A deep learning model of tumor cell architecture elucidates response and resistance to CDK4/6 inhibitors.
Journal
Nature cancer
ISSN: 2662-1347
Titre abrégé: Nat Cancer
Pays: England
ID NLM: 101761119
Informations de publication
Date de publication:
05 Mar 2024
05 Mar 2024
Historique:
received:
16
05
2022
accepted:
07
02
2024
medline:
6
3
2024
pubmed:
6
3
2024
entrez:
5
3
2024
Statut:
aheadofprint
Résumé
Cyclin-dependent kinase 4 and 6 inhibitors (CDK4/6is) have revolutionized breast cancer therapy. However, <50% of patients have an objective response, and nearly all patients develop resistance during therapy. To elucidate the underlying mechanisms, we constructed an interpretable deep learning model of the response to palbociclib, a CDK4/6i, based on a reference map of multiprotein assemblies in cancer. The model identifies eight core assemblies that integrate rare and common alterations across 90 genes to stratify palbociclib-sensitive versus palbociclib-resistant cell lines. Predictions translate to patients and patient-derived xenografts, whereas single-gene biomarkers do not. Most predictive assemblies can be shown by CRISPR-Cas9 genetic disruption to regulate the CDK4/6i response. Validated assemblies relate to cell-cycle control, growth factor signaling and a histone regulatory complex that we show promotes S-phase entry through the activation of the histone modifiers KAT6A and TBL1XR1 and the transcription factor RUNX1. This study enables an integrated assessment of how a tumor's genetic profile modulates CDK4/6i resistance.
Identifiants
pubmed: 38443662
doi: 10.1038/s43018-024-00740-1
pii: 10.1038/s43018-024-00740-1
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
© 2024. The Author(s).
Références
Hanahan, D. & Weinberg, R. A. The hallmarks of cancer. Cell 100, 57–70 (2000).
pubmed: 10647931
doi: 10.1016/S0092-8674(00)81683-9
Goel, S., Bergholz, J. S. & Zhao, J. J. Targeting CDK4 and CDK6 in cancer. Nat. Rev. Cancer 22, 356–372 (2022).
pubmed: 35304604
pmcid: 9149100
doi: 10.1038/s41568-022-00456-3
Watt, A. C. & Goel, S. Cellular mechanisms underlying response and resistance to CDK4/6 inhibitors in the treatment of hormone receptor-positive breast cancer. Breast Cancer Res. 24, 17 (2022).
pubmed: 35248122
pmcid: 8898415
doi: 10.1186/s13058-022-01510-6
Fassl, A., Geng, Y. & Sicinski, P. CDK4 and CDK6 kinases: from basic science to cancer therapy. Science 375, eabc1495 (2022).
pubmed: 35025636
pmcid: 9048628
doi: 10.1126/science.abc1495
Xu, X.-Q. et al. Intrinsic and acquired resistance to CDK4/6 inhibitors and potential overcoming strategies. Acta Pharmacol. Sin. 42, 171–178 (2021).
pubmed: 32504067
doi: 10.1038/s41401-020-0416-4
Gao, J. J. et al. CDK4/6 inhibitor treatment for patients with hormone receptor-positive, HER2-negative, advanced or metastatic breast cancer: a US Food and Drug Administration pooled analysis. Lancet Oncol. 21, 250–260 (2020).
pubmed: 31859246
doi: 10.1016/S1470-2045(19)30804-6
Li, J. et al. Association of cyclin-dependent kinases 4 and 6 inhibitors with survival in patients with hormone receptor-positive metastatic breast cancer: a systematic review and meta-analysis. JAMA Netw. Open 3, e2020312 (2020).
pubmed: 33048129
pmcid: 8094425
doi: 10.1001/jamanetworkopen.2020.20312
McCartney, A. et al. Mechanisms of resistance to CDK4/6 inhibitors: potential implications and biomarkers for clinical practice. Front. Oncol. 9, 666 (2019).
pubmed: 31396487
pmcid: 6664013
doi: 10.3389/fonc.2019.00666
Rafique, R., Islam, S. M. R. & Kazi, J. U. Machine learning in the prediction of cancer therapy. Comput. Struct. Biotechnol. J. 19, 4003–4017 (2021).
