Volume 11 Supplement 1
MTar: a computational microRNA target prediction architecture for human transcriptome
© Chandra et al; licensee BioMed Central Ltd. 2010
Published: 18 January 2010
MicroRNAs (miRNAs) play an essential task in gene regulatory networks by inhibiting the expression of target mRNAs. As their mRNA targets are genes involved in important cell functions, there is a growing interest in identifying the relationship between miRNAs and their target mRNAs. So, there is now a imperative need to develop a computational method by which we can identify the target mRNAs of existing miRNAs. Here, we proposed an efficient machine learning model to unravel the relationship between miRNAs and their target mRNAs.
We present a novel computational architecture MTar for miRNA target prediction which reports 94.5% sensitivity and 90.5% specificity. We identified 16 positional, thermodynamic and structural parameters from the wet lab proven miRNA:mRNA pairs and MTar makes use of these parameters for miRNA target identification. It incorporates an Artificial Neural Network (ANN) verifier which is trained by wet lab proven microRNA targets. A number of hitherto unknown targets of many miRNA families were located using MTar. The method identifies all three potential miRNA targets (5' seed-only, 5' dominant, and 3' canonical) whereas the existing solutions focus on 5' complementarities alone.
MTar, an ANN based architecture for identifying functional regulatory miRNA-mRNA interaction using predicted miRNA targets. The area of target prediction has received a new momentum with the function of a thermodynamic model incorporating target accessibility. This model incorporates sixteen structural, thermodynamic and positional features of residues in miRNA: mRNA pairs were employed to select target candidates. So our novel machine learning architecture, MTar is found to be more comprehensive than the existing methods in predicting miRNA targets, especially human transcritome.
MicroRNAs (miRNAs) are highly conserved, small but endogenous non-coding regulatory RNAs (18 to 24 nucleotides in length), that regulate gene expression. MicroRNAs can interact with target mRNAs, at specific sites either to induce cleavage of the message or to inhibit translation. Identifying their target mRNAs is vital in understanding cell functions like cell proliferation, differentiation and cell cycle. Also it throws light into the causes of diseases like lymphoma, leukemia, cancers and many cardiac problems where miRNA:mRNA pairing is found to play crucial roles [1, 2].
MicroRNA is first transcribed as longer RNA molecule called pri-miRNA. The pri-miRNA is processed in the nucleus itself into hairpin RNA of 60 to 120 nucleotides by a protein complex consisting of the ribonuclease Drosha and an RNA binding protein Pasha[3, 4]. This hairpin RNA, known as pre-miRNA, is transported to the cytoplasm via exportin-5 dependent mechanism. It is digested there by a dsRNA specific ribonuclease called Dicer to form the mature miRNA. Mature miRNA is bounded by a complex, similar to the RNA induced silencing complex (RISC) that participates in RNA interface (RNAi) [6, 7]. The mature miRNA makes base pairing with mRNA where complementarities exist between them. This results in target degradation in plants and destabilization in animals. In general, miRNAs can regulate gene expression either by translational inhibition or by mRNA destabilization.
Most of the existing solutions search for the complementarities of miRNA, only at the 3' end of mRNA thereby overlooking the complementarities in the 5' end of miRNA which is present in the third case (Figure 1c). As the pairing at 3' end of mRNA with 5' of miRNA is found to be more in number compared to the other, this results in missing of targets. We have paid adequate attention to this fact while designing MTar.
Survey of existing solutions
A number of computational tools are available for animal and plant miRNA target identification. Of these, only MiRanda and RNAhybrid provide source code. Most of these approaches are based on evolutionary conservation and the presence of miRNA target sites in 3' UTRs of target mRNAs and their relatively better complementarities to 5' end of miRNAs. At the initial stages of microRNA target identification, researchers used near-perfect complementarities to predict miRNA targets for model species from plants. Tools like miRCheck , findmiRNA , PatScan  and mirU  are used for rapid prediction of miRNA targets in plants where perfect complementarities of miRNA and mRNA make the task easier. Though the targets for plant miRNAs can be identified on a genome-wide scale by searching for the ones that require a high degree of sequence complementarities, this cannot be used as such to find targets for animal miRNAs. The animal miRNAs tested till date pair imperfectly with their targets and act to control translation. Also the systematic analysis of the complete miRNA complement has confirmed the absence of targets with perfect or near-perfect sequence complementarities. So, target prediction in animal transcriptomes calls for more complex algorithms due to the imperfect complementarities of miRNA: mRNA pairs.
