Internet & Technology

A Novel Hybridization of ABC with CBR for Pseudoknotted RNA Structure

Description
The RNA molecule is substantiated to play important functions in living cells. The class of RNA with pseudoknots, has essential roles in designing remedies for many virus diseases in therapeutic domain. These various useful functions can be inferred from RNA secondary structure with pseudoknots. Many computational intensive efforts have been emerged with the aim of predicting the pseudoknotted RNA secondary structure. The computational approaches are much promising to predict the RNA structure. The reason behind this is that, the experimental methods for determining the RNA tertiary structure are difficult, timeconsuming and tedious. In this paper, we introduce ABCRna, a novel method for predicting RNA secondary structure with pseudoknots. This method combines heuristic-based KnotSeeker with a thermodynamic programming model, UNAFold. ABCRna is a hybrid swarm-based intelligence method inspired by the secreting honey process in natural honey-bee colonies. The novel aspect of this method is adapting Case-Based Reasoning (CBR) and knowledge base, two prominent Artificial Intelligence techniques. They are employed particularly to enhance the quality performance of the proposed method. The CBR provides an intelligent decision, which results more accurate predicted RNA structure. This modified ABCRna method is tested using different kinds of RNA sequences to prove and compare its efficiency against other pseudoknotted RNA predicted methods in the literature. The proposed ABCRna algorithm performs faster with significant improvement in accuracy, even for long RNA sequences.
Published
of 11
All materials on our website are shared by users. If you have any questions about copyright issues, please report us to resolve them. We are always happy to assist you.
Related Documents
Share
Transcript
  (IJCSIS) International Journal of Computer Science and Information Security,Vol. 8  , No. 8  , 2010 A Novel Hybridization of ABC with CBR forPseudoknotted RNA Structure Ra’ed M. Al-Khatib, Nur’Aini Abdul Rashid and Rosni AbdullahSchool of Computer ScienceUniversiti Sains Malaysia USMPenang, Malaysiarmaak.cod09@student.usm.my, {nuraini, rosni} @ cs.usm.my  Abstract — The RNA molecule is substantiated to playimportant functions in living cells. The class of RNA withpseudoknots, has essential roles in designing remedies formany virus diseases in therapeutic domain. These varioususeful functions can be inferred from RNA secondarystructure with pseudoknots. Many computational intensiveefforts have been emerged with the aim of predicting thepseudoknotted RNA secondary structure. The computationalapproaches are much promising to predict the RNA structure.The reason behind this is that, the experimental methods fordetermining the RNA tertiary structure are difficult, time-consuming and tedious. In this paper, we introduce ABCRna, anovel method for predicting RNA secondary structure withpseudoknots. This method combines heuristic-basedKnotSeeker with a thermodynamic programming model,UNAFold. ABCRna is a hybrid swarm-based intelligencemethod inspired by the secreting honey process in naturalhoney-bee colonies. The novel aspect of this method is adaptingCase-Based Reasoning (CBR) and knowledge base, twoprominent Artificial Intelligence techniques. They areemployed particularly to enhance the quality performance of the proposed method. The CBR provides an intelligentdecision, which results more accurate predicted RNAstructure. This modified ABCRna method is tested usingdifferent kinds of RNA sequences to prove and compare itsefficiency against other pseudoknotted RNA predicted methodsin the literature. The proposed ABCRna algorithm performsfaster with significant improvement in accuracy, even for longRNA sequences.  Keywords-    RNA    secondary    structure; pseudoknots; Case-Bases Reasoning; Artificial Bee Colony (ABC) algorithm. I.   