pubmed: 34377366
pmcid: 8321893
doi: 10.1016/j.csbj.2021.07.003
Yu, M. K. et al. Visible machine learning for biomedicine. Cell 173, 1562–1565 (2018).
pubmed: 29906441
pmcid: 6483071
doi: 10.1016/j.cell.2018.05.056
Kim, Y.-A. et al. Identifying drug sensitivity subnetworks with NETPHIX. iScience 23, 101619 (2020).
pubmed: 33089107
pmcid: 7566085
doi: 10.1016/j.isci.2020.101619
Jin, I. & Nam, H. HiDRA: hierarchical network for drug response prediction with attention. J. Chem. Inf. Model. 61, 3858–3867 (2021).
pubmed: 34342985
doi: 10.1021/acs.jcim.1c00706
Ma, J. et al. Using deep learning to model the hierarchical structure and function of a cell. Nat. Methods 15, 290–298 (2018).
pubmed: 29505029
pmcid: 5882547
doi: 10.1038/nmeth.4627
Kuenzi, B. M. et al. Predicting drug response and synergy using a deep learning model of human cancer cells. Cancer Cell 38, 672–684 (2020).
pubmed: 33096023
pmcid: 7737474
doi: 10.1016/j.ccell.2020.09.014
Elmarakeby, H. A. et al. Biologically informed deep neural network for prostate cancer discovery. Nature 598, 348–352 (2021).
pubmed: 34552244
pmcid: 8514339
doi: 10.1038/s41586-021-03922-4
Huang, X. et al. ParsVNN: parsimony visible neural networks for uncovering cancer-specific and drug-sensitive genes and pathways. NAR Genom. Bioinform. 3, lqab097 (2021).
pubmed: 34729476
pmcid: 8557386
doi: 10.1093/nargab/lqab097
Ashburner, M. et al. Gene Ontology: tool for the unification of biology. The Gene Ontology Consortium. Nat. Genet. 25, 25–29 (2000).
pubmed: 10802651
pmcid: 3037419
doi: 10.1038/75556
Gillespie, M. et al. The reactome pathway knowledgebase 2022. Nucleic Acids Res. 50, D687–D692 (2022).
pubmed: 34788843
doi: 10.1093/nar/gkab1028
Zheng, F. et al. Interpretation of cancer mutations using a multiscale map of protein systems. Science 374, eabf3067 (2021).
pubmed: 34591613
pmcid: 9126298
doi: 10.1126/science.abf3067
Frampton, G. M. et al. Development and validation of a clinical cancer genomic profiling test based on massively parallel DNA sequencing. Nat. Biotechnol. 31, 1023–1031 (2013).
pubmed: 24142049
pmcid: 5710001
doi: 10.1038/nbt.2696
Beaubier, N. et al. Clinical validation of the Tempus xT next-generation targeted oncology sequencing assay. Oncotarget 10, 2384–2396 (2019).
pubmed: 31040929
pmcid: 6481324
doi: 10.18632/oncotarget.26797
Smyth, L. M. et al. Characteristics and outcome of AKT1
pubmed: 31924700
pmcid: 7125034
doi: 10.1158/2159-8290.CD-19-1209
Barretina, J. et al. The Cancer Cell Line Encyclopedia enables predictive modelling of anticancer drug sensitivity. Nature 483, 603–607 (2012).
pubmed: 22460905
pmcid: 3320027
doi: 10.1038/nature11003
Seashore-Ludlow, B. et al. Harnessing connectivity in a large-scale small-molecule sensitivity dataset. Cancer Discov. 5, 1210–1223 (2015).
pubmed: 26482930
pmcid: 4631646
doi: 10.1158/2159-8290.CD-15-0235
Basu, A. et al. An interactive resource to identify cancer genetic and lineage dependencies targeted by small molecules. Cell 154, 1151–1161 (2013).
pubmed: 23993102
pmcid: 3954635
doi: 10.1016/j.cell.2013.08.003
Garnett, M. J. et al. Systematic identification of genomic markers of drug sensitivity in cancer cells. Nature 483, 570–575 (2012).
pubmed: 22460902
pmcid: 3349233
doi: 10.1038/nature11005
Iorio, F. et al. A landscape of pharmacogenomic interactions in cancer. Cell 166, 740–754 (2016).
