Tomasz G. Smolinski

Computational Intelligence in Biomedicine and Bioinformatics

The purpose of this book is to provide an overview of powerful state-of-the-art methodologies that are currently utilized for biomedicine and/ or bioinformatics-oriented applications, so that researchers working in those fields could learn of new methods to help them tackle their problems. On the other hand, the CI community will find this book useful by discovering a new and intriguing area of applications. In order to help fill the gap between the scientists on both sides of this spectrum, the editors have solicited contributions from researchers actively applying computational intelligence techniques to important problems in biomedicine and bioinformatics.

Computational intelligence in modeling of biological neurons: A case study of an invertebrate pacemaker neuron

Computational modeling of biological neurons allows for exploration of many parameter combinations and various types of neuronal activity, without requiring a prohibitively large number of “wet” experiments. On the other hand, analysis and biological interpretation of such, often very extensive, databases of models can be difficult. In this article, we present two Computational Intelligence (CI) approaches, based on Artificial Neural Networks (ANN) and Multi-Objective Evolutionary Algorithms (MOEA), that we have successfully applied to the problem of analysis and interpretation of model neuronal data.

Computational Intelligence in Solving Bioinformatics Problems: Reviews, Perspectives, and Challenges

This chapter presents a broad overview of Computational Intelligence (CI) techniques including Artificial Neural Networks (ANN), Particle Swarm Optimization (PSO), Genetic Algorithms (GA), Fuzzy Sets (FS), and Rough Sets (RS). We review a number of applications of computational intelligence to problems in bioinformatics and computational biology, including gene expression, gene selection, cancer classification, protein function prediction, multiple sequence alignment, and DNA fragment assembly. We discuss some representative methods to provide inspiring examples to illustrate how CI could be applied to solve bioinformatic problems and how bioinformatics could be analyzed, processed, and characterized by computational intelligence. Challenges to be addressed and future directions of research are presented. An extensive bibliography is also included.

Hybridization of independent component analysis, rough sets, and multi-objective evolutionary algorithms for classificatory decomposition of cortical evoked potentials

This article presents a continuation of our research aiming at improving the effectiveness of signal decomposition algorithms by providing them with “classification-awareness.” We investigate hybridization of multi-objective evolutionary algorithms (MOEA) and rough sets (RS) to perform the task of decomposition in the light of the underlying classification problem itself. In this part of the study, we also investigate the idea of utilizing the Independent Component Analysis (ICA) to initialize the population in the MOEA.

Applications of Computational Intelligence in Biology

The purpose of this book is to provide a medium for an exchange of expertise and concerns. In order to achieve the goal, the editors have solicited contributions from both computational intelligence as well as biology researchers. They have collected contributions from the CI community describing powerful new methodologies that could, or currently are, utilized for biology-oriented applications. On the other hand, the book also contains chapters devoted to open problems in biology that are in need of strong computational techniques, so the CI community can find a brand new and potentially intriguing spectrum of applications.

Computer literacy for life sciences: helping the digital-era biology undergraduates face today's research.

Computer literacy plays a critical role in todays life sciences research. Without the ability to use computers to efficiently manipulate and analyze large amounts of data resulting from biological experiments and simulations, many of the pressing questions in the life sciences could not be answered. Todays undergraduates, despite the ubiquity of computers in their lives, seem to be largely unfamiliar with how computers are being used to pursue and answer such questions. This article describes an innovative undergraduate-level course, titled Computer Literacy for Life Sciences, that aims to teach students the basics of a computerized scientific research pursuit. The purpose of the course is for students to develop a hands-on working experience in using standard computer software tools as well as computer techniques and methodologies used in life sciences research. This paper provides a detailed description of the didactical tools and assessment methods used in and outside of the classroom as well as a discussion of the lessons learned during the first installment of the course taught at Emory University in fall semester 2009.

Computational Intelligence in Electrophysiology: Trends and Open Problems

This chapter constitutes mini-proceedings of the Workshop on Physiology Databases and Analysis Software that was a part of the Annual Computational Neuroscience Meeting CNS*2007 that took place in July 2007 in Toronto, Canada (http ://www.cnsorg.org). The main aim of the workshop was to bring together researchers interested in developing and using automated analysis tools and database systems for electrophysiological data. Selected discussed topics, including the review of some current and potential applications of Computational Intelligence (CI) in electrophysiology, database and electrophysiological data exchange platforms, languages, and formats, as well as exemplary analysis problems, are presented in this chapter. The authors hope that the chapter will be useful not only to those already involved in the field of electrophysiology, but also to CI researchers, whose interest will be sparked by its contents.

Classifying functional and non-functional model neurons using the theory of rough sets

We explored a 12-dimensional parameter space of a 2-compartment model of the AB (anterior burster) neuron, which is one of the two cells that form the pacemaker kernel in the pyloric network in the lobster stomatogastric ganglion (STG). The computational exploration started with a hand-tuned AB model [1] and systematically varied maximal conductances of membrane currents to determine ranges and variation steps that could potentially produce physiologically realistic behavior. We varied the conductances for the following currents in the model: fast sodium INa and delayed-rectifier potassium IKd in the axon compartment, and delayed-rectifier IKd, calcium-dependent IKCa, transient potassium IA, transient ICaT and persistent ICaS calcium, persistent sodium INaP, and hyperpolarization-activated inward Ih in the some/neurite (S/N) compartment. To model the descending modulatory inputs, a voltage-gated inward current (such as the one activated by the neuropeptide proctolin) Iproc was added to the S/N compartment. Both compartments also contained the leak current IL. Every parameter set representing an individual model neuron was simulated and analyzed in terms of its period, burst duration, spike and slow wave amplitude, number of spikes per burst, spike frequency, and after-hyperpolarization potential, as well as the model’s responses to neuromodulator deprivation and current injections. All of the above characteristics had to be within limits determined in physiological experiments performed on the AB cell, in order for a model to be classified as functional [2]. In addition to several other data mining and visualization techniques we have previously employed to analyze the parameter space of the “good” models [3], we propose to utilize the theory of rough sets (RS) to investigate the role and importance of the parameters in differentiating between the functional and non-functional models. One of the most useful aspects of the RS theory in these kinds of classification tasks is the concept of a reduct—the smallest possible subset of attributes (i.e., maximal conductances in our model) that preserves the classification accuracy of the full set of attributes [4]. There are usually several such reducts for a given problem, and by extracting the so-called core of the reducts (i.e., the attributes that all the discovered reducts have in common), one can estimate the relative importance of the attributes. For instance, based on the 10 reducts computed from our dataset, we can state that soma CaT, NaP, Kd, KCa, and Proc, are absolutely necessary for differentiation between the functional and non-functional models (they were included in all 10 reducts), the axon Na current is very important (utilized in 9 out of 10 reducts), while the leak currents (both in the soma and the axon) seem to be the least important (they were present in 6 and 7 of the reducts, respectively). Furthermore, based on reducts, one can easily generate IF-THEN rules that not only describe how the model’s proper behavior depends on its parameters, but also how those parameters (i.e., ionic currents) “cooperate” with one another to assure such activity. For example, one of the most trustworthy rules we discovered (confidence of 78%) describes the following relationship: IF soma NaP∈[2.7μS÷6.4μS) AND soma KCa∈[3,000μS÷6,000μS) AND axon Na∈[300μS÷450μS) THEN “functional AB model,” where the values in parentheses represent the ranges for the corresponding maximum membrane conductances.