Epidemiological data indicate that cancer is a growing global health problem. The World Health Organization (WHO) predicts an estimated 27 million new cases of cancer worldwide by 2030. Cancer is a genetic disease for which traditional treatments cause harmful side effects. After two decades of genomics technological breakthroughs, personalized medicine is being used to improve treatment outcomes and mitigate side effects.
Machine learning has been a successful methodology to extract knowledge from Big Data Bioinformatics. Machine learning algorithms use training datasets to reveal underlying patterns, design models, and make statistical predictions based on the best fit model. Indeed, well-known Machine Learning algorithms have been applied in several domains, such as genomics, proteomics, and systems biology. Machine Learning in Cancer has been used, for instance, to identify potential therapeutic targets, to propose the new therapies and minimize potential side effects using omics datasets.
There is a pressing need to design and develop new mathematical and computational strategies, in particular those based on Machine Learning methods, to harness cancer Big Data in an accurate and efficient fashion. To achieve this objective, high performance and high-throughput computing platforms and tools are of utmost importance. This Research Topic solicits papers describing contributions to the state of the art and practice in Big Data and Machine Learning methods applied to cancer theranostics, with a special focus on the analysis of large omics datasets and the utilization of scalable computational infrastructures.
Subtopics of interest include, but are not limited to:
- Multiscale advanced mathematical and computational models based on Machine Learning and Big Data methods applied to omics datasets
- Data-driven tumor modeling and simulation using omics datasets
- Tumor forecasting methods using Machine Learning algorithms on omics datasets
- Molecular subtyping, survival analysis and prediction using Machine Learning algorithms
- Machine Learning methods for Systems biology and networks
- Machine Learning methods for anticancer drug development
- Statistical methods and data mining for cancer theranostics
- Deep learning for cancer theranostics
- Big Data analytics for cancer theranostics
- High-performance and data-intensive computing for cancer theranostics
- Scalable and high throughput systems for large-scale cancer-data analytics
- Text analytics and natural language processing (NLP) for cancer research
- Automatic semantic annotation of medical content in the context of cancer disease
- Application of cloud computing, SaaS and PaaS architectures for cancer theranostics
- Computer-aided diagnosis (CADx) systems for cancer theranostics
- Computer vision, scientific visualization, and image processing for cancer theranostics
Epidemiological data indicate that cancer is a growing global health problem. The World Health Organization (WHO) predicts an estimated 27 million new cases of cancer worldwide by 2030. Cancer is a genetic disease for which traditional treatments cause harmful side effects. After two decades of genomics technological breakthroughs, personalized medicine is being used to improve treatment outcomes and mitigate side effects.
Machine learning has been a successful methodology to extract knowledge from Big Data Bioinformatics. Machine learning algorithms use training datasets to reveal underlying patterns, design models, and make statistical predictions based on the best fit model. Indeed, well-known Machine Learning algorithms have been applied in several domains, such as genomics, proteomics, and systems biology. Machine Learning in Cancer has been used, for instance, to identify potential therapeutic targets, to propose the new therapies and minimize potential side effects using omics datasets.
There is a pressing need to design and develop new mathematical and computational strategies, in particular those based on Machine Learning methods, to harness cancer Big Data in an accurate and efficient fashion. To achieve this objective, high performance and high-throughput computing platforms and tools are of utmost importance. This Research Topic solicits papers describing contributions to the state of the art and practice in Big Data and Machine Learning methods applied to cancer theranostics, with a special focus on the analysis of large omics datasets and the utilization of scalable computational infrastructures.
Subtopics of interest include, but are not limited to:
- Multiscale advanced mathematical and computational models based on Machine Learning and Big Data methods applied to omics datasets
- Data-driven tumor modeling and simulation using omics datasets
- Tumor forecasting methods using Machine Learning algorithms on omics datasets
- Molecular subtyping, survival analysis and prediction using Machine Learning algorithms
- Machine Learning methods for Systems biology and networks
- Machine Learning methods for anticancer drug development
- Statistical methods and data mining for cancer theranostics
- Deep learning for cancer theranostics
- Big Data analytics for cancer theranostics
- High-performance and data-intensive computing for cancer theranostics
- Scalable and high throughput systems for large-scale cancer-data analytics
- Text analytics and natural language processing (NLP) for cancer research
- Automatic semantic annotation of medical content in the context of cancer disease
- Application of cloud computing, SaaS and PaaS architectures for cancer theranostics
- Computer-aided diagnosis (CADx) systems for cancer theranostics
- Computer vision, scientific visualization, and image processing for cancer theranostics