I NTRODUCTION Ribonucleic acid or (RNA) is one of the nucleic acids,which plays diverse roles and functions. Basically, one kindof RNA is the messenger RNA (mRNA). It works as anintermediary in carrying the genetic information code fromDNA to make proteins [1]. This carried genetic code is usedin the natural process for synthesizing proteins in living cell.However, the recent biological studies confirmed that thereare other kinds of RNAs, which play various useful roles [2].The latest discovered functions of RNA molecule, include:splicing introns, catalyst for reaction and a regular in cellularactivities [3, 4]. Predicting the RNA structure is the key todetermine and scrutinize the active functions of RNAmolecule. This fact is emphasized by central dogma inbiochemistry and biology research domain [5, 6]. The RNAsecondary structural outputs provide the base for shaping theRNA three-dimension (3D) structure, which is the first stepof the RNA tertiary structure phase.The importance of the computational methods forpredicting RNA secondary structure has been acknowledgedas a demanding research area, by computer scientists. Also,there are many conditions, facing the experimental methodsthat are used by biologists [7, 8]. The Nuclear MagneticResonance (NMR) and X-ray crystallography are the twopopular experimental purification methods that are used todetermine the RNA 3D spatial structure [9, 10]. Lateststudies confirmed that many classes of RNA moleculebroadly fold in the pseudoknot motif [11, 12]. Whereas, theRNA structural functions of pseudoknot elements, have beenemphasized to be prominent for medical processes anddesigning anti-viral treatments, in therapeutic research [13].Consequently, the computational RNA prediction methodsfor predicting the RNA secondary structures are extensivelyutilized with manageable efforts [14].The RNA molecules come in two main shapes: the Stem-loop and the Pseudoknots, as illustrated in Figure 1 in termsof RNA structure classifiers [15]. The Stem-loop is a non-crossing RNA structure motif. While, the Pseudoknots is acrossing RNA structure, which plausibly has been spotted by[16]. Further, the pseudoknotted RNAs has been proven toplay several vital roles. From complexity points of view, thetop prediction methods of RNA without pseudoknotsfunctional element are MFold [17] and Vienna [18]algorithms which execute with complexities O ( n 3 ) in timeand O ( n 2 ) in space. PknotsRG [19] is one of the most properalgorithm for predicting RNA with pseudoknots. It requires O ( n 4 ) and O ( n 2 ) in time and space complexities, respectively.Even if the pseudoknotted RNA secondary structureprediction problem has been stated as Non-deterministicPolynomial time (NP)-Complete problem [20, 21], it is aninsisted matter to be solved [22, 23], in recent years.In order to overcome the prediction problem of RNAsecondary structure with pseudoknots, this article introduces School of Computer Sciences, University Sains Malaysia Penang, Malaysia. 289http://sites.google.com/site/ijcsis/ISSN 1947-5500  (IJCSIS) International Journal of Computer Science and Information Security,Vol. 8  , No. 8  , 2010 a nature-inspired hybrid method called “ABCRna”.Innovatively, this approach combines a new derivation fromArtificial Bee Colony (ABC) algorithm with a specialdeterministic constraints [24]. On top of this, it is borrowedfrom the Artificial Intelligence (AI) field, which is a kind of nature swarm-intelligence [25]. The objective of thisproposed method is to build the entire RNA secondarystructure with pseudoknots from a given single-strandedRNA primary sequence. Indeed, this proposed method is acombination of KnotSeeker (heuristic-based method [3])with UNAFold (a dynamic programming method [26]) forsolving the RNA structural related issue. This hybrid methodis a new derivation from ABC algorithm. It adapts theinspired swarm-based intelligence behavior of the honey-bees in collecting nectar and converting that to honey androyal jelly [27]. Naturally, every individual worker bee visitsmany flower patches during the round-trip of collectingnectar and pollen. Then it goes back to the hive to submit themixed nectar to the nurse bee. Finally, the nurse bee startsmaking honey by a natural biological secreting process.Intuitively, the proposed RNA structural hybrid methodis deployed and built to solve the related pseudoknotted RNAbioinformatics problem. By a deeper understanding of theCBR technique [28], the proposed hybrid model obtains aglobal optima RNA structural assurance results with moreaccuracy and better performance. Finally, the results showthat the ABCRna method significantly improves theexecution time and the accuracy in both sensitivity andspecificity. This improvement when comparing the outputswith the other pseudoknotted RNA prediction methodsexisting in the state-of-the-art like; FlexStem [29], HotKnots[30] and PknotsRG [19].The remainder of this article is ordered as follows: In thenext section, we start with describing the secondary structureof the RNA molecule, in computer context representation. Insection 3 background materials, gives a concise expression tothe generic ABC optimization method. Then, a derivation of  Figure 1. A stem-loop and pseudoknots of RNA structures types.  