CoChat
Sign Up
Cited by 320Genomics and Chromatin DynamicsRNA Research and SplicingBioinformatics and Genomic Networks

The DOI matches its Crossref record; 76 of the 80 references it cites were found in a registry or an index.

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

Open access
Basu, Sumanta, Kumbier, Karl, Brown, James B., Yu, Bin·2018·Proceedings of the National Academy of Sciences
DOI 10.1073/pnas.1711236115PMC PMC5828575

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

Significance: We developed a predictive, stable, and interpretable tool: the iterative random forest algorithm (iRF). iRF discovers high-order interactions among biomolecules with the same order of computational cost as random forests. We demonstrate the efficacy of iRF by finding known and promising interactions among biomolecules, of up to fifth and sixth order, in two data examples in transcriptional regulation and alternative splicing.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1073/pnas.1711236115

Cites

76 of 76 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1. iRF workflow. Iteratively reweighted RFs (blue boxes) are trained on full data D and pass Gini importance as weights to the next iteration. In iteration K (red box), feature-weighted RFs are grown using w^(K) on B bootstrap samples of the full data D(1),…,D(B). Decision paths and predicted leaf node labels are passed to the RIT (green box), which computes prevalent interactions in the RF ensemble. Recovered interactions are scored for stability across (outer-layer) bootstrap samples.
Fig. 1. iRF workflow. Iteratively reweighted RFs (blue boxes) are trained on full data D and pass Gini importance as weights to the next iteration. In iteration K (red box), feature-weighted RFs are grown using w^(K) on B bootstrap samples of the full data D(1),…,D(B). Decision paths and predicted leaf node labels are passed to the RIT (green box), which computes prevalent interactions in the RF ensemble. Recovered interactions are scored for stability across (outer-layer) bootstrap samples.CC BY-NC-ND · PubMed Central
Fig. 2. (A) Accuracy of iRF (AUC-PR) in predicting active elements from TF binding and histone modification data. (B) The 20 most stable interactions recovered by iRF after five iterations. Interactions that are a strict subset of another interaction with stability score ≥0.5 have been removed for cleaner visualization. iRF recovers known interactions among Gt, Kr, and Hb and interacting roles of master regulator Zld. (C) Surface maps demonstrating the proportion of active enhancers by quantiles of Zld, Gt, and Kr binding (held-out test data). On the subset of data where Kr binding is lower than the median Kr level, the proportion of active enhancers does not change with Gt and Zld. On the subset of data with Kr binding above the median level, the structure of the response surface reflects an order-3 AND interaction: Increased levels of Zld, Gt, and Kr binding are indicative of enhancer status for a subset of observations. (D) Quantiles of Zld, Gt, and Kr binding grouped by enhancer status (balanced sample of held-out test data). The block of active elements highlighted in red represents the subset of observations for which the AND interaction is active.
Fig. 2. (A) Accuracy of iRF (AUC-PR) in predicting active elements from TF binding and histone modification data. (B) The 20 most stable interactions recovered by iRF after five iterations. Interactions that are a strict subset of another interaction with stability score ≥0.5 have been removed for cleaner visualization. iRF recovers known interactions among Gt, Kr, and Hb and interacting roles of master regulator Zld. (C) Surface maps demonstrating the proportion of active enhancers by quantiles of Zld, Gt, and Kr binding (held-out test data). On the subset of data where Kr binding is lower than the median Kr level, the proportion of active enhancers does not change with Gt and Zld. On the subset of data with Kr binding above the median level, the structure of the response surface reflects an order-3 AND interaction: Increased levels of Zld, Gt, and Kr binding are indicative of enhancer status for a subset of observations. (D) Quantiles of Zld, Gt, and Kr binding grouped by enhancer status (balanced sample of held-out test data). The block of active elements highlighted in red represents the subset of observations for which the AND interaction is active.CC BY-NC-ND · PubMed Central
Fig. 3. (A) Accuracy of iRF (AUC-PR) in classifying included exons from excluded exons in held-out test data. iRF shows 7% increase in AUC-PR over RF. (B) An order-6 interaction recovered by iRF (stability score 0.5) displayed on a superheat map which juxtaposes two separately clustered heat maps of exons with high and low splicing rates. Coenrichment of all six plotted features reflects an AND-type rule indicative of high splicing rates for the exons highlighted in red (held-out test data). The subset of Pol II, S2 phospho-Pol II, H3K36me3, H3K79me2, and H4K20me1 was recovered as an order-5 interaction in all bootstrap samples (stability score 1.0). (C) The 20 most stable interactions recovered in the second iteration of iRF. Interactions that are a strict subset of another interaction with stability score ≥0.5 have been removed for cleaner visualization.
Fig. 3. (A) Accuracy of iRF (AUC-PR) in classifying included exons from excluded exons in held-out test data. iRF shows 7% increase in AUC-PR over RF. (B) An order-6 interaction recovered by iRF (stability score 0.5) displayed on a superheat map which juxtaposes two separately clustered heat maps of exons with high and low splicing rates. Coenrichment of all six plotted features reflects an AND-type rule indicative of high splicing rates for the exons highlighted in red (held-out test data). The subset of Pol II, S2 phospho-Pol II, H3K36me3, H3K79me2, and H4K20me1 was recovered as an order-5 interaction in all bootstrap samples (stability score 1.0). (C) The 20 most stable interactions recovered in the second iteration of iRF. Interactions that are a strict subset of another interaction with stability score ≥0.5 have been removed for cleaner visualization.CC BY-NC-ND · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 80 references

