Clare Bates Congdon

The volume and complexity of biological and biomedical research continues to grow exponentially with cutting-edge technologies such as high-throughput sequencing. Unfortunately, bioinformatics analysis is often considered only after data have been generated, which significantly limits the ability to make sense of complex big data. This unique book...

Background: We identify the agricultural inputs that drove the growth in global and regional crop yields from 1975 to the mid-2000s. Methods: We compare and contrast the inputs that drove yield change as identified by econometrically estimated yield functions and decision trees that use yield change as the class attribute. Results: We find that imp...

We identify the agricultural inputs that drove the growth in global and regional crop yields from 1975 to the mid-2000s. We find that improvements in agricultural technology, increased fertilizer use, and changes in crop mix around the world explained most of the gain in global crop yields, although impacts varied across the latitude gradient. Clim...

To determine whether hepatic depletion of vitamin A (VA) stores has an effect on the postnatal heart, studies were carried out with mice lacking liver retinyl ester stores fed either a VA-sufficient (LRVAS) or VA-deficient (LRVAD) diet (to deplete circulating retinol and extrahepatic stores of retinyl esters). There were no observable differences i...

This report is the outcome of the meeting "Environmental and Human Health Consequences of Arsenic" held at the MDI Biological Laboratory in Salisbury Cove, Maine, August 13-15, 2014. Human exposure to arsenic represents a significant health problem worldwide that requires immediate attention according to the World Health Organization (WHO). One bil...

In this project, we develop and deliver a workshop to teach undergraduate Science, Technology, Engineering and Mathematics (STEM) faculty the creative thinking process and help them to develop modules for their classes. Leaning on ideas back to Plato's Theaetetus, we divide the creative process into seven discrete stages, and have developed exercis...

Computational methods of inferring regions of noncoding DNA that regulate gene activity are important to efficient biological validation of gene regulatory control. In many cases the available resources may allow for relatively few biological assays to be performed, and computational results allow these assays to be tightly focused on the highest c...

Gene expression profiles quantify the expression of thousands of genes simultaneously, providing a snapshot in time of gene expression in a specific tissue. A gene expression profile can be helpful in understanding the association of genes to the progression of cancer and patient outcomes. However, these complex associations can be difficult to det...

In this work, we extend GAMI (Genetic Algorithms for Motif Inference), a de novo motif inference system, to find sets of motifs that may function as part of a cis-regulatory module (CRM) using a comparative genomics approach. Evidence suggests that most transcription factors binding sites are part of a CRM, so our new approach is expected to yield...

The human genome encodes for over 1800 microRNAs (miRNAs), which are short non-coding RNA molecules that function to regulate gene expression post-transcriptionally. Due to the potential for one miRNA to target multiple gene transcripts, miRNAs are recognized as a major mechanism to regulate gene expression and mRNA translation. Computational predi...

Currently there are definitions from many agencies and research societies defining "bioinformatics" as deriving knowledge from computational analysis of large volumes of biological and biomedical data. Should this be the bioinformatics research focus? We will discuss this issue in this review article. We would like to promote the idea of supporting...

One of the grand challenges of AI is to create general intelligence: an agent that can excel at many tasks, not just one. In the area of games, this has given rise to the challenge of General Game Playing (GGP). In GGP, the game (typically a turn-taking board game) is defined declaratively in terms of the logic of the game (what happens when a move...

In this work, we extend GAMI, a de novo motif inference system, to find sets of motifs that may function as part of a cis-regulatory module (CRM). Evidence suggests that most transcription factors in humans are part of a CRM, so this approach is expected to yield stronger candidates for de novo inference of candidate regulatory elements.

Mobile gaming is an arena full of innovation, with developers exploring new kinds of games, with new kinds of interaction between the mobile device, players, and the connected world that they live in and move through. The mobile gaming world is a perfect playground for AI and CI, generating a maelstrom of data for games that use adaptation, learnin...

Although most verified functional elements in non-coding DNA contain a highly conserved core region, this concept is not generally incorporated into de novo motif inference systems. In this work, we explore the utility of adding the notion of conserved core regions into a comparative genomics approach for the search for putative functional elements...

The goal of this project was to update and analyze the genome annotation of the bacteriophage GFØ-1 (bacterial host: Pseudoalteromonas sp.). Until quite recently, phage PM-2 was the only characterized species in the Corticoviridae family. This partial characterization of the complete GFØ-1 genome has revealed that predicted ORFs have homologues in...