ABC is adapted to generate the proposed method. Next, theCBR as a modern AI technique, is extensively and widelydiscussed, from theoretical concept. Section 4 presents theproposed method with the implemental mapping betweenpseudoknotted RNA secondary structural prediction and thesecreting process of making honey. Subsequently, thefollowing section reports the comparative benchmark of theproposed method. The results of ABCRna is comparingagainst the results of other RNA prediction methods in theliterature. Finally, the article ends with conclusion remarks,in section 6.II.   S ECONDARY S TRUCTURES OF RNA    A.    RNA Stem-Loop (non-pseudoknots) The single-stranded RNA molecule forms many foldedstructures in hierarchal shape; the primary RNA singlesequence, the secondary structure of RNA molecule, thethree-dimensional (3D) or tertiary RNA functional structureand the quaternary structure for RNA polymerase [31].Generally, the RNA computational methods predict thesecondary structure of the given RNA primary sequence.Thus, the  RNA secondary structure defines: as an RNAstructural motif, which in some parts includes the double-stranded motifs. These parts joined by complementary andcanonical base pairings with the other parts, which are thenon-paired single bases. The double-stranded motif partscoming in several shaped of stem-loops: hairpin , internal (or interior  ), bulge , multi - branch external bases and stacking (or helices ) loops. As explained above and illustrated in Figure2, the RNA primary sequence (RNA bases) folds and joinson itself in real RNA secondary structure by hydrogenchemical bonds for low energy and more stability [15]. Inmathematical and computational representation concept, thevarious layers of RNA structures can be defined as follows: ã    b =   b 1 , b 2 , … , b i , …, b n , where  b is an RNA primarysequence and b i is the RNA base or nucleotide [32, 33].The element b i is also a member of set which includes{‘  A ’,’ C  ’,’ G ’,’ U  ’,’  N  ’}. While, the first four alphabets arerepresentation of the srcinal paired bases (paired-nucleotides) of the real RNA molecule:  Adenine, Cytosine,Guanine and Uracil , respectively. The last nucleotide ‘  N  ’is assigned to the non-paired base. Such that the n is thelength of the given RNA sequence and 1≤≤ . ã   S ={( b i , b  j )}, such that ( b i , b  j ) belongs to the canonical basepairs. S is the secondary structure of the given RNAprimary sequence which satisfies the following conditions:-   ( b i , b  j ) ∈ {(  A , U  ), ( U  ,  A ), ( G , C  ), ( C  , G ), ( G , U  ) ,( U  , G )},these are the sets of RNA base-pairs. While, the basepairs include in the set { A-U  , U-A , G-C  , C-G } is aWatson-Crick RNA base-pairs [34], the set { A-U  , U-A }is a Wobble RNA base-pair [35].-   Then S = {( b i , b  j ): 1≤<≤ and  −> },where  is a threshold constant number depend onthe limit length of the minimum un-paired bases in astem-loop (hairpin, stem or bulge ... etc). The  istypically taken to be equal three. 290http://sites.google.com/site/ijcsis/ISSN 1947-5500  (IJCSIS) International Journal of Computer Science and Information Security,Vol. 8  , No. 8  , 2010 -   If ( b i , b  j ) ∈   S , ( b k  , b l ) ∈   S and if  b i = b k  , then b  j = b l . Thisimplies ( b i , b  j ) = ( b k  , b l ). In another words, every base(nucleotide) in RNA secondary structure make join byhydrogen bond at most with another one base (non-tripleor only allow one-to-one).-   If ( b i , b  j ) ∈   S , ( b k  , b l ) ∈   S and < , this can include twolocation elements in RNA stem-loop structure ( non- pseudoknots ):    If  <<< , then the two base pairs are form atype of nested location elements (nested-fashion), asdepictured in Figure 3 a .      If  <<< , then the two base pairs are form atype of juxtaposed location elements (juxtaposed-fashion) [36], as shown in Figure 3 b .    B.    RNA with Pseudoknots The majority of RNA molecule classes fold in functionalstructural elements called pseudoknots. Indeed, they belongto the (3D) tertiary structure element and perform animportant useful roles and constructive functions [37].The pseudoknots substructure can theoretically satisfy thefollowing term. If there are two base pairs ( b i , b  j ) and ( b k  , b l ),then satisfy the conditions: <<< or <<< ,as shown in Figure 3 c and d. These two base paired shapesare represented the pseudoknots RNA structural elements. Inanother word, the pseudoknots is a crossing sub-structuralfunctional element in the RNA molecules. It formsinteraction the unpaired bases part of the stem-loop, whichfolds back and join in a loop region located outside thatstem-loop.In spite of the prediction algorithms of RNA withpseudoknots structural elements, have been proven to be NP-complete problem [21]. It is a demanding research areabecause of the pseudoknotted RNAs has importance as keyfunctions. Further it plays essential roles in viral and cellularregulatory [38]. Figure 2. Different RNA element shapes, the image is adapted from [39].Figure 3. The diagrammatic position relation between different types of RNA base pairs. (a) two base-pair in juxtaposed fashion. (b) two base-pair innested fashion. (c)&(d) two base-pair in pseudoknots. III.   