CONTENTS:I. ABSTRACT II. INTRODUCTION III. EARLIER MEASURES IV.

NEWER APPROACHES a) b) c)
USING NEURAL NETWORKS USING CELLULAR AUTOMATA DISTRIBUTED DATABASES

2 3 5 7
7 13 18

V. TWO STAGE CLASSIFIER VI. FUTURE WORKS VII. CONCLUSION VIII. REFERENCES
1|Pa ge

21 23 24 24

PROTEIN CODING REGION IDENTIFICATION
Abstract:- Genes carry the instructions for making proteins that are found in a cell as a specific sequence of nucleotides in DNA molecules. These specific sequences of bases encode instructions on how to make protein. But the regions of gene that code for proteins may occupy only a small region of a sequence. The problem of gene recognition is to define an algorithm which takes as input DNA sequence and produces as output a feature table describing the location and structure of the patterns making up any genes present in the sequence. Identifying the coding region is of vital importance in understanding these genes. Here I have given certain pattern classifiers which will the test data set presented by fickett and tung to identify protein coding regions. Firstly we have considered some of the test data set using earlier measures for PCRI. We have described some of them not all Then we have proposed both Feed Forward connectivity and Backpropagation approach of neural networks for test data identification. We have found a highly accurate but space consuming CRM module. We have compared its results Then we propose cellular automata based pattern classifier to identify the coding region of a DNA sequence both in centralized and distributed databases. CA is simple efficient and produces more accurate classifier than that have previously been obtained for a range of different sequence lengths. And we have compared some of the older measures with FMACA based pattern classifier. At the end a genetic algorithm based two-stage pattern classifier was used to solve the PCRI. And although implementation was not done but we have found its effectiveness in various other data bases and suitable work can be done in this direction.

2|Pa ge

There are two types of regions Coding and Non-coding.N C N h t is P otein Coding egion dentifi tion? It is a technique to identify the coding (EXONS) and non coding (INTRONS) region in a protein coding base.Protein Synthesis in a DNA 3|Page . Our objective is to define an algorithm which takes an input DNA sequence and produces an output a feature table describing the location and structure. A protein coding gene basically found in a t -RNA It is any pattern in a DNA sequence It results in the generation of protein product through a process known as transcription. Fig 1:.

A great many ideas have been suggested for recognition of the components of genes. 2. Finding Protein coding regions these sequences biochemicall is time consuming and expensi e. How to build an algorithm for PCRI? A natural overall approach to building gene recognition algorithms is to first construct component algorithms that recogni e the major features of genes: statistical bias in Exon sequence. etc. enhancers. Fig 2:. It i i . It can be a good mechani m for genetic engineering. 4. 3.. Possibilit exists of using computational procedures to anal l i i i t t i t i e raw base sequence information and to predict coding regions (as well as other signal regions) by the use of duplicate fragments. promoters. the patterns at Intron junctions.How to Develop an Algorithm 4|Page . but for a systematic approach to building a comprehensive recognition algorithm one thing is still missing. and then to build a combined algorithm that recogni es when all these component patterns occur in a pattern consistent with that present in a gene . namely an objective comparison and evaluation of the competing recognition techniques.bje tives of PC :1.

According to Fickett and tung there are 21 coding measures I.It is again a vector of the 440 amino acids frequency which are obtained by translating from nucleotide sequence to an amino acid string Fig 3:. Codon usage Measure :. Open Reading Frame Measure:. Dicodon Measure:. If f(b. Hyper plane Equation was used. It contains an entry which gives longest contiguous subsequence that has all entries from s V.The extent to which the nucleotide is distributed over the three codon positions. IV. Position asymmetry measure: . VII.i) is the frequency of base b over position I and (b) = ™i f( b.(b) )2 VI. i )/3 Asymmetry is defined as assymm(b) = ™i ( f( b .It is the vector of 4096 dicodon frequencies of every possible dicodon where the dicodon counts are accumulated at sights whose starting point is multiple of 3.The Run feature is a vector of length 14 for each non trivial subset S = {A.ARL R MEASURES:A.G.The codon usage feature is a vector of 64 codon frequencies. II.C.It is simply the longest sequence of codons that do not contain a stop codon. Measures for Protein Coding regions Identifications Definition:.T}.Training Set of Fickett And Tung DataBase 5|Page .They are offset by 1& 2 and similar to dicodon measure III. Diamino Acid Usage measure :. Hexamer-1 & 2 :. Run Measure: .A coding measure is a vector of measurements on a DNA sequence. i ) .

