CoChat
Sign Up
Cited by 152Computational Drug Discovery MethodsMachine Learning in Materials ScienceEffects and risks of endocrine disrupting chemicals

Comparing Multiple Machine Learning Algorithms and Metrics for Estrogen Receptor Binding Prediction

Open access
Russo, Daniel P., Zorn, Kimberley M., Clark, Alex M., Zhu, Hao, Ekins, Sean·2018·Molecular Pharmaceutics
DOI 10.1021/acs.molpharmaceut.8b00546PMC PMC6181119
Open this paper in CoChat — free account

Abstract

Many chemicals that disrupt endocrine function have been linked to a variety of adverse biological outcomes. However, screening for endocrine disruption using in vitro or in vivo approaches is costly and time-consuming. Computational methods, e.g., quantitative structure-activity relationship models, have become more reliable due to bigger training sets, increased computing power, and advanced machine learning algorithms, such as multilayered artificial neural networks. Machine learning models can be used to predict compounds for endocrine disrupting capabilities, such as binding to the estrogen receptor (ER), and allow for prioritization and further testing. In this work, an exhaustive comparison of multiple machine learning algorithms, chemical spaces, and evaluation metrics for ER binding was performed on public data sets curated using in-house cheminformatics software (Assay Central). Chemical features utilized in modeling consisted of binary fingerprints (ECFP6, FCFP6, ToxPrint, or MACCS keys) and continuous molecular descriptors from RDKit. Each feature set was subjected to classic machine learning algorithms (Bernoulli Naive Bayes, AdaBoost Decision Tree, Random Forest, Support Vector Machine) and Deep Neural Networks (DNN). Models were evaluated using a variety of metrics: recall, precision, F1-score, accuracy, area under the receiver operating characteristic curve, Cohen's Kappa, and Matthews correlation coefficient. For predicting compounds within the training set, DNN has an accuracy higher than that of other methods; however, in 5-fold cross validation and external test set predictions, DNN and most classic machine learning models perform similarly regardless of the data set or molecular descriptors used. We have also used the rank normalized scores as a performance-criteria for each machine learning method, and Random Forest performed best on the validation set when ranked by metric or by data sets. These results suggest classic machine learning algorithms may be sufficient to develop high quality predictive models of ER activity.

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 · 10.1021/acs.molpharmaceut.8b00546

Cites

75 of 75 references verified0 citation errors · 0 not checkable

Statistics

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?

  • For external test set predictions on multiple estrogen receptor datasets, DNN and most classic machine learning models perform similarly regardless of dataset or molecular descriptors.

    “For external test set predictions DNN and most classic machine learning models perform similarly regardless of dataset or molecular descriptors46.”

    From Exploiting machine learning for end-to-end drug discovery and development (2019) · cites this paper as [46]

  • For predicting compounds within the training set for multiple estrogen receptor datasets, DNNs had higher accuracy than other methods in 5-fold cross validation.

    “For predicting compounds within the training set, DNNs had higher accuracy than other methods in 5-fold cross validation.”

    From Exploiting machine learning for end-to-end drug discovery and development (2019) · cites this paper as [46]

Self-check

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

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

Cites

Flagged first, then by citations

Research works printed but not linked: 2

  1. [35]Korotcov A; Tkachenko V; Russo DP; Ekins S Comparison of Deep Learning With Multiple Machine Learning Methods and Metrics Using Diverse Drug Discovery Datasets. Mol Pharm 2018, 14, 4462– 4475. PMC5741413 29096442
  2. [55]Martin TM Prediction of in vitro and in vivo oestrogen receptor activity using hierarchical clustering. SAR QSAR Environ Res 2016, 27, (1), 17– 30. 26784454

Cited by

Sorted by citations

Related

Authors
Russo, D. P., Zorn, K. M., Clark, A. M., Zhu, H., & Ekins, S.
Affiliations
  • Rutgers, The State University of New Jersey (US)
  • Collaborations Pharmaceuticals (United States) (US)
  • Molecular Materials Informatics, Inc., Montreal, Quebec H3J 2S1, Canada
Corresponding author
Ekins, Sean
ORCID
Venue
Molecular Pharmaceutics
Publisher
American Chemical Society (ACS)
Published
2018-08-16
Volume
15
Issue
10
Pages
4361-4370
ISSN
  • 1543-8384 (ISSN-L)
  • 1543-8392
DOI
10.1021/acs.molpharmaceut.8b00546
PMC
PMC6181119
OpenAlex
W2887039457
Cited by
152
References
75
Citations by year
2026: 7 · 2025: 12 · 2024: 15 · 2023: 16 · 2022: 24 · 2021: 26 · 2020: 31 · 2019: 17 · 2018: 4
FWCI
14.59
Type
journal article
Language
en
Open access
Locations
  • Molecular Pharmaceutics (publishedVersion)
  • PubMed (publishedVersion)
  • PubMed Central (acceptedVersion)
Funders
National Institute of General Medical Sciences (R43GM122196)
Topics
  • Physical Sciences › Computer Science › Computational Theory and Mathematics › Computational Drug Discovery Methods
  • Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
  • Physical Sciences › Environmental Science › Health, Toxicology and Mutagenesis › Effects and risks of endocrine disrupting chemicals
Keywords
endocrine disruptors, machine learning algorithm comparison, deep neural network, random forest, molecular descriptors, chemical fingerprints, evaluation metrics, predictive toxicology, chemical prioritization
MeSH terms
Machine Learning, Algorithms, Animals, Bayes Theorem, Humans, Protein Binding, Receptors, Estrogen, Software, Support Vector Machine

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