Byoung-Tak Zhang

Molecular Basis for the Recognition of Primary microRNAs by the Drosha-DGCR8 Complex

The Drosha-DGCR8 complex initiates microRNA maturation by precise cleavage of the stem loops that are embedded in primary transcripts (pri-miRNAs). Here we propose a model for this process that is based upon evidence from both computational and biochemical analyses. A typical metazoan pri-miRNA consists of a stem of approximately 33 bp, with a terminal loop and flanking segments. The terminal loop is unessential, whereas the flanking ssRNA segments are critical for processing. The cleavage site is determined mainly by the distance (approximately 11 bp) from the stem-ssRNA junction. Purified DGCR8, but not Drosha, interacts with pri-miRNAs both directly and specifically, and the flanking ssRNA segments are vital for this binding to occur. Thus, DGCR8 may function as the molecular anchor that measures the distance from the dsRNA-ssRNA junction. Our current study thus facilitates the prediction of novel microRNAs and will assist in the rational design of small hairpin RNAs for RNA interference.

Balancing accuracy and parsimony in genetic programming

Genetic programming is distinguished from other evolutionary algorithms in that it uses tree representations of variable size instead of linear strings of fixed length. The flexible representation scheme is very important because it allows the underlying structure of the data to be discovered automatically. One primary difficulty, however, is that the solutions may grow too big without any improvement of their generalization ability. In this article we investigate the fundamental relationship between the performance and complexity of the evolved structures. The essence of the parsimony problem is demonstrated empirically by analyzing error landscapes of programs evolved for neural network synthesis. We consider genetic programming as a statistical inference problem and apply the Bayesian model-comparison framework to introduce a class of fitness functions with error and complexity terms. An adaptive learning method is then presented that automatically balances the model-complexity factor to evolve parsimonious programs without losing the diversity of the population needed for achieving the desired training accuracy. The effectiveness of this approach is empirically shown on the induction of sigma-pi neural networks for solving a real-world medical diagnosis problem as well as benchmark tasks.

Multiobjective evolutionary optimization of DNA sequences for reliable DNA computing

DNA computing relies on biochemical reactions of DNA molecules and may result in incorrect or undesirable computations. Therefore, much work has focused on designing the DNA sequences to make the molecular computation more reliable. Sequence design involves with a number of heterogeneous and conflicting design criteria and traditional optimization methods may face difficulties. In this paper, we formulate the DNA sequence design as a multiobjective optimization problem and solve it using a constrained multiobjective evolutionary algorithm (EA). The method is implemented into the DNA sequence design system, NACST/Seq, with a suite of sequence-analysis tools to help choose the best solutions among many alternatives. The performance of NACST/Seq is compared with other sequence design methods, and analyzed on a traveling salesman problem solved by bio-lab experiments. Our experimental results show that the evolutionary sequence design by NACST/Seq outperforms in its reliability the existing sequence design techniques such as conventional EAs, simulated annealing, and specialized heuristic methods.

Discovery of microRNA–mRNA modules via population-based probabilistic learning

MOTIVATION MicroRNAs (miRNAs) and mRNAs constitute an important part of gene regulatory networks, influencing diverse biological phenomena. Elucidating closely related miRNAs and mRNAs can be an essential first step towards the discovery of their combinatorial effects on different cellular states. Here, we propose a probabilistic learning method to identify synergistic miRNAs involving regulation of their condition-specific target genes (mRNAs) from multiple information sources, i.e. computationally predicted target genes of miRNAs and their respective expression profiles. RESULTS We used data sets consisting of miRNA-target gene binding information and expression profiles of miRNAs and mRNAs on human cancer samples. Our method allowed us to detect functionally correlated miRNA-mRNA modules involved in specific biological processes from multiple data sources by using a balanced fitness function and efficient searching over multiple populations. The proposed algorithm found two miRNA-mRNA modules, highly correlated with respect to their expression and biological function. Moreover, the mRNAs included in the same module showed much higher correlations when the related miRNAs were highly expressed, demonstrating our methods ability for finding coherent miRNA-mRNA modules. Most members of these modules have been reported to be closely related with cancer. Consequently, our method can provide a primary source of miRNA and target sets presumed to constitute closely related parts of gene regulatory pathways.

