Biological contextual information helps understand various phenomena occurring in the biological systems consisting of complex molecular relations. The construction of context-specific relational resources vastly relies on laborious manual extraction from unstructured literature. In this paper, we propose COMMODAR, a machine learning-based literature mining framework for context-specific molecular relations using multimodal representations. The main idea of COMMODAR is the feature augmentation by the cooperation of multimodal representations for relation extraction. We leveraged biomedical domain knowledge as well as canonical linguistic information for more comprehensive representations of textual sources. The models based on multiple modalities outperformed those solely based on the linguistic modality. We applied COMMODAR to the 14 million PubMed abstracts and extracted 9214 context-specific molecular relations. All corpora, extracted data, evaluation results, and the implementation code are downloadable at https://github.com/jae-hyun-lee/commodar . CCS CONCEPTS: • Computing methodologies~Information extraction • Computing methodologies~Neural networks • Applied computing~Biological networks.

The human colorectal carcinoma cell line (Caco-2) is a commonly used in-vitro test that predicts the absorption potential of orally administered drugs. In-silico prediction methods, based on the Caco-2 assay data, may increase the effectiveness of the high-throughput screening of new drug candidates. However, previously developed in-silico models that predict the Caco-2 cellular permeability of chemical compounds use handcrafted features that may be dataset-specific and induce over-fitting problems. Deep Neural Network (DNN) generates high-level features based on non-linear transformations for raw features, which provides high discriminant power and, therefore, creates a good generalized model. We present a DNN-based binary Caco-2 permeability classifier. Our model was constructed based on 663 chemical compounds with in-vitro Caco-2 apparent permeability data. Two hundred nine molecular descriptors are used for generating the high-level features during DNN model generation. Dropout regularization is applied to solve the over-fitting problem and the non-linear activation. The Rectified Linear Unit (ReLU) is adopted to reduce the vanishing gradient problem. The results demonstrate that the high-level features generated by the DNN are more robust than handcrafted features for predicting the cellular permeability of structurally diverse chemical compounds in Caco-2 cell lines.

BACKGROUND: Pandemic is a typical spreading phenomenon that can be observed in the human society and is dependent on the structure of the social network. The Susceptible-Infective-Recovered (SIR) model describes spreading phenomena using two spreading factors; contagiousness (β) and recovery rate (γ). Some network models are trying to reflect the social network, but the real structure is difficult to uncover. METHODS: We have developed a spreading phenomenon simulator that can input the epidemic parameters and network parameters and performed the experiment of disease propagation. The simulation result was analyzed to construct a new marker VRTP distribution. We also induced the VRTP formula for three of the network mathematical models. RESULTS: We suggest new marker VRTP (value of recovered on turning point) to describe the coupling between the SIR spreading and the Scale-free (SF) network and observe the aspects of the coupling effects with the various of spreading and network parameters. We also derive the analytic formulation of VRTP in the fully mixed model, the configuration model, and the degree-based model respectively in the mathematical function form for the insights on the relationship between experimental simulation and theoretical consideration. CONCLUSIONS: We discover the coupling effect between SIR spreading and SF network through devising novel marker VRTP which reflects the shifting effect and relates to entropy.

BACKGROUND: Side effects are unwanted responses to drug treatment and are important resources for human phenotype information. The recent development of a database on side effects, the side effect resource (SIDER), is a first step in documenting the relationship between drugs and their side effects. It is, however, insufficient to simply find the association of drugs with biological processes; that relationship is crucial because drugs that influence biological processes can have an impact on phenotype. Therefore, knowing which processes respond to drugs that influence the phenotype will enable more effective and systematic study of the effect of drugs on phenotype. To the best of our knowledge, the relationship between biological processes and side effects of drugs has not yet been systematically researched. METHODS: We propose 3 steps for systematically searching relationships between drugs and biological processes: enrichment scores (ES) calculations, t-score calculation, and threshold-based filtering. Subsequently, the side effect-related biological processes are found by merging the drug-biological process network and the drug-side effect network. Evaluation is conducted in 2 ways: first, by discerning the number of biological processes discovered by our method that co-occur with Gene Ontology (GO) terms in relation to effects extracted from PubMed records using a text-mining technique and second, determining whether there is improvement in performance by limiting response processes by drugs sharing the same side effect to frequent ones alone. RESULTS: The multi-level network (the process-drug-side effect network) was built by merging the drug-biological process network and the drug-side effect network. We generated a network of 74 drugs-168 side effects-2209 biological process relation resources. The preliminary results showed that the process-drug-side effect network was able to find meaningful relationships between biological processes and side effects in an efficient manner. CONCLUSIONS: We propose a novel process-drug-side effect network for discovering the relationship between biological processes and side effects. By exploring the relationship between drugs and phenotypes through a multi-level network, the mechanisms underlying the effect of specific drugs on the human body may be understood.

