A Novel Hybridization of ABC with CBR for Pseudoknotted RNA Structure

Document Sample
A Novel Hybridization of ABC with CBR for Pseudoknotted RNA Structure Powered By Docstoc
					                                                                         (IJCSIS) International Journal of Computer Science and Information Security,
                                                                                                                            Vol. 8, No. 8, 2010

           A Novel Hybridization of ABC with CBR for
                 Pseudoknotted RNA Structure
                                       Ra’ed M. Al-Khatib, Nur’Aini Abdul Rashid and Rosni Abdullah

                                                             School of Computer Science
                                                            Universiti Sains Malaysia USM
                                                                  Penang, Malaysia
                               , {nuraini, rosni} @

Abstract— The RNA molecule is substantiated to play                                 activities [3, 4]. Predicting the RNA structure is the key to
important functions in living cells. The class of RNA with                          determine and scrutinize the active functions of RNA
pseudoknots, has essential roles in designing remedies for                          molecule. This fact is emphasized by central dogma in
many virus diseases in therapeutic domain. These various                            biochemistry and biology research domain [5, 6]. The RNA
useful functions can be inferred from RNA secondary                                 secondary structural outputs provide the base for shaping the
structure with pseudoknots. Many computational intensive                            RNA three-dimension (3D) structure, which is the first step
efforts have been emerged with the aim of predicting the                            of the RNA tertiary structure phase.
pseudoknotted RNA secondary structure. The computational
approaches are much promising to predict the RNA structure.                             The importance of the computational methods for
The reason behind this is that, the experimental methods for                        predicting RNA secondary structure has been acknowledged
determining the RNA tertiary structure are difficult, time-                         as a demanding research area, by computer scientists. Also,
consuming and tedious. In this paper, we introduce ABCRna, a                        there are many conditions, facing the experimental methods
novel method for predicting RNA secondary structure with                            that are used by biologists [7, 8]. The Nuclear Magnetic
pseudoknots. This method combines heuristic-based                                   Resonance (NMR) and X-ray crystallography are the two
KnotSeeker with a thermodynamic programming model,                                  popular experimental purification methods that are used to
UNAFold. ABCRna is a hybrid swarm-based intelligence                                determine the RNA 3D spatial structure [9, 10]. Latest
method inspired by the secreting honey process in natural
                                                                                    studies confirmed that many classes of RNA molecule
honey-bee colonies. The novel aspect of this method is adapting
                                                                                    broadly fold in the pseudoknot motif [11, 12]. Whereas, the
Case-Based Reasoning (CBR) and knowledge base, two
prominent Artificial Intelligence techniques. They are
                                                                                    RNA structural functions of pseudoknot elements, have been
employed particularly to enhance the quality performance of                         emphasized to be prominent for medical processes and
the proposed method. The CBR provides an intelligent                                designing anti-viral treatments, in therapeutic research [13].
decision, which results more accurate predicted RNA                                 Consequently, the computational RNA prediction methods
structure. This modified ABCRna method is tested using                              for predicting the RNA secondary structures are extensively
different kinds of RNA sequences to prove and compare its                           utilized with manageable efforts [14].
efficiency against other pseudoknotted RNA predicted methods
                                                                                        The RNA molecules come in two main shapes: the Stem-
in the literature. The proposed ABCRna algorithm performs
                                                                                    loop and the Pseudoknots, as illustrated in Figure 1 in terms
faster with significant improvement in accuracy, even for long
RNA sequences.                                                                      of RNA structure classifiers [15]. The Stem-loop is a non-
                                                                                    crossing RNA structure motif. While, the Pseudoknots is a
  Keywords- RNA secondary structure; pseudoknots; Case-Bases                        crossing RNA structure, which plausibly has been spotted by
Reasoning; Artificial Bee Colony (ABC) algorithm.                                   [16]. Further, the pseudoknotted RNAs has been proven to
                                                                                    play several vital roles. From complexity points of view, the
                                                                                    top prediction methods of RNA without pseudoknots
                        I.      INTRODUCTION                                        functional element are MFold [17] and Vienna [18]
                                                                                    algorithms which execute with complexities O(n3) in time
    Ribonucleic acid or (RNA) is one of the nucleic acids,
                                                                                    and O(n2) in space. PknotsRG [19] is one of the most proper
which plays diverse roles and functions. Basically, one kind
                                                                                    algorithm for predicting RNA with pseudoknots. It requires
of RNA is the messenger RNA (mRNA). It works as an
                                                                                    O(n4) and O(n2) in time and space complexities, respectively.
intermediary in carrying the genetic information code from
                                                                                    Even if the pseudoknotted RNA secondary structure
DNA to make proteins [1]. This carried genetic code is used
                                                                                    prediction problem has been stated as Non-deterministic
in the natural process for synthesizing proteins in living cell.
                                                                                    Polynomial time (NP)-Complete problem [20, 21], it is an
However, the recent biological studies confirmed that there
                                                                                    insisted matter to be solved [22, 23], in recent years.
are other kinds of RNAs, which play various useful roles [2].
The latest discovered functions of RNA molecule, include:                              In order to overcome the prediction problem of RNA
splicing introns, catalyst for reaction and a regular in cellular                   secondary structure with pseudoknots, this article introduces
   School of Computer Sciences, University Sains Malaysia Penang, Malaysia.

