Dempster (DS) statistic-based charts are introduced, and their effectiveness is evaluated through simulations and real-life data applications. The performance of these charts is compared under various multivariate normal and non-normal distributions. Results indicate that DS and BS charts perform similarly, with the DS chart outperforming in low-dimensional normal distribution. Conversely, the SD chart outperformed in high-dimensional non-normal distributions. Additionally, the practical application of these proposed charts is illustrated through the monitoring of grease degradation in wind turbine bearings.

Arabic Text Clustering Using Self-Organizing Maps and Grey Wolf Optimization

Arabic text clustering is an essential topic in Arabic Natural Language Processing (ANLP). Its significance resides in various applications, such as document indexing, categorization, user review analysis, and others. After inspecting the current work on clustering Arabic text, it is observed that most researchers focus on applying K-Means clustering while hindering other clustering techniques. Our evaluation shows that K-Means has a weakness of inconsistent clustering results and weak clustering performance when the data dimensionality increases. Unlike K-Means clustering, Artificial Neural Networks (ANN) models such as Self-Organizing Maps (SOM) demonstrated higher accuracy and efficiency in clustering even with high dimensional datasets. In this paper, we introduce a new clustering model based on an optimization technique called Grey Wolf Optimization (GWO) used conjointly with SOM clustering to enhance its clustering performance and accuracy. The evaluation results of our proposed technique show an improvement in the effectiveness and efficiency in comparison with state-of-the-art approaches.

MCR toolkit: A GPU-based toolkit for multi-channel reconstruction of preclinical and clinical x-ray CT data.

The advancement of x-ray CT into the domains of photon counting spectral imaging and dynamic cardiac and perfusion imaging has created many new challenges and opportunities for clinicians and researchers. To address challenges such as dose constraints and scanning times while capitalizing on opportunities such as multi-contrast imaging and low-dose coronary angiography, these multi-channel imaging applications require a new generation of CT reconstruction tools. These new tools should exploit the relationships between imaging channels during reconstruction to set new image quality standards while serving as a platform for direct translation between the preclinical and clinical domains. We outline and demonstrate a new Multi-Channel Reconstruction (MCR) Toolkit for GPU-based analytical and iterative reconstruction of preclinical and clinical multi-energy and dynamic x-ray CT data. To promote open science, open-source distribution of the Toolkit will coincide with the release of this publication (GPL v3; gitlab.oit.duke.edu/dpc18/mcr-toolkit-public). The MCR Toolkit source code is implemented in C/C++ and NVIDIA's CUDA GPU programming interface, with scripting support from MATLAB and Python. The Toolkit implements matched, separable footprint CT reconstruction operators for projection and backprojection in two geometries: planar, cone-beam CT (CBCT) and 3rd generation, cylindrical multi-detector row CT (MDCT). Analytical reconstruction is performed using filtered backprojection (FBP) for circular CBCT, weighted FBP (WFBP) for helical CBCT, and cone-parallel projection rebinning followed by WFBP for MDCT. Arbitrary combinations of energy and temporal channels are iteratively reconstructed under a generalized multi-channel signal model for joint reconstruction. We solve this generalized model algebraically using the split Bregman optimization method and the BiCGSTAB(l) linear solver interchangeably for both CBCT and MDCT data. Rank-sparse kernel regression (RSKR) and patch-based singular value thresholding (pSVT) are used to regularize the energy and time dimensions, respectively. Under a Gaussian noise model, regularization parameters are estimated automatically from the input data, dramatically reducing algorithm complexity for end users. Multi-GPU parallelization of the reconstruction operators is supported to manage reconstruction times. Denoising with RSKR and pSVT and post-reconstruction material decomposition are illustrated with preclinical and clinical cardiac photon-counting (PC)CT data. A digital MOBY mouse phantom with cardiac motion is used to illustrate single energy (SE), multi-energy (ME), time resolved (TR), and combined multi-energy and time-resolved (METR) helical, CBCT reconstruction. A fixed set of projection data is used across all reconstruction cases to demonstrate the Toolkit's robustness to increasing data dimensionality. Identical reconstruction code is applied to in vivo cardiac PCCT data acquired in a mouse model of atherosclerosis (METR). Clinical cardiac CT reconstruction is illustrated using the XCAT phantom and the DukeSim CT simulator, while dual-source, dual-energy CT reconstruction is illustrated for data acquired with a Siemens Flash scanner. Benchmarking results with NVIDIA RTX 8000 GPU hardware demonstrate 61%-99% efficiency in scaling computation from one to four GPUs for these reconstruction problems. The MCR Toolkit provides a robust solution for temporal and spectral x-ray CT reconstruction problems and was built from the ground up to facilitate translation of CT research and development between preclinical and clinical applications.

