Your browser doesn't support javascript.
loading
Enhanced Feature Selection for Microbiome Data using FLORAL: Scalable Log-ratio Lasso Regression.
Fei, Teng; Funnell, Tyler; Waters, Nicholas R; Raj, Sandeep S; Sadeghi, Keimya; Dai, Anqi; Miltiadous, Oriana; Shouval, Roni; Lv, Meng; Peled, Jonathan U; Ponce, Doris M; Perales, Miguel-Angel; Gönen, Mithat; van den Brink, Marcel R M.
Afiliação
  • Fei T; Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center.
  • Funnell T; Department of Immunology, Sloan Kettering Institute, Memorial Sloan Kettering Cancer Center.
  • Waters NR; Department of Immunology, Sloan Kettering Institute, Memorial Sloan Kettering Cancer Center.
  • Raj SS; Department of Medicine, Memorial Sloan Kettering Cancer Center.
  • Sadeghi K; Department of Immunology, Sloan Kettering Institute, Memorial Sloan Kettering Cancer Center.
  • Dai A; Department of Immunology, Sloan Kettering Institute, Memorial Sloan Kettering Cancer Center.
  • Miltiadous O; Department of Pediatrics, Memorial Sloan Kettering Cancer Center.
  • Shouval R; Adult Bone Marrow Transplantation Service, Department of Medicine, Memorial Sloan Kettering Cancer Center.
  • Lv M; Department of Medicine, Weill Cornell Medical College.
  • Peled JU; Institute of Hematology, Peking University People's Hospital.
  • Ponce DM; Adult Bone Marrow Transplantation Service, Department of Medicine, Memorial Sloan Kettering Cancer Center.
  • Perales MA; Department of Medicine, Weill Cornell Medical College.
  • Gönen M; Adult Bone Marrow Transplantation Service, Department of Medicine, Memorial Sloan Kettering Cancer Center.
  • van den Brink MRM; Department of Medicine, Weill Cornell Medical College.
bioRxiv ; 2023 Dec 18.
Article em En | MEDLINE | ID: mdl-37205350
Identifying predictive biomarkers of patient outcomes from high-throughput microbiome data is of high interest, while existing computational methods do not satisfactorily account for complex survival endpoints, longitudinal samples, and taxa-specific sequencing biases. We present FLORAL (https://vdblab.github.io/FLORAL/), an open-source computational tool to perform scalable log-ratio lasso regression and microbial feature selection for continuous, binary, time-to-event, and competing risk outcomes, with compatibility of longitudinal microbiome data as time-dependent covariates. The proposed method adapts the augmented Lagrangian algorithm for a zero-sum constraint optimization problem while enabling a two-stage screening process for extended false-positive control. In extensive simulation and real-data analyses, FLORAL achieved consistently better false-positive control compared to other lasso-based approaches, and better sensitivity over popular differential abundance testing methods for datasets with smaller sample size. In a survival analysis in allogeneic hematopoietic-cell transplant, we further demonstrated considerable improvement by FLORAL in microbial feature selection by utilizing longitudinal microbiome data over only using baseline microbiome data.

Texto completo: 1 Base de dados: MEDLINE Tipo de estudo: Prognostic_studies / Risk_factors_studies Idioma: En Revista: BioRxiv Ano de publicação: 2023 Tipo de documento: Article

Texto completo: 1 Base de dados: MEDLINE Tipo de estudo: Prognostic_studies / Risk_factors_studies Idioma: En Revista: BioRxiv Ano de publicação: 2023 Tipo de documento: Article