                                                                                                              ISSN 1947-5500
                                                                     (IJCSIS) International Journal of Computer Science and Information Security,
                                                                                                                        Vol. 8, No. 8, 2010
a nature-inspired hybrid method called “ABCRna”.                               ABC is adapted to generate the proposed method. Next, the
Innovatively, this approach combines a new derivation from                     CBR as a modern AI technique, is extensively and widely
Artificial Bee Colony (ABC) algorithm with a special                           discussed, from theoretical concept. Section 4 presents the
deterministic constraints [24]. On top of this, it is borrowed                 proposed method with the implemental mapping between
from the Artificial Intelligence (AI) field, which is a kind of                pseudoknotted RNA secondary structural prediction and the
nature swarm-intelligence [25]. The objective of this                          secreting process of making honey. Subsequently, the
proposed method is to build the entire RNA secondary                           following section reports the comparative benchmark of the
structure with pseudoknots from a given single-stranded                        proposed method. The results of ABCRna is comparing
RNA primary sequence. Indeed, this proposed method is a                        against the results of other RNA prediction methods in the
combination of KnotSeeker (heuristic-based method [3])                         literature. Finally, the article ends with conclusion remarks,
with UNAFold (a dynamic programming method [26]) for                           in section 6.
solving the RNA structural related issue. This hybrid method
is a new derivation from ABC algorithm. It adapts the
inspired swarm-based intelligence behavior of the honey-                                   II.   SECONDARY STRUCTURES OF RNA
bees in collecting nectar and converting that to honey and
royal jelly [27]. Naturally, every individual worker bee visits                A. RNA Stem-Loop (non-pseudoknots)
many flower patches during the round-trip of collecting                            The single-stranded RNA molecule forms many folded
nectar and pollen. Then it goes back to the hive to submit the                 structures in hierarchal shape; the primary RNA single
mixed nectar to the nurse bee. Finally, the nurse bee starts                   sequence, the secondary structure of RNA molecule, the
making honey by a natural biological secreting process.                        three-dimensional (3D) or tertiary RNA functional structure
    Intuitively, the proposed RNA structural hybrid method                     and the quaternary structure for RNA polymerase [31].
is deployed and built to solve the related pseudoknotted RNA                   Generally, the RNA computational methods predict the
bioinformatics problem. By a deeper understanding of the                       secondary structure of the given RNA primary sequence.
CBR technique [28], the proposed hybrid model obtains a                        Thus, the RNA secondary structure defines: as an RNA
global optima RNA structural assurance results with more                       structural motif, which in some parts includes the double-
accuracy and better performance. Finally, the results show                     stranded motifs. These parts joined by complementary and
that the ABCRna method significantly improves the                              canonical base pairings with the other parts, which are the
execution time and the accuracy in both sensitivity and                        non-paired single bases. The double-stranded motif parts
specificity. This improvement when comparing the outputs                       coming in several shaped of stem-loops: hairpin, internal (or
with the other pseudoknotted RNA prediction methods                            interior), bulge, multi-branch external bases and stacking (or
existing in the state-of-the-art like; FlexStem [29], HotKnots                 helices) loops. As explained above and illustrated in Figure
[30] and PknotsRG [19].                                                        2, the RNA primary sequence (RNA bases) folds and joins
                                                                               on itself in real RNA secondary structure by hydrogen
    The remainder of this article is ordered as follows: In the                chemical bonds for low energy and more stability [15]. In
next section, we start with describing the secondary structure                 mathematical and computational representation concept, the
of the RNA molecule, in computer context representation. In                    various layers of RNA structures can be defined as follows:
section 3 background materials, gives a concise expression to
the generic ABC optimization method. Then, a derivation of                     • b = b1, b2, …, bi, …, bn, where b is an RNA primary
                                                                                 sequence and bi is the RNA base or nucleotide [32, 33].
                                                                                 The element bi is also a member of set which includes
                                                                                 {‘A’,’C’,’G’,’U’,’N’}. While, the first four alphabets are
                                                                                 representation of the original 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 the
                                                                                 length of the given RNA sequence and 1 ≤ ≤ .
                                                                               • S ={(bi, bj)}, such that (bi, bj) belongs to the canonical base
                                                                                 pairs. S is the secondary structure of the given RNA
                                                                                 primary sequence which satisfies the following conditions:
                                                                                 - (bi, bj) ∈ {(A,U), (U,A), (G,C), (C,G), (G,U) ,(U,G)},
                                                                                   these are the sets of RNA base-pairs. While, the base
                                                                                   pairs include in the set { A-U , U-A , G-C , C-G} is a
                                                                                   Watson-Crick RNA base-pairs [34], the set { A-U , U-A}
                                                                                   is a Wobble RNA base-pair [35].
                                                                                 - Then S = {(bi, bj): 1 ≤ < ≤ and − >                  },
                                                                                   where         is a threshold constant number depend on
                                                                                   the limit length of the minimum un-paired bases in a
                                                                                   stem-loop (hairpin, stem or bulge ... etc). The      is
    Figure 1. A stem-loop and pseudoknots of RNA structures types.
                                                                                   typically taken to be equal three.

                                                                                                          ISSN 1947-5500
                                                                      (IJCSIS) International Journal of Computer Science and Information Security,
                                                                                                                         Vol. 8, No. 8, 2010
 - If (bi, bj) ∈ S, (bk, bl) ∈ S and if bi = bk, then bj = bl. This
   implies (bi, bj) = (bk, bl). In another words, every base
   (nucleotide) in RNA secondary structure make join by
   hydrogen bond at most with another one base (non-triple
   or only allow one-to-one).
 - If (bi, bj) ∈ S, (bk, bl) ∈ S and < , this can include two
   location elements in RNA stem-loop structure (non-
     If < < < , then the two base pairs are form a
     type of nested location elements (nested-fashion), as
     depictured in Figure 3 a.
     If < < < , then the two base pairs are form a
     type of juxtaposed location elements (juxtaposed-
     fashion) [36], as shown in Figure 3 b.
                                                                                 Figure 3. The diagrammatic position relation between different types of
                                                                                RNA base pairs. (a) two base-pair in juxtaposed fashion. (b) two base-pair in
                                                                                          nested fashion. (c)&(d) two base-pair in pseudoknots.
B. RNA with Pseudoknots
    The majority of RNA molecule classes fold in functional                                       III.   BACKGROUND MATERIALS
structural elements called pseudoknots. Indeed, they belong
to the (3D) tertiary structure element and perform an                           A. Problem Statement of RNA with Pseudoknot
important useful roles and constructive functions [37].                             Pseudoknotted RNA secondary structure is the problem
    The pseudoknots substructure can theoretically satisfy the                  of predicting its secondary structure from a given primary
following term. If there are two base pairs (bi, bj) and (bk, bl),              sequence. Particularly, it has recently become attractive
then satisfy the conditions: < < < or < < < ,                                   research area. Due to that the RNA with pseudoknots, has
as shown in Figure 3 c and d. These two base paired shapes                      many important and useful roles, which needs to be solved
are represented the pseudoknots RNA structural elements. In                     computationally [40]. The existing pseudoknotted RNA
another word, the pseudoknots is a crossing sub-structural                      prediction algorithms perform in exponential time
functional element in the RNA molecules. It forms                               complexity. The best prediction method run, in the worst
interaction the unpaired bases part of the stem-loop, which                     case, O(n4) in time and O(n2) in space [19]. Thus they run
folds back and join in a loop region located outside that                       very slowly and need an ever increasing memory-space,
stem-loop.                                                                      especially for long sequences. Veritably, this means that the
   In spite of the prediction algorithms of RNA with                            prediction solving algorithms of the pseudoknotted RNA
pseudoknots structural elements, have been proven to be NP-                     secondary structural problem, suffer from long execution
complete problem [21]. It is a demanding research area                          time and storage complexities. To the best knowledge of the
because of the pseudoknotted RNAs has importance as key                         authors, the final structural results suffer from poor quality
functions. Further it plays essential roles in viral and cellular               and inaccuracy, for long RNA sequences.
regulatory [38].                                                                    The pseudoknots class of the RNA structural prediction
                                                                                issue, has been proven an NP-complete problem [20].
                                                                                Increasingly, the collecting nectar to make honey is an
                                                                                inspired field for the bioinformatics researchers, which is
                                                                                derived from the original ABC model [24]. In this article, a
                                                                                new hybrid method as a sub-area of swarm intelligence
                                                                                approaches for solving the pseudoknotted RNA structural
                                                                                problem is adapted. Besides that the CBR as a modern AI
                                                                                technique highlighted a way to be deployed, in term of
                                                                                enhancement the final results of the proposed hybrid
                                                                                ABCRna model. From comparison points of view, we find
                                                                                this method improved the accuracy of the RNA structural
                                                                                outputs with good performance.

