i-Modern: Integrated multi-omics network model identifies potential therapeutic targets in glioma by deep learning with interpretability
Effective and precise classification of glioma patients for their disease risks is critical to improving early diagnosis and patient survival. In the recent past, a significant amount of multi-omics data derived from cancer patients has emerged. However, a robust framework for integrating multi-omic...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-01-01
|
Series: | Computational and Structural Biotechnology Journal |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2001037022002720 |
_version_ | 1797978251438587904 |
---|---|
author | Xingxin Pan Brandon Burgman Erxi Wu Jason H. Huang Nidhi Sahni S. Stephen Yi |
author_facet | Xingxin Pan Brandon Burgman Erxi Wu Jason H. Huang Nidhi Sahni S. Stephen Yi |
author_sort | Xingxin Pan |
collection | DOAJ |
description | Effective and precise classification of glioma patients for their disease risks is critical to improving early diagnosis and patient survival. In the recent past, a significant amount of multi-omics data derived from cancer patients has emerged. However, a robust framework for integrating multi-omics data types to efficiently and precisely subgroup glioma patients and predict survival prognosis is still lacking. In addition, effective therapeutic targets for treating glioma patients with poor prognoses are in dire need. To begin to resolve this difficulty, we developed i-Modern, an integrated Multi-omics deep learning network method, and optimized a sophisticated computational model in gliomas that can accurately stratify patients based on their prognosis. We built a survival-associated predictive framework integrating transcription profile, miRNA expression, somatic mutations, copy number variation (CNV), DNA methylation, and protein expression. This framework achieved promising performance in distinguishing high-risk glioma patients from those with good prognoses. Furthermore, we constructed multiple fully connected neural networks that are trained on prioritized multi-omics signatures or even only potential single-omics signatures, based on our customized scoring system. Together, the landmark multi-omics signatures we identified may serve as potential therapeutic targets in gliomas. |
first_indexed | 2024-04-11T05:20:01Z |
format | Article |
id | doaj.art-e31fa03c2a8d43c1ac702b2f9c856c22 |
institution | Directory Open Access Journal |
issn | 2001-0370 |
language | English |
last_indexed | 2024-04-11T05:20:01Z |
publishDate | 2022-01-01 |
publisher | Elsevier |
record_format | Article |
series | Computational and Structural Biotechnology Journal |
spelling | doaj.art-e31fa03c2a8d43c1ac702b2f9c856c222022-12-24T04:53:14ZengElsevierComputational and Structural Biotechnology Journal2001-03702022-01-012035113521i-Modern: Integrated multi-omics network model identifies potential therapeutic targets in glioma by deep learning with interpretabilityXingxin Pan0Brandon Burgman1Erxi Wu2Jason H. Huang3Nidhi Sahni4S. Stephen Yi5Department of Oncology, Livestrong Cancer Institutes, Dell Medical School, The University of Texas at Austin, Austin, TX 78712, USADepartment of Oncology, Livestrong Cancer Institutes, Dell Medical School, The University of Texas at Austin, Austin, TX 78712, USA; Interdisciplinary Life Sciences Graduate Programs (ILSGP), College of Natural Sciences, The University of Texas at Austin, Austin, TX 78712, USADepartment of Oncology, Livestrong Cancer Institutes, Dell Medical School, The University of Texas at Austin, Austin, TX 78712, USA; Neuroscience Institute and Department of Neurosurgery, Baylor Scott & White Health, Temple, TX 76502, USA; Department of Surgery, Texas A & M University Health Science Center, College of Medicine, Temple, TX 76508, USA; Department of Pharmaceutical Sciences, Texas A & M University Health Science Center, College of Pharmacy, College Station, TX 77843, USA; Corresponding authors at: Livestrong Cancer Institutes, University of Texas at Austin, Austin, TX 78712, USA (S. Stephen Yi); Baylor Scott & White Health, Temple, TX 76508, USA (E. Wu, J.H. Huang), Department of Epigenetics and Molecular Carcinogenesis, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA (N. Sahni).Neuroscience Institute and Department of Neurosurgery, Baylor Scott & White Health, Temple, TX 76502, USA; Department of Surgery, Texas A & M University Health Science Center, College of Medicine, Temple, TX 76508, USA; Corresponding authors at: Livestrong Cancer Institutes, University of Texas at Austin, Austin, TX 78712, USA (S. Stephen Yi); Baylor Scott & White Health, Temple, TX 76508, USA (E. Wu, J.H. Huang), Department of Epigenetics and Molecular Carcinogenesis, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA (N. Sahni).Department of Epigenetics and Molecular Carcinogenesis, The University of Texas MD Anderson Cancer Center, Houston, TX 77230, USA; Department of Bioinformatics and Computational Biology, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA; Quantitative