pubmed: 27397505
pmcid: 4967469
doi: 10.1016/j.cell.2016.06.017
Gao, H. et al. High-throughput screening using patient-derived tumor xenografts to predict clinical trial drug response. Nat. Med. 21, 1318–1325 (2015).
pubmed: 26479923
doi: 10.1038/nm.3954
Li, Z. et al. Loss of the FAT1 tumor suppressor promotes resistance to CDK4/6 inhibitors via the Hippo pathway. Cancer Cell 34, 893–905 (2018).
pubmed: 30537512
pmcid: 6294301
doi: 10.1016/j.ccell.2018.11.006
Finn, R. S. et al. The cyclin-dependent kinase 4/6 inhibitor palbociclib in combination with letrozole versus letrozole alone as first-line treatment of oestrogen receptor-positive, HER2-negative, advanced breast cancer (PALOMA-1/TRIO-18): a randomised phase 2 study. Lancet Oncol. 16, 25–35 (2015).
pubmed: 25524798
doi: 10.1016/S1470-2045(14)71159-3
DeMichele, A. et al. CDK 4/6 inhibitor palbociclib (PD0332991) in Rb
pubmed: 25501126
doi: 10.1158/1078-0432.CCR-14-2258
Garraway, L. A. & Lander, E. S. Lessons from the cancer genome. Cell 153, 17–37 (2013).
pubmed: 23540688
doi: 10.1016/j.cell.2013.03.002
Carpintero-Fernández, P. et al. Genome wide CRISPR/Cas9 screen identifies the coagulation factor IX (F9) as a regulator of senescence. Cell Death Dis. 13, 163 (2022).
pubmed: 35184131
pmcid: 8858321
doi: 10.1038/s41419-022-04569-3
Tsherniak, A. et al. Defining a cancer dependency map. Cell 170, 564–576 (2017).
pubmed: 28753430
pmcid: 5667678
doi: 10.1016/j.cell.2017.06.010
Fukazawa, T. et al. Inhibition of Myc effectively targets KRAS mutation-positive lung cancer expressing high levels of Myc. Anticancer Res. 30, 4193–4200 (2010).
pubmed: 21036740
Adam, G. et al. Machine learning approaches to drug response prediction: challenges and recent progress. NPJ Precis. Oncol. 4, 19 (2020).
pubmed: 32566759
pmcid: 7296033
doi: 10.1038/s41698-020-0122-1
Richards, A. L., Eckhardt, M. & Krogan, N. J. Mass spectrometry-based protein–protein interaction networks for the study of human diseases. Mol. Syst. Biol. 17, e8792 (2021).
pubmed: 33434350
pmcid: 7803364
doi: 10.15252/msb.20188792
Go, C. D. et al. A proximity-dependent biotinylation map of a human cell. Nature 595, 120–124 (2021).
pubmed: 34079125
doi: 10.1038/s41586-021-03592-2
Salas, D., Stacey, R. G., Akinlaja, M. & Foster, L. J. Next-generation interactomics: considerations for the use of co-elution to measure protein interaction networks. Mol. Cell. Proteomics 19, 1–10 (2020).
pubmed: 31792070
doi: 10.1074/mcp.R119.001803
Heusel, M. et al. Complex-centric proteome profiling by SEC–SWATH–MS. Mol. Syst. Biol. 15, e8438 (2019).
pubmed: 30642884
pmcid: 6346213
doi: 10.15252/msb.20188438
Qin, Y. et al. A multi-scale map of cell structure fusing protein images and interactions. Nature 600, 536–542 (2021).
pubmed: 34819669
pmcid: 9053732
doi: 10.1038/s41586-021-04115-9
Ji, W. et al. Combined androgen receptor blockade overcomes the resistance of breast cancer cells to palbociclib. Int. J. Biol. Sci. 15, 522–532 (2019).
pubmed: 30745839
pmcid: 6367574
doi: 10.7150/ijbs.30572
Mao, P. et al. Acquired FGFR and FGF alterations confer resistance to estrogen receptor (ER) targeted therapy in ER
pubmed: 32723837
doi: 10.1158/1078-0432.CCR-19-3958
Wang, T.-H. et al. Palbociclib induces DNA damage and inhibits DNA repair to induce cellular senescence and apoptosis in oral squamous cell carcinoma. J. Formos. Med. Assoc. 120, 1695–1705 (2021).