PicTar [23–25] predict miRNA targets in Drosophila and other species based on complementarities between miRNA and 3' UTR of mRNA sequence. PicTar used techniques like seed match, free energy calculation and species conservation. Its false positive rate has been estimated to be 30.0%.
TargetScan  is a tool used to predict miRNAs which bind to 3' UTRs of vertebrate transcriptomes. TargetScan could predict more than 451 human microRNA targets. TargetSanS , a modified version of TargetScan, omits multiple sites in each target and further filters the targets using thermodynamic stability criterion. Using this modified method more than 5300 human genes were predicted as possible targets of miRNAs . The false positive rate varies between 22% to 31%.
MiRanda [12, 27, 28], a target prediction tool, relies on the evolutionary relationships between miRNAs and their targets. This tool focused to sequence matching of miRNA: mRNA pairs, by estimating energy of physical interaction. MiRanda was initially developed for predicting miRNA targets in Drosophila  and was later extended to find miRNA targets in mammals (human, mouse and rat) and Zebrafish . The miRanda algorithm works by scanning for miRNA complementary pairs in the 3' UTR of an mRNA. Using this software, a large number of targets were identified including protein-coding genes in Homo sapiens. The false positive rate was estimated to be 24%.
The DIANA-microT  is a method based on the rules of single miRNA: mRNA pairing. It predicts targets which contain a single complementary site based on binding energies. MiTarget algorithm  combines thermodynamics based processing of RNA: RNA duplex interactions with the sequence analysis to predict miRNA targets. RNAhybrid is another computer program for predicting miRNA targets based on complementarities between miRNA and 3' UTR of coding sequence. This program was used to predict targets in Drosophila . MovingTarget  is a program used to detect miRNA targets satisfying a set of biological constraints. Using this program more than 83 potential targets was predicted in Drosophila. MicroTar  is a program used to detect target sites in C.elegans, Drosophila and mouse by target complementarities and thermodynamic data. This algorithm uses predicted free energies of unbounded mRNA and putative mRNA:miRNA hetero dimmers, implicitly addressing the accessibility of the mRNA 3' UTR. This software is able to predict both conserved and non-conserved targets.
Anyway most of these existing tools make use of the complementarities in the 5' end of the miRNA alone. But MTar, the proposed computational method, can trap all the three types of targets (5' seed-only, 5' dominant and 3' canonical) and hence found to be more accurate. Multiplicity and cooperation which are common in animal miRNA: mRNA interactions are also handled effectively by MTar.
Experimentally verified microRNAs and their targets are required for training dataset preparation. In the data collection step, we excluded the sequences that were not verified by wet lab experiments in order to ensure the quality of the training data. We also excluded all the targets whose exact binding site could not be verified accurately. The dataset was selected based on two criteria. 1) The binding site of miRNA:target duplex should be known. 2) The target site sequences should match its corresponding references mRNA sequence in NCBI gene database.
The miRNAs were downloaded from miRBase database . There are 706 reported human microRNA entries in the miRBase registry. The experimentally verified human microRNA targets were downloaded from Tarbase and miRecords registries. There are 609 human target sites for 443 genes by 107 miRNAs in Tarbase database . The miRecords , contains 778 human records for 651 genes by 125 miRNAs. After filtered the target sites from these sources, the combined dataset consists of 882 human records for 741 genes by 138 miRNAs. The positive dataset needs three types of target classes (5' seed-only, 5' dominant, and 3' canonical). The classification was done based on the complementarity in the seed region. Seed region is the region of the nucleotides from 2-8 or 2-9 positions of the miRNA from the 5' end.