and Computational Biosciences Program, Baylor College of Medicine, Houston, TX 77030, USA; Corresponding authors at: Livestrong Cancer Institutes, University of Texas at Austin, Austin, TX 78712, USA (S. Stephen Yi); Baylor Scott & White Health, Temple, TX 76508, USA (E. Wu, J.H. Huang), Department of Epigenetics and Molecular Carcinogenesis, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA (N. Sahni).Department of Oncology, Livestrong Cancer Institutes, Dell Medical School, The University of Texas at Austin, Austin, TX 78712, USA; Department of Surgery, Texas A & M University Health Science Center, College of Medicine, Temple, TX 76508, USA; Oden Institute for Computational Engineering and Sciences (ICES), The University of Texas at Austin, Austin, TX 78712, USA; Department of Biomedical Engineering, Cockrell School of Engineering, The University of Texas at Austin, Austin, TX 78712, USA; Corresponding authors at: Livestrong Cancer Institutes, University of Texas at Austin, Austin, TX 78712, USA (S. Stephen Yi); Baylor Scott & White Health, Temple, TX 76508, USA (E. Wu, J.H. Huang), Department of Epigenetics and Molecular Carcinogenesis, The University of Texas MD Anderson Cancer Center, Houston, TX 77030, USA (N. Sahni).Effective and precise classification of glioma patients for their disease risks is critical to improving early diagnosis and patient survival. In the recent past, a significant amount of multi-omics data derived from cancer patients has emerged. However, a robust framework for integrating multi-omics data types to efficiently and precisely subgroup glioma patients and predict survival prognosis is still lacking. In addition, effective therapeutic targets for treating glioma patients with poor prognoses are in dire need. To begin to resolve this difficulty, we developed i-Modern, an integrated Multi-omics deep learning network method, and optimized a sophisticated computational model in gliomas that can accurately stratify patients based on their prognosis. We built a survival-associated predictive framework integrating transcription profile, miRNA expression, somatic mutations, copy number variation (CNV), DNA methylation, and protein expression. This framework achieved promising performance in distinguishing high-risk glioma patients from those with good prognoses. Furthermore, we constructed multiple fully connected neural networks that are trained on prioritized multi-omics signatures or even only potential single-omics signatures, based on our customized scoring system. Together, the landmark multi-omics signatures we identified may serve as potential therapeutic targets in gliomas.http://www.sciencedirect.com/science/article/pii/S2001037022002720Multi-omicsDeep learning modelData integrationPatient stratificationGlioma |
spellingShingle | Xingxin Pan Brandon Burgman Erxi Wu Jason H. Huang Nidhi Sahni S. Stephen Yi i-Modern: Integrated multi-omics network model identifies potential therapeutic targets in glioma by deep learning with interpretability Computational and Structural Biotechnology Journal Multi-omics Deep learning model Data integration Patient stratification Glioma |
title | i-Modern: Integrated multi-omics network model identifies potential therapeutic targets in glioma by deep learning with interpretability |
title_full | i-Modern: Integrated multi-omics network model identifies potential therapeutic targets in glioma by deep learning with interpretability |
title_fullStr | i-Modern: Integrated multi-omics network model identifies potential therapeutic targets in glioma by deep learning with interpretability |
title_full_unstemmed | i-Modern: Integrated multi-omics network model identifies potential therapeutic targets in glioma by deep learning with interpretability |
title_short | i-Modern: Integrated multi-omics network model identifies potential therapeutic targets in glioma by deep learning with interpretability |
title_sort | i modern integrated multi omics network model identifies potential therapeutic targets in glioma by deep learning with interpretability |
topic | Multi-omics Deep learning model Data integration Patient stratification Glioma |
url | http://www.sciencedirect.com/science/article/pii/S2001037022002720 |
work_keys_str_mv | AT xingxinpan imodernintegratedmultiomicsnetworkmodelidentifiespotentialtherapeutictargetsingliomabydeeplearningwithinterpretability AT brandonburgman imodernintegratedmultiomicsnetworkmodelidentifiespotentialtherapeutictargetsingliomabydeeplearningwithinterpretability AT erxiwu imodernintegratedmultiomicsnetworkmodelidentifiespotentialtherapeutictargetsingliomabydeeplearningwithinterpretability AT jasonhhuang imodernintegratedmultiomicsnetworkmodelidentifiespotentialtherapeutictargetsingliomabydeeplearningwithinterpretability AT nidhisahni imodernintegratedmultiomicsnetworkmodelidentifiespotentialtherapeutictargetsingliomabydeeplearningwithinterpretability AT sstephenyi imodernintegratedmultiomicsnetworkmodelidentifiespotentialtherapeutictargetsingliomabydeeplearningwithinterpretability |