                                                                                B. Swarm-Intelligence in AI Technology
                                                                                    Swarm Intelligence (SI): is an emergent and bioinspired
                                                                                field of AI, which has been generated from numerous
                                                                                researches in social insect’s behavioural models [41]. The
                                                                                phrase swarm comes up to present solution to overcome the
                                                                                optimization problems. These optima solutions have been
Figure 2. Different RNA element shapes, the image is adapted from [39].         successfully got by utilizing the co-operative and

                                                                                                               ISSN 1947-5500
                                                            (IJCSIS) International Journal of Computer Science and Information Security,
                                                                                                               Vol. 8, No. 8, 2010
coordinative efforts among the worker-insects. The                     approach [49]. The worker-bees perform the collecting
inspiration of the swarm intelligence is gained from many              nectar and secreting honey process in a well-organized
social insects behavioral models like; honey-bees colony and           behavioral model known as bees foraging process [50]. It is
ant-colony. For instance in bee-colony, the objective of the           obvious that, this gigantic task is beyond the ability of every
swarm is the quantity and quality production of honey by the           worker-bee individually. Nevertheless, all the group
mutual teamwork. It is a key fact that, the amount of honey            members interact among each other in a fashion to solve the
that an individual worker-bee harvests is worthless. But, the          collective bee-foraging problem.
honey production by all worker-bees is considerably much
better than the crop of an individual one [42].                            The main incentive task in bee’s colony is the foraging
                                                                       (collecting nectar to make honey). To investigate the bee
     Lately, swarm intelligence has obtained high interest to          foraging process Seeley in [51], introduced a detailed
be adapted by many researchers from diverse fields. The list           systematic mechanism. It is about the self organized
compromises, but it is not limited of: engineering, science            honeybee’s social behavioral model in collecting forage, as
and commerce fields. The computer researchers propose                  shown in Figure 4. In the proposed system, every worker bee
swarm intelligence optimization methods to solve many                  (forager) visits many flowers from the same type within 30
complex problems that suffer from severe drawbacks. The                to 120 minutes of foraging trip. All the collected nectars,
typical research domain of the computational swarm                     from these flower patches, have been stored in the forager
intelligence is to solve many real-world problems. Some                honey stomach. Besides that, the forager commits several
applications of swarm intelligence in a development areas as           actions to provide a feedback. Waggle dance is providing the
follows: (i) The routing optimization in different                     profitability rating of nectar in the flower patches, the odor,
communication network [43]. (ii) The job scheduling [44].              location and other required information [52, 53].
(iii) The swarm control in the Unmanned Aerial Vehicles                Accordingly, the making honey and royal jelly process starts
(UAV) for both civil-military purposes [45, 46].                       when the worker-bee back to hive from the foraging round-
                                                                       trip journey.
C. Honey-Bee Colony Structure
                                                                            Soon after reaching the hive from the foraging trip, the
    Many social insects live in colonies have instinctual              field bee (forager) gears up to submit that nectar, which
ability to perform as agents in a group for solving complex            already stored in her honey sac [54]. This process of
problems and to complete their tasks. The new AI                       submission the gathered nectar to the house bee (nurse bee)
disciplinary “swarm-intelligence” has been attractively                is accomplished in a regurgitated behavior. The role of the
produced by deep knowledge of the biological swarm in                  house bee is converting that nectar to honey or royal jelly
solving the problems. This can done by a behavioral                    (bee food) in a secreting process. In this synthesizing honey
interaction among thousands members of the swarm-insects               process, the main work is to split the complex sucrose sugar
[47]. Naturally, the social insects have talent to be in self-         into fructose and glucose, which are simpler sugars and
organized behavioral models for achieving an intelligence              predominant in honey. This sucrose-splitting process is
solution of the vital tasks.                                           performed by adding the invertase, which is a special
    Honey-bees live in a well structured social insect’s               enzyme, to the nectar from the hypopharyngeal gland in the
colony called a hive. The hive typically is a composition of a         head of bee. Then, the new synthesized honey or royal jelly
solo queen, drones and workers [48]. Each one does the                 is spread out in a honey comb cells. The house bee exposes
following roles: (i) As usual, there is one queen. She is egg-         this secreted honey as a thin film to aware of the last
laying, female as a mother for other colony members and                filtration. This final step was done by increasing the surface
mates one time in her lifelong by drones. (ii) There are               area, to insure the fast evaporation of water in the well-done
drones or male bees as bee-colony fathers. Their main                  honey. Finally, the filled honey comb cells sealed and capped
responsibility is fertilizing the new queen in a mating flight         by propolis (plant gum), which is an adhesive material. This
party (social gathering) before dying. They live at most six           waxy cover prevents the honey from the bacterial attacks or
months and reach to hundreds up to several thousands during            in case of prevention the stored food to avoid the
the summer season. (iii) There are around 10,000 in winter to          fermentation.
60,000 in summer female worker-bees (foragers) in each
bee-colony. They do many important jobs including:                         Consequently, here the details of the foraging process are
collecting nectar to make food, raising and bringing up the            presented to make a base for our nature-inspired method. It is
broods and larvae’s, guarding and ventilating the hive. But,           a hybrid adaptation from the process of honeybees in
the primary resourceful task of the worker-bees is collecting          collecting nectar to make honey and royal jelly. The
the nectars and pollens from the flower patches (forage                proposed ABCRna method solves the secondary structure
field). Later, when they back to the hive the worker bees              prediction problem of RNA with pseudoknots. The idea is
secret the honey and royal jelly (food).                               stimulating a hybrid novelty swarm-intelligence approach
                                                                       from collecting nectar and making honey in the natural
                                                                       secretion process. ABCRna as a new optimization algorithm
D. Honey-bee Collecting Nectar (Foraging)
                                                                       is based on the main features of a hybrid between two
   Honey-bees collecting nectar process to make honey is to            heuristic-based method KnotSeeker [3] and dynamic
be considered as an optimization swarm-based intelligence              programming algorithms UNAFold [26].

                                                                                                 ISSN 1947-5500
                                                                         (IJCSIS) International Journal of Computer Science and Information Security,
                                                                                                                            Vol. 8, No. 8, 2010

      Figure 4. A secreting honey process: the simulation of honeybees                    Figure 5. The Case-Based Reasoning (CBR), a modern Artificial
     collecting nectar to secret honey and royal jelly mapping with a                            Intelligence methodology, adapted from [55].
          diagrammatic representation of the proposed method.

                                                                                   compromise from two main classes of algorithms;
                                                                                   deterministic and probabilistic. Figure 6 shows the general
E. CBR and KB
                                                                                   category of the global optimization methods to clear the
    It’s commonly known that the AI research area provides                         relation among all their characteristics. Definitely, the
many methodologies and technologies for solving complex                            deterministic algorithms are a type of algorithm which take a
problems, which the CBR is one of them. Recently, the CBR                          set of fixed inputs and produce a fixed result. While, the
has been successfully used to restore solution for a new                           heuristic is a single assumption works as a search strategy or
problem based on expertise by retrieving the similar mature                        technique in problem-solving. It is based on intelligence and
solutions of the past problems [55]. Originally, CBR comes                         experience, which can be applied loosely in computer
up from the cognitive science and the human expertise to                           implementation [58]. The meta-heuristic is based-on several
retain and retrieve the information. In another word in CBR                        assumptions work as an optimizer to improve a series of
method, the people solve the new problem by recalling how                          candidate solutions to reach to the final problem solving.
they solved the past similar problems. The CBR method                              Also it may use the many trials iteratively. In 2001, Geem et
includes a problem solving cycle with four main activities:                        al. introduced the Harmony Search (HS) algorithm, which
Retrieve, Reuse, Revise and Retain [56]. According to the                          was a new meta-heuristic algorithm based on natural-inspired
Figure 5, in the heart of this four-RE’s cycle there is a case-                    phenomena behavioral models [59]. The HS has been
library as a Knowledge Base (KB). This KB is used in                               developed from mimicking the natural phenomena of the
retrieval action to assess an intelligent decision of the similar                  musicians improvisation (music players). Several
cases for revising the final outputs by retrieving the most                        experiments proved that the HS as a meta-heuristic
correct solutions.                                                                 algorithm, is capable to solve the optimization problems with
    By referring to the adhere of exact matching concepts,                         more improved performance. The result makes the HS as a
the CBR is a generic AI methodology in problem solving                             durable meta-heuristic algorithm in solving the NP-complete
[57]. In the proposed ABCRna method, the CBR is deployed                           problems. The Traveling Salesman Problem (TSP) is an
as a modern AI inspired technique with KB to augment the                           example of NP-problem which was solved by HS [60].
result in retrieval steps. The role of CBR is finding the                              Now the main question, Is it feasible to develop a hybrid
current pseudoknotted RNA sub-structure with the exact                             meta-heuristic algorithm for building the pseudoknotted
matching from KB. The KB holds and clusters all real                               RNA structure with good performance and more accurate
pseudoknotted RNA sequences and their known native                                 result? To do this an optimized swarm-based intelligence
structures. If the retrieval one has pseudoknots in its                            algorithm would be inspired as a kind of stimulation from the
secondary structure, then the CBR chooses the current one.                         Artificial Bee Colony (ABC) algorithm [61]. This inspired
This CBR comparing process, enhances the quality of the                            proposal utilizes the ABC to solve the related issue of RNA
predicted pseudoknotted RNA secondary structure.                                   structure in bioinformatics. Moreover, the Particle Swarm
Moreover, it is deployed significantly to be an alternative                        Optimization (PSO) is a distinguished swarm-based
development technique for solving the secondary structure                          intelligence algorithm that models some animal social
prediction problem of RNA with pseudoknots.                                        behavior like fish schooling or swarm of honey-bees [62].
                                                                                   PSO has been proposed by Kennedy in 1995 and has reached
                                                                                   to be an interesting area of knowledge to exploit for
F. Preliminarly in Optimization
                                                                                   developing a new meta-heuristic algorithm by mimicking
   According to the theoretical viewpoint, the optimization                        and inspiring the natural phenomena of animals and colony
methods are branch of the applied mathematics and basically                        insects.