The incorporation of learning into commercial games can enrich the player experience, but may concern developers in terms of issues such as losing control of their game world. We explore a number of applied research and some fielded applications that point to the tremendous possibilities of machine learning research including game genres such as re...

The core idea of evolution is that order in living systems emerges from a simple process of variation and selection. In biological systems we usually understand the source of variation as best described by the mechanisms of genetics. If human social systems are evolutionary systems, however, it would seem the variation that most explains the source...

Presents the guest editorial for this issue of the publication.

In this work, personality profiles are used to develop parameterized bot behaviors. While the personality profile structure was originally designed as a descriptive tool for human behavior, as used here it is a generative tool, allowing a plurality of different behaviors to result from a single rule set. This paper describes our use of the Five-Fac...

FRIGHT is a rule-based intelligent agent for playing the ghost team in the Ms. Pac-Man vs Ghosts Competition held at the 2012 IEEE Conference on Computational Intelligence and Games. FRIGHT uses rule sets with high-level abstractions of the game state and actions, and employs evolutionary computation to learn rule sets; a distributed homogenous-age...

We have developed GAMMI, an approach to the inference of cis-regulatory modules that employs an evolutionary search to identify modules conserved across a set of DNA sequences from different species. This paper describes the motivation and system design for GAMMI, and presents the results of initial tests of the system using artificial sequences wi...

In this work, we present GAMID, an extension of GAMI (Genetic Algorithms for Motif Inference), which allows the system to ignore some of the sequences when looking for candidate conserved motifs in noncoding DNA. This ability is useful both when looking for candidate motifs in co-expressed genes (where it is not expected that all genes respond to t...

Recent advances in high-throughput DNA sequencing technologies have equipped biologists with a powerful new set of tools for advancing research goals. The resulting flood of sequence data has made it critically important to train the next generation of scientists to handle the inherent bioinformatic challenges. The North East Bioinformatics Collabo...

We have developed GAMS, a system for the inference of cis-regulatory modules that uses a genetic algorithms approach to discover putatively conserved modules in large noncoding DNA sequences from divergent species. This paper describes the approach and presents preliminary results.

In this work, we present GAMID, and extension of GAMI. GAMID is designed to be used for motif inference in noncoding DNA for co-expressed genes or for divergent species. In these cases, we would like to allow the inferred motif to be present in only a subset of the input data. This paper describes the approach and presents preliminary results.

The Onychophora, Priapulida and Tardigrada, along with the Arthropoda, Nematoda and several other small phyla, form the superphylum Ecdysozoa. Numerous peptidomic studies have been undertaken for both the arthropods and nematodes, resulting in the identification of many peptides from each group. In contrast, little is known about the peptides used...

REALM is a rule-based evolutionary computation agent for playing a modified version of Super Mario Bros. according to the rules stipulated in the Mario AI Competition held in the 2010 IEEE Symposium on Computational Intelligence and Games. Two alternate representations for the REALM rule sets are reported here, in both hand-coded and learned versio...

RAMP is a rule-based agent for playing Ms. Pac-Man according to the rules stipulated in the 2008 World Congress on Computational Intelligence Ms. Pac-Man Competition. During the competition, our highest score was 15,970, outscoring the eleven other entrants in the competition. In runs reported here, RAMP achieves an average score over 10,000 and a...

The goal of this project is to develop an agent to play the first-person shooter game Unreal Tournament 2004 , a fast-paced and dynamic environment that demands that the agent must be capable of making decisions quickly. An additional goal of this project is to explore evolutionary computation as a means for learning the rule sets used to control t...

The human genome is approximately 3 billion basepairs long. An estimated 2--3% of DNA codes for genes; the remaining 97--98% is noncoding DNA [11]. Although the noncoding regions in DNA were once called "junk DNA" (with the assumption that these regions were not serving a purpose) it is now understood that within noncoding DNA are functional region...

In previous work, we presented GAMI, an approach to motif inference that uses a genetic algorithms search. GAMI is designed specifically to find putative conserved regulatory motifs in noncoding regions of divergent species, and is designed to allow for analysis of long nucleotide sequences. In this work, we compare GAMI's performance when run with...