Randomly generated negative examples were not included in the training set, as such sequences are often found to interact with miRNAs due to their low signal to noise ratios as it is evident from previous studies [15, 26, 29]. Deletion of target positions on the target miRNA sequence can give a large number of negative examples. We generate a common negative dataset contains non miRNA:mRNA target sites with different parameter score. We collected examples with more than 4 mer matched at their seed part. Alignments of sequences in the training datasets were thoroughly checked in order to avoid ambiguities. The training set consisted of 350 examples with 150 positives and 200 negatives. The selection of positive dataset was based on the availability of experimentally verified target sites for the three class of targets in Tarbase registry. From these sequences three separate training datasets were created for three target classes (5' seed-only, 5' dominant, and 3' canonical). The training dataset contains 40 positives and 56 negatives for 3' canonical target class, 58 positives and 74 negatives for 5' dominant target class and 52 positives and 70 negatives for 5' seed-only target class.
Parameters used for miRNA target prediction
Obtained by the sum of pair scores in the seed region. G:C and A:U with 5, G:U with 2 and the others with -3
Out seed score
Obtained by the sum of pair scores in a non-seed region. G:C and A:U with 5, G:U with 2 and the others with -3
Number of WC pairs in the duplex
Number of wobble pairs in the duplex
Number of mismatches in duplex
Length of largest bulge in the duplex
Number of bulges in the duplex
Proportion of 'A', 'G','C' and 'U' in the target sequence
Free energy is calculated using RNAfold of the target sequence
Calculated using RNAfold for a duplex formed by the miRNA and its target. RNAfold is the part of ViennaRNA package 
Normalized free energy
NFE = (-1 * free energy of target sequence)/log(length of target * length of miRNA)
Difference in hybridization energy
Difference in the hybridization energies of miRNA:perfect target (reverse complement of miRNA) duplex and miRNA: target duplex
Positional pair score
This score is considered by both pairing and positioning. G:C and A:U with 5, G:U with 1, all other mismatches awarded with -3 and the mismatches containing gaps are awarded with -1. Positional weight is 1 for all non-seed position and 2 for all seed position. The total score is obtained by the sum of the product of the weight and the corresponding pair score through out the mirna: target duplex
Obtained by the sum of diagonal elements in the matrix formed by miRNA and its target. The scores are based on WC pairs: 5, Wobble pairs: 2, Inserts: -1, Deletes: -1, Symmetric mismatches: -3, Mismatches: -2
Deviation matrix score
Deviation of the matrix score with the score obtained by a perfect target ie, the reverse complement of miRNA
Deviation positional score
Deviation of the positional pair score with the score obtained with a perfect target
5' seed-only: For this class, a minimum of 6 WC pairs and no mismatch in the seed region are allowed. No G:U pair is allowed in the seed region. The non-seed region may contain a minimum of 4 matching pairs including G:U pairs.
5' dominant: A minimum of 5 WC pairs, with one mismatch and a maximum of 2 G:U pairs are allowed in the seed region. Minimum 5 matching pairs including G:U pairs should be in the non-seed region.
3' Canonical: A minimum of 3 WC pairs, 4 mismatches and maximum 3 G:U pairs are allowed in the seed region. The non-seed region should contain a minimum 7 matching pairs including G:U pairs.
If the selected region does not belong to any of these classes, it is not considered for further processing. The predictions are strictly based on the class of the targets. Each of these segments is aligned with the miRNA to locate potential target candidates belonging to all the three different categories (5' seed-only, 5' dominant and 3' canonical) based on the nature of complementarities. After this, all overlaps are removed by filtering. Then, using the parameters listed in Table 1, a feature vector is formed by giving appropriate weights to the parameters for each of the candidates. Then they are submitted to an ANN classifier. The threshold levels for the parameters are different for targets of different categories. The validated potential targets are displayed along with their class to which they belong.
In this study, artificial neural networks (ANNs) were chosen as the tool for miRNA target verification as they are powerful classifiers whose ability to cope with complex data and their potential for modeling data of high non-linearity [42, 43]. We used a feed forward three layer multi layer perceptron (MLP) for the classification of target sites. Calculated value of the parameters (Table 1) of miRNA:mRNA pair was selected as a 16 dimensional vector and fed into 16 input nodes. Output is set as either '1', if the output pattern is true and -1', if the output pattern is false. Hence there is one unit in the output layer of the ANN. The number of units in the hidden layer was chosen as nine, by trail and error. We used a sigmoid transfer function as the activation function. Back propagation algorithm was used to train the network. The training can be performed with use of several optimization schemes and there is access to exact partial derivatives of network outputs versus its inputs. The over fitting was avoided and this package makes automatic normalization of input data . The learning rate and momentum were initially set at 0.2 and 0.8 respectively.
