Your browser doesn't support javascript.
loading
Discovery of sparse, reliable omic biomarkers with Stabl.
Hédou, Julien; Maric, Ivana; Bellan, Grégoire; Einhaus, Jakob; Gaudillière, Dyani K; Ladant, Francois-Xavier; Verdonk, Franck; Stelzer, Ina A; Feyaerts, Dorien; Tsai, Amy S; Ganio, Edward A; Sabayev, Maximilian; Gillard, Joshua; Amar, Jonas; Cambriel, Amelie; Oskotsky, Tomiko T; Roldan, Alennie; Golob, Jonathan L; Sirota, Marina; Bonham, Thomas A; Sato, Masaki; Diop, Maïgane; Durand, Xavier; Angst, Martin S; Stevenson, David K; Aghaeepour, Nima; Montanari, Andrea; Gaudillière, Brice.
Afiliação
  • Hédou J; Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA, USA.
  • Maric I; Department of Pediatrics, Stanford University, Stanford, CA, USA.
  • Bellan G; Télécom Paris, Institut Polytechnique de Paris, Paris, France.
  • Einhaus J; Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA, USA.
  • Gaudillière DK; Department of Pathology and Neuropathology, University Hospital and Comprehensive Cancer Center Tübingen, Tübingen, Germany.
  • Ladant FX; Division of Plastic and Reconstructive Surgery, Department of Surgery, Stanford University, Stanford, CA, USA.
  • Verdonk F; Department of Economics, Harvard University, Cambridge, MA, USA.
  • Stelzer IA; Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA, USA.
  • Feyaerts D; Sorbonne University, GRC 29, AP-HP, DMU DREAM, Department of Anesthesiology and Intensive Care, Hôpital Saint-Antoine, Assistance Publique-Hôpitaux de Paris, Paris, France.
  • Tsai AS; Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA, USA.
  • Ganio EA; Department of Pathology, University of California San Diego, La Jolla, CA, USA.
  • Sabayev M; Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA, USA.
  • Gillard J; Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA, USA.
  • Amar J; Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA, USA.
  • Cambriel A; Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA, USA.
  • Oskotsky TT; Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA, USA.
  • Roldan A; Department of Medical BioSciences, Radboud University Medical Center, Nijmegen, The Netherlands.
  • Golob JL; Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA, USA.
  • Sirota M; Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA, USA.
  • Bonham TA; Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, CA, USA.
  • Sato M; Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, CA, USA.
  • Diop M; Department of Medicine, University of Michigan Medical School, Ann Arbor, MI, USA.
  • Durand X; Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, CA, USA.
  • Angst MS; Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA, USA.
  • Stevenson DK; Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA, USA.
  • Aghaeepour N; Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA, USA.
  • Montanari A; École Polytechnique, Institut Polytechnique de Paris, Paris, France.
  • Gaudillière B; Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA, USA.
Nat Biotechnol ; 42(10): 1581-1593, 2024 Oct.
Article em En | MEDLINE | ID: mdl-38168992
ABSTRACT
Adoption of high-content omic technologies in clinical studies, coupled with computational methods, has yielded an abundance of candidate biomarkers. However, translating such findings into bona fide clinical biomarkers remains challenging. To facilitate this process, we introduce Stabl, a general machine learning method that identifies a sparse, reliable set of biomarkers by integrating noise injection and a data-driven signal-to-noise threshold into multivariable predictive modeling. Evaluation of Stabl on synthetic datasets and five independent clinical studies demonstrates improved biomarker sparsity and reliability compared to commonly used sparsity-promoting regularization methods while maintaining predictive performance; it distills datasets containing 1,400-35,000 features down to 4-34 candidate biomarkers. Stabl extends to multi-omic integration tasks, enabling biological interpretation of complex predictive models, as it hones in on a shortlist of proteomic, metabolomic and cytometric events predicting labor onset, microbial biomarkers of pre-term birth and a pre-operative immune signature of post-surgical infections. Stabl is available at https//github.com/gregbellan/Stabl .
Assuntos
Texto completo
Imprimir
XML
PubMed Links
Buscar no Google

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Biomarcadores / Aprendizado de Máquina Tipo de estudo: Prognostic_studies Limite: Humans Idioma: En Revista: Nat Biotechnol Assunto da revista: BIOTECNOLOGIA Ano de publicação: 2024 Tipo de documento: Article País de afiliação: Estados Unidos
Texto completo
Imprimir
XML
PubMed Links
Buscar no Google

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Biomarcadores / Aprendizado de Máquina Tipo de estudo: Prognostic_studies Limite: Humans Idioma: En Revista: Nat Biotechnol Assunto da revista: BIOTECNOLOGIA Ano de publicação: 2024 Tipo de documento: Article País de afiliação: Estados Unidos