Testing the boundaries: Normalizing Flows for higher dimensional data sets

Normalizing Flows (NFs) are emerging as a powerful class of generative models, as they not only allow for efficient sampling, but also deliver, by construction, density estimation. They are of great potential usage in High Energy Physics (HEP), where complex high dimensional data and probability distributions are everyday’s meal. However, in order to fully leverage the potential of NFs it is crucial to explore their robustness as data dimensionality increases. Thus, in this contribution, we discuss the performances of some of the most popular types of NFs on the market, on some toy data sets with increasing number of dimensions.

An efficient feature selection framework based on information theory for high dimensional data

Feature selection plays a vital role in many fields, particularly in pattern recognition and bioinformatics, for selecting informative and relevant features from high dimensional datasets. The increase in dimensionality of data along with the existence of redundant and irrelevant features leads to challenging performance issues when processing and analysing the data. In this paper, an effective feature selection technique called mutual information and Monte Carlo based feature selection (MIMCFS) is proposed. It comprises of two stages. The first stage aims to select predominant features from the high dimensional data. The second stage involves elimination of redundant features that were selected in the first stage. For the purpose of implementing the first stage, a new feature selection strategy based on the approximate Markov blanket and the concept of mutual information is proposed to find out irrelevant and redundant features. In second stage, to avoid misjudgement of redundant features as relevant features, a new strategy based on Monte Carlo tree search technique is proposed in order to completely eradicate redundant features and to improve feature interaction. For experimental evaluation, eight benchmark microarray datasets including imbalanced ones pertaining to cancer analysis are used. Further, in order to compare and justify the performance of the proposed feature selection method, seven state-of-art feature selection techniques namely CFS, Relief, DISR, JMI, CMIM and CMI are employed. The outputs from these feature selection techniques are provided to three standard classifiers namely Naive Bayes, SVM and C4.5 in order to assess the significance of the selected features in building classification models. 10-fold cross validation is adopted to evaluate the classifiers. Accuracy, precision, recall, f-measure, standard deviation, statistical significance metrics are measured to quantify the classifier performance. Experimental results demonstrate the outstanding performance of the proposed algorithm when compared to that of the standard existing methods.

Improved binary particle swarm optimization for feature selection with new initialization and search space reduction strategies

Feature selection (FS) is an important preprocessing technique for dimensionality reduction in classification problems. Particle swarm optimization (PSO) algorithms have been widely used as the optimizers for FS problems. However, with the increase of data dimensionality, the search space expands dramatically, which proposes significant challenges for optimization methods, including PSO. In this paper, we propose an improved sticky binary PSO (ISBPSO) algorithm for FS. ISBPSO adopts three new mechanisms based on a recently proposed binary PSO variant, sticky binary particle swarm optimization (SBPSO), to improve the evolutionary performance. First, a new initialization strategy using the feature weighting information based on mutual information is proposed. Second, a dynamic bits masking strategy for gradually reducing the search space during the evolutionary process is proposed. Third, based on the framework of memetic algorithms, a refinement procedure conducting genetic operations on the personal best positions of ISBPSO is used to alleviate the premature convergence problem. The results on 12 UCI datasets show that ISBPSO outperforms six benchmark PSO-based FS methods and two conventional FS methods (sequential forward selection and sequential backward selection) — ISBPSO obtains either higher or similar accuracies with fewer features in most cases. Moreover, ISBPSO substantially reduces the computation time compared with benchmark PSO-based FS methods. Further analysis shows that all the three proposed mechanisms are effective for improving the search performance of ISBPSO.

