With the development of machine learning and deep learning models, clinical informatics is incorporating oncology research into clinical practice to improve patient care from genomics, proteomics, bioinformatics, and biostatistics. In oncology, multi-omics data have the potential to reveal further system-level insights, but also present computational and biological challenges. First, analysis of big data through machine learning offers considerable advantages for assimilating and evaluating large amounts of complex oncology data. Second, key questions regarding the use of single versus multi-omics, the choice of clustering strategies, the ability to generalize multi-view methods, and the use of approximate p-values that can measure differential classification, tissue invasion, gene mutation prediction, and prognostic prediction. Also, due to the increasing use of multi-omics data, we anticipate that multi-omics data integration methods and their synergy with machine learning methods are important for the progress of personalized therapy in this tumor. Recently, there have been many efforts for multi-omics models in cancer genetics, including systems biology frameworks and genetic linkage. However, we have only just begun to deepen our biomedical understanding of cancer. Therefore, more research is needed to enrich the learning algorithms and layers of oncology research, and a multimodal approach will help match these open questions for treating malignant diseases and help develop new therapeutic strategies from this research area.
With this in mind, we have opened this research topic to implement relevant bioinformatics methods and oncology applications with a special focus on the learning model. potential topics include but are not limited to the following:
1. Identification and characterization of new advances in tumor treatment strategies based on characterizing different stages and machine learning.
2. Deep learning network system based on multi-omics.
3. Exploration of multi-omic machine learning predictor of cancer therapy response.
4. Machine and deep learning approaches for cancer combination therapy.
5. Bioinformatics and machine learning approach in tumors to identify potential drug targets and pathways.
6. Resources and novel algorithms for cancer research using AI.
Please Note: Manuscripts based on re-analysis of pre-existing data collections will only be considered when including appropriate experimental validation or in the context of novel data analysis methodologies and verification through independent datasets
With the development of machine learning and deep learning models, clinical informatics is incorporating oncology research into clinical practice to improve patient care from genomics, proteomics, bioinformatics, and biostatistics. In oncology, multi-omics data have the potential to reveal further system-level insights, but also present computational and biological challenges. First, analysis of big data through machine learning offers considerable advantages for assimilating and evaluating large amounts of complex oncology data. Second, key questions regarding the use of single versus multi-omics, the choice of clustering strategies, the ability to generalize multi-view methods, and the use of approximate p-values that can measure differential classification, tissue invasion, gene mutation prediction, and prognostic prediction. Also, due to the increasing use of multi-omics data, we anticipate that multi-omics data integration methods and their synergy with machine learning methods are important for the progress of personalized therapy in this tumor. Recently, there have been many efforts for multi-omics models in cancer genetics, including systems biology frameworks and genetic linkage. However, we have only just begun to deepen our biomedical understanding of cancer. Therefore, more research is needed to enrich the learning algorithms and layers of oncology research, and a multimodal approach will help match these open questions for treating malignant diseases and help develop new therapeutic strategies from this research area.
With this in mind, we have opened this research topic to implement relevant bioinformatics methods and oncology applications with a special focus on the learning model. potential topics include but are not limited to the following:
1. Identification and characterization of new advances in tumor treatment strategies based on characterizing different stages and machine learning.
2. Deep learning network system based on multi-omics.
3. Exploration of multi-omic machine learning predictor of cancer therapy response.
4. Machine and deep learning approaches for cancer combination therapy.
5. Bioinformatics and machine learning approach in tumors to identify potential drug targets and pathways.
6. Resources and novel algorithms for cancer research using AI.
Please Note: Manuscripts based on re-analysis of pre-existing data collections will only be considered when including appropriate experimental validation or in the context of novel data analysis methodologies and verification through independent datasets