Multi-omic machine learning predictor of breast cancer therapy response

被引:0
|
作者
Stephen-John Sammut
Mireia Crispin-Ortuzar
Suet-Feung Chin
Elena Provenzano
Helen A. Bardwell
Wenxin Ma
Wei Cope
Ali Dariush
Sarah-Jane Dawson
Jean E. Abraham
Janet Dunn
Louise Hiller
Jeremy Thomas
David A. Cameron
John M. S. Bartlett
Larry Hayward
Paul D. Pharoah
Florian Markowetz
Oscar M. Rueda
Helena M. Earl
Carlos Caldas
机构
[1] Li Ka Shing Centre,Cancer Research UK Cambridge Institute, University of Cambridge
[2] University of Cambridge,Department of Oncology
[3] University of Cambridge and Cambridge University Hospitals NHS Foundation Trust,CRUK Cambridge Centre, Cambridge Experimental Cancer Medicine Centre (ECMC) and NIHR Cambridge Biomedical Research Centre
[4] University of Cambridge, School of Clinical Medicine
[5] University of Cambridge,Institute of Astronomy
[6] Peter MacCallum Cancer Centre,Centre of Cancer Research and Sir Peter MacCallum Department of Oncology
[7] University of Melbourne,Warwick Clinical Trials Unit
[8] University of Warwick,Edinburgh Cancer Research Centre
[9] Western General Hospital,Laboratory Medicine and Pathobiology
[10] Q2 Laboratory Solutions, Strangeways Research Laboratory
[11] Ontario Institute for Cancer Research,MRC Biostatistics Unit
[12] University of Toronto,undefined
[13] University of Cambridge,undefined
[14] University of Cambridge,undefined
来源
Nature | 2022年 / 601卷
关键词
D O I
暂无
中图分类号
学科分类号
摘要
Breast cancers are complex ecosystems of malignant cells and the tumour microenvironment1. The composition of these tumour ecosystems and interactions within them contribute to responses to cytotoxic therapy2. Efforts to build response predictors have not incorporated this knowledge. We collected clinical, digital pathology, genomic and transcriptomic profiles of pre-treatment biopsies of breast tumours from 168 patients treated with chemotherapy with or without HER2 (encoded by ERBB2)-targeted therapy before surgery. Pathology end points (complete response or residual disease) at surgery3 were then correlated with multi-omic features in these diagnostic biopsies. Here we show that response to treatment is modulated by the pre-treated tumour ecosystem, and its multi-omics landscape can be integrated in predictive models using machine learning. The degree of residual disease following therapy is monotonically associated with pre-therapy features, including tumour mutational and copy number landscapes, tumour proliferation, immune infiltration and T cell dysfunction and exclusion. Combining these features into a multi-omic machine learning model predicted a pathological complete response in an external validation cohort (75 patients) with an area under the curve of 0.87. In conclusion, response to therapy is determined by the baseline characteristics of the totality of the tumour ecosystem captured through data integration and machine learning. This approach could be used to develop predictors for other cancers.
引用
收藏
页码:623 / 629
页数:6
相关论文
共 50 条
  • [1] Multi-omic machine learning predictor of breast cancer therapy response
    Sammut, Stephen-John
    Crispin-Ortuzar, Mireia
    Chin, Suet-Feung
    Provenzano, Elena
    Bardwell, Helen A.
    Ma, Wenxin
    Cope, Wei
    Dariush, Ali
    Dawson, Sarah-Jane
    Abraham, Jean E.
    Dunn, Janet
    Hiller, Louise
    Thomas, Jeremy
    Cameron, David A.
    Bartlett, John M. S.
    Hayward, Larry
    Pharoah, Paul D.
    Markowetz, Florian
    Rueda, Oscar M.
    Earl, Helena M.
    Caldas, Carlos
    [J]. NATURE, 2022, 601 (7894) : 623 - +
  • [2] Multi-omic machine learning predictor of chemotherapy response of esophageal cancer
    Sasagawa, Shota
    Kato, Hiroaki
    Nagaoka, Koji
    Todd, Johnson
    Maejima, Kazuhiro
    Okawa, Yuki
    Kakimi, Kazuhiro
    Yasuda, Takushi
    Nakagawa, Hidewaki
    [J]. CANCER SCIENCE, 2023, 114 : 1012 - 1012
  • [3] Multi-omic machine learning predictor of chemotherapy response of esophageal cancer
    Sasagawa, Shota
    Kato, Hiroaki
    Nagaoka, Koji
    Todd, Johnson
    Maejima, Kazuhiro
    Okawa, Yuki
    Kakimi, Kazuhiro
    Yasuda, Takushi
    Nakagawa, Hidewaki
    [J]. CANCER SCIENCE, 2023, 114 : 1469 - 1469
  • [4] Multi-omic integration by machine learning (MIMaL)
    Dickinson, Quinn
    Aufschnaiter, Andreas
    Ott, Martin
    Meyer, Jesse G.
    [J]. BIOINFORMATICS, 2022, 38 (21) : 4908 - 4918
  • [5] Explainable Machine Learning for Longitudinal Multi-Omic Microbiome
    Laccourreye, Paula
    Bielza, Concha
    Larranaga, Pedro
    [J]. MATHEMATICS, 2022, 10 (12)
  • [6] Multi-omic predictor of rapid and late relapse in primary triple negative breast cancer
    Zhang, Y.
    Nock, W.
    Asad, S.
    Adams, E.
    Singh, J.
    Damicis, A.
    Lustberg, M. B.
    Noonan, A.
    Reinbolt, R.
    Sardesai, S.
    VanDeusen, J.
    Wesolowski, R.
    Williams, N.
    Ramaswamy, B.
    Stover, D. G.
    [J]. CANCER RESEARCH, 2019, 79 (04)
  • [7] Molecular mechanisms of multi-omic regulation in breast cancer
    Ochoa, Soledad
    Hernandez-Lemus, Enrique
    [J]. FRONTIERS IN ONCOLOGY, 2023, 13
  • [8] A Predictive Model for Postoperative Recurrence of Lung Cancer Based on Multi-omic Machine Learning
    Chen, Z.
    Chen, Z.
    Kang, J.
    Li, Y.
    Xiao, W.
    Chen, J.
    Mo, Y.
    Zhong, W.
    [J]. JOURNAL OF THORACIC ONCOLOGY, 2023, 18 (11) : S183 - S184
  • [9] Functional impact of multi-omic interactions in breast cancer subtypes
    Ochoa, Soledad
    Hernandez-Lemus, Enrique
    [J]. FRONTIERS IN GENETICS, 2023, 13
  • [10] A multi-omic machine learning analysis to predict ALS disease progression
    Patel, Devanshi
    Sharma, Rhiya
    Jafarpour, Laleh
    Sheppard, Ashlyn
    Shen, Jie
    Chai, Charles
    [J]. MUSCLE & NERVE, 2022, 66 : S14 - S15