Hybrid Approach to Document Anomaly Detection: An Application to Facilitate RPA in Title Insurance

Anomaly detection (AD) is an important aspect of various domains and title insurance (TI) is no exception. Robotic process automation (RPA) is taking over manual tasks in TI business processes, but it has its limitations without the support of artificial intelligence (AI) and machine learning (ML). With increasing data dimensionality and in composite population scenarios, the complexity of detecting anomalies increases and AD in automated document management systems (ADMS) is the least explored domain. Deep learning, being the fastest maturing technology can be combined along with traditional anomaly detectors to facilitate and improve the RPAs in TI. We present a hybrid model for AD, using autoencoders (AE) and a one-class support vector machine (OSVM). In the present study, OSVM receives input features representing real-time documents from the TI business, orchestrated and with dimensions reduced by AE. The results obtained from multiple experiments are comparable with traditional methods and within a business acceptable range, regarding accuracy and performance.

A comparative user study of visualization techniques for cluster analysis of multidimensional data sets

This article presents an empirical user study that compares eight multidimensional projection techniques for supporting the estimation of the number of clusters, [Formula: see text], embedded in six multidimensional data sets. The selection of the techniques was based on their intended design, or use, for visually encoding data structures, that is, neighborhood relations between data points or groups of data points in a data set. Concretely, we study: the difference between the estimates of [Formula: see text] as given by participants when using different multidimensional projections; the accuracy of user estimations with respect to the number of labels in the data sets; the perceived usability of each multidimensional projection; whether user estimates disagree with [Formula: see text] values given by a set of cluster quality measures; and whether there is a difference between experienced and novice users in terms of estimates and perceived usability. The results show that: dendrograms (from Ward’s hierarchical clustering) are likely to lead to estimates of [Formula: see text] that are different from those given with other multidimensional projections, while Star Coordinates and Radial Visualizations are likely to lead to similar estimates; t-Stochastic Neighbor Embedding is likely to lead to estimates which are closer to the number of labels in a data set; cluster quality measures are likely to produce estimates which are different from those given by users using Ward and t-Stochastic Neighbor Embedding; U-Matrices and reachability plots will likely have a low perceived usability; and there is no statistically significant difference between the answers of experienced and novice users. Moreover, as data dimensionality increases, cluster quality measures are likely to produce estimates which are different from those perceived by users using any of the assessed multidimensional projections. It is also apparent that the inherent complexity of a data set, as well as the capability of each visual technique to disclose such complexity, has an influence on the perceived usability.

Applying uncertainty analysis to assess the variation of operator performance when manually gating Flow Cytometry data

Background & Aim The use of Flow Cytometry (FC) for cell identification and counting is prevalent within the biomanufacture of Advanced Therapy Medicinal Products (ATMPs) both in clinical centres and biomanufacturing facilities. Operators involved in the use of FC and the analysis of the resultant datasets have the option of manually gating cell clusters or using a range of automated software platforms (supplied by FC instrument manufacturers, or third party). It is well known that many operators prefer to manually gate on the basis of speed and simplicity, however with increasing data complexity (especially when dealing with multi-colour FC instruments) there is significant potential for variation in final cell count to increase as a function of operator subjectivity. Understanding this relationship between increasing data dimensionality and operator subjectivity during manual gating techniques is important because it allows process facilities to comprehend and quantify the potential for process error as a function of incorrect measurement data. This research has specifically considered how uncertainty analysis can be used to better define operator variation over and beyond traditional measures such as the Coefficient of Variation (CV), where CV is typically only representative of the final gating process and does not provide resolution of understanding at each gating step. Methods, Results & Conclusion Three stages of cell model complexity were designed and trialled (3, 5 and 8 step), measuring variation in manual gating sequence steps to obtain a target cell population, with operators selected from academic and industrial research, and national measurement laboratory process team environments. Increasing operator variation was found as a function of increasing FC data complexity. When considering 3 step, 5 step and 8 step FC analysis, operator CV was found to range from 6% to 57% (3 step to 8 step data respectively). At the same time uncertainty analysis was applied to each gating analysis step providing clear definition of variation at each step allowing the generation of inter- and intra-operator variation statistics. Resultant combined uncertainty statements expressed at a one sigma coverage factor (67%) showed variation from 12% (3 step data) through to 34% (8 step data). Process improvement for manually gated FC analysis can therefore take advantage of this more detailed variation analysis framework and provides a benchmark for future comparison with FC automated software platforms.

