Treffer: Combinatorial prediction of therapeutic perturbations using causally inspired neural networks.

Combinatorial prediction of therapeutic perturbations using causally inspired neural networks.

Gonzalez G; Imperial College London, London, UK.; F. Hoffmann-La Roche Ltd, Basel, Switzerland.; Prescient Design, Genentech, South San Francisco, CA, USA., Lin X; Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA., Herath I; Merck & Co., South San Francisco, CA, USA.; Cornell University, Ithaca, NY, USA.; University of Pittsburgh School of Medicine-Carnegie Mellon University, Pittsburgh, PA, USA., Veselkov K; Imperial College London, London, UK.; Yale School of Public Health, New Haven, CT, USA., Bronstein M; University of Oxford, Oxford, UK.; AITHYRA, Vienna, Austria., Zitnik M; Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA. marinka@hms.harvard.edu.; Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University, Cambridge, MA, USA. marinka@hms.harvard.edu.; Broad Institute of MIT and Harvard, Cambridge, MA, USA. marinka@hms.harvard.edu.; Harvard Data Science Initiative, Cambridge, MA, USA. marinka@hms.harvard.edu.

Nature biomedical engineering [Nat Biomed Eng] 2025 Sep 09. Date of Electronic Publication: 2025 Sep 09.

Ahead of Print

Journal Article

English

Publisher: Springer Nature Country of Publication: England NLM ID: 101696896 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 2157-846X (Electronic) Linking ISSN: 2157846X NLM ISO Abbreviation: Nat Biomed Eng Subsets: MEDLINE

Publication: London : Springer Nature
Original Publication: [London] : Macmillan Publishers Limited, [2016]-

Update of: bioRxiv. 2025 Jun 06:2024.01.03.573985. doi: 10.1101/2024.01.03.573985.. (PMID: 38260532)