In this work, we explore the utility of a complex adaptive systems approach for studying epistasis, the nonlinear effects among genes that contribute to different disease outcomes. Due to the nonlinear interactions among the genes, data such as this is difficult to model using traditional epidemiological tools. Thus, we have developed EpiSwarm, a S...

Many genetic diseases are not caused by the effects of a single gene, but rather, are due to multiple genes acting in concert. For complex diseases, looking at the effect of variation in a single gene may predict one disease outcome, while looking at the interactions of genetic variations across multiple genes gives us a richer understanding of the...

This project explores the use of evolutionary computation to design two-dimensional artwork in the suprematist style. Using OpenGL libraries for rendering and GAUL for the evolutionary component, GAUGUIN allows the user to create art, without requiring any technical or artistic training. In using an evolutionary process to create the composition, a...

Introduction Background in Phylogenetics Challenges and Opportunities for Evolutionary Computation One Contribution of Evolutionary Computation: Graphyl Some Other Contributions of Evolutionary computation Open Questions and Opportunities References

Computational inference of putative functional elements in noncoding DNA sequence can significantly hasten the search for verified functional elements, such as transcription factor binding sites. However, while computational methods are able to identify promising putative elements, the number of regions of interest may remain unrealistic for experi...

Phylogenetics is an approach used by biologists to investigate the evolutionary relationships among organisms. Typical software packages use heuristic search methods to navigate through the space of possible hypotheses (phylogenies) in an attempt to find one or more “best” hypotheses, as exhaustive search is not practical in this domain. We have de...

GENCEM is a genetic algorithms approach to coordinated exploration and mapping with multiple autonomous robots. Building on previous work in coordinated mapping, the work reported here compares static to evolutionary approaches for the same coordination tasks. In GENCEM, parameters affecting the coordination behaviors are evolved, leading to a deci...

This paper introduces RCS, a learning classifier system designed for evolutionary robotics research. In addition to describing the system, it will present the results of RCS applied to a pursuit task. In this test, performance was good and has been improved in ongoing work.

We have developed GAMI, an approach to motif inference that uses a genetic algorithms search and is designed specifically to work with divergent species and possibly long nucleotide sequences. The system design reduces the size of the search space as compared to typical window-location approaches for motif inference. This paper describes the motiva...

Research constitutes an intrinsic part of the intellectual activity of any faculty. Many times, however, heavy teaching loads and lack of incentives (such as institutional support and time releases) negatively affect the faculty's research work. Often, the knowledge level required in the research also limits the involvement of undergraduate student...

Predicting a patient's expected length of stay for an Emergency Department encounter is valuable to anticipate impending operational bottlenecks that may lead to diversion. We developed and validated an artificial neural network using data from >16,000 patients using clinical and operational parameters that are commonly available early during an en...

The creation of individual 3D models to include within a virtual world can be a time-consuming process. The standard approach to streamline this is to use procedural modeling tools, where the user adjusts a set of parameters that defines the tree. We have designed Gen- Tree, an interactive system that uses a genetic algorithms (GA) approach to evol...

Gaphyl is an application of evolutionary algorithms to phylogenetics, an approach used by biologists to investigate evolutionary relationships among organisms. For datasets larger than 20-30 species, exhaustive search is not practical in this domain. Gaphyl uses an evolutionary search mechanism to search the space of possible phylogenetic trees, in...

The OpenGL graphics libraries (http://www.opengl.org) provide a powerful environment for programming three-dimensional virtual worlds, and are used in a wide variety of applications. However, the creation of individual 3D models to include within a virtual world is an arduous and time-consuming process. We have designed GenTree, an interactive syst...

ed to build simple robots and program solutions to problems such as keeping a robot inside an area marked on the floor, following a line, and navigating around an obstacle. Students designed their own final projects, and were very enthusiastic and creative about doing so. Final projects included robots that played tag with each other, robots that c...

This research investigates the use of genetic algorithms to solve problems from cladistics - a technique used by biologists to hypothesize the evolutionary relationships between organisms. Since exhaustive search is not practical in this domain, typical cladistics software packages use heuristic search methods to navigate through the space of possi...

This paper describes an application of genetic algorithms (GA's) to classify epidemiological data, which is often challenging to classify due to noise and other factors. For such complex data (that requires a large number of very specific rules to achieve a high accuracy), smaller rule sets, composed of more general rules, may be preferable, even i...

