1
|
Foltz SM, Greene CS, Taroni JN. Cross-platform normalization enables machine learning model training on microarray and RNA-seq data simultaneously. Commun Biol 2023; 6:222. [PMID: 36841852 PMCID: PMC9968332 DOI: 10.1038/s42003-023-04588-6] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/02/2017] [Accepted: 02/13/2023] [Indexed: 02/27/2023] Open
Abstract
Large compendia of gene expression data have proven valuable for the discovery of novel biological relationships. Historically, most available RNA assays were run on microarray, while RNA-seq is now the platform of choice for many new experiments. The data structure and distributions between the platforms differ, making it challenging to combine them directly. Here we perform supervised and unsupervised machine learning evaluations to assess which existing normalization methods are best suited for combining microarray and RNA-seq data. We find that quantile and Training Distribution Matching normalization allow for supervised and unsupervised model training on microarray and RNA-seq data simultaneously. Nonparanormal normalization and z-scores are also appropriate for some applications, including pathway analysis with Pathway-Level Information Extractor (PLIER). We demonstrate that it is possible to perform effective cross-platform normalization using existing methods to combine microarray and RNA-seq data for machine learning applications.
Collapse
Affiliation(s)
- Steven M Foltz
- Department of Systems Pharmacology and Translational Therapeutics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
- Childhood Cancer Data Lab, Alex's Lemonade Stand Foundation, Wynnewood, PA, USA
| | - Casey S Greene
- Department of Systems Pharmacology and Translational Therapeutics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
- Center for Health AI, University of Colorado School of Medicine, Aurora, CO, USA.
- Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, CO, USA.
| | - Jaclyn N Taroni
- Department of Systems Pharmacology and Translational Therapeutics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
- Childhood Cancer Data Lab, Alex's Lemonade Stand Foundation, Wynnewood, PA, USA.
| |
Collapse
|
2
|
Jiang M, Xu H, Yu D, Yang L, Wu W, Wang H, Sun H, Zhu J, Zhao W, Fang Q, Yu J, Chen P, Wu S, Zheng Z, Zhang L, Hou L, Zhang H, Gu Y, He Y. Risk-score model to predict prognosis of malignant airway obstruction after interventional bronchoscopy. Transl Lung Cancer Res 2021; 10:3173-3190. [PMID: 34430356 PMCID: PMC8350098 DOI: 10.21037/tlcr-21-301] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/14/2021] [Accepted: 06/18/2021] [Indexed: 12/25/2022]
Abstract
Background Interventional bronchoscopy exhibits substantial effects for patients with malignant airway obstruction (MAO), while little information is available regarding the potential prognostic factors for these patients. Methods Between October 31, 2016, and July 31, 2019, a total of 150 patients undergoing interventional bronchoscopy and histologically-confirmed MAO were collected, in which 112 eligible participants formed the cohort for survival study. External validation cohort from another independent institution comprised 33 MAO patients with therapeutic bronchoscopy. The least absolute shrinkage and selection operator regression (LASSO) was applied to the model development dataset for selecting features correlated with MAO survival for inclusion in the Cox regression from which we elaborated the risk score system. A nomogram algorithm was also utilized. Results In our study, we observed a significant decline of stenosis rate after interventional bronchoscopy from 71.7%±2.1% to 36.6%±2.7% (P<0.001) and interventional bronchoscopy dilated airway effectively. Patients in our study undergoing interventional bronchoscopy had a median survival time of 614.000 days (95% CI: 269.876–958.124). Patients receiving distinct therapeutic methods of interventional bronchoscopy had different prognosis (P=0.022), and patients receiving treatment of electrocoagulation in combination with stenting and electrosurgical snare had worse survival than those receiving other options. Multivariate Cox analysis revealed that nonsmoking status, adenoid cystic carcinoma, and low preoperative stenosis length, as independent predictive factors for better overall survival (OS) of MAO patients. Then, the nomogram based on Cox regression and risk score system based on results from LASSO regression were elaborated respectively. Importantly, this risk score system was proved to have better performance than the nomogram and other single biomarkers such as traditional staging system (area under the curve 0.855 vs. 0.392–0.739). Survival curves showed that patients with the higher risk-score had poorer prognosis than those with lower risk-score (third quantile of OS: 126.000 days, 95% CI: 73.588–178.412 vs. 532.000 days, 95% CI: 0.000–1,110.372; P<0.001). Conclusions Nonsmoking status, adenoid cystic carcinoma, and low preoperative stenosis length, were independent predictive factors for better OS of MAO patients. We proposed a nomogram and risk score system for survival prediction of MAO patients undergoing interventional bronchoscopy with good performance.