Vincent, F. et al. Phenotypic drug discovery: recent successes, lessons learned and new directions. Nat. Rev. Drug Discov. 21, 899–914 (2022). (PMID: 35637317970895110.1038/s41573-022-00472-w)
Moffat, J. G., Vincent, F., Lee, J. A., Eder, J. & Prunotto, M. Opportunities and challenges in phenotypic drug discovery: an industry perspective. Nat. Rev. Drug Discov. 16, 531–543 (2017). (PMID: 2868576210.1038/nrd.2017.111)
Minikel, E. V., Painter, J. L., Dong, C. C. & Nelson, M. R. Refining the impact of genetic evidence on clinical success. Nature 629, 624–629 (2024). (PMID: 386324011109612410.1038/s41586-024-07316-0)
Druker, B. J. et al. Effects of a selective inhibitor of the Abl tyrosine kinase on the growth of Bcr–Abl positive cells. Nat. Med. 2, 561–566 (1996). (PMID: 861671610.1038/nm0596-561)
Bange, J., Zwick, E. & Ullrich, A. Molecular targets for breast cancer therapy and prevention. Nat. Med. 7, 548–552 (2001). (PMID: 1132905410.1038/87872)
Swinney, D. C. & Anthony, J. How were new medicines discovered? Nat. Rev. Drug Discov. 10, 507–519 (2011). (PMID: 2170150110.1038/nrd3480)
Musa, A. et al. A review of Connectivity Map and computational approaches in pharmacogenomics. Brief. Bioinform. 19, 506–523 (2018). (PMID: 28069634)
Davies, J. C., Alton, E. W. & Bush, A. Cystic fibrosis. BMJ 335, 1255–1259 (2007). (PMID: 18079549213705310.1136/bmj.39391.713229.AD)
Van Goor, F. et al. Rescue of CF airway epithelial cell function in vitro by a CFTR potentiator, VX-770. Proc. Natl Acad. Sci. USA 106, 18825–18830 (2009). (PMID: 19846789277399110.1073/pnas.0904709106)
Van Goor, F. et al. Correction of the F508del-CFTR protein processing defect in vitro by the investigational drug VX-809. Proc. Natl Acad. Sci. USA 108, 18843–18848 (2011). (PMID: 21976485321914710.1073/pnas.1105787108)
Keenan, A. B. et al. Connectivity mapping: methods and applications. Annu. Rev. Biomed. Data Sci. 2, 69–92 (2019). (PMID: 10.1146/annurev-biodatasci-072018-021211)
Keenan, A. B. et al. The Library of Integrated Network-based Cellular Signatures (LINCS) NIH program: system-level cataloging of human cells response to perturbations. Cell Syst. 6, 13–24 (2018). (PMID: 2919902010.1016/j.cels.2017.11.001)
Lamb, J. et al. The Connectivity Map: using gene-expression signatures to connect small molecules, genes, and disease. Science 313, 1929–1935 (2006). (PMID: 1700852610.1126/science.1132939)
Samart, K., Tuyishime, P., Krishnan, A. & Ravi, J. Reconciling multiple connectivity scores for drug repurposing. Brief. Bioinform. 22, bbab161 (2021). (PMID: 34013329859791910.1093/bib/bbab161)
Guney, E. Reproducible drug repurposing: when similarity does not suffice. Pac. Symp. Biocomput. 22, 132–143 (2017). (PMID: 27896969)
Chen, B. Reversal of cancer gene expression correlates with drug efficacy and reveals therapeutic targets. Nat. Commun. 8, 16022 (2017). (PMID: 28699633551018210.1038/ncomms16022)
Chen, B. et al. Computational discovery of niclosamide ethanolamine, a repurposed drug candidate that reduces growth of hepatocellular carcinoma cells in vitro and in mice by inhibiting cell division cycle 37 signaling. Gastroenterology 152, 2022–2036 (2017). (PMID: 2828456010.1053/j.gastro.2017.02.039)
Pessetto, Z. Y. et al. In silico and in vitro drug screening identifies new therapeutic approaches for Ewing sarcoma. Oncotarget 8, 4079–4095 (2016). (PMID: 535481410.18632/oncotarget.13385)
Morselli Gysi, D. et al. Network medicine framework for identifying drug-repurposing opportunities for COVID-19. Proc. Natl Acad. Sci. USA 118, e2025581118 (2021). (PMID: 33906951812685210.1073/pnas.2025581118)
Zhu, J. et al. Prediction of drug efficacy from transcriptional profiles with deep learning. Nat. Biotechnol. 39, 1444–1452 (2021). (PMID: 3414068110.1038/s41587-021-00946-z)