                                                                                                               ISSN 1947-5500
                                                                       (IJCSIS) International Journal of Computer Science and Information Security,
                                                                                                                          Vol. 8, No. 8, 2010

   Figure 6. A schematic diagram of the global optimization methods.

                    IV.    PROPOSED METHOD
    This section explains in details, the new hybrid of derived
ABC algorithm to overcome the pseudoknotted RNA
secondary structure prediction problem. The proposed hybrid                           Figure 7. Workflow of the ABCRna approach for predicting the
ABCRna method is inspired from the swarm-intelligence                                 pseudoknotted RNA secondary structure, some parts adapted [55].
social behavioral model of honey-bees in collecting nectar
and secreting honey, as shown in Figure 7. Hence, the                            algorithm called “ABCRna”, which is derived from the
authors develop ABCRna as a hybrid method in a simple                            original ABC algorithm [24]. It is developed as a hybrid
way to build the secondary structure of RNA molecule with                        adaptation between ABC models with deterministic
pseudoknots. The following sub-sections demonstrate                              constraints and inspired by the intelligence social behaviours
separately the paradigms of designing the proposed method.                       of bees in collecting nectar to secret honey. The proposed
These sub-sections describe the mapping of the all features                      method is applied to solve the pseudoknotted RNA
between the ABC optimized algorithm and the RNA                                  secondary structure prediction problem, which is a kind of
structural prediction problem. The final computational results                   combinatorial NP-complete problem [20].
of ABCRna for RNA structure reveal an optimized better
performance and more accuracy in terms of sensitivity and                            The bees in colony deliberated for collecting nectar and
specificity. Its computer code implementation shows less                         secreting honey and they compromise in three bee groups:
space and time complexities when comparing with other                            employed bees, unemployed bees (onlookers or scouts) and
state-of-the-art methods in solving such RNA prediction                          nurse bees, plus the food sources (flower patches
problem.                                                                         profitability). The first two groups of honeybees (employed
                                                                                 and unemployed) search for the last part which is the rich
    Here, the researchers underline the hybrid adaption                          food sources. The third bee component takes the collected
model as a new derivation from ABC algorithm to solve                            forage (nectar) from the first two groups by process of
RNA prediction problem. It is a first threshold further opens                    regurgitation. After that, the nurse bee starts making honey
the door in front of the other bioinformatics researchers to                     and royal jelly by a popular secretion honey process. The
follow. Furthermore, it gives immense opportunity to expand                      behavioral steps of the bees to carry out the forage collecting
this proposed optimizer in solving such kind of complex bio-                     process, has been shown in Figure 4. Naturally, it can be
computing problems. This is why the AI material already has                      described as follows:
presented in the background section to be a general guidance.
                                                                                 a) Employed bee (Forager): visits several food sources to
                                                                                 collect the harvested crop, in each round-trip foraging
A. Honey-bee Foraging Algorithm                                                  journey. Nectar from many flower patches accumulate and
    The innovative ABC as a swarm-based intelligence                             store in the foragers’ honey stomach (honey sac).
algorithm was deployed particularly based on the honeybee                        b) Nurse bee: working inside the hive and she receive the
natural social behaviours. A few other algorithms have been                      collected nectar from the employed bee (forager) by
derived by inspiring the honeybees swarm behavioral model,                       regurgitation process. After that, the nurse bee starting makes
intelligently [61]. Many researchers have been adapted such                      honey or royal jelly from the associated mixed nectar by
this swarm collective behaviours to solve optimization                           secreting invertase enzyme from the hypopharyngeal gland
combinatorial problems. Herein, we describe a new hybrid                         in her head. The corresponding enzyme assists to split the

