Complex biomarker discovery in neuroimaging data: Finding a needle in a haystack.

Neuropsychiatric disorders such as schizophrenia, bipolar disorder and Alzheimer's disease are major public health problems. However, despite decades of research, we currently have no validated prognostic or diagnostic tests that can be applied at an individual patient level. Many neuropsychiatric diseases are due to a combination of alterations that occur in a human brain rather than the result of localized lesions. While there is hope that newer imaging technologies such as functional and anatomic connectivity MRI or molecular imaging may offer breakthroughs, the single biomarkers that are discovered using these datasets are limited by their inability to capture the heterogeneity and complexity of most multifactorial brain disorders. Recently, complex biomarkers have been explored to address this limitation using neuroimaging data. In this manuscript we consider the nature of complex biomarkers being investigated in the recent literature and present techniques to find such biomarkers that have been developed in related areas of data mining, statistics, machine learning and bioinformatics.

In-silico identification of phenotype-biased functional modules.

BACKGROUND: Phenotypes exhibited by microorganisms can be useful for several purposes, e.g., ethanol as an alternate fuel. Sometimes, the target phenotype maybe required in combination with other phenotypes, in order to be useful, for e.g., an industrial process may require that the organism survive in an anaerobic, alcohol rich environment and be able to feed on both hexose and pentose sugars to produce ethanol. This combination of traits may not be available in any existing organism or if they do exist, the mechanisms involved in the phenotype-expression may not be efficient enough to be useful. Thus, it may be required to genetically modify microorganisms. However, before any genetic modification can take place, it is important to identify the underlying cellular subsystems responsible for the expression of the target phenotype. RESULTS: In this paper, we develop a method to identify statistically significant and phenotypically-biased functional modules. The method can compare the organismal network information from hundreds of phenotype expressing and phenotype non-expressing organisms to identify cellular subsystems that are more prone to occur in phenotype-expressing organisms than in phenotype non-expressing organisms. We have provided literature evidence that the phenotype-biased modules identified for phenotypes such as hydrogen production (dark and light fermentation), respiration, gram-positive, gram-negative and motility, are indeed phenotype-related. CONCLUSION: Thus we have proposed a methodology to identify phenotype-biased cellular subsystems. We have shown the effectiveness of our methodology by applying it to several target phenotypes. The code and all supplemental files can be downloaded from (http://freescience.org/cs/phenotype-biased-biclusters/).

NIBBS-search for fast and accurate prediction of phenotype-biased metabolic systems.

Understanding of genotype-phenotype associations is important not only for furthering our knowledge on internal cellular processes, but also essential for providing the foundation necessary for genetic engineering of microorganisms for industrial use (e.g., production of bioenergy or biofuels). However, genotype-phenotype associations alone do not provide enough information to alter an organism's genome to either suppress or exhibit a phenotype. It is important to look at the phenotype-related genes in the context of the genome-scale network to understand how the genes interact with other genes in the organism. Identification of metabolic subsystems involved in the expression of the phenotype is one way of placing the phenotype-related genes in the context of the entire network. A metabolic system refers to a metabolic network subgraph; nodes are compounds and edges labels are the enzymes that catalyze the reaction. The metabolic subsystem could be part of a single metabolic pathway or span parts of multiple pathways. Arguably, comparative genome-scale metabolic network analysis is a promising strategy to identify these phenotype-related metabolic subsystems. Network Instance-Based Biased Subgraph Search (NIBBS) is a graph-theoretic method for genome-scale metabolic network comparative analysis that can identify metabolic systems that are statistically biased toward phenotype-expressing organismal networks. We set up experiments with target phenotypes like hydrogen production, TCA expression, and acid-tolerance. We show via extensive literature search that some of the resulting metabolic subsystems are indeed phenotype-related and formulate hypotheses for other systems in terms of their role in phenotype expression. NIBBS is also orders of magnitude faster than MULE, one of the most efficient maximal frequent subgraph mining algorithms that could be adjusted for this problem. Also, the set of phenotype-biased metabolic systems output by NIBBS comes very close to the set of phenotype-biased subgraphs output by an exact maximally-biased subgraph enumeration algorithm ( MBS-Enum ). The code (NIBBS and the module to visualize the identified subsystems) is available at http://freescience.org/cs/NIBBS.

SPICE: discovery of phenotype-determining component interplays.

BACKGROUND: A latent behavior of a biological cell is complex. Deriving the underlying simplicity, or the fundamental rules governing this behavior has been the Holy Grail of systems biology. Data-driven prediction of the system components and their component interplays that are responsible for the target system's phenotype is a key and challenging step in this endeavor. RESULTS: The proposed approach, which we call System Phenotype-related Interplaying Components Enumerator (SPICE), iteratively enumerates statistically significant system components that are hypothesized (1) to play an important role in defining the specificity of the target system's phenotype(s); (2) to exhibit a functionally coherent behavior, namely, act in a coordinated manner to perform the phenotype-specific function; and (3) to improve the predictive skill of the system's phenotype(s) when used collectively in the ensemble of predictive models. SPICE can be applied to both instance-based data and network-based data. When validated, SPICE effectively identified system components related to three target phenotypes: biohydrogen production, motility, and cancer. Manual results curation agreed with the known phenotype-related system components reported in literature. Additionally, using the identified system components as discriminatory features improved the prediction accuracy by 10% on the phenotype-classification task when compared to a number of state-of-the-art methods applied to eight benchmark microarray data sets. CONCLUSION: We formulate a problem--enumeration of phenotype-determining system component interplays--and propose an effective methodology (SPICE) to address this problem. SPICE improved identification of cancer-related groups of genes from various microarray data sets and detected groups of genes associated with microbial biohydrogen production and motility, many of which were reported in literature. SPICE also improved the predictive skill of the system's phenotype determination compared to individual classifiers and/or other ensemble methods, such as bagging, boosting, random forest, nearest shrunken centroid, and random forest variable selection method.