Pham, T. H., Qiu, Y., Zeng, J., Xie, L. & Zhang, P. A deep learning framework for high-throughput mechanism-driven phenotype compound screening and its application to COVID-19 drug repurposing. Nat. Mach. Intell. 3, 247–257 (2021). (PMID: 33796820800909110.1038/s42256-020-00285-9)
Lotfollahi, M., Wolf, F. A. & Theis, F. J. scGen predicts single-cell perturbation responses. Nat. Methods 16, 715–721 (2019). (PMID: 3136322010.1038/s41592-019-0494-8)
Hetzel, L. et al. Predicting cellular responses to novel drug perturbations at a single-cell resolution. Adv. Neural Inf. Process. Syst. 35, 26711–26722 (2022).
Hauser, A. & Bühlmann, P. Two optimal strategies for active learning of causal models from interventional data. Int. J. Approx. Reason. 55, 926–939 (2014). (PMID: 10.1016/j.ijar.2013.11.007)
Ghassami, A. E., Salehkaleybar, S., Kiyavash, N. & Bareinboim, E. Budgeted experiment design for causal structure learning. In Proc. 35th International Conference on Machine Learning (eds Dy, J. & Krause, A.) 2788–2801 (Proceedings of Machine Learning Research, 2018).
Agrawal, R., Squires, C., Yang, K., Shanmugam, K. & Uhler, C. ABCD-strategy: budgeted experimental design for targeted causal structure discovery. In Proc. 22nd International Conference on Artificial Intelligence and Statistics (eds Chaudhuri, K. & Sugiyama, M.) 3400–3409 (Proceedings of Machine Learning Research, 2019).
Bunne, C. et al. Learning single-cell perturbation responses using neural optimal transport. Nat. Methods 20, 1759–1768 (2023). (PMID: 377707091063013710.1038/s41592-023-01969-x)
Barr, M. P. et al. Vascular endothelial growth factor is an autocrine growth factor, signaling through neuropilin-1 in non-small cell lung cancer. Mol. Cancer 14, 45 (2015). (PMID: 25889301439279310.1186/s12943-015-0310-8)
Riquelme, E. et al. VEGF/VEGFR-2 upregulates EZH2 expression in lung adenocarcinoma cells and EZH2 depletion enhances the response to platinum-based and VEGFR-2–targeted therapy. Clin. Cancer Res. 20, 3849–3861 (2014). (PMID: 24850841419058610.1158/1078-0432.CCR-13-1916)
Huynh-Thu, V. A., Irrthum, A., Wehenkel, L. & Geurts, P. Inferring regulatory networks from expression data using tree-based methods. PloS ONE 5, e12776 (2010). (PMID: 20927193294691010.1371/journal.pone.0012776)
Yuan, B. et al. CellBox: interpretable machine learning for perturbation biology with application to the design of cancer combination therapy. Cell Syst. 12, 128–140 (2021). (PMID: 3337358310.1016/j.cels.2020.11.013)
Kamimoto, K. et al. Dissecting cell identity via network inference and in silico gene perturbation. Nature 614, 742–751 (2023). (PMID: 36755098994683810.1038/s41586-022-05688-9)
Piran, Z., Cohen, N., Hoshen, Y. & Nitzan, M. Disentanglement of single-cell data with biolord. Nat. Biotechnol. 42, 1678–1683 (2024). (PMID: 382254661155456210.1038/s41587-023-02079-x)
Roohani, Y., Huang, K. & Leskovec, J. Predicting transcriptional outcomes of novel multigene perturbations with gears. Nat. Biotechnol. 42, 927–935 (2024). (PMID: 3759203610.1038/s41587-023-01905-6)
Barabási, A. L., Gulbahce, N. & Loscalzo, J. Network medicine: a network-based approach to human disease. Nat. Rev. Genet. 12, 56–68 (2011). (PMID: 21164525314005210.1038/nrg2918)
Ruiz, C., Zitnik, M. & Leskovec, J. Identification of disease treatment mechanisms through the multiscale interactome. Nat. Commun. 12, 1796 (2021). (PMID: 33741907797981410.1038/s41467-021-21770-8)
Eyuboglu, S., Zitnik, M. & Leskovec, J. Mutual interactors as a principle for phenotype discovery in molecular interaction networks. Pac. Symp. Biocomput. 28, 61–72 (2023). (PMID: 36540965)
Gu, Z. et al. Role of duplicate genes in genetic robustness against null mutations. Nature 421, 63–66 (2003). (PMID: 1251195410.1038/nature01198)