Identification of biochemical networks by S-tree based genetic programming

MOTIVATION Most previous approaches to model biochemical networks have focused either on the characterization of a network structure with a number of components or on the estimation of kinetic parameters of a network with a relatively small number of components. For system-level understanding, however, we should examine both the interactions among the components and the dynamic behaviors of the components. A key obstacle to this simultaneous identification of the structure and parameters is the lack of data compared with the relatively large number of parameters to be estimated. Hence, there are many plausible networks for the given data, but most of them are not likely to exist in the real system. RESULTS We propose a new representation named S-trees for both the structural and dynamical modeling of a biochemical network within a unified scheme. We further present S-tree based genetic programming to identify the structure of a biochemical network and to estimate the corresponding parameter values at the same time. While other evolutionary algorithms require additional techniques for sparse structure identification, our approach can automatically assemble the sparse primitives of a biochemical network in an efficient way. We evaluate our algorithm on the dynamic profiles of an artificial genetic network. In 20 trials for four settings, we obtain the true structure and their relative squared errors are <5% regardless of releasing constraints about structural sparseness. In addition, we confirm that the proposed algorithm is robust within +/-10% noise ratio. Furthermore, the proposed approach ensures a reasonable estimate of a real yeast fermentation pathway. The comparatively less important connections with non-zero parameters can be detected even though their orders are below 10(-2). To demonstrate the usefulness of the proposed algorithm for real experimental biological data, we provide an additional example on the transcriptional network of SOS response to DNA damage in Escherichia coli. We confirm that the proposed algorithm can successfully identify the true structure except only one relation.

Evolutionary induction of sparse neural trees

This paper is concerned with the automatic induction of parsimonious neural networks. In contrast to other program induction situations, network induction entails parametric learning as well as structural adaptation. We present a novel representation scheme called neural trees that allows efficient learning of both network architectures and parameters by genetic search. A hybrid evolutionary method is developed for neural tree induction that combines genetic programming and the breeder genetic algorithm under the unified framework of the minimum description length principle. The method is successfully applied to the induction of higher order neural trees while still keeping the resulting structures sparse to ensure good generalization performance. Empirical results are provided on two chaotic time series prediction problems of practical interest.

AptaCDSS-E: A classifier ensemble-based clinical decision support system for cardiovascular disease level prediction

Conventional clinical decision support systems are generally based on a single classifier or a simple combination of these models, showing moderate performance. In this paper, we propose a classifier ensemble-based method for supporting the diagnosis of cardiovascular disease (CVD) based on aptamer chips. This AptaCDSS-E system overcomes conventional performance limitations by utilizing ensembles of different classifiers. Recent surveys show that CVD is one of the leading causes of death and that significant life savings can be achieved if precise diagnosis can be made. For CVD diagnosis, our system combines a set of four different classifiers with ensembles. Support vector machines and neural networks are adopted as base classifiers. Decision trees and Bayesian networks are also adopted to augment the system. Four aptamer-based biochip data sets including CVD data containing 66 samples were used to train and test the system. Three other supplementary data sets are used to alleviate data insufficiency. We investigated the effectiveness of the ensemble-based system with several different aggregation approaches by comparing the results with single classifier-based models. The prediction performance of the AptaCDSS-E system was assessed with a cross-validation test. The experimental results show that our system achieves high diagnosis accuracy (>94%) and comparably small prediction difference intervals (<6%), proving its usefulness in the clinical decision process of disease diagnosis. Additionally, 10 possible biomarkers are found for further investigation.

A reinforcement learning agent for personalized information filtering

This paper describes a method for learning users interests in the Web-based personalized information filtering system called WAIR. The proposed method analyzes users reactions to the presented documents and learns from them the profiles for the individual users. Reinforcement learning is used to adapt the term weights in the user profile so that users preferences are best represented. In contrast to conventional relevance feedback methods which require explicit user feedbacks, our approach learns user preferences implicitly from direct observations of user behaviors during interaction. Field tests have been made which involved 7 users reading a total of 7,700 HTML documents during 4 weeks. The proposed method showed superior performance in personalized information filtering compared to the existing relevance feedback methods.

Learning user's preferences by analyzing Web-browsing behaviors

This paper describes a method for an information filtering agent to learn users preferences. The proposed method observes users reactions to the filtered documents and learns from them the profiles for the individual users. Reinforcement learning is used to adapt the most significant terms that best represent users interests. In contrast to conventional relevance feedback methods which require explicit user feedbacks, our approach learns user preferences implicitly from direct observations of browsing behaviors during interaction. Field tests have been made which involved 10 users reading a total of 18,750 HTML documents during 45 days. The proposed method showed superior performance in personalized information filtering compared to the existing relevance feedback methods.

Text filtering by boosting naive Bayes classifiers

Several machine learning algorithms have recently been used for text categorization and filtering. In particular, boosting methods such as AdaBoost have shown good performance applied to real text data. However, most of existing boosting algorithms are based on classifiers that use binary-valued features. Thus, they do not fully make use of the weight information provided by standard term weighting methods. In this paper, we present a boosting-based learning method for text filtering that uses naive Bayes classifiers as a weak learner. The use of naive Bayes allows the boosting algorithm to utilize term frequency information while maintaining probabilistically accurate confidence ratio. Applied to TREC-7 and TREC-8 filtering track documents, the proposed method obtained a significant improvement in LF1, LF2, F1 and F3 measures compared to the best results submitted by other TREC entries.