[{"publication_identifier":{"eissn":["2041-1723"]},"title":"Causal inference for multiple risk factors and diseases from genomics data","date_published":"2026-08-25T00:00:00Z","file_date_updated":"2026-10-07T09:50:18Z","scopus_import":"1","author":[{"orcid":"0000-0001-6617-9742","last_name":"Machnik","first_name":"Nick N","full_name":"Machnik, Nick N","id":"3591A0AA-F248-11E8-B48F-1D18A9856A87"},{"id":"b9f6d5ef-7774-11eb-a47f-df2c75c02ee7","full_name":"Mahmoudi, Seyed Mahdi","last_name":"Mahmoudi","first_name":"Seyed Mahdi"},{"last_name":"Borczyk","first_name":"Malgorzata","full_name":"Borczyk, Malgorzata"},{"full_name":"Krätschmer, Ilse","last_name":"Krätschmer","id":"30d4014e-7753-11eb-b44b-db6d61112e73","first_name":"Ilse","orcid":"0000-0002-5636-9259"},{"first_name":"Markus J.","last_name":"Bauer","full_name":"Bauer, Markus J."},{"orcid":"0000-0001-8982-8813","id":"E5D42276-F5DA-11E9-8E24-6303E6697425","last_name":"Robinson","first_name":"Matthew Richard","full_name":"Robinson, Matthew Richard"}],"publication":"Nature Communications","dataavailabilitystatement":"This project uses the UK Biobank data under project number 35520.\r\nUK Biobank genotypic and phenotypic data is available through a\r\nformal request at (http://www.ukbiobank.ac.uk). All of the data generated\r\nin this study are provided in the Source Data file. Source data\r\nare provided with this paper. The CI-GWAS code is fully open source and available at https://github.\r\ncom/medical-genomics-group/ci-gwasand has been archived on\r\nZenodo52. The scripts used to execute the model are available at\r\nhttps://github.com/medical-genomics-group/ci-gwas. R version 4.2.1 is\r\navailable at https://www.r-project.org/. Plink version 1.9 is available at\r\nhttps://www.cog-genomics.org/plink/1.9/.","_id":"23043","acknowledgement":"We thank Zoltan Kutalik andmembers of the Robinson group at ISTA for\r\ntheir comments, which improved this manuscript. We would like to\r\nacknowledge the participants and investigators of the UK Biobank study.\r\nHigh-performance computing was supported by the Scientific Service\r\nUnits (SSU) of IST Austria through resources provided by Scientific\r\nComputing (SciComp). This work was funded by a research collaboration agreement between\r\nBoehringer Ingelheim and the research group of MRR at the Institute of\r\nScience and Technology Austria. Additional funding was also provided\r\nby an SNSF Eccellenza Grant to MRR (PCEGP3-181181), and by core\r\nfunding from the Institute of Science and Technology Austria. MB was\r\nfunded by the National Science Center Poland grant SONATINA UMO-\r\n2021/40/C/NZ2/00218.","oa_version":"Published Version","status":"public","department":[{"_id":"MaRo"}],"has_accepted_license":"1","language":[{"iso":"eng"}],"acknowledged_ssus":[{"_id":"ScienComp"}],"month":"08","fulldoi":"https://doi.org/10.1038/s41467-026-76877-7","abstract":[{"lang":"eng","text":"Mendelian randomization, the standard instrument variable causal-inference approach for genomics, can be severely biased by inadequate selection of appropriate instrument variables and horizontal pleiotropy. We introduce Causal Inference GWAS, a graphical approach that selects genetic instruments from summary statistics controlling for linkage and pleiotropy, accommodates rare variants and binary outcomes, distinguishes direct from indirect risk factors in high dimensions, and flags latent confounding. Applied to 9 risk factors, 4 metabolic disease outcomes, and 8.4M variants across 458,747 UK Biobank individuals, our method runs in 20 minutes, identifying only 696 genome-wide valid instruments. We replicate nearly all previously reported risk factor-outcome paths, but find that most are indistinguishable from unmeasured confounding. This suggests robust biobank causal inference will require longitudinal and family data to resolve temporal precedence from reverse causation. Our approach offers a principled first step toward screening genuine causal signal from phenotypic correlation in biobank data."