Types of approaches Direct approach: Look for stretches that can be interpreted as protein using the genetic code Example: Open reading Frame measure Statistical approaches: Use other knowledge about likely coding regions Example: Dicodon usage Fig 4:-Open Reading Frame Measure Calculation Windows: Many sequence analyses require calculating some statistic over a long sequence looking for regions where the statistic is unusually high or low To do this. we define a window si e to be the width of the region over which each calculation is to be done 6|Page .B.

7|Pa ge . combined with an internal function. Weights:. It receives a set of input signals and. VII. II. Unsupervised learning:. they consist of many units connected to each other by variable strength links layer and one µoutput¶ layer ± and are known as µperceptrons¶. VI. VIII. Using neural networks:I.Name of this network is due to the direction of flow of the data. the neural network should be capable of predicting an output given a previously unseen set of inputs. But we can have multiple layer also.the task for the network is to relate the variables it receives in the input layer to some desired behaviour at the output layer by repeatedly presenting the examples to the network in a process known as training. Learning:.Unsupervised learning does not require a desired response (and therefore output data) to train and is concerned with discovering a common set of features across the input data in one class or pattern. converts the input signals to an output signal. This training is known as supervised learning IV.NEWER APPROACHES:1. So What we get a measure for learning. Once trained.Neural networks were originally conceived as computational models of the way in which the human brain works. Processing:-The unit (also known as a neuron or node) is the main processing element of the neural network.The errors incurred during learning are propagated back through the network. Feed-Forward Approach:. Like the human brain. Back Propagation:.The simplest neural networks there are only two layers ± one µinput¶ III. V.It is a number associated with a node which decreases or increases with each learning. Archi ecture :. Defi i i :.

.Preceptron Learning Rule Where w (t) is the weight value at time t. Adapt the weights: (a) if correct w (t + 1) = w (t).i (t). . 2. i ) and the desired output (o) data to the network 3.PERCEPTRON LE RNING RULE 1. ¡ ¡ ¡ ¡ ¡ ¡   ¡ ¡ Fig 1:. Calculate the output from the network using the expression: f (s) 4. i3 . w (t + 1) is the weight value at time t + 1 (i. Present the input data (1. (c) if output is 1 and should be 0 w (t + 1) = w (t) . after updating) and f (s) is the function used to compute the output in the network 8|Page . Initiali e the network weights and unit thresholds to some small random values.e. i2. (b) if output is 0 and should be 1 w (t + 1) = w (t) + i (t).

. i ) and the desired output (o) data to the network.BackPropagation 9|Page ¢ . starting from the output layer and moving backwards using the equation Wij (t + 1) = wij (t) + pjopj d is the desired output.Backpropagation:1. i3 . 2. Adapt the weights. 3. Calculate the output from the network using the expression f (s) ] for each layer in the network. The output from the final layer is the vector of output values. o is the actual output c is a constant used in the sigmoid function. i2. 4. . Initiali e the thresholds and weights. Present the input data (i1. The sum shown for hidden layers is over the k nodes in the layer above the current layer for which the pj will already have been computed Fig 6:.

Feed Forward Connectivity:I.Feed Forward Connectivity Fig 1:.s sixsi Where si represents the probability of codon s at position i p (T {Xi})=1/(1 + exp(™sTsNs + )) Ts = log ( qs + ps ) And = log (p (f)/p (t)) Fig 7:. Given a collection of examples labeled true or false for exons it is true for introns it is false II. Assuming that individual codon positions are independent of the codons p({Xi} T)=šI. III.Protein Synthesis in a DNA Fig 1:.Protein Synthesis in a DNA 10 | P a g e . We can employ a supervised Neural Network by using Bayes theorem p(T {Xi}) = p({Xi} T)p(T)/{p({Xi} T)p(T)+p({Xi} F)p(F)} Here P(t) and p(f) are the priori probabilities of the true class and false class.

3.CRM Based Approach:1. To determine the likely hood of a given sequence position a program written in C language is used which calculates the sensors Values for a 99 base sequence and the sensor signals between 0. 2 Hidden layers of 14 and 5 nodes . The Coding Module is used to find exons or parts of exons that encode protein.0 and 1. and an output node. CRM means Coding Recognition Module. 6. 2.0 are then evaluated. This network is consisting of 7 input nodes . In the following table we will see that it is a very accurate algorithm Fig 10:. 5. 4. A back propagation neural net was created to integrate the output from the 7 sensors Algorithms.Using A CRM Module 11 | P a g e .