Research works printed but not linked: 1

  1. RS Hallmann, LG Schneeweiss, E Correa, J Zamora, Fine needle aspiration biopsy of thymic carcinoid tumor: A case with immunocytochemical correlation. Acta Cytol 42, 1042–1043 (1998).

Cited by

Sorted by citations

Items 301–320 of 320

Related

See all

Metadata

Authors
Basu, S., Kumbier, K., Brown, J. B., & Yu, B.
Affiliations
  • Cornell University (US)
  • University of California, Berkeley (US)
  • Lawrence Berkeley National Laboratory (US)
Corresponding author
  • Brown, James B.
  • Yu, Bin
ORCID
Venue
Proceedings of the National Academy of Sciences
Publisher
National Academy of Sciences
Published
2018-01-19
Volume
115
Issue
8
Pages
1943-1948
ISSN
  • 0027-8424 (ISSN-L)
  • 1091-6490
DOI
10.1073/pnas.1711236115
PMC
PMC5828575
OpenAlex
W2731142262
Cited by
317
References
80
Citations by year
2026: 24 · 2025: 32 · 2024: 39 · 2023: 51 · 2022: 48 · 2021: 42 · 2020: 46 · 2019: 20 · 2018: 12
FWCI
10.76
Type
journal article
Language
en
Open access
Licence
Locations
  • Proceedings of the National Academy of Sciences (publishedVersion, cc-by-nc-nd)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • eScholarship (California Digital Library) (submittedVersion)
  • OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • HHS | NIH | National Human Genome Research Institute (U01HG007031, R00 HG006698)
  • DOD | United States Army | RDECOM | Army Research Office (W911NF1710005)
  • DOD | United States Navy | Office of Naval Research (N00014-16-1- 2664)
  • U.S. Department of Energy (DOE DE-AC02-05CH11231, DE-SC0017069)
  • National Science Foundation (CCF-0939370)
  • HHS | NIH |U.S. National Library of Medicine (T32LM012417)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Chromatin Dynamics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › RNA Research and Splicing
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
Keywords
higher-order interactions, epistasis, H3K36me3, epigenetic interactions
MeSH terms
Algorithms, Animals, Drosophila, Models, Genetic, Alternative Splicing, Gene Expression Regulation, Developmental, Computational Biology, Gene Regulatory Networks, Genome-Wide Association Study

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review