A Meta-Analysis Based Method for Prioritizing Candidate Genes Involved in a Pre-specific Function

Abstract

The identification of genes associated with a given biological function in plants remains a challenge, although network-based gene prioritization algorithms have been developed for Arabidopsis thaliana and many non-model plant species. Nevertheless, these network-based gene prioritization algorithms have encountered several problems; one in particular is that of unsatisfactory prediction accuracy due to limited network coverage, varying link quality, and/or uncertain network connectivity. Thus, a model that integrates complementary biological data may be expected to increase the prediction accuracy of gene prioritization. Toward this goal, we developed a novel gene prioritization method named RafSee, to rank candidate genes using a random forest algorithm that integrates sequence, evolutionary, and epigenetic features of plants. Subsequently, we proposed an integrative approach named RAP (Rank Aggregation-based data fusion for gene Prioritization), in which an order statistics-based meta-analysis was used to aggregate the rank of the network-based gene prioritization method and RafSee, for accurately prioritizing candidate genes involved in a pre-specific biological function. Finally, we showcased the utility of RAP by prioritizing 380 flowering-time genes in Arabidopsis. The “leave-one-out” cross-validation experiment showed that RafSee could work as a complement to a current state-of-art network-based gene prioritization system (AraNet v2). Moreover, RAP ranked 53.68% (204/380) flowering-time genes higher than AraNet v2, resulting in an 39.46% improvement in term of the first quartile rank. Further evaluations also showed that RAP was effective in prioritizing genes-related to different abiotic stresses. To enhance the usability of RAP for Arabidopsis and non-model plant species, an R package implementing the method is freely available at http://bioinfo.nwafu.edu.cn/software.

Transcriptome-Wide Annotation of m5C RNA Modifications Using Machine Learning

“…Third, the base preferences around the m 5 C sites are not strong enough, increasing the difficulties in computational predictions with traditional statistical approaches. Machine learning (ML) is a branch of artificial intelligence technology that has been widely used in engineering, computer science, informatics and biology (Ma et al, 2014a , 2017 ; Cui et al, 2015 ; Libbrecht and Noble, 2015 ; Zhai et al, 2016 ). The biggest advantage of ML systems is that they can automatically learn interesting patterns from existing datasets and bring about self-improvement of system performance for accurately predicting novel knowledge from a new data set (Ma et al, 2014a , b ).…”

Prioritization and Evaluation of Flooding Tolerance Genes in Soybean [Glycine max (L.) Merr.]

“…The proportion of P -value less than 0.05 does not exceed 81% in the four time points ( Table 4 ). On the other hand, to compare the random forest method with our prioritized algorithm, the modified random forest method was conducted to satisfy our data format ( Zhai et al, 2016 ). As a result, a total of 83 prioritized genes (ranked in the top 83 genes) were also identified based on the modified random forest method.…”

“…We also compared the prioritized FTgenes (using weighted scheme) selected by our proposed algorithm with other existing methods, e.g., random forest algorithm (Rafsee) ( Zhai et al, 2016 ) and network-based gene prioritization method (SoyNet) ( Kim et al, 2017 ). Due to the difference of sources and characteristics for data mining between other methods and our study, we modified the random forest algorithm used in Rafsee without changing the idea and concept and applied it to our test genes.…”

“…These genes were linked to the pathways including protein synthesis, nucleotide metabolism, hormone metabolism and glycolysis signaling which were induced by submergence conditions ( Yin et al, 2017 ). Although previous studies were abundant, it was still costly and time-consuming for experimental validation of each of the flooding tolerance candidate genes ( Rhee and Mutwil, 2014 ; Zhai et al, 2016 ). Furthermore, the data collected from previous studies had large batch effects ( Goh et al, 2017 ), thus making it thorny to unify and integrate.…”

“…Recently, network analysis advanced the development of gene prioritization. Zhai et al (2016) proposed rank aggregation-based data fusion for a gene prioritization (RAP) method that integrated RafSee and AraNet v2 prioritization algorithms, a total of 380 flowering-time genes of Arabidopsis thaliana were identified. They found that the prioritized genes identified by the RAP method had a higher ranking in comparison to those that identified by AraNet v2.…”