The training dataset is divided into two subsets. First subset (70% of the total training data) were used to train the neural network. Second subset was used to stop the training process once the model had reached the performance conditions like optimal error value thus preventing over training. Once the training is stopped, the efficiency of the model was further assessed by presenting another data subset, to determine the performance for unseen cases which were not involved in the training process. Optimization was done by repeating the process with different data subsets. The optimization needs nearly 500 epochs for this network. Three separate ANNs for each target class (5' seed-only, 5' dominant and 3' canonical) were trained to validate the target candidates of three different classes. Each ANN was trained with their training set and optimized the network as discussed above.
Results and discussion
Extensive evaluation of MTar architecture was carried out using human genome. We could computationally predict 2663 target sites including 819 experimentally verified targets of 129 miRNAs (MFE below 17.0 Kcal/mol). For evaluation, the miRNA test data was downloaded from miRBase registry and the mRNA sequences from NCBI RefSeq and Biomart  cites.
Role of parameter in target prediction
Positional pair score
Deviation positional score
Deviation matrix score
Out seed score
Normalized free energy
Difference in hybridization energy
Length - bulge
Comparison with existing approaches
miRNA:mRNA targets result comparison (882 target sites for 138 miRNAs and 741 mRNAs)
No. of targets predicted
Total targets predicted by each tool for the experimentally proven miRNAs
No of microRNAs
The MiTarget is one of the latest web based miRNA target prediction tool, which predict most of the 5' seed-only and 5' dominant miRNA target regions but it fails in identifying 3' canonical targets. This may be the due to picking the features from 5' part of the miRNA only while it is binding to the 3' part of the mRNA and ignoring the 3' part of the miRNA target.
After testing the MTar with a set of data, the test was repeated for MiRanda, TargetScan, RNA22, PicTar and MiTarget, with the same dataset. Figure 3 depicts the receiver operator characteristics curve for MTar along with a comparison of other three tools (MiTarget, MiRanda and TargetScan). The other three methods not provide cutoffs, so ROC generation was difficult. MiRanda shows a specificity of 82% by the test dataset. The specificity of PicTar nearly 70% and that of TargetScan is comes around 80% by the same dataset. We are not ploted the position of these two tools in Figure 3, due to their low specificity. The sensitivity of these tools are seen in Table 3. MTar gives an average accuracy of 92.8%, sensitivity as high as 94.5% and a specificity of 90.5% for the miRNA targets in the testing dataset.
The relative merit and comprehensiveness of MTar can be attributed to the following facts. First, the approach identifies all the three types of targets (5' seed-only, 5' dominant, and 3' canonical) in a single framework unlike other approaches. The second reason is the use of all the three properties (positional, thermodynamic and structural features) of the miRNA:mRNA duplex for the target identification. Third, multiple target sites are treated differently by set of user-defined biological constraints. A user can fix the free energy cutoff criteria of a miRNA:mRNA pair. Finally, our method is a desktop application for human transcriptome and also extensible to the other species.
In this paper, we proposed a novel computational method for microRNA target prediction (MTar), which can identify all known three types of miRNA targets (5' seed-only, 5' dominant, and 3' canonical). Most of the computational methods for miRNA target prediction combine 5' seed matches, thermodynamic stability and conservation analysis in order to maximize specificity of the algorithms. Especially, evolutionary conservation is found to be an excellent tool for filtering out false positives thereby increasing specificity. MTar uses all these features and also takes into consideration the structural and positional features of miRNA: mRNA formation. The method makes use of three ANN verifiers, thoroughly trained by proved biological data. Sixteen positional, thermodynamic and structural features of miRNA: mRNA pairs were employed to select target candidates. Extensive evaluation of the proposed method was carried out using human genome. MTar identifies potential targets of 101 experimentally proved microRNAs. The performance of MTar was compared against existing solutions and the method is found to be more accurate. Our method predicts the three types of targets with a prominent accuracy (92.8%), sensitivity (94.5%) and specificity (90.5%). The false positive rate of MTar is 9.5% for MFE ≤ -17.0 Kcal/mol. The false positive rate can still be reduced by adjusting the MFE between miRNA:mRNA pairs but at the cost of lowered sensitivity. MTar has another edge due to its trainability as the performance can still be improved.