Deutscher, D., Meilijson, I., Kupiec, M. & Ruppin, E. Multiple knockout analysis of genetic robustness in the yeast metabolic network. Nat. Genet. 38, 993–998 (2006). (PMID: 1694101010.1038/ng1856)
Deutscher, D., Meilijson, I., Schuster, S. & Ruppin, E. Can single knockouts accurately single out gene functions? BMC Syst. Biol. 2, 50 (2008). (PMID: 18564419244311010.1186/1752-0509-2-50)
Ochoa, D. et al. The next-generation Open Targets Platform: reimagined, redesigned, rebuilt. Nucleic Acids Res. 51, D1353–D1359 (2023). (PMID: 3639949910.1093/nar/gkac1046)
Cai, Q. et al. The role of dexmedetomidine in tumor-progressive factors in the perioperative period and cancer recurrence: a narrative review. Drug Des. Devel. Ther. 16, 2161–2175 (2022). (PMID: 35821701927128110.2147/DDDT.S358042)
Gainor, J. F. et al. Pralsetinib for ret fusion-positive non-small-cell lung cancer (arrow): a multi-cohort, open-label, phase 1/2 study. Lancet Oncol. 22, 959–969 (2021). (PMID: 3411819710.1016/S1470-2045(21)00247-3)
Faraat Ali, G. C. & Kumari, N. Pralsetinib: chemical and therapeutic development with FDA authorization for the management of ret fusion-positive non-small-cell lung cancers. Arch. Pharm. Res. 45, 309–327 (2022). (PMID: 3559822810.1007/s12272-022-01385-3)
Wu, J. et al. Expression and potential molecular mechanism of TOP2A in metastasis of non-small cell lung cancer. Sci. Rep. 14, 12228 (2024). (PMID: 388066101113340510.1038/s41598-024-63055-2)
Pautier, P. et al. Doxorubicin–trabectedin with trabectedin maintenance in leiomyosarcoma. N. Engl. J. Med. 391, 789–799 (2024). (PMID: 3923134110.1056/NEJMoa2403394)
Hartwell, L. H., Hopfield, J. J., Leibler, S. & Murray, A. W. From molecular to modular cell biology. Nature 402, C47–C52 (1999). (PMID: 1059122510.1038/35011540)
Menche, J. et al. Uncovering disease–disease relationships through the incomplete interactome. Science 347, 1257601 (2015). (PMID: 25700523443574110.1126/science.1257601)
Szklarczyk, D. et al. The string database in 2023: protein–protein association networks and functional enrichment analyses for any sequenced genome of interest. Nucleic Acids Res. 51, D638–D646 (2023). (PMID: 3637010510.1093/nar/gkac1000)
Bagherian, M. et al. Machine learning approaches and databases for prediction of drug-target interaction: a survey paper. Brief. Bioinform. 22, 247–269 (2021). (PMID: 3195097210.1093/bib/bbz157)
Pan, J. et al. Sparse dictionary learning recovers pleiotropy from human cell fitness screens. Cell Syst. 13, 286–303 (2022). (PMID: 35085500903505410.1016/j.cels.2021.12.005)
Huang, K. et al. Deeppurpose: a deep learning library for drug–target interaction prediction. Bioinformatics 36, 5545–5547 (2020). (PMID: 801646710.1093/bioinformatics/btaa1005)
Hart, G. T., Ramani, A. K. & Marcotte, E. M.How complete are current yeast and human protein-interaction networks? Genome Biol. 7, 120 (2006). (PMID: 17147767179458310.1186/gb-2006-7-11-120)
Stumpf, M. P. et al. Estimating the size of the human interactome. Proc. Natl Acad. Sci. USA 105, 6959–6964 (2008). (PMID: 18474861238395710.1073/pnas.0708078105)
Zitnik, M., Sosič, R., Feldman, M. W. & Leskovec, J. Evolution of resilience in protein interactomes across the tree of life. Proc. Natl Acad. Sci. USA 116, 4426–4433 (2019). (PMID: 30765515641079810.1073/pnas.1818013116)
Schölkopf, B. et al. Toward causal representation learning. Proc. IEEE 109, 612–634 (2021). (PMID: 10.1109/JPROC.2021.3058954)
Gustafsdottir, S. M. et al. Multiplex cytological profiling assay to measure diverse. PLoS ONE 8, e80999 (2013). (PMID: 24312513384704710.1371/journal.pone.0080999)
Bray, M.-A. et al. Cell Painting, a high-content image-based assay for morphological profiling using multiplexed fluorescent dyes. Physiol. Behav. 176, 139–148 (2017).
