Reinforcement Learning Method for BioAgents

  title={Reinforcement Learning Method for BioAgents},
  author={C{\'e}lia Ghedini Ralha and Hugo W. Schneider and Maria Emilia Telles Walter and Ana L{\'u}cia Cetertich Bazzan},
  journal={2010 Eleventh Brazilian Symposium on Neural Networks},
Machine Learning (ML) techniques are being employed in bioinformatics with increasing success. [] Key Method Experiments were done with real data from two different genome sequencing projects: Paracoccidioides brasiliensis - Pb fungus and Paullinia cupana - Guaraná plant. To assign reinforcement signals we have used reference genomes with curated annotations that are considered correct, these signals tackle specific databases and alignment algorithms. The results obtained with the inclusion of a RL layer in…

Figures and Tables from this paper

Applications of Deep Learning and Reinforcement Learning to Biological Data

This paper provides a comprehensive survey on the application of DL, RL, and deep RL techniques in mining biological data and compares the performances of DL techniques when applied to different data sets across various application domains.

THESIS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY Application of Machine Learning in Systems Biology

This thesis addressed the challenge of noisy response values in biological datasets by deriving a theoretical upper bound for the coefficient of determination (R2) for regression models and demonstrated that the transfer learning-based regression models outperform the classical ones trained on rationally engineered features in both cases.

Uma ferramenta multiagente baseada em conhecimento para anotação de proteínas : um estudo de caso para o Fungo Saccharomyces cerevisiae

This dissertation presents BioAgents-Prot, a knowledge based multiagent tool, which simulates biologists expertise to annotate proteins, and shows the usefulness of BioAgent-Prot in annotation step of transcriptome projects.

A Multi-agent Tool to Annotate Biological Sequences

A sophisticated prototype named BioAgents is developed, which simulates biologists knowledge and experience to annotate DNA or RNA sequences in genome sequencing projects, where different specialized intelligent agents work together to accomplish the automatic annotation of sequences.

ncRNA-Agents : anotação de RNAs não-codificadores baseada em sistema multiagente

This thesis presents an architecture for ncRNAs annotation based on the multi-agent system paradigm, where each agent has knowledge and reasonig about a speci c aspect of RNA, which contributes to a curated ncRNA annotation, with associated quality and explanationsbased on the results of the tools used by the system to recommend the annotation.

ncRNA-Agents: A Multiagent System for Non-coding RNA Annotation

Experiments with real data of fungi allowed to identify novel putative ncRNAs, which shows the usefulness of the multiagent system presented, using inference rules to simulate biologists' reasoning.

Learning Where to See: A Novel Attention Model for Automated Immunohistochemical Scoring

This is the first study using DRL for IHC scoring and could potentially lead to wider use of DRL in the domain of computational pathology reducing the computational burden of the analysis of large multi-gigapixel histology images.



Using BioAgentsfor Supporting Manual Annotation on Genome Sequencing Projects

This work presents a new version of BioAgents, a multiagent system (MAS) for supporting manual annotation, which simulates the biologists' knowledge and experience for annotating DNA sequences in genome sequencing projects.

A multi-agent system for automated genomic annotation

DECAF, a multi-agent system toolkit based on RETSINA and TAEMS, is used to construct a prototype multi- agent system for automated annotation and database storage of sequencing data for herpesviruses.

A Multi-agent System to Facilitate Knowledge Discovery : an application to Bioinformatics

This article proposes an architecture for an environment which combines different symbolic Machine Learning algorithms encapsulated in agents that collaborate to improve their knowledge and uses this environment to acquire rules for annotation of the field “Keywords” in the SWISS-PROT database.

Improving the Caenorhabditis elegans Genome Annotation Using Machine Learning

The state-of-the-art machine learning methods employed to assay and improve the accuracy of the genome annotation of the nematode Caenorhabditis elegans are concluded to be greatly enhanced using modern machine learning technology.

Automated annotation of keywords for proteins related to mycoplasmataceae using machine learning techniques

The aim of this procedure is to complete the annotation of keywords of those proteins which is far from adequate, and to produce a prototype of the validation environment, which is aimed at an expert who does not have a deep knowledge of the structure of the current databases containing the necessary information s/he needs.

Reinforcement Learning: An Introduction

This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.

Prediction of Enzyme Classification from Protein Sequence without the Use of Sequence Similarity

A novel approach for predicting the function of a protein from its amino-acid sequence that uses machine learning techniques to induce classifiers that predict the EC class of an enzyme from features extracted from its primary sequence.

Beyond the "best" match: machine learning annotation of protein sequences by integration of different sources of information

This work has developed and compared the automatic annotation of four bacterial genomes employing a 5-fold cross-validation procedure and several machine learning methods and found the neural network approach showed the best performance.

SOM-PORTRAIT: Identifying Non-coding RNAs Using Self-Organizing Maps

This work proposes a method for identifying non-coding RNAs using Self Organizing Maps using self-Organizing Maps, named SOM-PORTRAIT, and applied it to a data set containing Assembled ESTs of the Paracoccidioides brasiliensis fungus transcriptome.

Machine learning approaches to gene recognition

This article surveys several efforts that apply machine learning techniques to gene recognition in two broad classes: search by signal and search by content.