Paradigm shifts in genomics through the FANTOM projects

Abstract

Big leaps in science happen when scientists from different backgrounds interact. In the past 15 years, the FANTOM Consortium has brought together scientists from different fields to analyze and interpret genomic data produced with novel technologies, including mouse full-length cDNAs and, more recently, expression profiling at single-nucleotide resolution by cap-analysis gene expression. The FANTOM Consortium has provided the most comprehensive mouse cDNA collection for functional studies and extensive maps of the human and mouse transcriptome comprising promoters, enhancers, as well as the network of their regulatory interactions. More importantly, serendipitous observations of the FANTOM dataset led us to realize that the mammalian genome is pervasively transcribed, even from retrotransposon elements, which were previously considered junk DNA. The majority of products from the mammalian genome are long non-coding RNAs (lncRNAs), including sense-antisense, intergenic, and enhancer RNAs. While the biological function has been elucidated for some lncRNAs, more than 98 % of them remain without a known function. We argue that large-scale studies are urgently needed to address the functional role of lncRNAs.

Fig. 1

a An example of seven alternative promoters within the transcriptional unit of UDP-glucuronyl transferase gene. Light blue boxes indicate groups of CAGE tags transcribed from specific tissues. Reproduced, with permission, from the original publication (Carninci et al. 2005). b The FANTOM3 work revealed that roughly 47 % of the transcribed RNAs are messenger RNAs, encoding for proteins, while 53 % of the transcribed RNAs do not encode for proteins. Numerous reports since the discovery revealed that non-coding RNAs are functionally versatile and have shown to interact and/or regulate various processes including transcription, translation, and epigenetic modifications

Fig. 2

CAGE analysis in FANTOM4 revealed the concerted interplay of transcription factors during monocyte differentiation. Reproduced, with permission, from the original publication (Suzuki et al. 2009)

Fig. 3

FANTOM5 profiled the broadest collection of human cell types using CAGE; the co-expression network shown here revealed clusters of cell types based on similar function and developmental lineages. Reproduced, with permission, from the original publication (Forrest et al. 2014)

Fig. 4

On December 8, 2014 we counted the number of references in PubMed for protein-coding and non-coding genes in release 21 of the GENCODE human gene set. Non-coding genes comprise of both lincRNAs and antisense transcripts as listed in GENCODE. We found multiple PubMed references for most protein-coding genes; in contrast, most non-coding RNAs did not have any reference in PubMed