                                                                                                              ISSN 1947-5500
                                                                    (IJCSIS) International Journal of Computer Science and Information Security,
                                                                                                                       Vol. 8, No. 8, 2010
complex sugar (sucrose) to two simplifier sugars (fructose                    steps: (i) the employed bee visits many flower patches in
and glucose), which are principal of new well-done honey.                     each round-trip of collecting nectar journey. All gathered
                                                                              nectar is stored in her honey stomach. The employed bee
                                                                              backs to the hive with holding the mixed nectar. Then, she
B. The Classical ABC Algorithm                                                will submit this mixture to the nurse bee.
    The ABC algorithm is a new AI model, which has been                          Moreover, the secretion process of the honey by nurse
stimulated by the collective behavior of the social honeybees                 bee performs in many steps, as follows:
based on swam intelligence. It uses multi-resource and multi-
form to perform the job with full optimization [24]. The                      a) The harvest of the forage (the mixed nectar), has been
ABC algorithm originally is divided into three parts:                         collected from many flowers. By mapping this phase with
employed bees, onlookers and scouts. The employed bee is a                    the RNA related issue, the predicted RNA secondary
hard-worker part in the colony that responsible to collect                    structure is collected from many existed RNA predicted
food. Onlookers part is waiting inside the hive to decide on a                methods, as illustrated in Figure 7.
forage source. Scouts is performed a general search to find                   b) The nurse bee starts make honey by secreting invertase
the food resources.                                                           enzyme from the gland in her head. This enzyme simplifies
                                                                              the sucrose which is a complex sugar in the nectar to two
                                                                              types (fructose and glucose) of simpler sugars, which are
C. Hybrid ABC Algorithm for RNA Structural Prediction                         composed the well done honey. By mapping this with RNA
  Our proposed ABCRna method is a hybrid model based                          structural problem, there is an agent program, which is
on the PSO and it is derived from the original ABC model.                     working like that enzyme. This function re-constructs the
This new derivation of the modified ABC is associated with                    entire secondary structure of RNA sequence with
a specific case corresponding to the pseudoknotted RNA                        pseudoknots from many parts.
secondary structure prediction problem. The worker bee
(employed bee) works as an agent, visits many rich flower
patches (artificial food sources) to collect the nectar.                                  V.    BENCHMARK TESTS AND RESULTS
Thereafter, all collected nectar from many flowers stored in
foragers’ honey stomach, which will be a mixture of nectar                        We evaluated ABCRna on different types of
from several food sources (many flowers). Then, the                           pseudoknotted RNA classes. The proposed method is built to
employed bee (forager) back to the hive from the foraging                     predict the RNA secondary structure with pseudoknots. The
journey with the mixed nectar fills her honey stomach. In                     comparisons of the ABCRna results have been performed by
the hive, the forager submits the crop (collected nectar) to                  measuring the accuracy of its outputs to the outputs that has
the nurse bee in a regurgitation process. Finally, the nurse                  been achieved from FlexStem [29], HotKnots [30] and
bee now is ready to make honey from the corresponding                         pknotsRG [19]. These accuracy measurements compromise
mixture of gathered nectar that submitted by employed bee.                    three statistical notations: (Sensitivity S, Selectivity P and F-
The nurse bee starts secreting the honey or royal jelly                       measure). They can be calculated by applying the following
associated with specific needs of the hive. Here, the final                   formulas, which derived from [63]:
well-done honey is represented the good solutions for the
RNA structural prediction problem. In another words, the                                                      TP
concluding honey in mapping segment, stands for the more                              Sensitivity      =           × 100                          1
                                                                                                           TP + FN
accurate pseudoknotted RNA secondary structure for a
giving primary sequence.
   The central phase of the ABCRna method is a HoneyRna                                Speci icity     =           × 100                          2
                                                                                                           TP + FP
algorithm, which is a modified from ABC algorithm to solve
the pseudoknotted RNA structural prediction method. This
HoneyRna algorithm is illustrated in Figure 7 and computes                        F − measure = 2 ×             ×                × 100,           3
in steps as follows:                                                                                                    +
1: Initialize
                                                                              where TP is represented the True Positive, which denotes the
3:     Place the employed bee on her food sources (many flowers)
                                                                              number of base pairs that are predicted correctly and
4:     Place the nurse bee on hive working to receive mixed nectar
                                                                              presented in the known native structure. FN is represented
5:     Secret enzyme to split the complex nectar to a simpler honey
                                                                              the False Negative, which counts the base pairs that are
6:     Fill the secreting food (honey & royal jelly) in the honeycomb
                                                                              presented in the known native structure, but they are not
7:     Filter the well-done honey from extra water by evaporation
                                                                              reported in the predicted structure. FP is represented the
                                                                              False positive, which denotes the number of base pairs,
8:     Cap and seal the filled cell with food by adhesive wax
                                                                              presented in the native known structure, but they are not in
9: UNTIL (Demanded food is met)
                                                                              predicted structure. F-measure is a single measure that
    In the modified ABC algorithm, each cycle of the                          combines both sensitivity and specificity of the predictor
collecting nectar and secreting honey process includes three                  algorithm in a unique performance measure.

                                                                                                           ISSN 1947-5500
                                                                         (IJCSIS) International Journal of Computer Science and Information Security,
                                                                                                                            Vol. 8, No. 8, 2010

                 (a) Native structure of TMV of length 412 nt.
                                                                                           (b) Structure of TMV predicted by our ABCRna method.

                                                                                      (d) Structure of TMV predicted by HotKnots, 2005 [30].

           (c) Structure of TMV predicted by FlexStem, 2008 [29].

                                                                                      (e) Structure of TMV predicted by PknotsRG,2004 [19].

  Figure 8. Plots of qualitative comparison analysis of TMV structures: (a) The known native secondary structure of TMV molecule. (b) Secondary structure
predicted by our proposed ABCRna method, with highest excellent sensitivity of (92.9%) and specificity (95.6%). (c) Secondary structure predicted by FlexStem
(sensitivity of 44.3% and specificity 44.9%). (d) Secondary structure predicted by HotKnots (sensitivity of 67.1% and specificity 81.0%). (e) Secondary structure
                                               predicted by pknotsRG (sensitivity of 60.0% and specificity 66.7%).
                                                                                                                     ISSN 1947-5500
                                                                                  (IJCSIS) International Journal of Computer Science and Information Security,
                                                                                                                                     Vol. , No. , 2010
     Here, the comparison analysis of the outputs are                                           require an enormous amount of memory (RAM) and run in
performed between our proposed ABCRna method against to                                         exponential time. To reach to a fair comparison, the outputs
the FlexStem [29], HotKnots [30] and pknotsRG [19]. One                                         for these scenarios put out of the result. Also, all five existing
example of this comparison pricess uses the RNA sequence                                        methods (FlexStem [29], HotKnots [30], pknotsRG [19],
tobacco mosaic virus (TMV) from 3’UTR type [64]. The                                            NUPACK [66] and pknotsRE [67]), have been implemented
length of TMV is equal 214 nucleotides (nt), which its                                          in the same machine, a PC Ubuntu 10.04 64-bit Linux OS,
accession number “J02415”. Our proposed ABCRna method                                           with AMD Phenom-II 810 2.6-GHz Quad-Core processor
obtained the highest results, Sensitivity (S = 92.9%) and                                       and Dual Channel 4GB (2x2GB) DDR2-800 Memory
Specificity (P = 95.6%), which are measured according to                                        (RAM).
the known native structure of TMV molecule. The sensitivity
and specificity of FlexStem [29], HotKnots [30] and                                                 Table 1 summarizes the final comparison analysis of the
pknotsRG [19], are listed in the legend of the illustrative                                     results among the predicted RNA structures from our
Figure 8, respectively. Finally, the Figure 8 depicts a                                         proposed ABCRna method and the best ones from FlexStem
qualitative comparison analysis among the output of our                                         [29], HotKnots [30], pknotsRG [19], NUPACK [66] and
ABCRna and the best result of all others methods from the                                       pknotsRE [67] methods. The comparison process has been
literature. This comparison analysis is applied on the                                          done in respects to the three accuracy metrics listed in
secondary structure of TMV RNA molecule, which its                                              Equations (1, 2 and 3). The evaluation of these comparative
images are produced by PseudoViewer software tool [65].                                         results were performed and verified according to the standard
NUPACK [66] and pknotsRE [67] methods cannot predict                                            native structures of each RNA molecule. The analyses show
the secondary structure of RNA sequences in larger than the                                     the results of the ABCRna method are significantly better
length of 200 nt and 150 nt, respectively. The reason behind                                    than the results of other methods from literature, in terms of
                                                                                                sensitivity, specificity and F-measure.
that the both algorithms NUPACK [66] and pknotsRE [67],


                 RNA sequence                      ABCRna (2010)        FlexStem (2008)     HotKnots (2005)          pknotsRG (2004)      NUPACK (2003)        pknotsRE (1999)

                       RNA     Accession Length
 Seq. ID, Ref.                                    S      P      F      S      P      F      S         P        F     S      P       F     S      P      F      S      P      F
                       class   Number     (nt)

 HDV-It_g [68] Ribozymes       X04451     87      90.6   93.5   92.1   84.4   79.4   81.8   71.9      82.1    76.7   90.6   93.5   92.1   62.5   62.5   62.5   81.3   81.3   81.3

 BMV [69]         3’-UTR       J02042     145     73.8   62.0   67.4   45.2   38.8   41.8   31.0      31.7    31.3   47.6   43.5   45.5   45.2   44.2   44.7   45.2   44.2   44.7

 FMDV-A [70]      5’-UTR       AY593751   165     83.3   54.1   65.6   66.7   41.0   50.8   12.5      07.3    09.2   66.7   41.0   50.8   62.5   34.9   44.8    *      *      *

 TMV [71]         3’-UTR       J02415     214     92.9   95.6   94.2   44.3   44.9   44.6   67.1      81.0    73.4   60.0   66.7   63.2    *      *      *      *      *      *

The highest results are in bold, and “*” denotes that the algorithm is unable to complete the run.

