Luis Rocha

Indiana University, School of Informatics, Faculty Member

Followers

181

Following

Co-authors

Public Views

InterestsView All (6)

Uploads

Papers by Luis Rocha

Biomedical Article Classification Using an Agent-Based Model of T-Cell Cross-Regulation

Lecture Notes in Computer Science, 2010

Uncovering protein interaction in abstracts and text using a novel linear model and word proximity networks

Genome Biology, 2008

Background: We participated in three of the protein-protein interaction subtasks of the Second Bi... more Background: We participated in three of the protein-protein interaction subtasks of the Second BioCreative Challenge: classification of abstracts relevant for protein-protein interaction (interaction article subtask [IAS]), discovery of protein pairs (interaction pair subtask [IPS]), and identification of text passages characterizing protein interaction (interaction sentences subtask [ISS]) in full-text documents. We approached the abstract classification task with a novel, lightweight linear model inspired by spam detection techniques, as well as an uncertainty-based integration scheme. We also used a support vector machine and singular value decomposition on the same features for comparison purposes. Our approach to the full-text subtasks (protein pair and passage identification) includes a feature expansion method based on word proximity networks. Results: Our approach to the abstract classification task (IAS) was among the top submissions for this task in terms of measures of performance used in the challenge evaluation (accuracy, F-score, and area under the receiver operating characteristic curve). We also report on a web tool that we produced using our approach: the Protein Interaction Abstract Relevance Evaluator (PIARE). Our approach to the full-text tasks resulted in one of the highest recall rates as well as mean reciprocal rank of correct passages. Conclusion: Our approach to abstract classification shows that a simple linear model, using relatively few features, can generalize and uncover the conceptual nature of protein-protein interactions from the bibliome. Because the novel approach is based on a rather lightweight linear model, it can easily be ported and applied to similar problems. In full-text problems, the expansion of word features with word proximity networks is shown to be useful, although the need for some improvements is discussed.

Download

Genotype Editing and the Evolution of Regulation and Memory

Lecture Notes in Computer Science

Our agent-based model of genotype editing is defined by two distinct genetic components: a coding... more Our agent-based model of genotype editing is defined by two distinct genetic components: a coding portion encoding phenotypic solutions, and a non-coding portion used to edit the coding material. This set up leads to an indirect, stochastic genotype/phenotype mapping which captures essential aspects of RNA editing. We show that, in drastically changing environments, genotype editing leads to qualitatively different solutions from those obtained via evolutionary algorithms that only use coding genetic material. In particular, we show how genotype editing leads to the emergence of regulatory signals, and also to a resilient memory of a previous environment 1 Introduction: RNA Editing RNA Editing [Bass, 2001] refers to the post-transcriptional alteration of genetic information. It occurs in various forms such as insertion, deletion, or substitution. It can be implemented via non-coding RNAs (ncRNAs) such as guide RNA's or via enzymes (e.g. adenosine deaminase acting on RNA (ADAR), also known as RNA Editase) In either case, genetic information is altered after transcription and before translation (for an overview see [Huang et al., 2007]). Previously we quantitatively established the advantages of genotype editing against the canonical evolutionary algorithm in various static and dynamic environments (e.g. [Huang et al., 2007]). Here, using our Agent-Based Model of Genotype Editing (section 2) in drastically changing environments (section 3), we focus instead on the qualitatively different evolutionary solutions attainable via genotype editing. Specifically, we show how genotype editing leads to the emergence of regulatory signals that allow agents to better adapt to radically different environments (section 4). We also show how the inclusion of non-coding genetic material, with the function of editing coding material, allows agents to evolve a memory of previous environments-a capacity not attainable by the canonical evolutionary algorithms which use only coding genetic material (section 5). 2 Modeling Genotype Editing The Genetic Algorithm (GA) [Holland, 1975] is an idealized model of natural selection-and the canonical evolutionary algorithm. In a traditional GA, the code between genotype and phenotype is a direct and unique mapping. In biology, however, before a gene is translated into a protein it may be altered, namely by functional or non-coding RNA (ncRNA) used for editing or other regulatory functions. To study and exploit the biological principle behind RNA

Download

Classification of Protein-Protein Interaction Full-Text Documents Using Text and Citation Network Features

IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2010

AbstractWe participated (as Team 9) in the Article Classification Task of the Biocreative II.5 C... more

Collective classification of textual documents by guided self-organization in T-Cell cross-regulation dynamics

Evolutionary Intelligence, 2011

An integrated pharmacokinetics ontology and corpus for text mining

BMC Bioinformatics, 2013

Background Drug pharmacokinetics parameters, drug interaction parameters, and pharmacogenetics da... more Background Drug pharmacokinetics parameters, drug interaction parameters, and pharmacogenetics data have been unevenly collected in different databases and published extensively in the literature. Without appropriate pharmacokinetics ontology and a well annotated pharmacokinetics corpus, it will be difficult to develop text mining tools for pharmacokinetics data collection from the literature and pharmacokinetics data integration from multiple databases. Description A comprehensive pharmacokinetics ontology was constructed. It can annotate all aspects of in vitro pharmacokinetics experiments and in vivo pharmacokinetics studies. It covers all drug metabolism and transportation enzymes. Using our pharmacokinetics ontology, a PK-corpus was constructed to present four classes of pharmacokinetics abstracts: in vivo pharmacokinetics studies, in vivo pharmacogenetic studies, in vivo drug interaction studies, and in vitro drug interaction studies. A novel hierarchical three level annotatio...

Download

CANA: A Python Package for Quantifying Control and Canalization in Boolean Networks

Frontiers in physiology, 2018

Logical models offer a simple but powerful means to understand the complex dynamics of biochemica... more Logical models offer a simple but powerful means to understand the complex dynamics of biochemical regulation, without the need to estimate kinetic parameters. However, even simple automata components can lead to collective dynamics that are computationally intractable when aggregated into networks. In previous work we demonstrated that automata network models of biochemical regulation are highly canalizing, whereby many variable states and their groupings are redundant (Marques-Pita and Rocha, 2013). The precise charting and measurement of such canalization simplifies these models, making even very large networks amenable to analysis. Moreover, canalization plays an important role in the control, robustness, modularity and criticality of Boolean network dynamics, especially those used to model biochemical regulation (Gates and Rocha, 2016; Gates et al., 2016; Manicka, 2017). Here we describe a new publicly-available Python package that provides the necessary tools to extract, measu...

Download

An agent based model of genotype editing

This paper presents our investigation on an agent-based model of Genotype Editing. This model is ... more This paper presents our investigation on an agent-based model of Genotype Editing. This model is based on several characteristics that are gleaned from the RNA editing system as observed in several organisms. The incorporation of editing mechanisms in an evolutionary agent-based model provides a means for evolving agents with heterogenous post-transcriptional processes. The study of this agent-based genotype-editing model has

Download

An evolutionary model of genotype editing

Evolutionary algorithms rarely deal with ontogenetic, noninherited alteration of genetic informat... more Evolutionary algorithms rarely deal with ontogenetic, noninherited alteration of genetic information because they are based on a simple, direct genotype-phenotype distinction. In contrast, in Nature several processes have been discovered which alter genetic information encoded in DNA before it is translated into amino-acid chains. Ontogenetically altered genetic information is not inherited but extensively used in regulation and development of phenotypes. An example of posttranscriptional alteration of gene-encoding sequences is the process of RNA Editing. Here we introduce a novel Agentbased model of genotype editing and a computational study of its evolutionary performance in static and dynamic environments. This model builds on our previous Genetic Algorithm with Edition, but presents a fundamentally novel architecture in which coding and non-coding genetic components are allowed to co-evolve. Our goal is twofold: (1) to study the role of RNA Editing regulation in the evolutionary process, and (2) to investigate the conditions under which genotype edition improves the performance of evolutionary algorithms. We show that edition allows evolving agents to perform better in several classes of fitness functions, both in static and dynamic environments.

