Evidence map›Paper›PMID 29351989›Full record

ArticleProceedings of the National Academy of Sciences of the United States of America2018

Iterative random forests to discover predictive and stable high-order interactions.

Sumanta Basu, Karl Kumbier, James B Brown, Bin Yu

Open access · bronzeAbstract read
In one paragraph

Article in Proceedings of the National Academy of Sciences of the United States of America, 2018. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 112 papers, 1 of them a synthesis that pooled it.

0numbers the graph read from it
0cells of the map it votes in
112citing papers in PubMed, 1 pooled it
11.6field-weighted citation impact, top 1% of its field
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

112 citing papers in PubMed, 1 synthesis or guideline pooled it, 308 citations in OpenAlex.

  1. Pooled it
  2. Trial
  3. Article
  4. Artificial intelligence to investigate metabolomics data for precision medicine.Metabolomics : Official journal of the Metabolomic Society · 2026
    Review
  5. Article
  6. Article
  7. Article
  8. Article
  9. Article
  10. Article
  11. Article
  12. Article
  13. Article
  14. Article
  15. Article
  16. Article
  17. Epistasis in cardiac traits.Nature cardiovascular research · 2025
    Article
  18. Article
  19. Article
  20. Deciphering epistatic genetic regulation of cardiac hypertrophy.medRxiv : the preprint server for health sciences · 2025
    Article

52 more citing papers are in PubMed but not listed here.

4 · The record

Corrections and comments

5 · Who and what money

Authors and funding

4 authors at 2 institutions in 2 countries.

Sumanta BasuDepartment of Biological Statistics and Computational Biology, Cornell University, Ithaca, NY 14853.
Karl KumbierStatistics Department, University of California, Berkeley, CA 94720.
James B BrownData Driven Decisions Department, Preminon LLC, Antioch, CA 94531; binyu@stat.berkeley.edu jbbrown@lbl.gov.
Bin YuData Driven Decisions Department, Preminon LLC, Antioch, CA 94531; binyu@stat.berkeley.edu jbbrown@lbl.gov.
Antioch University · USUniversity of California, Berkeley · US

Funding

Removing statistical bottle-necks in data analysis for the ENCODE ConsortiumU01HG007031 · NHGRI · UNIVERSITY OF CALIFORNIA BERKELEY · PI BICKEL, PETER J · 2012 to 2015
$1.5M
Biomedical Big Data Training Program at UC BerkeleyT32LM012417 · NLM · UNIVERSITY OF CALIFORNIA BERKELEY · PI JORDAN, MICHAEL, NIELSEN, RASMUS · 2016 to 2020
$1.4M
Nonparametric methods for functional and translational genomicsR00HG006698 · NHGRI · UNIVERSITY OF CALIF-LAWRENC BERKELEY LAB · PI BROWN, JAMES BENTLEY · 2014 to 2016
$747k
NHGRI NIH HHS R00 HG006698NHGRI NIH HHS U01 HG007031NLM NIH HHS T32 LM012417
6 · The paper itself

Abstract

Genomics has revolutionized biology, enabling the interrogation of whole transcriptomes, genome-wide binding sites for proteins, and many other molecular processes. However, individual genomic assays measure elements that interact in vivo as components of larger molecular machines. Understanding how these high-order interactions drive gene expression presents a substantial statistical challenge. Building on random forests (RFs) and random intersection trees (RITs) and through extensive, biologically inspired simulations, we developed the iterative random forest algorithm (iRF). iRF trains a feature-weighted ensemble of decision trees to detect stable, high-order interactions with the same order of computational cost as the RF. We demonstrate the utility of iRF for high-order interaction discovery in two prediction problems: enhancer activity in the early

Indexed as

Models, GeneticAlgorithmsAlternative SplicingAnimalsComputational BiologyDrosophilaGene Expression Regulation, DevelopmentalGene Regulatory NetworksGenome-Wide Association Studygenomicshigh-order interactioninterpretable machine learningrandom forestsstability

Identifiers

PMID29351989
PMCPMC5828575
OpenAlexW2731142262

What OpenQuestion holds

Textmetadata
LicenceCC BY-NC-ND
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.