CoChat
Sign Up
PreprintCited by 7Computational Drug Discovery MethodsGene expression and cancer classificationMachine Learning in Materials Science

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

Compound activity prediction with dose-dependent transcriptomic profiles and deep learning

Open access
Godinez, William J., Trifonov, Vladimir, Fang, Bin, Kuzu, Guray, Pei, Luying, Guiguemde, W. Armand, Martin, Eric J., King, Frederick J., Jenkins, Jeremy L., Skewes-Cox, Peter·2023·Journal of Chemical Information and Modeling
DOI 10.1101/2023.08.03.551883

Preprint — published as 10.1021/acs.jcim.3c01855 · Paper page

Open this paper in CoChat — free accountOpen PDF

Abstract

Predicting compound activity in assays is a long-standing challenge in drug discovery. Computational models based on compound-induced gene-expression signatures from a single profiling assay have shown promise towards predicting compound activity in other, seemingly unrelated, assays. Applications of such models include predicting mechanisms-of-action (MoA) for phenotypic hits, identifying off-target activities, and identifying polypharmacologies. Here, we introduce Transcriptomics-to-Activity Transformer (TAT) models that leverage gene-expression profiles observed over compound treatment at multiple concentrations to predict compound activity in other biochemical or cellular assays. We built TAT models based on gene-expression data from a RASL-Seq assay to predict the activity of 2,692 compounds in 262 dose response assays. We obtained useful models for 51% of the assays as determined through a realistic held-out set. Prospectively, we experimentally validated the activity predictions of a TAT model in a malaria inhibition assay. With a 63% hit rate, TAT successfully identified several sub-micromolar malaria inhibitors. Our results thus demonstrate the potential of transcriptomic responses over compound concentration and the TAT modeling framework as a cost-efficient way to identify the bioactivities of promising compounds across many assays.

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 · 10.1101/2023.08.03.551883

