SB Mirza

Knowledge-based expert systems and a proof-of-concept case study for multiple sequence alignment construction and analysis
Mohamed Radhouene Aniba,Sophie Siguenza, Anne Friedrich,Frederic Plewniak ,Olivier Poch,Aron Marchler-Bauer and Julie Dawn Thompson
SB MIRZA FA11-RBI-004 MS 2nd semester Bioinformatics
ABSTRACT
Bioinformatic information being produced to handle the various applications used to study the information presents a major data management and analysis challenge to researchers. It is impossible to analyse manually all the information. And new approaches are needed that are capable of processing the large-scale heterogeneous data to extract the pertinent information.
Cont
A general methodology for building knowledgebased expert systems is described, focusing on the (Unstructured Information Management Architecture), UIMA, which provides facilities for both data and process management.
New Challenges
Such system level studies necessitate a combination of experimental, theoretical and computational approaches. A major challenge for bioinformaticians in the post-genomic era is clearly the management, validation and analysis of this mass of experimental and predicted data.
Approaches
One approach has been data warehousing, where all the relevant databases are stored in a unified format and mined through a uniform interface Distributed systems implement software to access heterogeneous databases that are dispersed over the internet and provide a query facility to access the data.
SRS and entrez are probably the most widely used database query and navigation systems for the life science community. Semantic web based methods have been introduced which add meaning to the raw data by using formal descriptions of the concepts
KNOWLEDGE-BASED EXPERT SYSTEMS

There are several forms of expert systems that have been classified according to the methodology rule-based systems use a set of rules to analyse information about a specific class of problems and recommend one or more possible solution. case-based reasoning systems adapt solutions that were used to solve previous problems and use them to solve new problems.
Cont
Neural networks implement software simulations of massively parallel processes involving the processing of elements that are interconnected in a network architecture. Fuzzy expert systems use the method of fuzzy logic which deals with uncertainty and is used in areas where the results are not always binary.
The knowledge base contains domain expertise in the form of facts that the expert system will use to make determinations. The working storage is a database containing data specific to a problem being solved. The inference engine is the code at the core of the system which derives recommendations from the knowledge base and problem-specific data in the working storage
Cont
The knowledge acquisition module is used to update or expand dynamic knowledge bases. The user interface controls the dialog between the user and the system.
Expert systems and their architecture

The sequence of steps used to analyse a particular problem is not explicitly programmed, but is defined dynamically for each new case. Expert systems allow more than one line of reasoning to be pursued and presented
Cont
Problem solving is accomplished by applying specific knowledge rather than a specific technique. when the expert system does not produce the desired results, the solution is to expand the knowledge base rather than to reprogramme the procedures.
Tools for implementation of expert systems
Expert system shell is a piece of software which provides a development framework containing the user interface. (CLIPS) (JESS) The use of a shell can reduce the amount of maintenance required and increase reusability and flexibility of the application. An alternative is toBuild a customised expert system using conventional languages. It has been recommended to use a
Expert systems in bioinformatics

In the biocomputing domain, various expert systems have been built for specific tasks. Artificial neural networks have been used successfully for pattern discovery in many areas, including DNA and protein sequence analysis and microarray data analysis. Fuzzy logic approaches have also been applied to the analysis of gene expression data.
Cont
An active area of research has been the reconstruction of functional networks, such as expression data or interaction data, and intelligent systems, neural networks, genetic algorithms, etc. These approaches are also finding applications, e.g drug discovery and design or medical diagnosis. An important task in bioinformatics is the extraction of knowledge from the biomedical literature.
Cont
FIGENIX addresses the problems of automatic structural and functional annotation under the supervision of a rule-based expert system.
Case-based approaches and rule-based systems have also been applied widely. But there is no standard architecture that would allow exchange of information code between the many different applications.
A PROPOSED SOLUTION FOR BIOINFORMATICS:UIMA