The authors wish to thank Department of Biotechnology, Government of India for the open access publication charges.
This article has been published as part of BMC Bioinformatics Volume 11 Supplement 1, 2010: Selected articles from the Eighth Asia-Pacific Bioinformatics Conference (APBC 2010). The full contents of the supplement are available online at http://www.biomedcentral.com/1471-2105/11?issue=S1.
- Esquek KA, Slack FJ: Oncomirs microRNAs with a role in Cancer. Nature Reviews Cancer 2006, 6: 259–269. 10.1038/nrc1840View ArticleGoogle Scholar
- Marilena VI, Manuela F, Chang-Gong L, Angelo V, Riccardo S, Silvia S, Eros M, Massimo P, Muller F, Manuela C, et al.: MicroRNA Gene Expression Deregulation in Human Breast Cancer. Cancer Research 2005, 65: 7065–7070. 10.1158/0008-5472.CAN-05-1783View ArticleGoogle Scholar
- Bartel DP: MicroRNAs: genomics, biogenesis, mechanism, and function. Cell 2004, 116: 281–297. 10.1016/S0092-8674(04)00045-5View ArticlePubMedGoogle Scholar
- Kim VN: MicroRNA biogenesis:coordinated cropping and dicing. Nat Rev Mol Cell Biol 2005, 6: 376–385. 10.1038/nrm1644View ArticlePubMedGoogle Scholar
- Gregory R, Chendrimada T, Shiekhattar R: Human RISC couples microRNA biogenesis and posttranscriptional gene silencing. Cell 2005, 123: 631–640. 10.1016/j.cell.2005.10.022View ArticlePubMedGoogle Scholar
- Bernstein E, Caudy A, Hammond S, Hannon G: Roll for a bidentate ribonuclease in the initiation step of RNA interface. Nature 2001, 409: 363–366. 10.1038/35053110View ArticlePubMedGoogle Scholar
- Hutvagner G, Zamore PD: A microRNA in a multiple turnover RANi enzyme complex. Science 2002, 297: 2056–2060. 10.1126/science.1073827View ArticlePubMedGoogle Scholar
- Reinhart BJ, Weinstein EG, Rhoades MW, Bartel B, Bartel DP: MicroRNA in Plants. Genes Dev 2002, 16: 1616–1626. 10.1101/gad.1004402PubMed CentralView ArticlePubMedGoogle Scholar
- Rhoades B, Reinhart B, Bartel B, Bartel DP: Prediction of Plant microRNA Targets. Cell 2002, 110: 513–520. 10.1016/S0092-8674(02)00863-2View ArticlePubMedGoogle Scholar
- Lewis B, Burge C, Bartel DP: Conserved Seed Pairing, Often Flanked by Adenosines, Indicates that Thousands of Human Genes are microRNA Targets. Cell 2005, 120: 15–20. 10.1016/j.cell.2004.12.035View ArticlePubMedGoogle Scholar
- Rehmsmeier M, Steffen P, Hochsmann M, Giegrich R: Fast and Effective prediction of microRNA/target duplexes. RNA 2004, 10: 1507–1517. 10.1261/rna.5248604PubMed CentralView ArticlePubMedGoogle Scholar
- John B, Enright AJ, Arvin A, Tuschl T, Sander C, Marks DS: Human MicroRNA Targets. PLoS Biol 2004, 2: e363. 10.1371/journal.pbio.0020363PubMed CentralView ArticlePubMedGoogle Scholar
- Kim JT, Gewehr JE, Martinetz T: Binding Matrix a novel approach for binding site recognition. J Bioinform Comput Biol 2004, 2: 289–307. 10.1142/S0219720004000569View ArticlePubMedGoogle Scholar
- Moxon S, Moulton V, Kim JT: A scoring matrix approach to detecting miRNA target sites. Algorithms Mol Biol 2008, 3: 3. 10.1186/1748-7188-3-3PubMed CentralView ArticlePubMedGoogle Scholar
- Brennecke J, Stark A, Russell RB, Cohen SM: Principles of microRNA-target recognition. PLoS Biol 2005, 3: e85. 10.1371/journal.pbio.0030085PubMed CentralView ArticlePubMedGoogle Scholar