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

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

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

Flagged first, then by citations

Research works printed but not linked: 36

  1. 10.2174/138161207782794257 · DOI
  2. 10.1039/c8sc00148k · DOI · Paper page
  3. 2019, All-Assay-Max2 pQSAR: Activity Predictions as Accurate as Four-Concentration IC50s for 8558 Novartis Assays, Journal of Chemical Information and Modeling, 59, 4450, 10.1021/acs.jcim.9b00375 · DOI
  4. 2020, Using Predicted Bioactivity Profiles to Improve Predictive Modeling, J. Chem. Inf. Model, 60, 2830, 10.1021/acs.jcim.0c00250 · DOI
  5. 10.1021/acs.jcim.0c00864 · DOI
  6. 10.1126/science.1132939 · DOI · Paper page
  7. 2012, RASL-seq for Massively Parallel and Quantitative Analysis of Gene Expression, Curr. Protoc. Mol. Biol, 98, 4.13.1
  8. 10.1016/j.cell.2017.10.049 · DOI · Paper page
  9. 10.1038/s41467-017-00136-z · DOI
  10. 10.1038/s41467-018-06500-x · DOI · Paper page
  11. Baillif, B. , Wichard, J. , Méndez-Lucio, O. & Rouquié, D . Exploring the Use of Compound-Induced Transcriptomic Data Generated From Cell Lines to Predict Compound Activity Toward Molecular Targets. Front. Chem. 8, (2020). · DOI
  12. 2023, Predicting compound activity from phenotypic profiles and chemical structures, Nat. Commun, 14, 1967, 10.1038/s41467-023-37570-1 · DOI
  13. 2022, Integrating cell morphology with gene expression and chemical structure to aid mitochondrial toxicity detection, Commun. Biol, 5, 858, 10.1038/s42003-022-03763-5 · DOI
  14. 2022, High-dimensional gene expression and morphology profiles of cells across 28,000 genetic and chemical perturbations, Nat. Methods, 19, 1550, 10.1038/s41592-022-01667-0 · DOI
  15. 2023, Using chemical and biological data to predict drug toxicity, SLAS Discov, 28, 53, 10.1016/j.slasd.2022.12.003 · DOI
  16. 10.1371/journal.pcbi.1000512 · DOI
  17. 2020, Gene-signature-derived IC50s/EC50s reflect the potency of causative upstream targets and downstream phenotypes, Sci. Rep, 10, 9670, 10.1038/s41598-020-66533-5 · DOI
  18. Vaswani, A. et al. Attention is All you Need. in Advances in Neural Information Processing Systems (eds. Guyon, I. , et al.) vol. 30 (Curran Associates, Inc., 2017).
  19. 10.18653/v1/N19-1423 · DOI · Paper page
  20. 2020, Advances in Neural Information Processing Systems, 33, 1877
  21. Wei, J. , et al. Chain of Thought Prompting Elicits Reasoning in Large Language Models. in Advances in Neural Information Processing Systems (eds. Oh, A. H. , Agarwal, A. , Belgrave, D. & Cho, K. ) (2022).
  22. Yun, S. , Jeong, M. , Kim, R. , Kang, J. & Kim, H. J. Graph Transformer Networks. in Advances in Neural Information Processing Systems (eds. Wallach, H. , et al.) vol. 32 (Curran Associates, Inc., 2019).
  23. Dosovitskiy, A. , et al. An Image is Worth 16×16 Words: Transformers for Image Recognition at Scale. in International Conference on Learning Representations (2021).
  24. Alayrac, J.-B. , et al. Flamingo: a Visual Language Model for Few-Shot Learning. in Advances in Neural Information Processing Systems (eds. Oh, A. H. , Agarwal, A. , Belgrave, D. & Cho, K. ) (2022).
  25. 2019, Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction, ACS Central Science, 5, 1572, 10.1021/acscentsci.9b00576 · DOI
  26. Madani, A. et al. Large language models generate functional protein sequences across diverse families. Nat. Biotechnol. (2023). · DOI · Paper page
  27. 2020, Systematic Chemogenetic Library Assembly, Cell Chem. Biol, 27, 1124, 10.1016/j.chembiol.2020.07.004 · DOI
  28. 10.1101/580654 · DOI
  29. 2016, Drug Repositioning for Cancer Therapy Based on Large-Scale Drug-Induced Transcriptional Signatures, PLOS ONE, 11, e0150460, 10.1371/journal.pone.0150460 · DOI
  30. 10.1089/adt.2018.845 · DOI
  31. 2016, Transcriptional Characterization of Compounds: Lessons Learned from the Public LINCS Data, ASSAY Drug Dev. Technol, 14, 252, 10.1089/adt.2016.715 · DOI
  32. Kingma, D. P. & Ba, J . Adam: A Method for Stochastic Optimization. in 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings (2015).
  33. 2011, Scikit-learn: Machine Learning in Python, J. Mach. Learn. Res, 2, 2825
  34. 10.1126/science.781840 · DOI
  35. 10.1128/AAC.01607-06 · DOI
  36. 2018, Helios: History and Anatomy of a Successful In-House Enterprise High-Throughput Screening and Profiling Data Analysis System, SLAS Discov. Adv. Sci. Drug Discov, 23, 474, 10.1177/2472555217752140 · DOI

Metadata

Authors
Godinez, W. J., Trifonov, V., Fang, B., Kuzu, G., Pei, L., Guiguemde, W. A., Martin, E. J., King, F. J., Jenkins, J. L., & Skewes-Cox, P.
Corresponding author
Godinez, William J.
ORCID
Venue
Journal of Chemical Information and Modeling
Publisher
openRxiv
Published
2023-08-06
Volume
64
Issue
7
Pages
2695-2704
ISSN
1549-9596 (ISSN-L)
DOI
10.1101/2023.08.03.551883
OpenAlex
W4391389313
Cited by
7
References
1
Citations by year
2026: 1 · 2025: 4 · 2024: 2
FWCI
1.47
Type
journal article
Language
en
Open access
Licence
cc-by-nc-nd
Locations
  • Journal of Chemical Information and Modeling (publishedVersion)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • The Novartis Repository (Novartis) (submittedVersion)
Topics
  • Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene expression and cancer classification
  • Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
Keywords
compound activity prediction, dose-dependent gene expression, gene expression signatures, dose-response assay, off-target effects, polypharmacology, mechanism of action, deep learning
MeSH terms
Deep Learning, Humans, Malaria, Gene Expression Profiling, Drug Discovery, Transcriptome

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