Back

FlowTransOP: Distributional Translation of Omics Signatures via Constrained Deep Flow Matching

Meimetis, N.; Magliacane, S.; Hoang, T. N.; Lauffenburger, D. A.

2026-05-29 bioinformatics
10.64898/2026.05.27.728305 bioRxiv
Show abstract

Observations from pre-clinical models rarely generalize to human patients, leading to many failures in clinical trials. Most existing methods cannot handle domains with non-overlapping features and no paired samples. Here, we developed FlowTransOP to translate biological observations across such domains without requiring 1-to-1 feature mappings and paired data, while providing a guideline for model selection across four translational regimes. We use flow matching to align full domain distributions in a pre-aligned latent space, with a structural regularization term that keeps similar conditions proximate after transformation. FlowTransOP remains competitive with gold-standard approaches requiring paired samples, but outperforms them when pairs become scarce (<35 pairs) or when cross-domain features are only moderately correlated (r<=0.58). Overall, FlowTransOP can translate perturbations between pre-clinical models and patients when direct correspondences are unavailable, enabling reliable therapeutic inference. As a proof-of-concept, we trained a foundational mouse-human transcriptomic map on ARCHS4 and applied it to liver disease predictions.

Matching journals

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

1
Nature Communications
○ 5641 papers in training set
Top 5%
26.2%
Similar papers in this journal
2
Nature Methods
○ 385 papers in training set
Top 0.8%
12.5%
Similar papers in this journal
3
Cell Systems
○ 201 papers in training set
Top 0.3%
9.6%
Similar papers in this journal
4
Nature Machine Intelligence
○ 70 papers in training set
Top 0.4%
5.4%
Similar papers in this journal
50% of probability mass above
5
Nature Biotechnology
○ 172 papers in training set
Top 0.8%
4.8%
Similar papers in this journal
6
Genome Biology
○ 637 papers in training set
Top 3%
4.8%
7
Nature
○ 645 papers in training set
Top 4%
4.3%
8
Bioinformatics
◐ 1204 papers in training set
Top 5%
4.0%
9
Nature Biomedical Engineering
○ 47 papers in training set
Top 0.3%
3.4%
10
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 22%
2.4%
11
Briefings in Bioinformatics
◐ 354 papers in training set
Top 4%
2.4%
12
Nucleic Acids Research
◐ 1281 papers in training set
Top 10%
1.5%
13
Cell Reports Methods
○ 165 papers in training set
Top 2%
1.4%
14
Cell Genomics
○ 172 papers in training set
Top 3%
1.1%
15
iScience
○ 1154 papers in training set
Top 28%
1.1%
16
Patterns
○ 78 papers in training set
Top 2%
1.1%
17
PLOS Computational Biology
● 1863 papers in training set
Top 17%
1.1%
18
Scientific Reports
○ 3612 papers in training set
Top 64%
1.1%
19
Nature Computational Science
○ 55 papers in training set
Top 2%
0.8%
20
Communications Biology
○ 993 papers in training set
Top 31%
0.8%
21
eLife
● 5828 papers in training set
Top 67%
0.8%
22
Nature Genetics
○ 286 papers in training set
Top 5%
0.8%
23
Molecular Systems Biology
○ 162 papers in training set
Top 3%
0.8%
24
Cell Reports Medicine
○ 153 papers in training set
Top 6%
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.