}],"date_updated":"2026-10-07T09:54:59Z","day":"25","volume":17,"date_created":"2026-10-04T22:01:53Z","DOAJ_listed":"1","article_processing_charge":"Yes","tmp":{"name":"Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)","image":"/images/cc_by_nc_nd.png","legal_code_url":"https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode","short":"CC BY-NC-ND (4.0)"},"type":"journal_article","publisher":"Springer Nature","OA_type":"gold","intvolume":"        17","file":[{"creator":"dernst","access_level":"open_access","success":1,"file_id":"23070","checksum":"05517674168a275c70f18e964ce33d8b","date_updated":"2026-10-07T09:50:18Z","file_name":"2026_NatureComm_Machnik.pdf","date_created":"2026-10-07T09:50:18Z","relation":"main_file","file_size":2345578,"content_type":"application/pdf"}],"article_number":"10153 ","supplementarymaterial":"no","article_type":"original","OA_place":"publisher","das_tickbox":"1","oa":1,"related_material":{"record":[{"status":"public","id":"18648","relation":"earlier_version"}]},"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","citation":{"chicago":"Machnik, Nick N, Seyed Mahdi Mahmoudi, Malgorzata Borczyk, Ilse Krätschmer, Markus J. Bauer, and Matthew Richard Robinson. “Causal Inference for Multiple Risk Factors and Diseases from Genomics Data.” <i>Nature Communications</i>. Springer Nature, 2026. <a href=\"https://doi.org/10.1038/s41467-026-76877-7\">https://doi.org/10.1038/s41467-026-76877-7</a>.","mla":"Machnik, Nick N., et al. “Causal Inference for Multiple Risk Factors and Diseases from Genomics Data.” <i>Nature Communications</i>, vol. 17, 10153, Springer Nature, 2026, doi:<a href=\"https://doi.org/10.1038/s41467-026-76877-7\">10.1038/s41467-026-76877-7</a>.","ista":"Machnik NN, Mahmoudi SM, Borczyk M, Krätschmer I, Bauer MJ, Robinson MR. 2026. Causal inference for multiple risk factors and diseases from genomics data. Nature Communications. 17, 10153.","apa":"Machnik, N. N., Mahmoudi, S. M., Borczyk, M., Krätschmer, I., Bauer, M. J., &#38; Robinson, M. R. (2026). Causal inference for multiple risk factors and diseases from genomics data. <i>Nature Communications</i>. Springer Nature. <a href=\"https://doi.org/10.1038/s41467-026-76877-7\">https://doi.org/10.1038/s41467-026-76877-7</a>","ieee":"N. N. Machnik, S. M. Mahmoudi, M. Borczyk, I. Krätschmer, M. J. Bauer, and M. R. Robinson, “Causal inference for multiple risk factors and diseases from genomics data,” <i>Nature Communications</i>, vol. 17. Springer Nature, 2026.","short":"N.N. Machnik, S.M. Mahmoudi, M. Borczyk, I. Krätschmer, M.J. Bauer, M.R. Robinson, Nature Communications 17 (2026).","ama":"Machnik NN, Mahmoudi SM, Borczyk M, Krätschmer I, Bauer MJ, Robinson MR. Causal inference for multiple risk factors and diseases from genomics data. <i>Nature Communications</i>. 2026;17. doi:<a href=\"https://doi.org/10.1038/s41467-026-76877-7\">10.1038/s41467-026-76877-7</a>"},"publication_status":"published","corr_author":"1","researchdata_availability":"yes","doi":"10.1038/s41467-026-76877-7","year":"2026","quality_controlled":"1","ddc":["570"]}]