MOTIVATION: Gene set analysis has become an important tool for the functional interpretation of high-throughput gene expression datasets. Moreover, pattern analyses based on inferred gene set activities of individual samples have shown the ability to identify more robust disease signatures than individual gene-based pattern analyses. Although a number of approaches have been proposed for gene set-based pattern analysis, the combinatorial influence of deregulated gene sets on disease phenotype classification has not been studied sufficiently. RESULTS: We propose a new approach for inferring combinatorial Boolean rules of gene sets for a better understanding of cancer transcriptome and cancer classification. To reduce the search space of the possible Boolean rules, we identify small groups of gene sets that synergistically contribute to the classification of samples into their corresponding phenotypic groups (such as normal and cancer). We then measure the significance of the candidate Boolean rules derived from each group of gene sets; the level of significance is based on the class entropy of the samples selected in accordance with the rules. By applying the present approach to publicly available prostate cancer datasets, we identified 72 significant Boolean rules. Finally, we discuss several identified Boolean rules, such as the rule of glutathione metabolism (down) and prostaglandin synthesis regulation (down), which are consistent with known prostate cancer biology. AVAILABILITY: Scripts written in Python and R are available at http://biosoft.kaist.ac.kr/~ihpark/. The refined gene sets and the full list of the identified Boolean rules are provided in the Supplementary Material. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Genome-wide expression profiles of diseased samples have been exploited to predict disease states. Recently, network-based approaches utilizing molecular interaction networks integrated with gene expression profiles have been proposed to address challenges which arise from smaller number of samples compared to the large number of predictors, and genetic heterogeneity of samples in complex diseases such as cancer. However, previous network-based methods only focus on expression levels of proteins, nodes in the network though the identification of condition-responsive interactions, edges under the phenotype of interest must enlighten another aspect of pathogenic processes. Thus, we propose a novel network-based classification which focuses on both nodes with discriminative expression levels and edges with condition-responsive correlations across two phenotypes. The extracted modules with condition-responsive interactions not only provide candidate molecular models for disease, and their activities inferred from a subset of member genes serve as better predictors in classification compared to the conventional gene-centric method.

Reverse engineering of gene regulatory networks from microarray time series data has been a challenging problem due to the limit of available data. In this paper, a new approach is proposed based on the concept of transfer entropy. Using this information theoretic measure, causal relations between pairs of genes are assessed to draw a causal network. A heuristic rule is then applied to differentiate direct and indirect causality. Simulation on a synthetic network showed that the transfer entropy can identify both linear and nonlinear causality. Application of the method in a biological data identified many causal interactions with biological information supports.

MOTIVATION: Clustering technique is used to find groups of genes that show similar expression patterns under multiple experimental conditions. Nonetheless, the results obtained by cluster analysis are influenced by the existence of missing values that commonly arise in microarray experiments. Because a clustering method requires a complete data matrix as an input, previous studies have estimated the missing values using an imputation method in the preprocessing step of clustering. However, a common limitation of these conventional approaches is that once the estimates of missing values are fixed in the preprocessing step, they are not changed during subsequent processes of clustering; badly estimated missing values obtained in data preprocessing are likely to deteriorate the quality and reliability of clustering results. Thus, a new clustering method is required for improving missing values during iterative clustering process. RESULTS: We present a method for Clustering Incomplete data using Alternating Optimization (CIAO) in which a prior imputation method is not required. To reduce the influence of imputation in preprocessing, we take an alternative optimization approach to find better estimates during iterative clustering process. This method improves the estimates of missing values by exploiting the cluster information such as cluster centroids and all available non-missing values in each iteration. To test the performance of the CIAO, we applied the CIAO and conventional imputation-based clustering methods, e.g. k-means based on KNNimpute, for clustering two yeast incomplete data sets, and compared the clustering result of each method using the Saccharomyces Genome Database annotations. The clustering results of the CIAO method are more significantly relevant to the biological gene annotations than those of other methods, indicating its effectiveness and potential for clustering incomplete gene expression data. AVAILABILITY: The software was developed using Java language, and can be executed on the platforms that JVM (Java Virtual Machine) is running. It is available from the authors upon request.

