CoChat
Sign Up
PreprintCited by 4Computational Drug Discovery MethodsFerroptosis and cancer prognosisGene expression and cancer classification

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

Learning chemical sensitivity reveals mechanisms of cellular response

Open access
Connell, William, Garcia, Kristle, Goodarzi, Hani, Keiser, Michael J.·2023·Communications Biology
DOI 10.1101/2023.08.26.554851PMC PMC11402971

Preprint — published as 10.1038/s42003-024-06865-4 · Paper page

Open this paper in CoChat — free accountOpen PDF

Abstract

Chemical probes interrogate disease mechanisms at the molecular level by linking genetic changes to observable traits. However, comprehensive chemical screens in diverse biological models are impractical. To address this challenge, we developed ChemProbe, a model that predicts cellular sensitivity to hundreds of molecular probes and drugs by learning to combine transcriptomes and chemical structures. Using ChemProbe, we inferred the chemical sensitivity of cancer cell lines and tumor samples and analyzed how the model makes predictions. We retrospectively evaluated drug response predictions for precision breast cancer treatment and prospectively validated chemical sensitivity predictions in new cellular models, including a genetically modified cell line. Our model interpretation analysis identified transcriptome features reflecting compound targets and protein network modules, identifying genes that drive ferroptosis. ChemProbe is an interpretable in silico screening tool that allows researchers to measure cellular response to diverse compounds, facilitating research into molecular mechanisms of chemical sensitivity.

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 · 10.1101/2023.08.26.554851