pubmed: 33342707
doi: 10.1016/j.jfma.2020.12.009
Fernández-Aroca, D. M. et al. P53 pathway is a major determinant in the radiosensitizing effect of palbociclib: implication in cancer therapy. Cancer Lett. 451, 23–33 (2019).
pubmed: 30872077
doi: 10.1016/j.canlet.2019.02.049
Pancholi, S. et al. Tumour kinome re-wiring governs resistance to palbociclib in oestrogen receptor positive breast cancers, highlighting new therapeutic modalities. Oncogene 39, 4781–4797 (2020).
pubmed: 32307447
pmcid: 7299844
doi: 10.1038/s41388-020-1284-6
Shu, S. et al. Synthetic lethal and resistance interactions with BET bromodomain inhibitors in triple-negative breast cancer. Mol. Cell 78, 1096–1113 (2020).
pubmed: 32416067
pmcid: 7306005
doi: 10.1016/j.molcel.2020.04.027
Zhou, M. et al. Combining histone deacetylase inhibitors (HDACis) with other therapies for cancer therapy. Eur. J. Med. Chem. 226, 113825 (2021).
pubmed: 34562854
pmcid: 9363153
doi: 10.1016/j.ejmech.2021.113825
Wang, B. et al. Pharmacological CDK4/6 inhibition reveals a p53-dependent senescent state with restricted toxicity. EMBO J. 41, e108946 (2022).
pubmed: 34985783
pmcid: 8922251
doi: 10.15252/embj.2021108946
Ji, W. et al. c-myc regulates the sensitivity of breast cancer cells to palbociclib via c-myc/miR-29b-3p/CDK6 axis. Cell Death Dis. 11, 760 (2020).
pubmed: 32934206
pmcid: 7493901
doi: 10.1038/s41419-020-02980-2
Wiesel-Motiuk, N. & Assaraf, Y. G. The key roles of the lysine acetyltransferases KAT6A and KAT6B in physiology and pathology. Drug Resist. Updat. 53, 100729 (2020).
pubmed: 33130515
doi: 10.1016/j.drup.2020.100729
Rokudai, S. et al. MOZ increases p53 acetylation and premature senescence through its complex formation with PML. Proc. Natl Acad. Sci. USA 110, 3895–3900 (2013).
pubmed: 23431171
pmcid: 3593914
doi: 10.1073/pnas.1300490110
Kitabayashi, I., Aikawa, Y., Nguyen, L. A., Yokoyama, A. & Ohki, M. Activation of AML1-mediated transcription by MOZ and inhibition by the MOZ–CBP fusion protein. EMBO J. 20, 7184–7196 (2001).
pubmed: 11742995
pmcid: 125775
doi: 10.1093/emboj/20.24.7184
Borrow, J. et al. The translocation t(8;16)(p11;p13) of acute myeloid leukaemia fuses a putative acetyltransferase to the CREB-binding protein. Nat. Genet. 14, 33–41 (1996).
pubmed: 8782817
doi: 10.1038/ng0996-33
Li, J. Y., Daniels, G., Wang, J. & Zhang, X. TBL1XR1 in physiological and pathological states. Am. J. Clin. Exp. Urol. 3, 13–23 (2015).
pubmed: 26069883
pmcid: 4446378
Tomita, A., Buchholz, D. R. & Shi, Y.-B. Recruitment of N-CoR/SMRT–TBLR1 corepressor complex by unliganded thyroid hormone receptor for gene repression during frog development. Mol. Cell. Biol. 24, 3337–3346 (2004).
pubmed: 15060155
pmcid: 381683
doi: 10.1128/MCB.24.8.3337-3346.2004
Perissi, V. et al. TBL1 and TBLR1 phosphorylation on regulated gene promoters overcomes dual CtBP and NCoR/SMRT transcriptional repression checkpoints. Mol. Cell 29, 755–766 (2008).
pubmed: 18374649
pmcid: 2364611
doi: 10.1016/j.molcel.2008.01.020
Priebbenow, D. L. et al. Discovery of acylsulfonohydrazide-derived inhibitors of the lysine acetyltransferase, KAT6A, as potent senescence-inducing anti-cancer agents. J. Med. Chem. 63, 4655–4684 (2020).
