SpliceVisuL: Visualization of Bidirectional LongShort-term Memory Networks for Splice JunctionPrediction
Dutta, A.; Dalmia, A.; R, A.; Singh, K. K.; Anand, A.
Show abstract
Neural models have been able to obtain state-of-the-art performances on several genome sequence-based prediction tasks. Such models take only nucleotide sequences as input and learn relevant features on its own. However, extracting the interpretable motifs from the model remains a challenge. This work explores various existing visualization techniques in their ability to infer relevant sequence information learned by a recurrent neural network (RNN) on the task of splice junction identification. The visualization techniques have been modulated to suit the genome sequences as input. The visualizations inspect genomic regions at the level of a single nucleotide as well as a span of consecutive nucleotides. This inspection is performed based on modification of input sequences (perturbation-based) or the embedding space (back-propagation based). We infer features pertaining to both canonical and non-canonical splicing from a single neural model. Results indicate that the visualization techniques produce comparable performance for branchpoint detection. However, in case of canonical donor and acceptor junction motifs, perturbation based visualizations perform better than back-propagation based visualizations and vice-versa for non-canonical motifs.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Detection of alternative splicing: deep sequencing or deep learning? 95%
- A novel splicing graph allows a direct comparison between exon-based and splice junction-based approaches to alternative splicing detection 94%
- sincFold: end-to-end learning of short- and long-range interactions in RNA secondary structure 94%
Similar papers in this journal
- Informative RNA-base embedding for functional RNA structural alignment and clustering by deep representation learning 94%
- Tailored machine learning models for functional RNA detection in genome-wide screens 93%
- DeepCOMBI: Explainable artificial intelligence for the analysis and discovery in genome-wide association studies 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.