Consumable-free Comprehensive Three-Dimensional Gas Chromatography and PARAFAC for Determination of Allergens in Perfumes

A new consumable-free three-dimensional comprehensive gas chromatography (GC3-FID) was designed with modulators already known to comprehensive two-dimensional gas chromatography (GC × GC) users to showcase the opportunity of implementing GC3 systems. A hybrid interface composed of a thermal desorption modulator and a fast forward-flush differential flow modulator was used with modulation periods of 6 s and 300 ms, respectively. The determination of allergens in perfumes associated with chemometric tools, namely, parallel factor analysis (PARAFAC) was accomplished to demonstrate the validity of the proposed system. Evaluated allergens included already regulated ones in Brazil and Europe, such as geraniol and menthol, as well as potential allergens recommended in a 2011 opinion reported by the European Scientific Committee on Consumer Safety. Limits of detection were found to be suitable for current regulations, under 0.001% or 10 µL L−1 for leave-on products. Considerations on the required acquisition rates, the limitations imposed by current modulator technology, the modulation periods used, and how they affect all three dimensions are thoroughly discussed. A GC3 coupled with mass spectrometry (GC3-MS) approach is also covered, as well as a comparison of the signal resolution/deconvolution with the increase of data dimensionality. Lastly, the union of GC3 and chemometric tools allowed for a solution that may be used for both qualitative and quantitative analyses.

Joint Semi-Supervised Feature Selection and Classification through Bayesian Approach

With the increasing data dimensionality, feature selection has become a fundamental task to deal with high-dimensional data. Semi-supervised feature selection focuses on the problem of how to learn a relevant feature subset in the case of abundant unlabeled data with few labeled data. In recent years, many semi-supervised feature selection algorithms have been proposed. However, these algorithms are implemented by separating the processes of feature selection and classifier training, such that they cannot simultaneously select features and learn a classifier with the selected features. Moreover, they ignore the difference of reliability inside unlabeled samples and directly use them in the training stage, which might cause performance degradation. In this paper, we propose a joint semi-supervised feature selection and classification algorithm (JSFS) which adopts a Bayesian approach to automatically select the relevant features and simultaneously learn a classifier. Instead of using all unlabeled samples indiscriminately, JSFS associates each unlabeled sample with a self-adjusting weight to distinguish the difference between them, which can effectively eliminate the irrelevant unlabeled samples via introducing a left-truncated Gaussian prior. Experiments on various datasets demonstrate the effectiveness and superiority of JSFS.

Integrated transcriptomic-genomic tool Texomer profiles cancer tissues.

Profiling of both the genome and the transcriptome promises a comprehensive, functional readout of a tissue sample, yet analytical approaches are required to translate the increased data dimensionality, heterogeneity and complexity into patient benefits. We developed a statistical approach called Texomer ( https://github.com/KChen-lab/Texomer ) that performs allele-specific, tumor-deconvoluted transcriptome-exome integration of autologous bulk whole-exome and transcriptome sequencing data. Texomer results in substantially improved accuracy in sample categorization and functional variant prioritization.

Object-Oriented Method Combined with Deep Convolutional Neural Networks for Land-Use-Type Classification of Remote Sensing Images

Land-use information provides a direct representation of the effect of human activities on the environment, and an accurate and efficient land-use classification of remote sensing images is an important element of land-use and land-cover change research. To solve the problems associated with traditional land-use classification methods (e.g., rapid increase in dimensionality of data, inadequate feature extraction, and low running efficiency), a method that combines object-oriented approach with deep convolutional neural network (COCNN) is presented. First, a multi-scale segmentation algorithm is used to segment images to generate image segmentation regions with high homogeneity. Second, a typical rule set of feature objects is constructed on the basis of the object-oriented segmentation results, and the segmentation objects are classified and extracted to form a training sample set. Third, a convolutional neural network (CNN) model structure is modified to improve classification performance, and the training algorithm is optimized to avoid the overfitting phenomenon that occurs during training using small datasets. Ten land-use types are classified by using the remote sensing images covering the area around Fuxian Lake as an example. By comparing the COCNN method with the method based solely on CNN, precision and kappa index were selected to evaluate the classification accuracy of the two methods. For the COCNN method, on the basis of the classification statistics, precision and kappa index coefficients are 96.2% and 0.96, respectively, which are 8.98% and 0.1 higher than those of the method based solely on CNN. Experimental results show that the COCNN method reasonably and efficiently combines object-oriented and deep learning approaches, thereby effectively solving the problem of the inaccurate classification of typical features with better classification accuracy than the simple use of CNN.

