In the post-genomic era, image-based transcriptomics have received huge attention, because the visualization of gene expression distribution is able to reveal spatial and temporal expression pattern, which is significantly important for understanding biological mechanisms. 

The Berkeley Drosophila Genome Project (BDGP) has collected a large-scale spatial gene expression database for studying Drosophila embryogenesis. Given the expression images, how to annotate them for the study of Drosophila embryonic development is the next urgent task. In order to speed up the labor-intensive labeling work, automatic tools are highly desired. 

However, conventional image annotation tools are not applicable here, because the labeling is at the gene-level rather than the image-level, where each gene is represented by a bag of multiple related images, showing a multi-instance phenomenon, and the image quality varies by image orientations and experiment batches. Moreover, different local regions of an image correspond to different CV annotation terms, i.e. an image has multiple labels. Designing an accurate annotation tool in such a multi-instance multi-label (MIML) scenario is a very challenging task.

To address these challenges, we develop a new annotator for the fruit fly embryonic images, AnnoFly. Driven by an attention-enhanced RNN model, it can weigh images of different qualities, so as to focus on the most informative image patterns. We assess the new model on three standard data sets. The experimental results reveal that the attention-based model provides a transparent approach for identifying the important images for labeling, and it substantially enhances the accuracy compared with the existing annotation methods, including both single-instance and multi-instance learning methods.

Input: 1 to 10 gene expression images of Drosophila embryos generated by using in situ hybridization technology.

(Note: For the best annotation performance, we recommend that images are sized to 320x128 pixels and standardized using the procedure described in Konikoff et al. 2012, PMID: 21960044.)

Output: Probabilities of the annotation terms.

(Note: Gene expression patterns are annotated with a controlled vocabulary for developmental anatomy of Drosophila embryo genesis. AnnoFly outputs probabilities for the top 30 most frequent labels according to the CV term frequency in the BDGP database http://insitu.fruitfly.org/cgi-bin/ex/insitu.pl)