Presentation is loading. Please wait.

Presentation is loading. Please wait.

DNA Barcode Data Analysis Boosting Accuracy by Combining Simple Classification Methods CSE 377 – Bioinformatics - Spring 2006 Sotirios Kentros Univ. of.

Similar presentations


Presentation on theme: "DNA Barcode Data Analysis Boosting Accuracy by Combining Simple Classification Methods CSE 377 – Bioinformatics - Spring 2006 Sotirios Kentros Univ. of."— Presentation transcript:

1 DNA Barcode Data Analysis Boosting Accuracy by Combining Simple Classification Methods CSE 377 – Bioinformatics - Spring 2006 Sotirios Kentros Univ. of Connecticut Bogdan Paşaniuc

2 2 Outline Motivation Problem Definition The Methods  Hamming Distance and Minimum Hamming Distance  Aminoacid Similarity and Minimum Aminoacid Similarity  Dinucleotide Distance  Trinucleotide Distance  Nucleotide Frequency Similarity Combining the Methods Results  Specie Classification  New Specie Recognition Conclusion Future Work

3 3 Motivation “DNA barcoding” was proposed as a tool for differentiating biological species Goal: To make a “finger print” for species, using a short sequence of DNA Assumption: mitochondrial DNA evolve at a lower rate than regular DNA Mitochondrial DNA: High interspecie variability while retaining low intraspecie sequence variability Choice was cytochrome c oxidase subunit 1 mitochondrial region ("COI", 648 base pairs long).

4 4 Problem definition The scope of our project was to explore if by combining simple classification methods one can increase the classification accuracy. We address two problems: Classification of individuals given a training set of species. Identification of individuals that belong in new species. All the sequences are aligned

5 5 Problem definition Specie differentiation:  INPUT: a set S of aligned DNA sequences for which the specie is known and x a new sequence  OUTPUT: find the specie of x, given that there are sequences in S that have the same specie as x

6 6 Problem definition Specie differentiation&New Specie Determination:  INPUT: a set S of aligned DNA sequences for which the specie is known and x a new sequence  OUTPUT: find the specie of x, if there is at least a sequence in S with the same specie or determine if it is a new specie.

7 7 Methods Used Hamming Distance and Minimum Hamming Distance Aminoacid Similarity and Minimum Aminoacid Similarity Dinucleotide Distance Trinucleotide Distance Nucleotide Frequency Similarity

8 8 Methods Specie S1 x d(x,S1) Specie S2 d(x,S2) … Specie Sn d(x,Sn) 1.d(x,Si) = Minimum{ d(x,y) | sequence y belongs to specie Si } Notation: Minimum “Method” Classifier 2.d(x,Si) = Average{ d(x,y) | sequence y belongs to specie Si } Notation: “Method” Classifier

9 9 Hamming Distance Average:  Given new sequence x find specie S such that the minimum hamming distances on the average from x to y (y in S) is minimized  Assign to S to y Minimum  Given new sequence x find y such that the minimum hamming distance from x to y is minimized  Assign specie(y) to x

10 10 Aminoacid Similarity Genetic code:  rules that map DNA sequences to proteinsDNA sequencesproteins  Codon: tri-nucleotide unit that encodes for one aminoacid  Divide DNA seq. into codons and substitute each one by its corresp. aminoacid Blosum62 (BLOck SUbstitution Matrix)  20x20 matrix that gives score for each two aminoacids based on aminoacid properties  The higher the score the more likely no functional change in the protein

11 11 Aminoacid Similarity Distance(x,y)  DNA sequences x, y ->Aminoacid sequences x’, y’ (using codon to aminoacid transf.)  Using the Blosum aminoacid substitution matrix get the score of the alignment Average:  Find the specie with maximum average similarity Minimum:  Find the sequence with max. similarity

12 12 Dinucleotide Distance For each specie find the frequency with which each Dinucleotide appears. Compute the frequency of each Dinucleotide in the unclassified sequence. Find the specie with the minimum Mean Square distance to the new unclassified sequence For New Species, after classifying the individual find the Average Intraspecie Mean Square distance for the candidate specie. If the individual is close enough, assign him at the specie, otherwise he belongs in a New Specie. in/dels are ignored