pubmed: 32118427
doi: 10.1021/acs.jmedchem.9b02071
Baell, J. B. et al. Inhibitors of histone acetyltransferases KAT6A/B induce senescence and arrest tumour growth. Nature 560, 253–257 (2018).
pubmed: 30069049
doi: 10.1038/s41586-018-0387-5
Su, J. et al. The role of MOZ/KAT6A in hematological malignancies and advances in MOZ/KAT6A inhibitors. Pharmacol. Res. 174, 105930 (2021).
pubmed: 34626770
doi: 10.1016/j.phrs.2021.105930
Lira, M. E. et al. Abstract 2749. Liquid biopsy testing allows highly-sensitive detection of plasma cfDNA mutations in 87 breast cancer-related genes. Cancer Res. 77, 2749 (2017).
doi: 10.1158/1538-7445.AM2017-2749
Bailey, M. H. et al. Comprehensive characterization of cancer driver genes and mutations. Cell 174, 1034–1035 (2018).
pubmed: 30096302
pmcid: 8045146
doi: 10.1016/j.cell.2018.07.034
Ioffe, S. & Szegedy, C. Batch normalization: accelerating deep network training by reducing internal covariate shift. In Proc. 32nd International Conference on International Conference on Machine Learning Vol. 37 (eds Bach, F. & Blei, D.) 448–456 (JMLR.org, 2015).
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I. & Salakhutdinov, R. Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014).
Jolliffe, I. Principal component analysis. in Wiley StatsRef: Statistics Reference Online (Wiley, 2014); https://doi.org/10.1002/9781118445112.stat06472
Loshchilov, I. & Hutter, F. Decoupled weight decay regularization. Preprint at arXiv https://doi.org/10.48550/arXiv.1711.05101 (2017).
Breiman, L. Random forests. Mach. Learn. 45, 5–32 (2001).
doi: 10.1023/A:1010933404324
Friedman, J., Hastie, T. & Tibshirani, R. Regularization paths for generalized linear models via coordinate descent. J. Stat. Softw. 33, 1–22 (2010).
pubmed: 20808728
pmcid: 2929880
doi: 10.18637/jss.v033.i01
Hinton, G. E. Connectionist learning procedures. Artif. Intell. 40, 185–234 (1989).
doi: 10.1016/0004-3702(89)90049-0
Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
Stone, M. Cross-validatory choice and assessment of statistical predictions. J. R. Stat. Soc. Ser. B (Methodol.) 36, 111–133 (1974).
Akiba, T., Sano, S., Yanase, T., Ohta, T. & Koyama, M. Optuna: a next-generation hyperparameter optimization framework. in KDD ’19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2623–2631 (Association for Computing Machinery, 2019); https://doi.org/10.1145/3292500.3330701
Hoerl, A. E. & Kennard, R. W. Ridge regression: biased estimation for nonorthogonal problems. Technometrics 42, 80–86 (2000).
doi: 10.1080/00401706.2000.10485983
McCullagh, P. & Nelder, J. A. Generalized Linear Models 2nd edn (CRC, 1989).
Tibshirani, R. Regression Shrinkage and Selection via the Lasso (Stanford University Department of Statistics, 1994).
Subramanian, A. et al. Gene set enrichment analysis: a knowledge-based approach for interpreting genome-wide expression profiles. Proc. Natl Acad. Sci. USA 102, 15545–15550 (2005).
pubmed: 16199517
pmcid: 1239896
doi: 10.1073/pnas.0506580102
Fang, Z., Liu, X. & Peltz, G. GSEApy: a comprehensive package for performing gene set enrichment analysis in Python. Bioinformatics 39, btac757 (2023).
Dempster, J. M. et al. Chronos: a cell population dynamics model of CRISPR experiments that improves inference of gene fitness effects. Genome Biol. 22, 343 (2021).
pubmed: 34930405
pmcid: 8686573
doi: 10.1186/s13059-021-02540-7
Sanjana, N. E., Shalem, O. & Zhang, F. Improved vectors and genome-wide libraries for CRISPR screening. Nat. Methods 11, 783–784 (2014).
pubmed: 25075903
pmcid: 4486245
doi: 10.1038/nmeth.3047
van der Walt, S. et al. scikit-image: image processing in Python. PeerJ 2, e453 (2014).
pubmed: 25024921
pmcid: 4081273
doi: 10.7717/peerj.453