Integration of Machine Learning and Genome-scale Metabolic Modeling Implicates Lipid and Cysteine Metabolism as Critical Determinants of Radiation Therapy Response

AbstractResistance to ionizing radiation, a first-line therapy for many cancers, is a major clinical challenge. Personalized prediction of tumor radiosensitivity is not currently implemented clinically due to insufficient accuracy of existing machine learning classifiers. Despite the acknowledged role of tumor metabolism in radiation response, metabolomics data is rarely collected in large multi-omics initiatives such as The Cancer Genome Atlas (TCGA) and consequently omitted from algorithm development. In this study, we circumvent the paucity of personalized metabolomics information by characterizing 915 TCGA patient tumors with genome-scale metabolic Flux Balance Analysis models generated from transcriptomic and genomic datasets. Metabolic biomarkers differentiating radiation-sensitive and -resistant tumors are predicted and experimentally validated, enabling integration of metabolic features with other multi-omics datasets into ensemble-based machine learning classifiers for radiation response. These multi-omics classifiers show improved classification accuracy, identify clinical patient subgroups, and demonstrate the utility of personalized blood-based metabolic biomarkers for radiation sensitivity. The integration of machine learning with genome-scale metabolic modeling represents a significant methodological advancement for identifying prognostic metabolite biomarkers and predicting radiosensitivity for individual patients.

Download Full-text

Machine learning-based radiomic models to predict intensity-modulated radiation therapy response, Gleason score and stage in prostate cancer

La radiologia medica ◽

10.1007/s11547-018-0966-4 ◽

2019 ◽

Vol 124 (6) ◽

pp. 555-567 ◽

Cited By ~ 24

Author(s):

Hamid Abdollahi ◽

Bahram Mofid ◽

Isaac Shiri ◽

Abolfazl Razzaghdoust ◽

Afshin Saadipoor ◽

...

Keyword(s):

Prostate Cancer ◽

Machine Learning ◽

Radiation Therapy ◽

Gleason Score ◽

Intensity Modulated Radiation Therapy ◽

Therapy Response ◽

Intensity Modulated

Download Full-text

Genome-Scale Metabolic Modeling Enables In-Depth Understanding of Big Data

Metabolites ◽

10.3390/metabo12010014 ◽

2021 ◽

Vol 12 (1) ◽

pp. 14

Author(s):

Anurag Passi ◽

Juan D. Tibocha-Bonilla ◽

Manish Kumar ◽

Diego Tec-Campos ◽

Karsten Zengler ◽

...

Keyword(s):

Machine Learning ◽

Big Data ◽

Metabolic Pathways ◽

Drug Targets ◽

Metabolic Modeling ◽

Annotation Data ◽

Dynamic Resolution ◽

Different Types ◽

Eukaryotic Organisms ◽

Genome Scale

Genome-scale metabolic models (GEMs) enable the mathematical simulation of the metabolism of archaea, bacteria, and eukaryotic organisms. GEMs quantitatively define a relationship between genotype and phenotype by contextualizing different types of Big Data (e.g., genomics, metabolomics, and transcriptomics). In this review, we analyze the available Big Data useful for metabolic modeling and compile the available GEM reconstruction tools that integrate Big Data. We also discuss recent applications in industry and research that include predicting phenotypes, elucidating metabolic pathways, producing industry-relevant chemicals, identifying drug targets, and generating knowledge to better understand host-associated diseases. In addition to the up-to-date review of GEMs currently available, we assessed a plethora of tools for developing new GEMs that include macromolecular expression and dynamic resolution. Finally, we provide a perspective in emerging areas, such as annotation, data managing, and machine learning, in which GEMs will play a key role in the further utilization of Big Data.

Download Full-text

Integration of machine learning and genome-scale metabolic modeling identifies multi-omics biomarkers for radiation resistance

10.1101/2020.08.02.233098 ◽

2020 ◽

Author(s):

Joshua E. Lewis ◽

Melissa L. Kemp

Keyword(s):

Machine Learning ◽

Metabolic Flux ◽

Metabolic Modeling ◽

The Cancer Genome Atlas ◽

Radiation Response ◽

Metabolomics Data ◽

Machine Learning Classifiers ◽

Learning Classifiers ◽

Metabolic Biomarkers ◽

Genome Scale

AbstractResistance to ionizing radiation, a first-line therapy for many cancers, is a major clinical challenge. Personalized prediction of tumor radiosensitivity is not currently implemented clinically due to insufficient accuracy of existing machine learning classifiers. Despite the acknowledged role of tumor metabolism in radiation response, metabolomics data is rarely collected in large multi-omics initiatives such as The Cancer Genome Atlas (TCGA) and consequently omitted from algorithm development. In this study, we circumvent the paucity of personalized metabolomics information by characterizing 915 TCGA patient tumors with genome-scale metabolic Flux Balance Analysis models generated from transcriptomic and genomic datasets. Novel metabolic biomarkers differentiating radiation-sensitive and -resistant tumors were predicted and experimentally validated, enabling integration of metabolic features with other multi-omics datasets into ensemble-based machine learning classifiers for radiation response. These multi-omics classifiers showed improved classification accuracy, identified novel clinical patient subgroups, and demonstrated the utility of personalized blood-based metabolic biomarkers for radiation sensitivity. The integration of machine learning with genome-scale metabolic modeling represents a significant methodological advancement for identifying prognostic metabolite biomarkers and predicting radiosensitivity for individual patients.

Download Full-text