The purpose of data description is to give a compact description of the target data that represents most of its characteristics. In a support vector data description (SVDD), the compact description of target data is given in a hyperspherical model, which is determined by a small portion of data called support vectors. Despite the usefulness of the conventional SVDD, however, it may not identify the optimal solution of target description especially when the support vectors do not have the overall characteristics of the target data. To address the issue in SVDD methodology, we propose a new SVDD by introducing new distance measurements based on the notion of a relative density degree for each data point in order to reflect the distribution of a given data set. Moreover, for a real application, we extend the proposed method for the protein localization prediction problem which is a multiclass and multilabel problem. Experiments with various real data sets show promising results.

MOTIVATION: Clustering has been used as a popular technique for finding groups of genes that show similar expression patterns under multiple experimental conditions. Many clustering methods have been proposed for clustering gene-expression data, including the hierarchical clustering, k-means clustering and self-organizing map (SOM). However, the conventional methods are limited to identify different shapes of clusters because they use a fixed distance norm when calculating the distance between genes. The fixed distance norm imposes a fixed geometrical shape on the clusters regardless of the actual data distribution. Thus, different distance norms are required for handling the different shapes of clusters. RESULTS: We present the Gustafson-Kessel (GK) clustering method for microarray gene-expression data. To detect clusters of different shapes in a dataset, we use an adaptive distance norm that is calculated by a fuzzy covariance matrix (F) of each cluster in which the eigenstructure of F is used as an indicator of the shape of the cluster. Moreover, the GK method is less prone to falling into local minima than the k-means and SOM because it makes decisions through the use of membership degrees of a gene to clusters. The algorithmic procedure is accomplished by the alternating optimization technique, which iteratively improves a sequence of sets of clusters until no further improvement is possible. To test the performance of the GK method, we applied the GK method and well-known conventional methods to three recently published yeast datasets, and compared the performance of each method using the Saccharomyces Genome Database annotations. The clustering results of the GK method are more significantly relevant to the biological annotations than those of the other methods, demonstrating its effectiveness and potential for clustering gene-expression data. AVAILABILITY: The software was developed using Java language, and can be executed on the platforms that JVM (Java Virtual Machine) is running. It is available from the authors upon request. SUPPLEMENTARY INFORMATION: Supplementary data are available at http://dragon.kaist.ac.kr/gk.

MOTIVATION: The structural interaction of proteins and their domains in networks is one of the most basic molecular mechanisms for biological cells. Topological analysis of such networks can provide an understanding of and solutions for predicting properties of proteins and their evolution in terms of domains. A single paradigm for the analysis of interactions at different layers, such as domain and protein layers, is needed. RESULTS: Applying a colored vertex graph model, we integrated two basic interaction layers under a unified model: (1) structural domains and (2) their protein/complex networks. We identified four basic and distinct elements in the model that explains protein interactions at the domain level. We searched for motifs in the networks to detect their topological characteristics using a pruning strategy and a hash table for rapid detection. We obtained the following results: first, compared with a random distribution, a substantial part of the protein interactions could be explained by domain-level structural interaction information. Second, there were distinct kinds of protein interaction patterns classified by specific and distinguishable numbers of domains. The intermolecular domain interaction was the most dominant protein interaction pattern. Third, despite the coverage of the protein interaction information differing among species, the similarity of their networks indicated shared architectures of protein interaction network in living organisms. Remarkably, there were only a few basic architectures in the model (>10 for a 4-node network topology), and we propose that most biological combinations of domains into proteins and complexes can be explained by a small number of key topological motifs. CONTACT: [email protected].