Functional annotation of hierarchical modularity.

In biological networks of molecular interactions in a cell, network motifs that are biologically relevant are also functionally coherent, or form functional modules. These functionally coherent modules combine in a hierarchical manner into larger, less cohesive subsystems, thus revealing one of the essential design principles of system-level cellular organization and function-hierarchical modularity. Arguably, hierarchical modularity has not been explicitly taken into consideration by most, if not all, functional annotation systems. As a result, the existing methods would often fail to assign a statistically significant functional coherence score to biologically relevant molecular machines. We developed a methodology for hierarchical functional annotation. Given the hierarchical taxonomy of functional concepts (e.g., Gene Ontology) and the association of individual genes or proteins with these concepts (e.g., GO terms), our method will assign a Hierarchical Modularity Score (HMS) to each node in the hierarchy of functional modules; the HMS score and its p-value measure functional coherence of each module in the hierarchy. While existing methods annotate each module with a set of "enriched" functional terms in a bag of genes, our complementary method provides the hierarchical functional annotation of the modules and their hierarchically organized components. A hierarchical organization of functional modules often comes as a bi-product of cluster analysis of gene expression data or protein interaction data. Otherwise, our method will automatically build such a hierarchy by directly incorporating the functional taxonomy information into the hierarchy search process and by allowing multi-functional genes to be part of more than one component in the hierarchy. In addition, its underlying HMS scoring metric ensures that functional specificity of the terms across different levels of the hierarchical taxonomy is properly treated. We have evaluated our method using Saccharomyces cerevisiae data from KEGG and MIPS databases and several other computationally derived and curated datasets. The code and additional supplemental files can be obtained from http://code.google.com/p/functional-annotation-of-hierarchical-modularity/ (Accessed 2012 March 13).

Efficient α, ß-motif finder for identification of phenotype-related functional modules.

BACKGROUND: Microbial communities in their natural environments exhibit phenotypes that can directly cause particular diseases, convert biomass or wastewater to energy, or degrade various environmental contaminants. Understanding how these communities realize specific phenotypic traits (e.g., carbon fixation, hydrogen production) is critical for addressing health, bioremediation, or bioenergy problems. RESULTS: In this paper, we describe a graph-theoretical method for in silico prediction of the cellular subsystems that are related to the expression of a target phenotype. The proposed (α, ß)-motif finder approach allows for identification of these phenotype-related subsystems that, in addition to metabolic subsystems, could include their regulators, sensors, transporters, and even uncharacterized proteins. By comparing dozens of genome-scale networks of functionally associated proteins, our method efficiently identifies those statistically significant functional modules that are in at least α networks of phenotype-expressing organisms but appear in no more than ß networks of organisms that do not exhibit the target phenotype. It has been shown via various experiments that the enumerated modules are indeed related to phenotype-expression when tested with different target phenotypes like hydrogen production, motility, aerobic respiration, and acid-tolerance. CONCLUSION: Thus, we have proposed a methodology that can identify potential statistically significant phenotype-related functional modules. The functional module is modeled as an (α, ß)-clique, where α and ß are two criteria introduced in this work. We also propose a novel network model, called the two-typed, divided network. The new network model and the criteria make the problem tractable even while very large networks are being compared. The code can be downloaded from http://www.freescience.org/cs/ABClique/

DENSE: efficient and prior knowledge-driven discovery of phenotype-associated protein functional modules.

BACKGROUND: Identifying cellular subsystems that are involved in the expression of a target phenotype has been a very active research area for the past several years. In this paper, cellular subsystem refers to a group of genes (or proteins) that interact and carry out a common function in the cell. Most studies identify genes associated with a phenotype on the basis of some statistical bias, others have extended these statistical methods to analyze functional modules and biological pathways for phenotype-relatedness. However, a biologist might often have a specific question in mind while performing such analysis and most of the resulting subsystems obtained by the existing methods might be largely irrelevant to the question in hand. Arguably, it would be valuable to incorporate biologist's knowledge about the phenotype into the algorithm. This way, it is anticipated that the resulting subsytems would not only be related to the target phenotype but also contain information that the biologist is likely to be interested in. RESULTS: In this paper we introduce a fast and theoretically guranteed method called DENSE (Dense and ENriched Subgraph Enumeration) that can take in as input a biologist's prior knowledge as a set of query proteins and identify all the dense functional modules in a biological network that contain some part of the query vertices. The density (in terms of the number of network egdes) and the enrichment (the number of query proteins in the resulting functional module) can be manipulated via two parameters γ and µ, respectively. CONCLUSION: This algorithm has been applied to the protein functional association network of Clostridium acetobutylicum ATCC 824, a hydrogen producing, acid-tolerant organism. The algorithm was able to verify relationships known to exist in literature and also some previously unknown relationships including those with regulatory and signaling functions. Additionally, we were also able to hypothesize that some uncharacterized proteins are likely associated with the target phenotype. The DENSE code can be downloaded from http://www.freescience.org/cs/DENSE/