                 IV.      CONCLUSION AND FUTURE WORK                                               We believe that the proposed hybrid method have a high
                                                                                                potential with a great efficiency for the problems solved by
    This paper presented a novel hybrid method for solving                                      RNA community. This worthwhile domain is pregnant with
RNA secondary structure with pseudoknot functional                                              several future research directions such as: further study cases
classes. This hybrid method includes ABC model as a global                                      in CBR, different global optimization, different factors of
optimization method, hybridized with CBR as a local                                             analysis and hybridize more RNA prominent methods.
optimization technique. The proposed method used the
existing results from KnotSeeker and UNAFold to generate a
secondary structure of RNA includes pseudoknots, by using                                                                    ACKNOWLEDGMENT
an existing cases.                                                                                  This research was partly supported by a Universiti Sains
    Three evaluation mechanisms are used to measure the                                         Malaysia (USM) Fellowship, awarded to the corresponding
efficiency and performance of proposed method comparing                                         author. It was also funded by "Insentif APEX". The authors
to others from literature. The sensitivity, specificity and F-                                  gratefully acknowledge the reviewers for their helpful and
measure metrics showed that successful outcomes have been                                       useful comments.
recorded. Furthermore, three different comparative methods
are used in order to compare the obtained results. The                                                                             REFERENCES
proposed ABCRna hybrid method outperformed other                                                [1]       R. Williams and O. Luo, "Complexity, Post-genomic Biology and Gene
comparators in almost all standard benchmarks. Note that the                                              Expression Programs," Complex Physical, Biophysical and
                                                                                                          Econophysical Systems: Proceedings of the 22nd Canberra International
factor for comparison is the real native structure.                                                       Physics Summer School, p. 319, 2009.