B ACKGROUND M ATERIALS    A.   Problem Statement of RNA with Pseudoknot  Pseudoknotted RNA secondary structure is the problemof predicting its secondary structure from a given primarysequence. Particularly, it has recently become attractiveresearch area. Due to that the RNA with pseudoknots, hasmany important and useful roles, which needs to be solvedcomputationally [40]. The existing pseudoknotted RNAprediction algorithms perform in exponential timecomplexity. The best prediction method run, in the worstcase, O ( n 4 ) in time and O ( n 2 ) in space [19]. Thus they runvery slowly and need an ever increasing memory-space,especially for long sequences. Veritably, this means that theprediction solving algorithms of the pseudoknotted RNAsecondary structural problem, suffer from long executiontime and storage complexities. To the best knowledge of theauthors, the final structural results suffer from poor qualityand inaccuracy, for long RNA sequences.The pseudoknots class of the RNA structural predictionissue, has been proven an NP-complete problem [20].Increasingly, the collecting nectar to make honey is aninspired field for the bioinformatics researchers, which isderived from the srcinal ABC model [24]. In this article, anew hybrid method as a sub-area of swarm intelligenceapproaches for solving the pseudoknotted RNA structuralproblem is adapted. Besides that the CBR as a modern AItechnique highlighted a way to be deployed, in term of enhancement the final results of the proposed hybridABCRna model. From comparison points of view, we findthis method improved the accuracy of the RNA structuraloutputs with good performance.  B.   Swarm-Intelligence in AI TechnologySwarm Intelligence (SI): is an emergent and bioinspiredfield of AI, which has been generated from numerousresearches in social insect’s behavioural models [41]. Thephrase swarm comes up to present solution to overcome theoptimization problems. These optima solutions have beensuccessfully got by utilizing the co-operative and 291http://sites.google.com/site/ijcsis/ISSN 1947-5500  (IJCSIS) International Journal of Computer Science and Information Security,Vol. 8  , No. 8  , 2010 coordinative efforts among the worker-insects. Theinspiration of the swarm intelligence is gained from manysocial insects behavioral models like; honey-bees colony andant-colony. For instance in bee-colony, the objective of the swarm is the quantity and quality production of honey by themutual teamwork. It is a key fact that, the amount of honeythat an individual worker-bee harvests is worthless. But, thehoney production by all worker-bees is considerably muchbetter than the crop of an individual one [42].Lately, swarm intelligence has obtained high interest tobe adapted by many researchers from diverse fields. The listcompromises, but it is not limited of: engineering, scienceand commerce fields. The computer researchers proposeswarm intelligence optimization methods to solve manycomplex problems that suffer from severe drawbacks. Thetypical research domain of the computational swarmintelligence is to solve many real-world problems. Someapplications of swarm intelligence in a development areas asfollows: (i) The routing optimization in differentcommunication network [43]. (ii) The job scheduling [44].(iii) The swarm control in the Unmanned Aerial Vehicles(UAV) for both civil-military purposes [45, 46]. C.    