NMF based sparse Cholesky decomposition technique for dimensionality scale back in large data sets

This paper aims at resolving the issues related to increased dimensionality of data in data mining. In this paper, Sparse Cholesky decomposition (SCD) is combined with Non-integer Matrix Factorization (NMF) to remove the problems arising due to increased data dimensionality. The increased data dimensionality in datasets is probably due to non-orthogonality of datasets. The complex conjugate values is used to remove the sparse matrix and a complex gradient algorithm reduces the sparse matrix by the extraction of conjugate values. The SCD-MNF extracts the feature vector and upper triangular matrix linearly maps the feature vector obtained from the SCD. Hence, NMF is employed with SCD for structuring the datasets and this helps to form a well-defined data geometry. The proposed system is evaluated against normalized mutual information and accuracy against different text datasets. The results prove that SCD-NMF attains better results than conventional methods in finding the instances related to the given query.

Research on Online Mining Method of Real Time Soil Sensing Data in Farmland

With the wide application of various agriculture IOT sensor equipment, sensor networks produce ample data for observing dynamic soil properties in farmland. But data processing for analysis and visualization become increasingly difficult as data dimensionality increases. Meanwhile the devices sometimes lose data because of damage and power outages. In this study, exploratory data analysis (EDA) and spatiotemporal interpolation including time as a third dimension and spatial-temporal variogram are used to analyze the soil moisture and temperature data. The experimental results show that EDA can effectively reveal the implicit information of soil sensing data in multiple perspectives by a variety of visual ways. The leave-onestation- out cross-validation indicate that Kriging method based on spatial-temporal variogram has satisfied accuracy, which supplies an effective approach for interpolation and estimation of lost agriculture IOT sensing data. The results also have theoretic and practical value for regional soil management.

Subpixel Mapping of Urban Areas Using EnMAP Data and Multioutput Support Vector Regression

Hyperspectral remote sensing data offer the opportunity to map urban characteristics in detail. Though, adequate algorithms need to cope with increasing data dimensionality, high redundancy between individual bands, and often spectrally complex urban landscapes. The study focuses on subpixel quantification of urban land cover compositions using simulated environmental mapping and analysis program (EnMAP) data acquired over the city of Berlin, utilizing both machine learning regression and classification algorithms, i.e., multioutput support vector regression (MSVR), standard support vector regression (SVR), import vector machine classifier (IVM), and support vector classifier (SVC). The experimental setup incorporates a spectral library and a reference land cover fraction map used for validation purposes. The library spectra were synthetically mixed to derive quantitative training data for the classes vegetation, impervious surface, soil, and water. MSVR and SVR models were trained directly using the synthetic mixtures. For IVM and SVC, a modified hyperparameter selection approach is conducted to improve the description of urban land cover fractions by means of probability outputs. Validation results demonstrate the high potential of the MSVR for subpixel mapping in the urban context. MSVR outperforms SVR in terms of both accuracy and computational time. IVM and SVC work similarly well, yet with lower accuracies of subpixel fraction estimates compared to both regression approaches.

Reducing Dimensionality in Text Mining using Conjugate Gradients and Hybrid Cholesky Decomposition

Generally, data mining in larger datasets consists of certain limitations in identifying the relevant datasets for the given queries. The limitations include: lack of interaction in the required objective space, inability to handle the data sets or discrete variables in datasets, especially in the presence of missing variables and inability to classify the records as per the given query, and finally poor generation of explicit knowledge for a query increases the dimensionality of the data. Hence, this paper aims at resolving the problems with increasing data dimensionality in datasets using modified non-integer matrix factorization (NMF). Further, the increased dimensionality arising due to non-orthogonally of NMF is resolved with Cholesky decomposition (cdNMF). Initially, the structuring of datasets is carried out to form a well-defined geometric structure. Further, the complex conjugate values are extracted and conjugate gradient algorithm is applied to reduce the sparse matrix from the data vector. The cdNMF is used to extract the feature vector from the dataset and the data vector is linearly mapped from upper triangular matrix obtained from the Cholesky decomposition. The experiment is validated against accuracy and normalized mutual information (NMI) metrics over three text databases of varied patterns. Further, the results prove that the proposed technique fits well with larger instances in finding the documents as per the query, than NMF, neighborhood preserving: nonnegative matrix factorization (NPNMF), multiple manifolds non-negative matrix factorization (MMNMF), robust non-negative matrix factorization (RNMF), graph regularized non-negative matrix factorization (GNMF), hierarchical non-negative matrix factorization (HNMF) and cdNMF.