                                                                                                                                   ISSN 1947-5500
                                                                                 (IJCSIS) International Journal of Computer Science and Information Security,
                                                                                                                                    Vol. 8, No. 8, 2010
[2]    F. Buchholz, R. Kittler, M. Slabicki, and M. Theis, "Enzymatically                          Potential Phospho/Glycoproteins," Journal of Proteome Research, vol. 7,
       prepared RNAi libraries," Nat Meth, vol. 3, pp. 696-700, 2006.                              pp. 3194-3229, 2008.
[3]    J. Sperschneider and A. Datta, "KnotSeeker: Heuristic pseudoknot                     [28]   A. G. O. Yeh and X. Shi, "Case-based reasoning (CBR) in development
       detection in long RNA sequences," RNA, vol. 14, pp. 630-640, April                          control," International Journal of Applied Earth Observation and
       2008 2008.                                                                                  Geoinformation, vol. 3, pp. 238-251, 2001.
[4]    G. Sengle, A. Eisenführ, P. S. Arora, J. S. Nowick, and M. Famulok,                  [29]   X. Chen, S. He, D. Bu, F. Zhang, Z. Wang, R. Chen, and W. Gao,
       "Novel RNA catalysts for the Michael reaction," Chemistry & Biology,                        "FlexStem: improving predictions of RNA secondary structures with
       vol. 8, pp. 459-473, 2001.                                                                  pseudoknots by reducing the search space," Bioinformatics, vol. 24, p.
[5]    J. Mattick, "RNA regulation: a new genetics?," Nature Reviews Genetics,                     1994, 2008.
       vol. 5, pp. 316-323, 2004.                                                           [30]   J. REN, B. RASTEGARI, A. CONDON, and H. H. HOOS, "HotKnots:
[6]    O. Nureki, D. Vassylyev, M. Tateno, A. Shimada, T. Nakama, S. Fukai,                        Heuristic prediction of RNA secondary structures including
       M. Konno, T. Hendrickson, P. Schimmel, and S. Yokoyama, "Enzyme                             pseudoknots," RNA, vol. 11, pp. 1494-1504, October 2005 2005.
       structure with two catalytic sites for double-sieve selection of substrate,"         [31]   W. Tichelaar, W. G. SCHUTTER, A. C. ARNBERG, E. F. J.
       Science, vol. 280, p. 578, 1998.                                                            BRUGGEN, and W. STENDER, "The quaternary structure of
[7]    R. Rambo and J. Tainer, "Bridging the solution divide: comprehensive                        Escherichia coli RNA polymerase studied with (scanning) transmission
       structural analyses of dynamic RNA, DNA, and protein assemblies by                          (immuno)electron microscopy," European Journal of Biochemistry, vol.
       small-angle X-ray scattering," Current Opinion in Structural Biology,                       135, pp. 263-269, 1983.
       vol. 20, pp. 128-137, 2010.                                                          [32]   H. Liu, D. Xu, J. Shao, and Y. Wang, "An RNA folding algorithm
[8]    A. Heck, "Native mass spectrometry: a bridge between interactomics and                      including pseudoknots based on dynamic weighted matching,"
       structural biology," Nature Methods, vol. 5, pp. 927-933, 2008.                             Computational Biology and Chemistry, vol. 30, pp. 72-76, 2006.
[9]    H.-K. Cheong, E. Hwang, C. Lee, B.-S. Choi, and C. Cheong, "Rapid                    [33]   E. Westhof, "Toward atomic accuracy in RNA design," Nat Meth, vol. 7,
       preparation of RNA samples for NMR spectroscopy and X-ray                                   pp. 272-273, 2010.
       crystallography," Nucl. Acids Res., vol. 32, pp. e84-, June 15, 2004 2004.           [34]   T. Xia, J. SantaLucia, M. E. Burkard, R. Kierzek, S. J. Schroeder, X.
[10]   R. M. Al-Khatib, R. Abdullah, and N. Abdul Rashid, "A Comparative                           Jiao, C. Cox, and D. H. Turner, "Thermodynamic Parameters for an
       Taxonomy of Parallel Algorithms for RNA Secondary Structure                                 Expanded Nearest-Neighbor Model for Formation of RNA Duplexes with
       Prediction," Evolutionary Bioinformatics, vol. 6, p. 27, 2010.                              Watson-Crick Base Pairs," Biochemistry, vol. 37, pp. 14719-14735, 1998.
[11]   C. Wilson, J. Nix, and J. Szostak, "Functional Requirements for Specific             [35]   O. Schrader, T. Baumstark, and D. Riesner, "A Mini-RNA containing the
       Ligand Recognition by a Biotin-Binding RNA Pseudoknot†,"                                    tetraloop, wobble-pair and loop E motifs of the central conserved region
       Biochemistry, vol. 37, pp. 14410-14419, 1998.                                               of potato spindle tuber viroid is processed into a minicircle," Nucl. Acids
[12]   A. Roth and R. Breaker, "The structural and functional diversity of                         Res., vol. 31, pp. 988-998, February 1, 2003 2003.
       metabolite-binding riboswitches," Annual review of biochemistry, vol. 78,            [36]   A. Bar-Shira, A. Panet, and A. Honigman, "An RNA secondary structure
       pp. 305-334, 2009.                                                                          juxtaposes two remote genetic signals for human T-cell leukemia virus
[13]   Y. Takakura, "Towards therapeutic application of RNA-mediated gene                          type I RNA 3'-end processing," J. Virol., vol. 65, pp. 5165-5173, October
       regulation," Advanced Drug Delivery Reviews, vol. 61, pp. 667-667,                          1, 1991 1991.
       2009.                                                                                [37]   I. Brierley, S. Pennell, and R. J. C. Gilbert, "Viral RNA pseudoknots:
[14]   P. Menzel, J. Gorodkin, and P. F. Stadler, "The tedious task of finding                     versatile motifs in gene expression and replication," Nat Rev Micro, vol.
       homologous noncoding RNA genes," RNA, vol. 15, pp. 2075-2082,                               5, pp. 598-610, 2007.
       December 2009 2009.                                                                  [38]   M. N. Win and C. D. Smolke, "A modular and extensible RNA-based
[15]   R. M. Al-Khatib, R. Abdullah, and N. Abdul Rashid, "A Survey of                             gene-regulatory platform for engineering cellular function," Proceedings
       Compute Intensive Algorithms for Ribo Nucleic Acids Structural                              of the National Academy of Sciences, vol. 104, pp. 14283-14288,
       Detection," Journal of Computer Science, vol. 5, pp. 680-689, 2009.                         September 4, 2007 2007.
[16]   C. W. A. Pleij, K. Rietveld, and L. Bosch, "A new principle of RNA                   [39]   A. Mathuriya, D. A. Bader, C. E. Heitsch, and S. C. Harvey, "GTfold: a
       folding based on pseudoknotting," Nucl. Acids Res., vol. 13, pp. 1717-                      scalable multicore code for RNA secondary structure prediction," in
       1731, March 11, 1985 1985.                                                                  Proceedings of the 2009 ACM symposium on Applied Computing
[17]   M. Zuker, "Mfold web server for nucleic acid folding and hybridization                      Honolulu, Hawaii: ACM, 2009.
       prediction," Nucl. Acids Res., vol. 31, pp. 3406-3415, July 1, 2003 2003.            [40]   M. Masiero, G. Nardo, S. Indraccolo, and E. Favaro, "RNA interference:
[18]   I. L. Hofacker, "Vienna RNA secondary structure server," Nucl. Acids                        Implications for cancer treatment," Molecular Aspects of Medicine, vol.
       Res., vol. 31, pp. 3429-3431, July 1, 2003 2003.                                            28, pp. 143-166, 2007.
[19]   J. Reeder and R. Giegerich, "Design, implementation and evaluation of a              [41]   T. Schmickl, H. Hamann, H. Wِrn, and K. Crailsheim, "Two different
       practical pseudoknot folding algorithm based on thermodynamics," BMC                        approaches to a macroscopic model of a bio-inspired robotic swarm,"
       Bioinformatics, vol. 5, p. 104, 2004.                                                       Robotics and Autonomous Systems, vol. 57, pp. 913-921, 2009.
[20]   T. Akutsu, "Dynamic programming algorithms for RNA secondary                         [42]   D. Hill and T. Webster, "Apiculture and forestry (bees and trees),"
       structure prediction with pseudoknots," Discrete Applied Mathematics,                       Agroforestry Systems, vol. 29, pp. 313-320, 1995.
       vol. 104, pp. 45-62, 2000.                                                           [43]   S. Ziane and A. Melouk, "A swarm intelligent multi-path routing for
[21]   R. B. Lyngso and C. N. S. Pedersen, "RNA Pseudoknot Prediction in                           multimedia traffic over mobile ad hoc networks," in Proceedings of the
       Energy-Based Models," Journal of Computational Biology, vol. 7, pp.                         1st ACM international workshop on Quality of service & amp; security in
       409-427, 2000.                                                                              wireless and mobile networks Montreal, Quebec, Canada: ACM, 2005.
[22]   Q. Dong and Z. Wu, "A linear-time algorithm for solving the molecular                [44]   Z. Lian, B. Jiao, and X. Gu, "A similar particle swarm optimization
       distance geometry problem with exact inter-atomic distances," Journal of                    algorithm for job-shop scheduling to minimize makespan," Applied
       Global Optimization, vol. 22, pp. 365-375, 2002.                                            Mathematics and Computation, vol. 183, pp. 1008-1017, 2006.
[23]   U. Schِning and M. von Knop, "Using Stochastic Indexed Grammars for                  [45]   W. BRYAN, S. ADRIAN, R. DIRK, and O. JAMES, "UAV Swarm
       RNA Structure PredictionWith Pseudoknots," Bulletin of the EATCS, p.                        Control: Calculating Digital Pheromone Fields with the GPU," The
       185, 2010.                                                                                  Journal of Defense Modeling and Simulation: Applications,
[24]   D. Karaboga, "An idea based on honey bee swarm for numerical                                Methodology, Technology, vol. 3, pp. 167-176, 2006.
       optimization," in Technical Report-TR06, Erciyes University,                         [46]   P. Doherty, P. Haslum, F. Heintz, T. Merz, P. Nyblom, T. Persson, and
       Engineering Faculty, Computer Engineering Department, 2005.                                 B. Wingman, "A Distributed Architecture for Autonomous Unmanned
[25]   H. Chang, "Converging Marriage in Honey-Bees Optimization and                               Aerial Vehicle Experimentation," in Distributed Autonomous Robotic
       Application to Stochastic Dynamic Programming," Journal of Global                           Systems 6, 2007, pp. 233-242.
       Optimization, vol. 35, pp. 423-441, 2006.                                            [47]   E. Bonabeau, M. Dorigo, and G. Theraulaz, "Inspiration for optimization
[26]   N. Markham and M. Zuker, "DINAMelt web server for nucleic acid                              from social insect behaviour," Nature, vol. 406, pp. 39-42, 2000.
       melting prediction," Nucleic acids research, vol. 33, p. W577, 2005.                 [48]   S. Remolina and K. Hughes, "Evolution and mechanisms of long life and
[27]   T. Furusawa, R. Rakwal, H. W. Nam, J. Shibato, G. K. Agrawal, Y. S.                         high fertility in queen honey bees," AGE, vol. 30, pp. 177-185, 2008.
       Kim, Y. Ogawa, Y. Yoshida, Y. Kouzuma, Y. Masuo, and M. Yonekura,                    [49]   D. Karaboga and B. Akay, "A comparative study of Artificial Bee
       "Comprehensive Royal Jelly (RJ) Proteomics Using One- and Two-                              Colony algorithm," Applied Mathematics and Computation, vol. 214, pp.
       Dimensional Proteomics Platforms Reveals Novel RJ Proteins and                              108-132, 2009.