Collapse
Affiliation(s)
- Minlin Jiang
- Department of Medical Oncology, Shanghai Pulmonary Hospital, Tongji University Medical School Cancer Institute, Tongji University School of Medicine, Shanghai, China.,Tongji University, Shanghai, China
| | - Hao Xu
- Department of Respiratory, the Second Affiliated Hospital of Zhejiang University, Hangzhou, China
| | - Dongmei Yu
- Department of Endoscopy Center, Shanghai Pulmonary Hospital, Tongji University Medical School Cancer Institute, Tongji University School of Medicine, Shanghai, China
| | - Li Yang
- Department of Endoscopy Center, Shanghai Pulmonary Hospital, Tongji University Medical School Cancer Institute, Tongji University School of Medicine, Shanghai, China
| | - Wenhui Wu
- Pulmonary Hypertension Research Group, Quebec Heart and Lung Institute Research Centre (IUCPQ), Québec City, QC, Canada
| | - Hao Wang
- Department of Medical Oncology, Shanghai Pulmonary Hospital, Tongji University Medical School Cancer Institute, Tongji University School of Medicine, Shanghai, China.,Tongji University, Shanghai, China
| | - Hui Sun
- Department of Medical Oncology, Shanghai Pulmonary Hospital, Tongji University Medical School Cancer Institute, Tongji University School of Medicine, Shanghai, China
| | - Jun Zhu
- Department of Medical Oncology, Shanghai Pulmonary Hospital, Tongji University Medical School Cancer Institute, Tongji University School of Medicine, Shanghai, China
| | - Wencheng Zhao
- Department of Medical Oncology, Shanghai Pulmonary Hospital, Tongji University Medical School Cancer Institute, Tongji University School of Medicine, Shanghai, China
| | - Qiyu Fang
- Department of Medical Oncology, Shanghai Pulmonary Hospital, Tongji University Medical School Cancer Institute, Tongji University School of Medicine, Shanghai, China
| | - Jia Yu
- Department of Medical Oncology, Shanghai Pulmonary Hospital, Tongji University Medical School Cancer Institute, Tongji University School of Medicine, Shanghai, China
| | - Peixin Chen
- Department of Medical Oncology, Shanghai Pulmonary Hospital, Tongji University Medical School Cancer Institute, Tongji University School of Medicine, Shanghai, China.,Tongji University, Shanghai, China
| | - Shengyu Wu
- Department of Medical Oncology, Shanghai Pulmonary Hospital, Tongji University Medical School Cancer Institute, Tongji University School of Medicine, Shanghai, China.,Tongji University, Shanghai, China
| | - Zixuan Zheng
- Department of Medical Oncology, Shanghai Pulmonary Hospital, Tongji University Medical School Cancer Institute, Tongji University School of Medicine, Shanghai, China.,Tongji University, Shanghai, China
| | - Liping Zhang
- Department of Pathology, Shanghai Pulmonary Hospital, Tongji University Medical School Cancer Institute, Tongji University School of Medicine, Shanghai, China
| | - Likun Hou
- Department of Pathology, Shanghai Pulmonary Hospital, Tongji University Medical School Cancer Institute, Tongji University School of Medicine, Shanghai, China
| | - Huixian Zhang
- Department of Medical Oncology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Ye Gu
- Department of Endoscopy Center, Shanghai Pulmonary Hospital, Tongji University Medical School Cancer Institute, Tongji University School of Medicine, Shanghai, China
| | - Yayi He
- Department of Medical Oncology, Shanghai Pulmonary Hospital, Tongji University Medical School Cancer Institute, Tongji University School of Medicine, Shanghai, China
| |
Collapse
|
3
|
Samart K, Tuyishime P, Krishnan A, Ravi J. Reconciling multiple connectivity scores for drug repurposing. Brief Bioinform 2021; 22:6278144. [PMID: 34013329 PMCID: PMC8597919 DOI: 10.1093/bib/bbab161] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/08/2020] [Revised: 04/02/2021] [Accepted: 04/07/2021] [Indexed: 12/16/2022] Open
Abstract
The basis of several recent methods for drug repurposing is the key principle that an
efficacious drug will reverse the disease molecular ‘signature’ with minimal side effects.
This principle was defined and popularized by the influential ‘connectivity map’ study in
2006 regarding reversal relationships between disease- and drug-induced gene expression
profiles, quantified by a disease-drug ‘connectivity score.’ Over the past 15 years,
several studies have proposed variations in calculating connectivity scores toward
improving accuracy and robustness in light of massive growth in reference drug profiles.
However, these variations have been formulated inconsistently using various notations and
terminologies even though they are based on a common set of conceptual and statistical
ideas. Therefore, we present a systematic reconciliation of multiple disease-drug
similarity metrics (\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
}{}$ES$\end{document}, \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
}{}$css$\end{document},
\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
}{}$Sum$\end{document}, \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
}{}$Cosine$\end{document},
\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
}{}$XSum$\end{document}, \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
}{}$XCor$\end{document},
\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
}{}$XSpe$\end{document}, \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
}{}$XCos$\end{document},
\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
}{}$EWCos$\end{document}) and connectivity scores
(\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
}{}$CS$\end{document}, \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
}{}$RGES$\end{document},
\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
}{}$NCS$\end{document}, \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
}{}$WCS$\end{document},
\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
}{}$Tau$\end{document}, \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
}{}$CSS$\end{document},
\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
}{}$EMUDRA$\end{document}) by defining them using consistent
notation and terminology. In addition to providing clarity and deeper insights, this
coherent definition of connectivity scores and their relationships provides a unified
scheme that newer methods can adopt, enabling the computational drug-development community
to compare and investigate different approaches easily. To facilitate the continuous and
transparent integration of newer methods, this article will be available as a live
document (https://jravilab.github.io/connectivity_scores) coupled with a GitHub
repository (https://github.com/jravilab/connectivity_scores) that any researcher can
build on and push changes to.
Collapse
Affiliation(s)
- Kewalin Samart
- Computational Mathematics, and Computational Math, Science & Engineering at Michigan State University, East Lansing, MI, USA
| | - Phoebe Tuyishime
- College of Agriculture and Natural Resources at Michigan State University, East Lansing, MI, USA
| | - Arjun Krishnan
- Departments of Computational Math, Science & Engineering, and Biochemistry & Molecular Biology at Michigan State University, East Lansing, MI, USA
| | - Janani Ravi
- Pathobiology and Diagnostic Investigation at Michigan State University, East Lansing, MI, USA
| |
Collapse
|