Fig 11:.Table showing a Database comparison for CRM NOTE:.we see that our classifier almost gives a 99% accuracy. 12 | P a g e .

qi+1(t) ) Fuzzy Cellular Automata:An elementary FCA is a linear array of cells which evolves in time. qi(t) . Each cell of the array assumes a state qi. the next state qi(t+1) of a cell is assumed to be dependent only on itself and on its two neighbours (left and right). as noted in is an inverted tree.2. Using Cellular Automata:A Cellular Automaton (CA) can be viewed as an autonomous finite state machine (FSM) consisting of a number of cells.1] (fuzzy states) and changes its state according to a local evolution function on its own state and states of its two neighbours. In a 3-neighborhood dependency. each rooted on a cyclic state. ‡ The transient states finally settles down to one of the attractor basins after passing through a lot of intermediate states. ‡ Each component. a rational value in the interval [0. FMACA:‡ A FMACA is a special class of FCA that can efficiently model an associative memory to perform pattern recognition/classification task ‡ Its state transition behaviour consists of multiple components . and is denoted as qi(t+1)=f(qi-1(t) .State diagram of 3 cell 3 state FMACA 13 | P a g e . ‡ A cycle in a component is referred to as an attractor. Fig 12:. The global evolution results from synchronous application of the local rule to all cells of the array.

Step 2. then repeat the steps 1 to 4.e. Step 3. 14 | P a g e . The elements of the training set S get distributed into k attractor basins/nodes. FMACA with k attractor basins is generated. Otherwise if S/ belongs to more than one class. Step 4. Let S/ be the set of elements in an attractor basin.FMACA BASED K-means clustering Algorithm:Algorithm 1:Step 1. Step 5. all patterns of S/ are covered by an attractor basin/node belonging to only one particular class). then mark it as a leaf node and label that attractor basin/node as that class. We show the algorithmic approach on building a tree classifier. Stop. If S/ belongs to any one particular class (i.

Less number of nodes leading to low memory overhead 3. From a one dimensional point of view a DNA sequence contain characters from a 4-letter base pair S = {A. C. We have followed this procedure in our study and we have used the benchmark human dna database developed fickett and tung. Small tree height leading to low retrieval time. An important issue in applying FMACA works to DNA sequence classification is how to encode DNA sequences as the input of the FMACA based tree structure classifier. SSdistances =™ x-C(x)2] where C(x) is the mean of the cluster that DNA position x is assigned to Minimizing the SSdistances is equivalent to minimizing the Mean Squared Error (MSE) Wrong to state that lesser MSE means better classifications The basic criteria for FMACA tree design are: 1. Thus good implementation must be the focus.Implementation:For using a FMACA based classifier we need a limited window for eg 100 base pairs which can be used for standard experimental observations and it computes the features of that window alone. Errors and other Benchmarks:The objective function (which is to be minimized) is the sums of squares distances of each DNA sequence and its assigned cluster centres. Time complexity is O(n) By using Dependency Vector scheme 15 | P a g e . Low error rate leading to maximum classification accuracy. 2. The goal is to identify whether the entirely all-coding or all-non coding. T}. G.

16 | P a g e .Here we have compared with some of the other measures and found out that our FMACA based classifier is indeed a very accurate classifier. We have shown that in the graphs below. And also takes very less memory overhead and retrieval time.

FMACA INTERFACE 17 | P a g e .Fig 12:.

18 | P a g e . ` the base classifier at each local site must have high classification accuracy ` it must be scalable to handle disk resident datasets. ISSUES IN DISTRIBUTED DATABASES ` The aggregation of the base classifiers ` The communication cost from different local data sources to the central location where final classification is performed.DISTRIBUTED DATABASES ` Distributed classifiers work in ensemble learning approach ` Multiple classifiers as base classifiers at different data sources. ` Results derived out of base classifiers are next combined at central location to enhance the classification accuracy of predictive models. ` It should have high throughput with less storage requirements ` Volume of data transferred from each local to central site should be minimum ` Aggregation of base classifiers must induce globally meaningful knowledge.

We have shown here algorithmic approach for distributed database PCRI 19 | P a g e .

