Tenth International Workshop CIA 2006, Edinburgh Evaluating Dynamic Services in Bioinformatics Maíra R. Rodrigues Michael Luck University of Southampton, UK Outline 2 Bioinformatics Agents and Bioinformatics Model for Cooperative Interactions: Overview Requirements for Service Evaluation Evaluation Method Example Scenario Conclusion Future Work ECS - University of Southampton CIA 2006 Bioinformatics Bioinformatics Bioinformatics Services Heterogeneous Locally and remotely used Continuous update Management and analysis of biological data and tools 3 Application of computer technology to manage and analyse biological data Suitability of an agent-based approach ECS - University of Southampton CIA 2006 Bioinformatics Interrelated data Cooperative applications Services free of charge 4 Participants request and provide services to each other Non-economic exchange of different types of tools and data Interactions are based on reciprocal relations ECS - University of Southampton CIA 2006 Agents and Bioinformatics The agent-based approach: Therefore.. 5 Agents provide and request bioinformatics services Existence of alternative providers Services are provided with different levels of quality (heterogeneity) Agents need to select service providers ECS - University of Southampton CIA 2006 Agents for Interaction Agent-based applications in bioinformatics: Our concern: 6 Concerned with high-level management tasks Model non-economic cooperative interactions Evaluation method for bioinformatics services to determine an agent’s satisfaction Guide agent’s decisions over service providers ECS - University of Southampton CIA 2006 Model for Cooperative Interactions Model non-economic cooperative interactions based on exchange values (Piaget 1973) • effort • credit 7 A1 A2 service ECS - University of Southampton • satisfaction • debt CIA 2006 Model for Cooperative Interactions Model non-economic cooperative interactions based on exchange values (Piaget 1973) • effort A1 A2 • credit • credit • satisfaction 8 • satisfaction • debt • debt A1 A2 ECS - University of Southampton • effort CIA 2006 Model for Cooperative Interactions Exchange values result from the agent’s evaluation of the service Service Evaluation Exchange Values Partner Selection (future interactions) 9 ECS - University of Southampton CIA 2006 Model for Cooperative Interactions Exchange values result from the agent’s evaluation of the service Exchange values (Rodrigues, Luck 2005, 2006) Current work focus on service evaluation Service Evaluation Exchange Values Partner Selection (future interactions) 10 ECS - University of Southampton CIA 2006 Service Evaluation Bio-Services are dynamic: Evaluation requires 11 Constant updates Regular behaviour, but Sensitive to different parameter configuration Repeated evaluation Attach context information Evaluation of different aspects of the service ECS - University of Southampton CIA 2006 Service Evaluation Evaluation method should address: 12 Generality: apply to different types of bioservices and aspects of these services Continuity: repeat evaluation every time a service is received Consistency: compare evaluations made at different points in time Discriminated information: allow flexible decision-making by using evaluation of individual aspects or a global evaluation ECS - University of Southampton CIA 2006 Alternative Approaches Quantitative approaches Qualitative approaches: 13 Scoring or utility functions • Objective values • Precision, consistency, combination is straightforward Classification rules (e.g., poor, good, excellent) • Subjective values ECS - University of Southampton CIA 2006 Evaluation Method Choose evaluation attributes for service examples: performance, quality, reliability, etc. For each attribute, associate result measures Pieces of information derived from service result that can determine the service utility in relation to an attribute (observed value). Static or dynamic measures (e.g., quality of interface and response time) 14 ECS - University of Southampton CIA 2006 Evaluation Method General evaluation function for evaluation attributes (utility): For a set of attributes A = {a1,..,ai} result measure for ai Ui = bc evaluation strictness 1 Ui 0 c 15 ECS - University of Southampton CIA 2006 Evaluation Process Before evaluation: Repeat evaluation process every time a service is received 16 Identify evaluation attributes for services and result measures for each attribute Input is the service result and configuration used For each evaluation attribute ai • Compute result measures • Calculate evaluation Ui • Store evaluation Output is a set of evaluations (evaluation tuple) ECS - University of Southampton CIA 2006 Evaluating Bio-Services Proteomics research 17 Protein identification services • Input: file (list of unknown peptides) • Process: database + matching algorithm • Output: list of proteins, peptides per protein Services: OMSSA, MASCOT, Tandem Local and Remote Heterogeneous results for same input data Sensitive to different input configurations Evaluation can be used as criterion for future selection ECS - University of Southampton CIA 2006 Evaluating Bio-Services Evaluation attributes: 18 Sensitivity • Capacity of matching related proteins Accuracy • Capacity of identifying true matches Performance • Time taken from input submission until result is received ECS - University of Southampton CIA 2006 Evaluating Bio-Services Result measures (rm): Sensitivity • Number of proteins • Peptide ratio - peptides per protein • Influence of input size • Increasing utility rm = 19 input_size peptide_ratio x protein_number ECS - University of Southampton CIA 2006 Evaluating Bio-Services Accuracy • Number of false positives • Decreasing utility rm = false_positives Performance: • Response time • Influence of input size • Decreasing utility response_time rm = input_size 20 ECS - University of Southampton CIA 2006 Evaluating Bio-Services Evaluation functions: Sensitivity (U1): Ui = 0.5rm • U1 increases with peptide_ratio and protein_number Accuracy (U2): • U2 decreases with false_positives Performance (U3): • U3 decreases with response_time 21 ECS - University of Southampton CIA 2006 Evaluating Bio-Services Practical evaluation: Evaluation of sensitivity 22 Same input spectra Two different configurations (C1 and C2) Evaluation reflects different results for C1 and C2 ECS - University of Southampton CIA 2006 Evaluating Bio-Services Evaluation of performance Again, evaluation reflects different results for C1 and C2 23 ECS - University of Southampton CIA 2006 Conclusions Present an evaluation method to be used by agents requesting dynamic services in bioinformatics Discussion of issues for efficient evaluation of these services, including 24 Adoption of a repeated evaluation process Absolute evaluations Generation of individual and compatible evaluations Single evaluation must be calculated during selection ECS - University of Southampton CIA 2006 Conclusions 25 Show the application of the evaluation method for protein identification services Importance of dynamic (repeated) evaluation is shown through empirical results Provide more accurate information for agents that need to select services with dynamic characteristics ECS - University of Southampton CIA 2006 Future Work Develop selection strategies that use and combine service evaluations Combination through objective and subjective values Probabilistic analysis of past evaluations Consider similarity between different service configurations Validate evaluation results with those of bioinformaticians 26 ECS - University of Southampton CIA 2006 Thank you 27 ECS - University of Southampton CIA 2006 References J. Piaget. Sociological Studies. Routlege, London, 1973. M. R. Rodrigues and M. Luck. Analysing partner selection through exchange values. In Jaime Sichman and Luis Antunes, editors, Multi-Agent-Based Simulation VI, volume 3891 of Lecture Notes in Artificial Intelligence, pages 24-40, Berlin Heidelberg, 2006a. Springer-Verlag. M. R. Rodrigues and M. Luck. Cooperative interactions: An exchange values model. In Coordination, Organization, Institutions and Norms in Agent Systems (COIN), ECAI Conference, Riva del Garda, Italy, August 2006b. 28 ECS - University of Southampton CIA 2006