HCNM: Heterogeneous Correlation Network Model for Multi-level Integrative Study of Multi-omics Data for Cancer Subtype Prediction.

Integrative analysis of multi-omics data is important for biomedical applications, as it is required for a comprehensive understanding of biological function. Integrating multi-omics data serves multiple purposes, such as, an integrated data model, dimensionality reduction of omic features, patient clustering, etc. For oncological data, patient clustering is synonymous to cancer subtype prediction. However, there is a gap in combining some of the widely used integrative analyses to build more powerful tools. To bridge the gap, we propose a multi-level integration algorithm to identify representative integrative subspace and use it for cancer subtype prediction. The three integrative approaches we implement on multi-omics features are, (1) multivariate multiple (linear) regression of the features from a cohort of patients/samples, (2) network construction using different omics features, and (3) fusion of sample similarity networks across the features. We use a type of multilayer network, called heterogeneous network, as a data model to transition between a network-free (NF) regression model and a network-based (NB) model, which uses correlation networks. The heterogeneous networks consist of intra- and inter-layer graphs. Our proposed heterogeneous correlation network model, HCNM, is central to our algorithm for gene-ranking, integrative subspace identification, and tumor-specific subtypes prediction. The genes of our representative integrative subspace have been enriched with gene-ontology and found to exhibit significant gene-disease association (GDA) scores. The subspace in genes which is less than 5% of the total gene-set of each genomic feature is used with NB fusion integrative model to predict sample subtypes. As the identified integrative subspace data of multi-omics is less prone to noise, bias, and outliers, our experiments show that the subtypes in our results agree with previous benchmark studies and exhibit better classification between poor and good survival of patient cohorts.Clinical relevance: Finding significant cancer-specific genes and subtypes of cancer is vital for early prognosis, and personalized treatment; therefore, improves survival probability of a patient.

Case Report: Obsessive compulsive disorder in posterior cerebellar infarction - illustrating clinical and functional connectivity modulation using MRI-informed transcranial magnetic stimulation.

Objectives: We describe atypical and resistant neuropsychiatric clinical manifestations in a young male with posterior cerebellar gliosis. We also attempt to test the mediating role of the cerebellum in the clinical presentation by manipulating the frontal-cerebellar network using MRI-informed transcranial magnetic stimulation (TMS). Methods: A case report of a young adult male describing obsessive-compulsive symptoms, probably secondary to an infarct in the cerebellar right crus II, combined with an examination of behavioral and functional connectivity changes following TMS treatment. Results: Obsessions, compulsions, and pathological slowing were observed in the background of a posterior cerebellar infarct, along with impairments in vigilance, working memory, verbal fluency, visuospatial ability, and executive functions, in the absence of any motor coordination difficulties. These symptoms did not respond to escitalopram. MRI-informed intermittent theta-burst stimulation delivered to the pre-supplementary motor area identified based on its connectivity with the cerebellar lesion in the crus II resulted in partial improvement of symptoms with enhanced within and between-network modularity of the cerebellar network connectivity. Conclusion: We illustrate a case of OCD possibly secondary to a posterior cerebellar infarct, supporting the role of the cerebellum in the pathophysiology of OCD. Functional connectivity informed non-invasive neuromodulation demonstrated partial treatment response. A seriation technique showed extended connectivity of the cerebellar lesion regions following the neuromodulatory treatment.

A Multiscale Consensus Method Using Factor Analysis to Extract Modular Regions in the Functional Brain Network.

The brain functional connectivity network is complex, generally constructed using correlations between the regions of interest (ROIs) in the brain, corresponding to a parcellation atlas. The brain is known to exhibit a modular organization, referred to as "functional segregation." Generally, functional segregation is extracted from edge-filtered, and optionally, binarized network using community detection and clustering algorithms. Here, we propose the novel use of exploratory factor analysis (EFA) on the correlation matrix for extracting functional segregation, to avoid sparsifying the network by using a threshold for edge filtering. However, the direct usability of EFA is limited, owing to its inherent issues of replication, reliability, and generalizability. In order to avoid finding an optimal number of factors for EFA, we propose a multiscale approach using EFA for node-partitioning, and use consensus to aggregate the results of EFA across different scales. We define an appropriate scale, and discuss the influence of the "interval of scales" in the performance of our multiscale EFA. We compare our results with the state-of-the-art in our case study. Overall, we find that the multiscale consensus method using EFA performs at par with the state-of-the-art.Clinical relevance: Extracting modular brain regions allows practitioners to study spontaneous brain activity at resting state.

Integrative regression network for genomic association study.

BACKGROUND: The increasing availability of multiple types of genomic profiles measured from the same cancer patients has provided numerous opportunities for investigating genomic mechanisms underlying cancer. In particular, association studies of gene expression traits with respect to multi-layered genomic features are highly useful for uncovering the underlying mechanism. Conventional correlation-based association tests are limited because they are prone to revealing indirect associations. Moreover, integration of multiple types of genomic features raises another challenge. METHODS: In this study, we propose a new framework for association studies called integrative regression network that identifies genomic associations on multiple high-dimensional genomic profiles by taking into account the associations between as well as within profiles. We employed high-dimensional regression techniques to first identify the associations between different genomic profiles. Based on the resulting regression coefficients, a regression network was constructed within each profile. For example, two methylation features having similar regression coefficients with respect to a number of gene expression traits are likely to be involved in the same biological process and therefore we define an edge between two methylation features in the regression network. To extract more reliable associations, multiple sparse structured regression techniques were applied and the resulting multiple networks were merged as the integrative regression network using a similarity network fusion technique. RESULTS: Experiments were carried out using four different sparse structured regression methods on five cancer types from TCGA. The advantages and disadvantages of each regression method were also explored. We find there was large inconsistency in the results from different regression methods, which supports the need to extract the proposed integrative regression network from multiple complimentary regression techniques. Fusing multiple regression networks by using similarity measurements led to the identification of significant gene pairs and a resulting network with better topological properties. CONCLUSIONS: We developed and validated the integrative regression network scheme on multi-layered genomic profiles from TCGA. Our method facilitates identification of the strong signals as well as weaker signals by fusing information from different regression techniques. It could be extended to integrate results obtained from different cancer types as well.