Using the robot as a metaphor for assisting students in understanding problem solving in general, the algorithmic process, and the relationship between algorithms and computing agents is not new. While simulated robot environments have existed for many years (e.g. Karel the Robot[3]) it is only recently that the technology for inexpensively supplyi...

This research investigates the use of genetic algorithms to solve problems from cladistics --- a technique used by biologists to hypothesize the evolutionary relationships between organisms. Since exhaustive search is not practical in this domain, typical cladistics software packages use heuristic search methods to navigate through the space of pos...

This research investigates the use of genetic algorithms (GA's) to solve problems from cladistics --- a technique used by biologists to hypothesize the evolutionary relationships between organisms. Since exhaustive search is not practical in this domain, typical cladistics software packages use heuristic search methods to navigate through the space...

Machine learning is typically considered a graduate-level course with an artificial intelligence course as a prerequisite. However, it does not need to be positioned this way, and in the liberal arts curriculum in particular, there are advantages to offering this course to undergraduate students. An undergraduate course in machine learning is easil...

The demand for computer science faculty is growing rapidly, along with the demand for seats in computer science courses. The problem of finding, recruiting, and retaining computer science faculty may have reached crisis proportions[1]. Meeting this demand means an influx of new faculty, including perhaps nontraditional faculty such as adjuncts from...

The demand for computer science faculty is growing rapidly, along with the demand for seats in computer science courses. The problem of finding, recruiting, and retaining computer science faculty may have reached crisis proportions[1]. Meeting this demand means an influx of new faculty, including perhaps nontraditional faculty such as adjuncts from...

Describes an application of genetic algorithms (GAs) to classify epidemiological data, which is often challenging to classify due to noise and other factors. For such complex data (that requires a large number of very specific rules in order to achieve high accuracy), smaller rule sets, composed of more general rules, may be preferable, even if the...

A COMPARISON OF GENETIC ALGORITHMS AND OTHER MACHINE LEARNING SYSTEMS ON A COMPLEX CLASSIFICATION TASK FROM COMMON DISEASE RESEARCH by Clare Bates Congdon Co-Chairs: John H. Holland, John E. Laird The thesis project is an investigation of some well-known machine learning systems and evaluates their utility when applied to a classification task from...

this document. The user interface is implemented in Tcl, which is a simple command interpreter [Ousterhout, 1994]. Tcl includes familiar programming constructs such as variables, conditionals, iteration, and procedures. Tcl also provides a convenient mechanism for the addition of a variety of extensions to Soar, such as graphical interfaces and sim...

This paper is intended to compare the two architectures, focusing on abilities exhibited in the robot competition and the underlying approaches used by the two teams. A shorter version of this paper appeared originally in [6].

The Carmel project (computer-aided robotics for maintenance, emergency, and life support) which won the AAAI 1992 Robot Competition, is discussed. Carmel's design philosophy and architecture, obstacle avoidance, global path planning, vision sensing, landmark triangulation, and supervisory planning system are described. The Carmel project shows that...

This paper describes the design and implementation of an integrated system for combining obstacle avoidance, path planning, landmark detection and position triangulation. Such an integrated system allows the robot to move from place to place in an environment, avoiding obstacles and planning its way out of traps, while maintaining its position and...

This paper describes the design and implementation of an integrated system for combining obstacle avoidance, path planning, landmark detection and position triangulation. Such an integrated system allows the robot to move from place to place in an environment, avoiding obstacles and planning its way out of traps, while maintaining its position and...

The University of Michigan's CARMEL and SRI International's FLAKEY were the first- and second-place finishers, respectively, at the 1992 Robot Competition sponsored by the American Association for Artificial Intelligence. The two teams used vastly different approaches in the design of their robots. Many of these differences were for technical reaso...

Last summer, AAAI sponsored a mobile robot competition in conjunction with the AAAI-92 conference in San Jose, California. Ten robots from across the country competed in the competition, with CARMEL from the University of Michigan finishing first. CARMEL is a Cybermotion K2A mobile platform with a ring of 24 sonar sensors and a single black and whi...

Gameplay The purpose of Rogue is "to descend into the Dungeons of Doom, defeat monsters, find treasure, and return to the surface with the amulet of Yendor using its levitation capabilities." Figure: The player ('@') is fighting a bat ('B'). History In the late 1970s, Ken Arnold designed a library (later named curses[1]) to put characters at specif...