The most difficult aspects of building an expert system in this domain is information integration, because of the heterogeneity of traditional biological data resources. The results of certain programmes, database annotations in natural language or the scientific literature is stored in different formats. The principal challenge with unstructured information is needed to be analysed to identify, locate and relate the entities and relationships of interest.
Cont
OpenNLP, GATE and UIMA, Open NLP is an umbrella structure to open source projects for the treatment of natural language. Open NLP and GATE, contain many powerful and robust algorithms for the processing of natural language texts. UIMA allows the analysis structured and unstructured data. It provides powerful capabilities for distributed computing through services and is scalable and extensible software architecture.
Overview of UIMA
A Collection Reader (CR), which allows the CPE to treat all the data in a given collection. A corpus: AEs and AAEs, possibly managed by FCs and CAS Consumer (CC), takes the results from the CAS and stores them in an exploitable format The first layer of a UIMA application, represents the Working Storage and contains the systems memory and used to
Cont
store the metadata associated with each AE.
Cont
AAEs and each module in the application layer can then update the metadata in the CAS at each step of the data analysis. In an expert system, the analysis pipeline is not pre-defined by the developer or user, but depends the previous experience gained by the system. The third layer corresponds to the User Interface between the final user and the system. It provides powerful capabilities for distributed computing through services and is scalable and extensible software architecture.
Cont
UIMA is now exploited by numerous application related to the biological domain.
A CASE STUDY: THE ALEXSYS MULTIPLE ALIGNM ENT EXPERT SYSTEM

The first formal algorithm for Multiple sequence alignment (MSA) was computationally expensive and most programmes employ some kind of heuristic approach. The progressive alignment procedure exploits the fact that homologous sequences are evolutionarily related.
Cont
This method involves three main steps: 1:Pairwise sequence alignment and distance matrix calculation 2: guide tree construction 3:multiple alignment
Different MSA tools

DbClustal Tcoffee MAFFT Muscle 3DCoffee PRALINE Refiner PipeAlign
AlexSys prototype: objectives

Multiple sequence comparisons or alignments provide the basis for most of the computational methods used in genomic analyses or proteomics projects. The MSA programmes are capable of aligning difficult, divergent sets of sequences with consistently high quality. Alignments Expert SYStem evaluate and optimise all the steps involved in the construction and analysis of a multiple alignment.
Design and implementation

The TSs represent the prototypes memory (the UIMA CAS) The prototype currently uses five TSs: Sequence, Matrix, Tree, Parameter and Alignment. With TS we can build the second application layer containing the AEs, grouped together into AAEs. This is designed to perform three main tasks: input data handling, annotation and information extraction and MSA construction.
The modular structure of the AlexSys prototype.
Clustal W alignment optimisation using UIMA
The final enhancement to the ClustalW algorithm involved the addition of a post-processing refinement step Many approaches are developed to improve MSA, based on an optimisation of the Sum of Pairs objective function.
CONCLUSION
a number of requirements for a general expert system for systems biology: Easy integration of heterogeneous, distributed data structured, semi-structured and unstructured. Easy integration of different analysis modules and reuse of existing modules. complex workflow capabilities, support for decision rules and automatic reasoning facilities for implementation in a distributed grid computing environment.

SB Mirza

Uploaded by

Copyright:

Available Formats

SB Mirza

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

SB Mirza

Uploaded by

Copyright:

Available Formats

Knowledge-based expert systems and a proof-of-concept case study for multiple sequence alignment construction and analysis

SB MIRZA FA11-RBI-004 MS 2nd semester Bioinformatics

KNOWLEDGE-BASED EXPERT SYSTEMS

Expert systems and their architecture

Tools for implementation of expert systems

Expert systems in bioinformatics

A PROPOSED SOLUTION FOR BIOINFORMATICS:UIMA

A CASE STUDY: THE ALEXSYS MULTIPLE ALIGNM ENT EXPERT SYSTEM

Different MSA tools

AlexSys prototype: objectives

Design and implementation

The modular structure of the AlexSys prototype.

Clustal W alignment optimisation using UIMA

You might also like

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.