- Grimson A, Farh K, Johnston W, Engele PG, Lim L, Bartel DP: Micro RNA targeting specificity in mammals: determinants beyond seed pairing. Mol Cell 2007, 27: 91–105. 10.1016/j.molcel.2007.06.017PubMed CentralView ArticlePubMedGoogle Scholar
- Sethupathy P, Corda B, Hatzigeorgiou AG: TarBase: A comprehensive database of experimentally supported animal microRNA targets. RNA 2006, 12: 192–197. 10.1261/rna.2239606PubMed CentralView ArticlePubMedGoogle Scholar
- Stark A, Brennecke J, Bushati N, Russell RB, Cohen SM: Animal MicroRNAsconfer robustness to gene expression and have a significant impact on 3'UTR evolution. Cell 2005, 123: 1133–1146. 10.1016/j.cell.2005.11.023View ArticlePubMedGoogle Scholar
- Bentwich I, Avniel A, Karov Y, Aharonov R, Gilad S, Barad O, Barzilai A, Einat P, Einav U, Meiri E, et al.: Identification of hundreds of conserved and nonconserved human microRNAs. Nat Genet 2005, 37: 766–770. 10.1038/ng1590View ArticlePubMedGoogle Scholar
- Johnes-Rahoades MW, Bartel DP: Computational identification of Plant microRNAs and their targets, inducing a stress-induced miRNA. Mol Cell 2004, 14: 787–799. 10.1016/j.molcel.2004.05.027View ArticleGoogle Scholar
- Adai A, Cameron J, Sizolwenkosi M, Sarah A, Varun M, Vicki V, Venkatesan S: Computational Prediction of miRNAs in Arabidopsis thaliana. Genome Research 2005, 15: 78–91. 10.1101/gr.2908205PubMed CentralView ArticlePubMedGoogle Scholar
- Zhang Y: miRU: an automated plant miRNA target prediction server. Nucleic Acids Res 2005, 33: W701-W704. 10.1093/nar/gki383PubMed CentralView ArticlePubMedGoogle Scholar
- Grun D, Wang YL, Langenberger D, Gunsalus KC, Rajewsky N: microRNA target predictions across seven Drosophila species and comparison to mammalian targets. PLoS Comput Biol 2005, 1: e13. 10.1371/journal.pcbi.0010013PubMed CentralView ArticlePubMedGoogle Scholar
- Krek A, Grun D, Poy MN, Wolf R, Rosenberg L, Epstein EJ, MacMenamin P, daPiedade I, Gunsalus KC, Stoffel M, et al.: Combinatorial microRNA target predictions. Nat Genet 2005, 37: 495–500. 10.1038/ng1536View ArticlePubMedGoogle Scholar
- Lall S, Grun D, Krek A, Chen K, Wang Y, Dewey CN, Sood P, Colombo T, Bray N, Macmenamin P, et al.: A genome-wide map of conserved microRNA targets in C. elegans. Curr Biol 2006, 16: 460–471. 10.1016/j.cub.2006.01.050View ArticlePubMedGoogle Scholar
- Lewis BP, Shih IH, Jones-Rhoades MW, Bartel DP, Burge CB: Prediction of mammalian microRNA targets. Cell 2003, 115: 787–798. 10.1016/S0092-8674(03)01018-3View ArticlePubMedGoogle Scholar
- Enright AJ, John B, Gaul U, Tuschl T, Sander C, Marks DS: MicroRNA Targets in Drosophila. Genome Biol 2003, 5: R1. 10.1186/gb-2003-5-1-r1PubMed CentralView ArticlePubMedGoogle Scholar
- Betel D, Wilson M, Gabow A, Marks DS, Sander C: The microRNA.org resource: targets and expression. Nucleic Acids Res 2008, 36: D149-D153. 10.1093/nar/gkm995PubMed CentralView ArticlePubMedGoogle Scholar
- Kiriakidou M, Nelson PT, Kouranov A, Fitzeiv P, Bouyioukos C, Mourelatos Z, Hatzigeorgiou A: A combined computational-experimental approach predicts human microRNA targets. Genes Dev 2004, 18: 1165–1178. 10.1101/gad.1184704PubMed CentralView ArticlePubMedGoogle Scholar
- Kim S, Nam J, Rhee J, Lee W, Zhang B: MiTarget: miRNA target gene prediction using an SVM. BMC Bioinformatics 2006, 7: 441. 10.1186/1471-2105-7-441View ArticleGoogle Scholar
