Back

SIEVE: Sparse Interpretable Exome Variant Explainer

Bagordo, D.; Grigorean, C.; Mazzanti, A.; Ruocco, M.; Lescai, F.

2026-08-06 bioinformatics
10.64898/2026.08.01.742212 bioRxiv
Show abstract

Whole-exome case-control studies contain rare and common variation, yet analytical methods usually partition the frequency spectrum, discard positional context, or depend on fixed annotations. We present SIEVE, a deep-learning framework for interpretable variant and gene prioritisation. It reads every observed exonic variant without a frequency filter, represents genomic position through self-attention, and calibrates attributions against a permuted-label null. Across coronary artery disease, early-onset myocardial infarction and Crohns disease, discrimination matches the liability-threshold expectation for each trait, while recovery of catalogued associations rises with annotation depth. Against burden testing, single-variant association and polygenic scoring, SIEVE recovers overlapping but largely distinct candidates.

Matching journals

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

1
Nature Communications
○ 5641 papers in training set
Top 10%
18.2%
Similar papers in this journal
2
Nature Genetics
○ 286 papers in training set
Top 0.2%
18.2%
Similar papers in this journal
3
Nature Biotechnology
○ 172 papers in training set
Top 0.3%
7.8%
Similar papers in this journal
4
Nature
○ 645 papers in training set
Top 2%
6.6%
Similar papers in this journal
50% of probability mass above
5
Genome Biology
○ 637 papers in training set
Top 2%
6.2%
Similar papers in this journal
6
Nature Methods
○ 385 papers in training set
Top 2%
5.4%
7
Science
● 477 papers in training set
Top 1%
5.4%
8
Genome Research
● 468 papers in training set
Top 2%
3.4%
9
Bioinformatics
◐ 1204 papers in training set
Top 5%
3.2%
10
The American Journal of Human Genetics
○ 234 papers in training set
Top 2%
2.6%
11
Cell Systems
○ 201 papers in training set
Top 2%
2.4%
12
Nucleic Acids Research
◐ 1281 papers in training set
Top 7%
2.4%
13
Nature Machine Intelligence
○ 70 papers in training set
Top 1%
2.1%
14
Cell
○ 431 papers in training set
Top 5%
1.9%
15
Genome Medicine
○ 183 papers in training set
Top 3%
1.4%
16
Nature Computational Science
○ 55 papers in training set
Top 1%
1.1%
17
Nature Biomedical Engineering
○ 47 papers in training set
Top 2%
0.8%
18
Cell Genomics
○ 172 papers in training set
Top 5%
0.8%
19
Science Advances
● 1243 papers in training set
Top 31%
0.8%
20
PLOS Computational Biology
● 1863 papers in training set
Top 20%
0.8%

"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.