Computational prediction of microRNAs from Toxoplasma gondii potentially regulating the hosts' gene expression.

MicroRNAs (miRNAs) were discovered two decades ago, yet there is still a great need for further studies elucidating their genesis and targeting in different phyla. Since experimental discovery and validation of miRNAs is difficult, computational predictions are indispensable and today most computational approaches employ machine learning. Toxoplasma gondii, a parasite residing within the cells of its hosts like human, uses miRNAs for its post-transcriptional gene regulation. It may also regulate its hosts' gene expression, which has been shown in brain cancer. Since previous studies have shown that overexpressed miRNAs within the host are causal for disease onset, we hypothesized that T. gondii could export miRNAs into its host cell. We computationally predicted all hairpins from the genome of T. gondii and used mouse and human models to filter possible candidates. These were then further compared to known miRNAs in human and rodents and their expression was examined for T. gondii grown in mouse and human hosts, respectively. We found that among the millions of potential hairpins in T. gondii, only a few thousand pass filtering using a human or mouse model and that even fewer of those are expressed. Since they are expressed and differentially expressed in rodents and human, we suggest that there is a chance that T. gondii may export miRNAs into its hosts for direct regulation.

Machine learning methods for microRNA gene prediction.

MicroRNAs (miRNAs) are single-stranded, small, noncoding RNAs of about 22 nucleotides in length, which control gene expression at the posttranscriptional level through translational inhibition, degradation, adenylation, or destabilization of their target mRNAs. Although hundreds of miRNAs have been identified in various species, many more may still remain unknown. Therefore, discovery of new miRNA genes is an important step for understanding miRNA-mediated posttranscriptional regulation mechanisms. It seems that biological approaches to identify miRNA genes might be limited in their ability to detect rare miRNAs and are further limited to the tissues examined and the developmental stage of the organism under examination. These limitations have led to the development of sophisticated computational approaches attempting to identify possible miRNAs in silico. In this chapter, we discuss computational problems in miRNA prediction studies and review some of the many machine learning methods that have been tried to address the issues.

Can MiRBase provide positive data for machine learning for the detection of MiRNA hairpins?

Experimental detection and validation of miRNAs is a tedious, time-consuming, and expensive process. Computational methods for miRNA gene detection are being developed so that the number of candidates that need experimental validation can be reduced to a manageable amount. Computational methods involve homology-based and ab inito algorithms. Both approaches are dependent on positive and negative training examples. Positive examples are usually derived from miRBase, the main resource for experimentally validated miRNAs. We encountered some problems with miRBase which we would like to report here. Some problems, among others, we encountered are that folds presented in miRBase are not always the fold with the minimum free energy; some entries do not seem to conform to expectations of miRNAs, and some external accession numbers are not valid. In addition, we compared the prediction accuracy for the same negative dataset when the positive data came from miRBase or miRTarBase and found that the latter led to more precise prediction models. We suggest that miRBase should introduce some automated facilities for ensuring data quality to overcome these problems.