Back

Uncovering Heterogeneous Effects via Localized Feature Selection

Liu, X.; Gu, J.; Chen, Z.; Chu, B.; Liu, L.; Morrison, T.; Butler, R. R.; Edelson, J.; Li, J.; Longo, F. M.; Tang, H.; Ionita-laza, I.; Sabatti, C.; Candes, E.; He, Z.

2025-06-09 bioinformatics
10.1101/2025.06.03.657761 bioRxiv
Show abstract

Identifying features that interact to trigger disease, while accounting for heterogeneity across diverse populations, is essential for the development of precision and targeted medicine. Despite the availability of vast and complex health-related datasets, most existing works focus on identifying disease-associated features at the population level or within a few subpopulations, often overlooking individual-level heterogeneity within these groups. To address this limitation, we propose a novel framework that utilizes localized test statistics to identify disease-associated features tailored to individual profiles. Our method leverages the recently developed knockoffs methodology to control the noise level of the selection set so that the results are replicable. Moreover, it allows for the discovery of hidden heterogeneous effects within the data, as demonstrated in an application to single-cell RNA sequencing data for Alzheimers disease. By aggregating localized feature selection results, our framework also enables powerful population-level feature selection. Our framework provides a powerful tool for exploratory studies of precision medicine, offering the potential to generate novel hypotheses for confirmatory biological experiments.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

1
Nature Communications
○ 5641 papers in training set
Top 14%
12.8%
Similar papers in this journal
2
Patterns
○ 78 papers in training set
Top 0.1%
8.8%
Similar papers in this journal
3
Bioinformatics
◐ 1204 papers in training set
Top 3%
7.8%
Similar papers in this journal
4
Cell Systems
○ 201 papers in training set
Top 0.6%
6.2%
Similar papers in this journal
5
PLOS Computational Biology
● 1863 papers in training set
Top 6%
5.5%
Similar papers in this journal
6
Communications Biology
○ 993 papers in training set
Top 2%
4.8%
7
Briefings in Bioinformatics
◐ 354 papers in training set
Top 2%
4.0%
50% of probability mass above
8
The American Journal of Human Genetics
○ 234 papers in training set
Top 1%
4.0%
9
Genome Biology
○ 637 papers in training set
Top 3%
4.0%
10
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 14%
3.5%
11
Nature Computational Science
○ 55 papers in training set
Top 0.2%
3.2%
12
Statistics in Medicine
○ 40 papers in training set
Top 0.2%
2.6%
13
Genome Research
● 468 papers in training set
Top 2%
2.6%
14
BMC Bioinformatics
○ 457 papers in training set
Top 3%
2.4%
15
Nature Methods
○ 385 papers in training set
Top 4%
2.1%
16
Scientific Reports
○ 3612 papers in training set
Top 48%
2.0%
17
PNAS Nexus
◐ 159 papers in training set
Top 0.8%
1.9%
18
Biostatistics
◐ 24 papers in training set
Top 0.2%
1.9%
19
eLife
● 5828 papers in training set
Top 51%
1.7%
20
Nature Machine Intelligence
○ 70 papers in training set
Top 2%
1.1%
21
iScience
○ 1154 papers in training set
Top 27%
1.1%
22
Genetic Epidemiology
○ 55 papers in training set
Top 0.6%
1.0%
23
Bioinformatics Advances
◐ 203 papers in training set
Top 4%
1.0%
24
Nature Genetics
○ 286 papers in training set
Top 5%
0.8%
25
PLOS ONE
● 5266 papers in training set
Top 59%
0.8%
26
Biometrics
◐ 23 papers in training set
Top 0.3%
0.6%
27
Journal of Biomedical Informatics
○ 47 papers in training set
Top 1%
0.6%
28
NeuroImage
○ 903 papers in training set
Top 6%
0.6%
29
Cell Reports Methods
○ 165 papers in training set
Top 4%
0.6%
30
Cell Genomics
○ 172 papers in training set
Top 5%
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.