Back

Generative modeling for RNA splicing predictions and design

Wu, D.; Maus, N.; Jha, A.; Yang, K.; Wales-McGrath, B. D.; Jewell, S.; Tangiyan, A.; Choi, P.; Gardner, J. R.; Barash, Y.

2025-01-24 bioinformatics
10.1101/2025.01.20.633986 bioRxiv
Show abstract

Alternative splicing (AS) of pre-mRNA plays a crucial role in tissue-specific gene regulation, with disease implications due to splicing defects. Predicting and manipulating AS can therefore uncover new regulatory mechanisms and aid in therapeutics design. We introduce TrASPr+BOS, a generative AI model with Bayesian Optimization for predicting and designing RNA for tissue-specific splicing outcomes. TrASPr is a multi-transformer model that can handle different types of AS events and generalize to unseen cellular conditions. It then serves as an oracle, generating labeled data to train a Bayesian Optimization for Splicing (BOS) algorithm to design RNA for condition-specific splicing outcomes. We show TrASPr+BOS outperforms existing methods, enhancing tissue-specific AUPRC by up to 1.8 fold and capturing tissue-specific regulatory elements. We validate hundreds of predicted novel tissue-specific splicing variations and confirm new regulatory elements using dCas13. We envision TrASPr+BOS as a light yet accurate method researchers can probe or adopt for specific tasks.

Published in eLife (predicted rank #14) · training set

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

1
Genome Biology
○ 637 papers in training set
Top 0.3%
18.3%
Similar papers in this journal
2
Bioinformatics
◐ 1204 papers in training set
Top 1%
18.3%
Similar papers in this journal
3
Genome Research
● 468 papers in training set
Top 0.5%
9.6%
Similar papers in this journal
4
Nucleic Acids Research
◐ 1281 papers in training set
Top 3%
6.7%
Similar papers in this journal
50% of probability mass above
5
RNA
● 189 papers in training set
Top 0.3%
6.2%
Similar papers in this journal
6
Nature Communications
○ 5641 papers in training set
Top 27%
5.4%
7
Bioinformatics Advances
◐ 203 papers in training set
Top 1%
4.3%
8
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 1%
4.0%
9
Nature Methods
○ 385 papers in training set
Top 3%
3.2%
10
The American Journal of Human Genetics
○ 234 papers in training set
Top 2%
2.4%
11
PLOS Computational Biology
● 1863 papers in training set
Top 12%
2.4%
12
Cell Systems
○ 201 papers in training set
Top 2%
2.1%
13
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 28%
1.7%
eLife · published here
● 5828 papers in training set
Top 54%
1.5%
15
Briefings in Bioinformatics
◐ 354 papers in training set
Top 6%
1.1%
16
Molecular Biology and Evolution
◐ 542 papers in training set
Top 4%
1.1%
17
Nature Biotechnology
○ 172 papers in training set
Top 4%
1.1%
18
Cell Reports Methods
○ 165 papers in training set
Top 3%
1.1%
19
BMC Genomics
○ 406 papers in training set
Top 8%
0.8%
20
GENETICS
◐ 483 papers in training set
Top 4%
0.8%
21
BMC Bioinformatics
○ 457 papers in training set
Top 6%
0.6%
22
Nature Machine Intelligence
○ 70 papers in training set
Top 3%
0.6%

"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.