Honey-Bee Colony Structure Many social insects live in colonies have instinctualability to perform as agents in a group for solving complexproblems and to complete their tasks. The new AIdisciplinary “ swarm-intelligence ” has been attractivelyproduced by deep knowledge of the biological swarm insolving the problems. This can done by a behavioralinteraction among thousands members of the swarm-insects[47]. Naturally, the social insects have talent to be in self-organized behavioral models for achieving an intelligencesolution of the vital tasks.Honey-bees live in a well structured social insect’scolony called a hive. The hive typically is a composition of asolo queen, drones and workers [48]. Each one does thefollowing roles: (i) As usual, there is one queen. She is egg-laying, female as a mother for other colony members andmates one time in her lifelong by drones. (ii) There aredrones or male bees as bee-colony fathers. Their mainresponsibility is fertilizing the new queen in a mating flightparty (social gathering) before dying. They live at most sixmonths and reach to hundreds up to several thousands duringthe summer season. (iii) There are around 10,000 in winter to60,000 in summer female worker-bees (foragers) in eachbee-colony. They do many important jobs including:collecting nectar to make food, raising and bringing up thebroods and larvae’s, guarding and ventilating the hive. But,the primary resourceful task of the worker-bees is collectingthe nectars and pollens from the flower patches (foragefield). Later, when they back to the hive the worker beessecret the honey and royal jelly (food).  D.    Honey-bee Collecting Nectar (Foraging) Honey-bees collecting nectar process to make honey is tobe considered as an optimization swarm-based intelligenceapproach [49]. The worker-bees perform the collectingnectar and secreting honey process in a well-organizedbehavioral model known as bees foraging process [50]. It isobvious that, this gigantic task is beyond the ability of everyworker-bee individually. Nevertheless, all the groupmembers interact among each other in a fashion to solve thecollective bee-foraging problem.The main incentive task in bee’s colony is the foraging( collecting nectar to make honey ). To investigate the beeforaging process Seeley in [51], introduced a detailedsystematic mechanism. It is about the self organizedhoneybee’s social behavioral model in collecting forage, asshown in Figure 4. In the proposed system, every worker bee(forager) visits many flowers from the same type within 30to 120 minutes of foraging trip. All the collected nectars,from these flower patches, have been stored in the foragerhoney stomach. Besides that, the forager commits severalactions to provide a feedback. Waggle dance is providing theprofitability rating of nectar in the flower patches, the odor,location and other required information [52, 53].Accordingly, the making honey and royal jelly process startswhen the worker-bee back to hive from the foraging round-trip journey.Soon after reaching the hive from the foraging trip, thefield bee (forager) gears up to submit that nectar, whichalready stored in her honey sac [54]. This process of submission the gathered nectar to the house bee (nurse bee)is accomplished in a regurgitated behavior. The role of thehouse bee is converting that nectar to honey or royal jelly(bee food) in a secreting process. In this synthesizing honeyprocess, the main work is to split the complex sucrose sugarinto fructose and glucose, which are simpler sugars andpredominant in honey. This sucrose-splitting process isperformed by adding the invertase , which is a specialenzyme, to the nectar from the hypopharyngeal gland in thehead of bee. Then, the new synthesized honey or royal jellyis spread out in a honey comb cells. The house bee exposesthis secreted honey as a thin film to aware of the lastfiltration. This final step was done by increasing the surfacearea, to insure the fast evaporation of water in the well-donehoney. Finally, the filled honey comb cells sealed and cappedby propolis (plant gum), which is an adhesive material. Thiswaxy cover prevents the honey from the bacterial attacks orin case of prevention the stored food to avoid thefermentation.Consequently, here the details of the foraging process arepresented to make a base for our nature-inspired method. It isa hybrid adaptation from the process of honeybees incollecting nectar to make honey and royal jelly. Theproposed ABCRna method solves the secondary structureprediction problem of RNA with pseudoknots. The idea isstimulating a hybrid novelty swarm-intelligence approachfrom collecting nectar and making honey in the naturalsecretion process. ABCRna as a new optimization algorithmis based on the main features of a hybrid between twoheuristic-based method KnotSeeker [3] and dynamicprogramming algorithms UNAFold [26]. 292http://sites.google.com/site/ijcsis/ISSN 1947-5500
Search
Similar documents
View more...
Tags
Related Search
We Need Your Support
Thank you for visiting our website and your interest in our free products and services. We are nonprofit website to share and download documents. To the running of this website, we need your help to support us.

Thanks to everyone for your continued support.

No, Thanks