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: 54

  1. 10.1038/nchembio.1867 · DOI · Paper page
  2. 10.1016/j.chembiol.2010.05.013 · DOI
  3. 10.1016/j.ccell.2017.06.005 · DOI
  4. Roden, D. M. et al. Pharmacogenomics. Lancet 394, 521–532 (2019). · DOI
  5. 2022, Understanding Drug Sensitivity and Tackling Resistance in Cancer, Cancer Res, 82, 1448, 10.1158/0008-5472.CAN-21-3695 · DOI
  6. 10.1093/bib/bbz171 · DOI
  7. 10.1038/nbt.2877 · DOI
  8. Partin, A. et al. Deep learning methods for drug response prediction in cancer: Predominant and emerging trends. Front. Med. 10, 1086097 (2023). · DOI
  9. 10.1371/journal.pone.0061318 · DOI
  10. Chiu, Y.-C. et al. Predicting drug response of tumors from integrated genomic profiles by deep neural networks. BMC Med. Genomics 12, 18 (2019). · DOI
  11. 10.1093/bioinformatics/btz318 · DOI · Paper page
  12. 10.1158/1541-7786.MCR-17-0378 · DOI
  13. Rampasek, L. , Hidru, D. , Smirnov, P. , Haibe-Kains, B. & Goldenberg, A. Dr.VAE: Drug Response Variational Autoencoder. arXiv [stat.ML] (2017).
  14. 2021, DeepDSC: A Deep Learning Method to Predict Drug Sensitivity of Cancer Cell Lines, IEEE/ACM Trans. Comput. Biol. Bioinform, 18, 575, 10.1109/TCBB.2019.2919581 · DOI
  15. 2022, Deep transfer learning of cancer drug responses by integrating bulk and single-cell RNA-seq data, Nat. Commun, 13, 6494, 10.1038/s41467-022-34277-7 · DOI
  16. 10.1093/bioinformatics/btaa822 · DOI
  17. Yi, H.-C. , You, Z.-H. , Huang, D.-S. & Kwoh, C. K . Graph representation learning in bioinformatics: trends, methods and applications. Brief. Bioinform. 23, (2022). · DOI
  18. Zuo, Z. et al. SWnet: a deep learning model for drug response prediction from cancer genomic signatures and compound chemical structures. BMC Bioinformatics 22, 434 (2021). · DOI
  19. 2019, Toward Explainable Anticancer Compound Sensitivity Prediction via Multimodal Attention-Based Convolutional Encoders, Mol. Pharm, 16, 4797, 10.1021/acs.molpharmaceut.9b00520 · DOI
  20. 2018, Cancer Drug Response Profile scan (CDRscan): A Deep Learning Model That Predicts Drug Effectiveness from Cancer Genomic Signature, Sci. Rep, 8, 8857, 10.1038/s41598-018-27214-6 · DOI
  21. 10.1038/s41551-023-01034-0 · DOI
  22. 10.1093/nar/gkaa327 · DOI
  23. Parca, L. et al. Modeling cancer drug response through drug-specific informative genes. Sci. Rep. 9, 15222 (2019). · DOI
  24. Zhang, H. , Chen, Y. & Li, F . Predicting Anticancer Drug Response With Deep Learning Constrained by Signaling Pathways. Frontiers in Bioinformatics 1, 10 (2021). · DOI
  25. 10.1016/j.ccell.2020.09.014 · DOI · Paper page
  26. 10.1038/nchembio.1986 · DOI
  27. 10.1038/s41586-019-1186-3 · DOI · Paper page
  28. Perez, E. , Strub, F. , De Vries, H. & Dumoulin, V . Film: Visual reasoning with a general conditioning layer. arXiv preprint arXiv (2017). · DOI · Paper page
  29. Chuang, K. V. & Keiser, M. J . Comment on ‘Predicting reaction performance in C–N cross-coupling using machine learning’. Science 362, eaat8603 (2018). · DOI
  30. 2018, Adversarial Controls for Scientific Machine Learning, ACS Chem. Biol, 13, 2819, 10.1021/acschembio.8b00881 · DOI
  31. 2020, Effect of Pembrolizumab Plus Neoadjuvant Chemotherapy on Pathologic Complete Response in Women With Early-Stage Breast Cancer: An Analysis of the Ongoing Phase 2 Adaptively Randomized I-SPY2 Trial, JAMA Oncol, 6, 676, 10.1001/jamaoncol.2019.6650 · DOI · Paper page
  32. 10.1016/j.ccell.2022.05.005 · DOI
  33. 10.12659/MSMBR.892101 · DOI
  34. 1997, Analysis of the FHIT gene and FRA3B region in sporadic breast cancer, preneoplastic lesions, and familial breast cancer probands, Cancer Res, 57, 3664
  35. 10.1002/(SICI)1097-0215(19981209)78:6<766::AID-IJC15>3.0.CO;2-L · DOI
  36. 1980, Variations in cell form and cytoskeleton in human breast carcinoma cells in vitro, Cancer Res, 40, 3118
  37. 10.1007/BF02616120 · DOI · Paper page
  38. 10.1038/s41587-019-0037-y · DOI · Paper page
  39. 10.1038/nature03799 · DOI · Paper page
  40. 2022, Two isoleucyl tRNAs that decode synonymous codons divergently regulate breast cancer metastatic growth by controlling translation of proliferation-regulating genes, Nat Cancer, 3, 1484, 10.1038/s43018-022-00469-9 · DOI
  41. 10.1016/j.cell.2014.12.018 · DOI · Paper page
  42. Gupta, A. & Arora, S . A Simple Saliency Method That Passes the Sanity Checks. arXiv [cs.LG] (2019).
  43. Adebayo, J., et al. Sanity Checks for Saliency Maps. arXiv [cs.CV] (2018).
  44. 10.1021/jm401411z · DOI
  45. 10.1093/nar/gku1003 · DOI · Paper page
  46. 10.1016/j.cell.2022.06.003 · DOI
  47. Li, J. et al. Ferroptosis: past, present and future. Cell Death Dis. 11, 88 (2020). · DOI · Paper page
  48. Li, Z. et al. Ribosome stalling during selenoprotein translation exposes a ferroptosis vulnerability. Nat. Chem. Biol. 1–11 (2022). · DOI
  49. 10.1373/clinchem.2008.110056 · DOI
  50. Tsimberidou, A. M. , Fountzilas, E. , Nikanjam, M. & Kurzrock, R . Review of precision cancer medicine: Evolution of the treatment paradigm. Cancer Treat. Rev. 86, 102019 (2020). · DOI
  51. 10.1038/nbt.3300 · DOI · Paper page
  52. Avsec, Ž.,, 2021, Base-resolution models of transcription-factor binding reveal soft motif syntax, Nat. Genet, 53, 354, 10.1038/s41588-021-00782-6 · DOI · Paper page
  53. Rives, A. et al. Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc. Natl. Acad. Sci. U. S. A. 118, (2021). · DOI · Paper page
  54. 2023, A sense-antisense RNA interaction promotes breast cancer metastasis via regulation of NQO1 expression, Nat Cancer, 4, 682, 10.1038/s43018-023-00554-7 · DOI

Metadata

Authors
Connell, W., Garcia, K., Goodarzi, H., & Keiser, M. J.
Affiliations
University of California, San Francisco (US)
Corresponding author
Keiser, Michael J.
ORCID
Venue
Communications Biology
Publisher
openRxiv
Published
2023-08-28
Volume
7
Issue
1
Pages
1149-1149
ISSN
2399-3642 (ISSN-L)
DOI
10.1101/2023.08.26.554851
PMC
PMC11402971
OpenAlex
W4402552237
Cited by
4
References
1
Citations by year
2026: 2 · 2025: 2
FWCI
0.85
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • Communications Biology (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • eScholarship (California Digital Library) (submittedVersion, cc-by)
  • PubMed Central (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
  • U.S. Department of Health and Human Services (U01 MH115747-02)
  • Silicon Valley Community Foundation (DAF2018-191905, 10.13039/100014989)
  • Chan Zuckerberg Initiative (DAF2018-191905)
  • National Institutes of Health
  • National Institute of Mental Health (U01MH115747)
  • National Institute of General Medical Sciences (P41GM103504)
Topics
  • Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Cancer Research › Ferroptosis and cancer prognosis
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene expression and cancer classification
Keywords
chemosensitivity, drug response prediction, cancer cell lines, tumor samples, ferroptosis, model interpretability, compound targets, virtual screening

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