                                                                                                                             ISSN 1947-5500
                                                                             (IJCSIS) International Journal of Computer Science and Information Security,
                                                                                                                                Vol. 8, No. 8, 2010
[50]   I. Cakmak, C. Sanderson, T. D. Blocker, L. Lisa Pham, S. Checotah, A.            [62]   J. Kennedy and R. Eberhart, "Particle swarm optimization," in Neural
       A. Norman, B. K. Harader-Pate, R. Tyler Reidenbaugh, P. Nenchev, J. F.                  Networks, 1995. Proceedings., IEEE International Conference on, 1995,
       Barthell, and H. Wells, "Different solutions by bees to a foraging                      pp. 1942-1948 vol.4.
       problem," Animal Behaviour, vol. 77, pp. 1273-1280, 2009.                        [63]   P. Baldi, S. Brunak, Y. Chauvin, C. Andersen, and H. Nielsen,
[51]   T. D. Seeley, "Social foraging by honeybees: how colonies allocate                      "Assessing the accuracy of prediction algorithms for classification: an
       foragers among patches of flowers," Behavioral Ecology and                              overview," Bioinformatics, vol. 16, p. 412, 2000.
       Sociobiology, vol. 19, pp. 343-354, 1986.                                        [64]   F. H. D. van Batenburg, A. P. Gultyaev, and C. W. A. Pleij,
[52]   T. D. Seeley, A. S. Mikheyev, and G. J. Pagano, "Dancing bees tune both                 "PseudoBase: structural information on RNA pseudoknots," Nucl. Acids
       duration and rate of waggle-run production in relation to nectar-source                 Res., vol. 29, pp. 194-195, January 1, 2001 2001.
       profitability," Journal of Comparative Physiology A: Neuroethology,              [65]   Y. Byun and K. Han, "PseudoViewer3: generating planar drawings of
       Sensory, Neural, and Behavioral Physiology, vol. 186, pp. 813-819,                      large-scale RNA structures with pseudoknots," Bioinformatics, vol. 25, p.
       2000.                                                                                   1435, 2009.
[53]   K. R. Abbott and R. Dukas, "Honeybees consider flower danger in their            [66]   R. Dirks and N. Pierce, "A partition function algorithm for nucleic acid
       waggle dance," Animal Behaviour, vol. 78, pp. 633-635, 2009.                            secondary structure including pseudoknots," J Comput Chem, vol. 24, pp.
[54]   T. Kubo, M. Sasaki, J. Nakamura, H. Sasagawa, K. Ohashi, H. Takeuchi,                   1664 - 1677, 2003.
       and S. Natori, "Change in the Expression of Hypopharyngeal-Gland                 [67]   E. Rivas and S. R. Eddy, "A dynamic programming algorithm for RNA
       Proteins of the Worker Honeybees (Apis melliferaL.) with Age and/or                     structure prediction including pseudoknots," Journal of Molecular
       Role," J Biochem, vol. 119, pp. 291-295, February 1, 1996 1996.                         Biology, vol. 285, pp. 2053-2068, 1999.
[55]   A. Aamodt and E. Plaza, "Case-based reasoning: foundational issues,              [68]   M. D. Been and G. S. Wickham, "Self-Cleaving Ribozymes of Hepatitis
       methodological variations, and system approaches," AI Commun., vol. 7,                  Delta Virus RNA," European Journal of Biochemistry, vol. 247, pp. 741-
       pp. 39-59, 1994.                                                                        753, 1997.
[56]   I. Watson, "Case-based reasoning is a methodology not a technology,"             [69]   C. W. A. Pleij, J. P. Abrahams, A. v. Belkum, K. Rietveld, and L. Bosch,
       Knowledge-Based Systems, vol. 12, pp. 303-308, 1999.                                    "The spatial folding of the 3' noncoding region of aminoacylatable plant
[57]   L. Portinale, D. Magro, and P. Torasso, "Multi-modal diagnosis                          viral RNAs," M. Brinton and R. Ruecker, Editors, Positive Strand RNA
       combining case-based and model-based reasoning: a formal and                            Viruses, A. R. Liss, New York (1987), pp. 299–316, 1987 1987.
       experimental analysis," Artificial Intelligence, vol. 158, pp. 109-153,          [70]   B. E. Clarke, A. L. Brown, K. M. Currey, S. E. Newton, D. J. Rowlands,
       2004.                                                                                   and A. R. Carroll, "Potential secondary and tertiary structure in the
[58]   J. Pearl, Heuristics: Intelligent search strategies for computer problem                genomic RNA of foot and mouth disease virus," Nucleic Acids Research,
       solving, 1984.                                                                          vol. 15, pp. 7067-7079, September 11, 1987 1987.
[59]   Z. Geem, J. Kim, and G. V. Loganathan, "A New Heuristic Optimization             [71]   R. Koenig, S. Barends, A. P. Gultyaev, D.-E. Lesemann, H. J. Vetten, S.
       Algorithm: Harmony Search," SIMULATION, vol. 76, pp. 60-68, 2001.                       Loss, and C. W. A. Pleij, "Nemesia ring necrosis virus: a new tymovirus
[60]   K. S. Lee and Z. W. Geem, "A new structural optimization method based                   with a genomic RNA having a histidylatable tobamovirus-like 3' end," J
       on the harmony search algorithm," Computers & Structures, vol. 82, pp.                  Gen Virol, vol. 86, pp. 1827-1833, June 1, 2005 2005.
       781-798, 2004.
[61]   D. Karaboga and B. Basturk, "On the performance of artificial bee colony
       (ABC) algorithm," Applied Soft Computing, vol. 8, pp. 687-697, 2008.

                         Ra'ed M. Al-Khatib received his Bachelors                                               Nur’Aini Abdul Rashid received her Bachelor's
                         degree in Computer Science from Mu'tah                                                  Degree in Computer Science from Mississippi
                         University, Karak, Jordan in 1993 and Masters                                           State University, U.S.A. in 1985. She joined the
                         Degree in Computer Engineering-Embedded                                                 School of Computer Sciences at Universiti Sains
                         System from Yarmouk University, Irbid, Jordan in                                        Malaysia in 1988 as a tutor. She received her
                         2006. He is currently a researcher at the Parallel                                      Master's Degree in Computer Sciences from
                         and Distributed Processing Research Group and a                                         Universiti Sains Malaysia, Penang, Malaysia in
                         PhD candidate as well under the supervision of                                          1995. She continued in the School of Computer
                         Professor Dr. Rosni Abdullah and Associated                                             Sciences at Universiti Sains Malaysia as a lecturer
                         Professor Dr. Nur'Aini Abdul Rashid at the School                                       from 1995. She received an award from USM in
                         of Computer Sciences, Universiti Sains Malaysia                                         2002 to pursue her PhD at Universiti Sains
                         in the area of Parallel Algorithms Applied to                                           Malaysia, Penang in the area of Parallel methods.
                         Bioinformatics Applications.                                                            She was promoted to Senior Lecturer in 2004. She
                                                                                                                 is currently an Associate Professor in the School of
                         Rosni Abdullah received her Bachelor's Degree in                                        Computer Sciences and also member of the
                         Computer Science and Applied Mathematics and                                            Parallel and Distributed Processing Research
                         Masters Degree in Computer Science from                                                 Group which focus on grid computing and
                         Western Michigan University, Kalamazoo,                                                 bioinformatics research. Her current research work
                         Michigan, U.S.A. in 1984 and 1986 respectively.                                         is in the area of Parallel Algorithms applied to
                         She joined the School of Computer Sciences at                                           Bioinformatics Applications, Genomic Information
                         Universiti Sains Malaysia in 1987 as a lecturer.                                        Retrieval, Text Search and Comparison Methods.
                         She received an award from USM in 1993 to
                         pursue her PhD at Loughborough University in
                         United Kingdom in the area Parallel Algorithms.
                         She was promoted to Associate Professor in 2000
                         and to Professor in 2008. She has held several
                         administrative positions such as First Year
                         Coordinator, Programme Chairman and Deputy
                         Dean for Postgraduate Studies and Research. She
                         is currently the Dean of the School of Computer
                         Sciences and also Head of the Parallel and
                         Distributed Processing Research Group which
                         focus on grid computing and bioinformatics
                         research. Her current research work is in the area
                         of Parallel Algorithms for Bioinformatics

                                                                                                                        ISSN 1947-5500