Web Apollo: a web-based genomic annotation editing platform

Abstract

Web Apollo is the first instantaneous, collaborative genomic annotation editor available on the web. One of the natural consequences following from current advances in sequencing technology is that there are more and more researchers sequencing new genomes. These researchers require tools to describe the functional features of their newly sequenced genomes. With Web Apollo researchers can use any of the common browsers (for example, Chrome or Firefox) to jointly analyze and precisely describe the features of a genome in real time, whether they are in the same room or working from opposite sides of the world.

Figure 1

Web Apollo architecture. Web Apollo (components within the central turquoise box) acts as a mediating agent between users (top blue box) and external sources and sinks of data (lower green and peach boxes). Two user interface components operate on the client-side, within the browser environment. The JBrowse component visualizes various DNA features, and the Web Apollo component captures user manipulations. The Data Services module dynamically delivers genomic data and features to the user interface as JBrowse compatible JSON. Most of the primary genomic data is harvested and formatted in advance as part of the initial server setup. In addition, data from other sources may be dynamically provided using the Trellis framework or uploaded by the user from the browser. The Annotation Editing Engine and User Management components also sit on the server side. The first responds to users actions on the client by modifying the underlying data models appropriately, and second manages user accounts and login services. Annotations created by users can be exported as either GFF3 or FASTA file, or directly saved to a Chado database (plug-in adapters may be added to export genomic annotations to additional repositories). The arrows indicate where there are interactions between components, with the arrowhead indicating the direction of data flow.

Figure 2

Example of the Web Apollo interface. Moving from top to bottom these example tracks from the honeybee (Apis mellifera) genome display: (A) In-progress gene models interactively being edited by the user. (B) The honeybee consortium's official gene set. (C) Transcripts from the NCBI RefSeq database. (D) Output from MAKER. (E) Output from various different gene prediction programs. (F, I, J) Contigs generated from RNA-seq data for respectively: nurse bees, testes, and ovaries. (G) Coverage map from the nurse bee RNA-seq data. (H) RNA-Seq data from forager bees displayed as a 'heat map'. Note that none of the gene predictions are in agreement regarding intron-exon boundaries in (E), which illustrates why manual review is needed. Web Apollo gives biologists the ability to manually resolve disagreements and create a more accurate set of gene predictions to improve upstream analysis pipelines in subsequent runs, as well as provide a more reliable substrate for downstream analyses.

Figure 3

Example of sequence alteration editing operations. The top panel shows a transcript annotation (in blue) flagged with an orange exclamation icon indicating that the curated intron-exon junction does not follow a canonical splice site pattern, that is, having a 'GT' immediately 3' of the junction. In the second panel a curator has examined this issue and determined that a base was mis-called in the assembly, and has therefore added a substitution annotation (shown in yellow), substituting a 'T' for a 'C'. This change immediately triggers removal of the non-canonical warning icon, because with the substitution the splice junction now has the canonical 'GT'. In the third panel a curator has created a sequence insertion annotation (shown in green) upstream of the splice, and this leads to a stop codon that truncates the CDS. In the last panel a sequence deletion annotation has been created (shown in red), which causes a frame shift for the annotation transcript, and results in the reversal of the CDS truncation.

Figure 4

RNA-Seq evidence provides support for alternative isoforms. In this example from the bovine genome (Bos taurus) the RNA-Seq data was stored as a BAM file and dynamically uploaded. Individual aligned reads are shown in teal. The example highlights the importance of utilizing deep RNA sequencing for curation. Two different splice variants are visible: one variant is visible in the Dog Ensembl track and a different one is visible in the Mouse Ensembl track. The RNA-Seq data track clearly shows evidence that both variants are present in the bovine. Edge-matching (in red) highlights the concordance in exon boundaries between the different tracks.

Figure 5

History tracking and edit operation. Two History windows show how the transcript changed between edit operations. Each History entry shows the edit operation, the user who made the edit, and the date. The top window shows the transcript after merging of two exons and the one below shows the transcript after an exon has been deleted. Users can click on different History entries, which will display how the transcript looked at that point in time.