Waleed Khalifa

Feature Selection Has a Large Impact on One-Class Classification Accuracy for MicroRNAs in Plants

MicroRNAs (miRNAs) are short RNA sequences involved in posttranscriptional gene regulation. Their experimental analysis is complicated and, therefore, needs to be supplemented with computational miRNA detection. Currently computational miRNA detection is mainly performed using machine learning and in particular two-class classification. For machine learning, the miRNAs need to be parametrized and more than 700 features have been described. Positive training examples for machine learning are readily available, but negative data is hard to come by. Therefore, it seems prerogative to use one-class classification instead of two-class classification. Previously, we were able to almost reach two-class classification accuracy using one-class classifiers. In this work, we employ feature selection procedures in conjunction with one-class classification and show that there is up to 36% difference in accuracy among these feature selection methods. The best feature set allowed the training of a one-class classifier which achieved an average accuracy of ~95.6% thereby outperforming previous two-class-based plant miRNA detection approaches by about 0.5%. We believe that this can be improved upon in the future by rigorous filtering of the positive training examples and by improving current feature clustering algorithms to better target pre-miRNA feature selection.

The impact of feature selection on one and two-class classification performance for plant microRNAs

MicroRNAs (miRNAs) are short nucleotide sequences that form a typical hairpin structure which is recognized by a complex enzyme machinery. It ultimately leads to the incorporation of 18–24 nt long mature miRNAs into RISC where they act as recognition keys to aid in regulation of target mRNAs. It is involved to determine miRNAs experimentally and, therefore, machine learning is used to complement such endeavors. The success of machine learning mostly depends on proper input data and appropriate features for parameterization of the data. Although, in general, two-class classification (TCC) is used in the field; because negative examples are hard to come by, one-class classification (OCC) has been tried for pre-miRNA detection. Since both positive and negative examples are currently somewhat limited, feature selection can prove to be vital for furthering the field of pre-miRNA detection. In this study, we compare the performance of OCC and TCC using eight feature selection methods and seven different plant species providing positive pre-miRNA examples. Feature selection was very successful for OCC where the best feature selection method achieved an average accuracy of 95.6%, thereby being ∼29% better than the worst method which achieved 66.9% accuracy. While the performance is comparable to TCC, which performs up to 3% better than OCC, TCC is much less affected by feature selection and its largest performance gap is ∼13% which only occurs for two of the feature selection methodologies. We conclude that feature selection is crucially important for OCC and that it can perform on par with TCC given the proper set of features.

MicroRNA categorization using sequence motifs and k-mers

BackgroundPost-transcriptional gene dysregulation can be a hallmark of diseases like cancer and microRNAs (miRNAs) play a key role in the modulation of translation efficiency. Known pre-miRNAs are listed in miRBase, and they have been discovered in a variety of organisms ranging from viruses and microbes to eukaryotic organisms. The computational detection of pre-miRNAs is of great interest, and such approaches usually employ machine learning to discriminate between miRNAs and other sequences. Many features have been proposed describing pre-miRNAs, and we have previously introduced the use of sequence motifs and k-mers as useful ones. There have been reports of xeno-miRNAs detected via next generation sequencing. However, they may be contaminations and to aid that important decision-making process, we aimed to establish a means to differentiate pre-miRNAs from different species.ResultsTo achieve distinction into species, we used one species’ pre-miRNAs as the positive and another species’ pre-miRNAs as the negative training and test data for the establishment of machine learned models based on sequence motifs and k-mers as features. This approach resulted in higher accuracy values between distantly related species while species with closer relation produced lower accuracy values.ConclusionsWe were able to differentiate among species with increasing success when the evolutionary distance increases. This conclusion is supported by previous reports of fast evolutionary changes in miRNAs since even in relatively closely related species a fairly good discrimination was possible.

Distinguishing between MicroRNA Targets from Diverse Species using Sequence Motifs and K-mers.

A disease phenotype is often due to dysregulation of gene expression. Post-translational regulation of protein abundance by microRNAs (miRNAs) is, therefore, of high importance in, for example, cancer studies. MicroRNAs provide a complementary sequence to their target messenger RNA (mRNA) as part of a complex molecular machinery. Known miRNAs and targets are listed in miRTarBase for a variety of organisms. The experimental detection of such pairs is convoluted and, therefore, their computational detection is desired which is complicated by missing negative data. For machine learning, many features for parameterization of the miRNA targets are available and k-mers and sequence motifs have previously been used. Unrelated organisms like intracellular pathogens and their hosts may communicate via miRNAs and, therefore, we investigated whether miRNA targets from one species can be differentiated from miRNA targets of another. To achieve this end, we employed target information of one species as positive and the other as negative training and testing data. Models of species with higher evolutionary distance generally achieved better results of up to 97% average accuracy (mouse versus Caenorhabditis elegans) while more closely related species did not lead to successful models (human versus mouse; 60%). In the future, when more targeting data becomes available, models can be established which will be able to more precisely determine miRNA targets in hostpathogen systems using this approach.

A zero-norm feature selection method for improving the performance of the one-class machine learning for microRNA target detection

The application of one-class machine learning is gaining attention in the computational biology community. Different studies have described the use of two-class machine learning to predict microRNAs (miRNAs) gene target. Most of these methods require the generation of an artificial negative class. However, designation of the negative class can be problematic and if it is not properly done can affect the performance of the classifier dramatically and/or yield a biased estimate of performance. We present study using one-class machine learning for miRNA target discovery and compare one-class to two-class approaches using a zero-norm for feature selection. The usage of this simple feature selection cause an improving of the one-class results, where in some cases reaches the performance of the two-class approach.

Ensemble Clustering Classification Applied to Competing SVM and One-Class Classifiers Exemplified by Plant MicroRNAs Data

The performance of many learning and data mining algorithms depends critically on suitable metrics to assess efficiency over the input space. Learning a suitable metric from examples may, therefore, be the key to successful application of these algorithms. We have demonstrated that the k-nearest neighbor (kNN) classification can be significantly improved by learning a distance metric from labeled examples. The clustering ensemble is used to define the distance between points in respect to how they co-cluster. This distance is then used within the framework of the kNN algorithm to define a classifier named ensemble clustering kNN classifier (EC-kNN). In many instances in our experiments we achieved highest accuracy while SVM failed to perform as well. In this study, we compare the performance of a two-class classifier using EC-kNN with different one-class and two-class classifiers. The comparison was applied to seven different plant microRNA species considering eight feature selection methods. In this study, the averaged results show that ECkNN outperforms all other methods employed here and previously published results for the same data. In conclusion, this study shows that the chosen classifier shows high performance when the distance metric is carefully chosen.