- Burgler C, Macdonald PM: Prediction and verification of microRNA targets by Moving Targets, a highly adaptable prediction method. BMC Bioinformatics 2005, 6: 88. 10.1186/1471-2105-6-88View ArticleGoogle Scholar
- Thadani R, Tammi MT: MicroTar: Predicting microRNA targets from RNA duplexes. BMC Bioinformatics 2006, 7(Suppl 5):S20. 10.1186/1471-2105-7-S5-S20PubMed CentralView ArticlePubMedGoogle Scholar
- Griffiths-Jones S, Russell JG, Stijn D van, Alex B, Anton E J: miRBase: microRNA sequences, targets and gene nomenclature. Nucleic Acids Res 2006, 34: D140-D144. 10.1093/nar/gkj112PubMed CentralView ArticlePubMedGoogle Scholar
- Vinod C, Reshmi G: A Pre-microRNA Classifier by Structural and Thermodynamic Motifs. IEEE - NaBIC 2009, 2009: 9–11.Google Scholar
- Huynh T, Miranda K, Tay Y, Ang S, Tam L, Thomson AM, Lim B, Rigoutsos I: A pattern-based method for the identification of microRNA-target sites and their corresponding RNA/RNA complexes. Cell 2006, 126: 1203–1217. 10.1016/j.cell.2006.07.031View ArticlePubMedGoogle Scholar
- Gaidatzis D, van Nimwegen E, Hausser J, Zavolan M: Inference of miRNA targets using evolutionary conservation and pathway analysis. BMC Bioinformatics 2007, 8: 69. 10.1186/1471-2105-8-69PubMed CentralView ArticlePubMedGoogle Scholar
- Kertesz M, Iovino N, Unnerstall U, Gaul U, Segal E: The role of site accessibility in microRNA target recognition. Nature Genetics 2007, 39: 1278–1283. 10.1038/ng2135View ArticlePubMedGoogle Scholar
- Sactron O, Ola S, Saetrom P: Weighted Sequence motif as an improvd seed step in microRNA target prediction algorithms. RNA 2004, 11: 995–1003.Google Scholar
- Hofacker IL: Vienna RNA secondary structure server. Nucleic Acids Res 2003, 31: 3429–3431. 10.1093/nar/gkg599PubMed CentralView ArticlePubMedGoogle Scholar
- Doench JG, Sharp PA: Specificity of microRNA target selection in translational representation. Genome Res 2004, 18: 504–511.Google Scholar
- Smith TF, Waterman MS: Identification of Common Molecular Subse-quences. J Mol Biol 1981, 147: 195–197. 10.1016/0022-2836(81)90087-5View ArticlePubMedGoogle Scholar
- Khan J, Wei JS, Ringner M, Saal LH, Laddnyi M, Antonescu CR, Peterson C, Melter PS: Classification and diagonostic prediction of cancers using gene expression profiling an Artificial Neural Networks. Nat Med 2001, 7: 673–679. 10.1038/89044PubMed CentralView ArticlePubMedGoogle Scholar
- Lancashire L, Schmid O, Shah H, Ball G: Classification of bacterial species from proteomic data using combinatorial approaches incorporating artificial neural networks, cluster analysis and principal components analysis. Bioinformatics 2005, 21(10):2191–2199. 10.1093/bioinformatics/bti368View ArticlePubMedGoogle Scholar
- Keefe A K, Smedley D, London D, Spooner W, Melsoopp C, Hmmmond M, Roccaserra P, Cox T, Birney E: EnsMart: generic system for fast and flexible access to biological data. Genome Res 2004, 14: 160–169.Google Scholar
- Witten IH, Frank E: Data Mining. In Practical Machine Learning Tools and Techniques with Java Implementations. Edited by: Diane DC. United Kingdom: Morgan Kaufmann; 2000.Google Scholar
This article is published under license to BioMed Central Ltd. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.