The FMACA based base classifiers (BCi s) are next collected in the centralized location where predictive accuracy is tested with the test set. attrvalj. For Distributed Datasets: Total training set is equally distributed to each local site and then same scheme is employed at each local site to synthesize the FMACA. Every sequence is labeled according to whether it is entirely coding. which makes the problem of identifying coding regions somewhat harder. Comparison: All the attributes in a dataset are normalized to facilitate FMACA learning. The predictive accuracy of the proposed scheme is evaluated through the majority voting scheme. They have surveyed and compared it. then the normalized value of attrvalij i £ 20 | P a g e . For the first dataset. Coding Measure: Typically. non-overlapping human DNA sequences of length 54 have been extracted from all human sequences. The tree then classifies the Test Set. 2. There are 21 coding measures. The benchmark human data include three different datasets.Experimental observation 1. and the real value that class element j takes at attri is attrvalij. entirely non-coding. or mixed. a coding measure is a vector of measurements on a DNA subsequence. the possible value range of an attribute attri is (attrvali. 3. The dataset also includes the reverse complement of every sequence.max). and the mixed sequences are discarded. with shorter pieces at the ends discarded. 4. For Centralized Datasets: There is use of a training set exclusively to construct a FMACA tree based structured pattern classifier. This means that one-half of the data is guaranteed to be from the non-sense strand of the DNA. Suppose.min.

21 | P a g e .

We see as in below GA employed will significantly decrease the memory overhead 22 | P a g e .

Can be used to distinguish between different kinds of genes.FUTURE WORKS 1. Can be used successfully to locate a cancerous protein coding region 2. Can be used to genetically build protein Which can ensure higher immunity 3. ADVANTAGES 1. Fig 13:. Use of GA in FMACA classifiers 3. 2. Use of SVM {Support Vector Machines}.CANCER Treatment by Knowing The protein Code 23 | P a g e . Use of NNt Tree classification For MLP(multi layer perceptron) for better 4. Use of autoregressive modelling approach for introducing better Protein coding region identification.

Cattaneo. 1992. "Fuzzy Cellular Automata For Modeling Pattern Classifier. 5.Pal Chaudhuri. Fickett. pp. Wolfram. Natl. 15. Santoro (1993).. J. and K. Mauri. vol. 11. Thereby a lot of new opportunities emerge.. 8.CONCLUSION:So hereby conclude that by using efficient PCRI we can successfully make corrections to faulty genes. 6441-6450.. ´On The Relationship Between Boolean and Fuzzy Cellular Automata´ Pradipta Maji and P. Lapedes." Proc. A New Kind of Science (2002). Chandrama Shaw. ³Fuzzy Cellular Automata for Modeling Pattern Classifier´. pp. 2. Angelo B. Samik Barua. USA. 88. R. It is not far when our dream of becoming immortal and space travellers will come true. REFERENCES:1.. Heather Betel and Paola Flocchini. "Recognition of protein coding regions in dna sequences. Mural. J. F. Flocchini. Biplab K. 3. pp.Pal Chaudhuri. Mol. 13. Fuzzy cellular automata and their chaotic behavior. and N. Knowledge Discovery in Distributed Biological Datasets Using Fuzzy Cellular Automata Pradipta Maji. 20. pp. 5303-5318. vol. A. S. Hawaii. Sumanta Das. pp. G. 10. 7. Tung. S. Sci. 16. 4. 1992. G. Uberbacher and R. 1991 P. Mingarelli(2007). Pradipta Maji and P. vol. 14. Geurts. International Symposium on Nonlinear Theory and its Applications. 1285-1289. ³Fuzzy Cellular Automata Based Associative Memory for Pattern Recognition´ Pradipta Maji and Chandra Das . IEICE Volume 4. 2000. "Assessment of protein coding measures. Wolfram Media. 6. E88-D." Physica D. P. P. 9. April 2005. Mingarelli. Acad. Niloy Ganguly." J. and N. Farber. Maji and P. A study of fuzzy and many-valued logics in cellular automata. 691-702. P Pal Choudhary ³Cellular Automata in protein coding Region Identification ³ 9proceedings of ICISIP-2005 24 | P a g e . vol. P. 471-479. in Proc." Nucleic Acids Res. 226. 12." IEICE Transactions on Information and Systems. Il.Pal Chaudhuri. 1982. Fickett and C.Pal Chaudhuri. Champaign. ³ ³Theory and Application of Cellular Automata for Pattern Classification´ Pradipta Maji and P. Biol. Sirotkin. "Determination of eucaryotic protein coding regions using neural networks and information theory. Sikdar and P. E. Santoro. "Locating protein-coding regions in human dna sequences by a multiple sensor-neural network approach. 1126111265. Flocchini. Chaudhuri. 10. ³Basins of Attraction of Cellular Automata Based Associative Memory and its Rule Space´ Pradipta Maji. vol. "Convergence and Aperiodicity in Fuzzy Cellular Automata: Revisiting Rule 90." Nucleic Acids Res. A.

25 | P a g e .