MOTIVATION: The transcription of a gene is largely determined by short sequence motifs that serve as binding sites for transcription factors. Recent findings suggest direct relationships between the motifs and gene expression levels. In this work, we present a method for identifying regulatory motifs. Our method makes use of tree-based techniques for recovering the relationships between motifs and gene expression levels. RESULTS: We treat regulatory motifs and gene expression levels as predictor variables and responses, respectively, and use a regression tree model to identify the structural relationships between them. The regression tree methodology is extended to handle responses from multiple experiments by modifying the split function. The significance of regulatory elements is determined by analyzing tree structures and using a variable importance measure. When applied to two data sets of the yeast Saccharomyces cerevisiae, the method successfully identifies most of the regulatory motifs that are known to control gene transcription under the given experimental conditions, and suggests several new putative motifs. Analysis of the tree structures also reconfirms several pairs of motifs that are known to regulate gene transcription in combination. AVAILABILITY: http://if.kaist.ac.kr/~phuong/RegTree

A comparison method for discrete type-2 fuzzy values is proposed in this paper. The proposed method is based on the concept of the satisfaction function that handles the ambiguity in fuzzy comparisons using the possibility distribution of actual values. Some properties of the proposed comparison method are analyzed as well.

Intelligent systems require a systematic way to represent and handle temporal information containing uncertainty. In particular, a logical framework is needed that can represent uncertain temporal information and its relationships with logical formulae. Fuzzy linear temporal logic (FLTL), a generalization of propositional linear temporal logic (PLTL) with fuzzy temporal events and fuzzy temporal states defined on a linear time model, was previously proposed for this purpose. However, many systems are best represented by branching time models in which each state can have more than one possible future path. In this paper, fuzzy branching temporal logic (FBTL) is proposed to address this problem. FBTL adopts and generalizes concurrent tree logic (CTL*), which is a classical branching temporal logic. The temporal model of FBTL is capable of representing fuzzy temporal events and fuzzy temporal states, and the order relation among them is represented as a directed graph. The utility of FBTL is demonstrated using a fuzzy job shop scheduling problem as an example.

Computational discovery of transcriptional regulatory regions in DNA sequences provides an efficient way to broaden our understanding of how cellular processes are controlled. We formulate the regulatory element discovery problem in the regression framework with regulatory regions treated as predictor variables and gene expression levels as responses. We use regression tree models to identify structural relationships between predictors and responses. The regression tree methodology is extended to handle multiple responses from different experiments by modifying the split function. We apply this method to two data sets of the yeast Saccharomyces cerevisiae. The method successfully identifies most of regulatory motifs that are known to control gene transcription under the given experimental conditions. Our method also suggests several putative motifs that present novel regulatory motifs.

The goal of information retrieval system is to search the documents which user wants to obtain in a fast and efficient way. Many information retrieval models, including Boolean models, vector models, and fuzzy models based on the traditional fuzzy set theory, have been proposed to achieve these kinds of objectives. The previous models, however, have a limitation on the fact that they do not consider the user's preference in the document search process. In this paper, we proposed a new extended fuzzy information retrieval system which can handle the shortcomings of the previous ones. In the proposed model, a new similarity measure was applied in order to calculate the relevance degree among documents which can exploit the user's preference.

Deciding a proper metric for crisp values are well established and the results are clear, but the operation on fuzzy values are inherently ambiguous because the fuzzy values include uncertainty. This paper deals with this distance metric on a set of crisp/fuzzy values with different viewpoints. A bounded pseudo-metric function (distance function) for a set of crisp/fuzzy values is proposed. The distance function is based on the satisfaction function on continuous domain with a viewpoint. The viewpoint was adopted to incorporate user's preferences on the domain of discourse. The proposed distance function on a set of fuzzy values becomes a bounded metric function when the set of fuzzy values only contains crisp values. Then the role of viewpoints on the distance function is discussed. Finally, the relation between the proposed distance function and defuzzification is shown.

In this article a new approach for solving the hoist scheduling problem is proposed. It is based on two distinct, though coupled, multiagent systems. The first system is responsible for making a decision about the input date for the next job, while the second system is concerned with the assignment of transfer operations of jobs between tanks to the hoists. These multiagent systems use two different types of auction mechanisms to attain cooperation. Remaining conflicts are solved through self-assigned priorities. Partial results are proposed and issues related to further work on the topic are raised.

A hierarchical reduction method for Petri nets is proposed. After a brief survey on the existing methods of Petri net reduction, concepts such as reducible subnet, degree of subnet, and macronode are defined. The subnets are partially ordered by the degree of subnet, and thus the reducible subnets can be reduced into the macronodes. A reduced net can be obtained without changing the properties (for example, liveness and boundedness). A sequence of reduction results in a hierarchy of reduced Petri nets that allow easy verification and hierarchical decomposition of the system.