Enhanced hybrid method of divide-and-conquer and RBF neural networks for function approximation of complex problems

This paper provides an enhanced method focused on reducing the computational complexity of function approximation problems by dividing the input data vectors into small groups, which avoids the curse of dimensionality. The computational complexity and memory requirements of the approximated problem are higher when the input data dimensionality increases. A divide-and-conquer algorithm is used to distribute the input data of the complex problem to a divided radial basis function neural network (Div-RBFNN). Under this algorithm, the input data variables are typically distributed to different RBFNNs based on whether the number of the input data dimensions is odd or even. In this paper, each Div-RBFNN will be executed independently and the resulting outputs of all Div-RBFNNs will be grouped using a system of linear combination function. The parameters of each Div-RBFNN (centers, radii, and weights) will be optimized using an efficient learning algorithm, which depends on an enhanced clustering algorithm for function approximation, which clusters the centers of the RBFs. Compared to traditional RBFNNs, the proposed methodology reduces the number of executing parameters. It further outperforms traditional RBFNNs not only with respect to the execution time but also in terms of the number of executing parameters of the system, which produces better approximation error.

Abstract B1-04: Co-expression profiling and transcriptional network evidences from RNA-Seq data reveal specific molecular subtype features in breast cancer

Abstract Expression profiling is regarded as the gold standard for breast cancer subtypes, but the recent advent of integrative multi-omics is challenging the validity of findings based on clustering approaches, the stability of the identified groups, the overall reproducibility of the molecular subtypes associated to clusters, and the impacts in both diagnostic practice and therapy. The purpose of the study is to elucidate the relevance of method integration, moving from the limitations of co-expression dynamics revealed by clustering to the high potential of transcriptional network analysis aimed to merge gene expression signatures with oncogenic pathway activity, and better define distinct disease features, such as molecular subtypes. 106 solid normal and 124 solid tumor breast cancer paired-end RNA-Seq data were obtained from The Cancer Genome Atlas (TCGA). Tissue type for all samples is infiltrating ductal carcinoma from female patients. Median age of patients is 57 yrs for normal samples and 52.5 yrs for tumor samples. All samples were sequenced on Illumina Hi-Seq 2000 and each sample contains on average ~100 million reads. Only reads with mapping quality (MAQ) score >=20 were used and mapping rate for these reads was above 90% against repeat masked human transcriptome (build hg19). Fragment Per Kilobase per Million reads (FPKM) values were computed using TopHat and Cufflinks software. Comparison between normal and tumor samples generated 2344 significantly differentially expressed genes (DEGs; p-values≤0.05; fold-change≥2). The data cascade delivered several expression biotype categories, following ENSEMBL classification. Our focus was initially directed to the identification of molecular subtypes associated to clusters. The clusters were treated as seed classes informing on the target phenotypes, but needing refinement. We explored typical associations formed through hierarchical clustering, tested the robustness of the approach, and assessed the accuracy of sample assignment to clusters. Then, we analyzed transcriptional modularity and by constraining the search space of the problem we identified a list of candidate modules to reflect molecular subtype signatures. We annotated such modules and found distinctive features at both functional enrichment and pathway levels by using several software tools and visualization framework (ClueGO, EnrichmentMap, Cytoscape, etc). We demonstrate that limitations of hierarchical clustering methods for molecular subtyping can in part be bypassed by complementing the expression profiles with transcriptional modules that allow for multiple annotation and useful visualizations. Therefore, it is important to stress a general aspect - that integrative analysis is a key factor relying not just on increasing data dimensionality (i.e., multi-omics into play), but also relying on a refinement of the data cross-fertilization and analysis fusion performed at intra-omic scale, before dealing with inter-omics harmonization. Citation Format: Biju Issac, Nicholas F. Tsinoremas, Enrico Capobianco. Co-expression profiling and transcriptional network evidences from RNA-Seq data reveal specific molecular subtype features in breast cancer. [abstract]. In: Proceedings of the AACR Special Conference on Computational and Systems Biology of Cancer; Feb 8-11 2015; San Francisco, CA. Philadelphia (PA): AACR; Cancer Res 2015;75(22 Suppl 2):Abstract nr B1-04.