Chandrasekaran, S. N. et al. JUMP Cell Painting dataset: morphological impact of 136,000 chemical and genetic perturbations. Preprint at bioRxiv https://doi.org/10.1101/2023.03.23.534023 (2023).
Akbarzadeh, M. et al. Morphological profiling by means of the Cell Painting assay enables identification of tubulin-targeting compounds. Cell Chem. Biol. 29, 1053–1064 (2022). (PMID: 3496842010.1016/j.chembiol.2021.12.009)
Pruteanu, L. L. & Bender, A. Using transcriptomics and cell morphology data in drug discovery: the long road to practice. ACS Med. Chem. Lett. 14, 386–395 (2023). (PMID: 370773921010791010.1021/acsmedchemlett.3c00015)
Huang, K. et al. Artificial intelligence foundation for therapeutic science. Nat. Chem. Biol. 18, 1033–1036 (2022). (PMID: 36131149952984010.1038/s41589-022-01131-2)
Thomas, K. J. & Jacobson, M. R. Defects in mitochondrial fission protein dynamin-related protein 1 are linked to apoptotic resistance and autophagy in a lung cancer model. PLOS ONE 7, e45319 (2012). (PMID: 23028930344792610.1371/journal.pone.0045319)
Le, C. F., Yusof, M. Y. Y., Hassan, H. & Sekaran, S. D. In vitro properties of designed antimicrobial peptides that exhibit potent antipneumococcal activity and produce synergism in combination with penicillin. Sci. Rep. 5, 9761 (2015). (PMID: 25985150443490910.1038/srep09761)
Zhao, S., Song, P., Zhou, G., Zhang, D. & Hu, Y. METTL3 promotes the malignancy of non-small cell lung cancer by N6-methyladenosine modifying SFRP2. Cancer Gene Ther. 30, 1094–1104 (2023). (PMID: 3710606910.1038/s41417-023-00614-1)
Zhu, J.-Y., Park, T., Isola, P. & Efros, A. A. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proc. 2017 IEEE International Conference on Computer Vision (ICCV) 2242–2251 (IEEE, 2017).
Neal, B. Introduction to Causal Inference. Course Lecture Notes (draft). (Department of Statistics, Harvard University, 2020); https://www.bradyneal.com/Introduction_to_Causal_Inference-Dec17_2020-Neal.pdf.
Lotfollahi, M. et al. Predicting cellular responses to complex perturbations in high-throughput screens. Mol. Syst. Biol. 19, e11517 (2023). (PMID: 371540911025856210.15252/msb.202211517)
Paszke, A. et al. Automatic differentiation in PyTorch. In Proc. NIPS Workshop on Autodiff (2017).
Fey, M. & Lenssen, J. E. Fast graph representation learning with PyTorch Geometric. Preprint at https://arxiv.org/abs/1903.02428 (2019).
Heumos, L. et al. Best practices for single-cell analysis across modalities. Nat. Rev. Genet. 24, 550–572 (2023). (PMID: 3700240310.1038/s41576-023-00586-w)
Gayoso, A. et al. A Python library for probabilistic analysis of single-cell omics data. Nat. Biotechnol. 40, 163–166 (2022). (PMID: 3513226210.1038/s41587-021-01206-w)
Jovic, D. et al. Single-cell RNA sequencing technologies and applications: a brief overview. Clin. Transl. Med. 12, e694 (2022). (PMID: 35352511896493510.1002/ctm2.694)
Luecken, M. D. et al. Benchmarking atlas-level data integration in single-cell genomics. Nat. Methods 19, 41–50 (2021). (PMID: 34949812874819610.1038/s41592-021-01336-8)
Wishart, D. S. et al. DrugBank 5.0: a major update to the DrugBank database for 2018. Nucleic Acids Res. 46, D1074–D1082 (2018). (PMID: 2912613610.1093/nar/gkx1037)
Gonzalez, G. et al. Combinatorial prediction of therapeutic perturbations using causally-inspired neural networks (genetic data). Zenodo https://doi.org/10.5281/zenodo.15375990 (2025).
Gonzalez, G. et al. Combinatorial prediction of therapeutic perturbations using causally-inspired neural networks (chemical data). Zenodo https://doi.org/10.5281/zenodo.15390483 (2025).
Gonzalez, G. et al. PDGrapher. GitHub https://github.com/mims-harvard/PDGrapher/tree/main (2025).

Date Created: 20250909 Latest Revision: 20250916

20250916

10.1038/s41551-025-01481-x

40925962

MEDLINE