Download

Clustering of protein families in literature keyword space

Advances in Artificial Life: Proceedings of European Conference on Artificial Life 2007

Biologically Motivated Distributed Designs for Adaptive Knowledge Management

Eprint Arxiv Cs 0002010, Feb 16, 2000

The limitations of traditional IR and DIS are even more dramatic when contrasted with biological ... more The limitations of traditional IR and DIS are even more dramatic when contrasted with biological distributed systems such as immune, neural, insect, and social networks. Biological networks function largely in a distributed manner, without recourse to central controllers, while achieving tremendous ability to respond in concerted ways to different environmental necessities. In particular, they are typically endowed with the

Download

Biologically Motivated Distributed Design for Adaptive Knowledge Management

Symbiotic intelligence (poster): self-organizing knowledge on distributed networks driven by human interaction

Proceedings of the Sixth International Conference on Artificial Life, Aug 28, 1998

Syntactic Autonomy: Why There is No Autonomy Without Symbols and How Self-Organizing Systems Might Evolve Them

Ann N Y Acad Sci, 2006

A BSTRACT : Two different types of agency are discussed that are based on dynamically coherent an... more A BSTRACT : Two different types of agency are discussed that are based on dynamically coherent and incoherent couplings with an environment, respectively. I propose that until a private syntax (syntactic autonomy) is discovered by dynamically coherent agents, there are no significant or interesting types of closure or autonomy. When syntactic autonomy is established, then, because of a process of description-based selected self-organization, open-ended evolution is enabled. At this stage, in addition to dynamics, agents depend on localized, symbolic memory, thus adding a level of dynamic incoherence to their interaction with the environment. Furthermore, it is the appearance of syntactic autonomy that enables much more interesting types of closures among agents sharing the same syntax. To investigate how we can study the emergence of syntax from dynamic systems, experiments with cellular automata leading to emergent computation that solves nontrivial tasks are discussed. RNA editing is also mentioned as a process that may have been used to obtain a primordial biological code necessary for open-ended evolution. CLOSURE AND AGENTS To understand closure in evolutionary systems, we need to be able to distinguish between an evolving system and its environment, which typically includes other such systems. Indeed, the notion of closure can only be meaningful if we can discern some sort of autonomy of one system from its environment or, alternatively, a loop or cycle, established between more than one system. (For a discussion of the types of closures one can identify, see Joslyn, Ref. 1.) In both of these cases, in the context of evolutionary systems, we need first to understand the nature of distinguishable systems that are capable of evolving. In other words, we need to agree on what it is that allows us to separate a system from an environment so that we can refer to it as autonomous, or place it in some kind of loop with other systems or the environment? (For a discussion of possible types of system/environment couplings, particularly, of evolving couplings, see Ref. 2.) This separability implies some kind of agency, so let us start by discussing the notion of agent .

Download

An Adaptive System Approach to the Implementation and Evaluation of Digital Library Recommendation Systems

And the Adaptive Recommendation Project

Dl, 1999

TalkMine: a Soft Computing Approach to Adaptive Knowledge Recommendation

Summary: We present a soft computing recommendation system named TalkMine, to advance adaptive we... more Summary: We present a soft computing recommendation system named TalkMine, to advance adaptive web and digital library technology. TalkMine leads different databases or websites to learn new and adapt existing keywords to the categories recognized by its communities of users. It uses distributed artificial intelligence algorithms and soft computing technology. TalkMine is currently being implemented for the research library of

Download

In: Evolutionary Systems: Biological and Epistemological Perspectives on Selection and Self-Organization. S. Salthe, G. Van de Vijver, and M. Delpos (eds.). Kluwer Academic Publishers, pp. 341-358, 1998

In this paper I sketch a rough taxonomy of self-organization which may be of relevance in the stu... more In this paper I sketch a rough taxonomy of self-organization which may be of relevance in the study of cognitive and biological systems. I frame the problem both in terms of the language of second- order cybernetics as well as the language of current theories of self-organization and complexity. The goal of establishing such a taxonomy is to allow for a classification of different tools used both in Artificial Intelligence and Artificial Life, so that different aspects of cognitive and biological systems may be incorporated in more accurate models of such systems. In particular, I defend, on the one hand, that self-organization alone is not rich enough for our intended simulations, and on the other, that genetic selection in biology and symbolic representation in cognitive science alone leave out the very important (self-organizing) characteristics of particular embodiments of evolving and learning systems.

Self-Reference in Biological and Cognitive Systems

Luis Rocha

Uploads

Papers by Luis Rocha

Log In