13 13 Trinucleotide Distance For each specie find the frequency with which each Trinucleotide appears. Compute the frequency of Trinucleotide appearance of the unclassified sequence. Find the specie with the minimum Mean Square distance to the new unclassified sequence For New Species, after classifying the individual find the Average Intraspecie Mean Square distance for the candidate specie. If the individual is close enough, assign him at the specie, otherwise he belongs in a New Specie. in/dels are ignored

14 14 Nucleotide Frequency Similarity For each position in the DNA find the frequency with which the Nucleotides appear in the specie individuals. We include the frequency of in/dels appearing. For unclassified individuals compute the log of the probability that the individual belongs to the specie and assign it to the specie for which the probability is maximum. For new species, we compute the minimum probability for the individuals belonging in the specie and compare it with the one of the candidate specie in order to determine whether it belongs to the specie or not.

15 15 Combining the Methods The specie on which most classifiers agreed is returned Simple Voting:  Every classifier’s returned specie has a weight of 1  Output the specie with the most votes Weighted Voting  Every classifier has a different weight based on the accuracy of each independent method  Output the specie with largest total As expected weighted voting yields higher accuracy and thus in our results the combined method uses weighted voting

16 16 Datasets(1) We used the dataset provided at http://dimacs.rutgers.edu/workshops/BarcodeResearchchallanges consisting of 1623 aligned sequences classified into 150 species with each sequence consisting of 590 nucleotides on the average. http://dimacs.rutgers.edu/workshops/BarcodeResearchchallanges We randomly deleted from each specie 10 to 50 percent of the sequences  Deleted seq -> test  Remaining seq -> train We made sure that in every specie has a least one sequence

17 17 Methods Percent missing from each specie(%) 1020304050 Aminoacid Similarity 95.194.894.794.393 Min. Aminoacid Similarity 99.399.298.798.197.3 Hamming Dist.97.997.496.796.5 Min. Hamming Dist. 98.898.297.597.196.4 Nucleotide Freq Sim. 56.249.644.244.638.2 Dinucleotide Freq. Dist. 44.942.241.641.539.3 Trinucleotide Freq. Dist 70.968.16866.764.2 Combination 99.2 98.898.397.7 Specie Recovering Accuracy(in %) (no new specie)

18 18 Datasets(2) In order to test the accuracy of new specie detection and classification we devised a regular leave one out procedure. delete a whole specie randomly delete from each remaining specie 0 to 50 percent of the sequences  Deleted seq -> test  Remaining seq -> train The following table gives accuracy results on average for 150x6 different testcases

19 19 Methods Percent missing from each remaining specie(%) 01020304050 Aminoacid Similarity 65.149.243.642.041.037.4 Min. Aminoacid Similarity 72.661.056.256.452.651.0 Hamming Dist. 55.091.490.290.488.088.6 Min. Hamming Dist. 73.185.479.678.675.074.4 Dinucleotide Freq. Dist. 51.050.448.2 45.243.4 Trinucleotide Freq. Dist 56.563.661.863.059.257.4 Nucleotide Freq Sim. 73.056.249.644.244.038.2 Combination 80.593.291.6 88.488.6 Leave one out Accuracy(in %)

20 20 Conclusions(1) Every method show a tradeoff between new specie detection and classification accuracy Hamming distance performs very good when no new species are present but the accuracy results are low for new specie detection The combined method yields better accuracy results both on new specie detection and seq. classification. The runtime of all methods is within same order of magnitude

21 21 Conclusions(2) By combining simple classification methods, we managed to boost the accuracy both for classifying individuals in known species and for detecting new species As expected the results imply a tradeoff between classification and new specie detection  the higher the classification accuracy the lower the detection Hamming Distance is a very good metric for the training dataset provided

22 22 Future Work New specie clustering: determining the different new species present Further investigate threshold selection and weighting schemes. Possible ignoring parts of the given sequences could improve accuracy. Are there redundant/noisy regions? Use independent weighting schemes for new specie detection and classification into known species.

23 23 Questions Thank you.


Download ppt "DNA Barcode Data Analysis Boosting Accuracy by Combining Simple Classification Methods CSE 377 – Bioinformatics - Spring 2006 Sotirios Kentros Univ. of."

Similar presentations


Ads by Google