With the continuing advances of biotechnology and molecular biology of tumors, immunotherapy has become a vital therapeutic modality in cancer treatment. Nevertheless, only a small fraction of patients have been able to achieve clinical benefits. Moreover, the high cost and immune-related adverse events (irAEs) hinder its effective use in clinical practice. Therefore, clinical satisfaction with immunotherapy might be achieved by improving diagnostic accuracy and distinguishing patients with increased potential to benefit from immunotherapy.
Artificial intelligence, especially machine learning, can robustly solve classification or regression tasks by integrating multiple features. Scientists have developed many powerful predictive tools or novel molecular markers for immunotherapy through machine learning combined with clinical features, genomics, radiomics, histological features, or single-cell sequencing data. Machine learning techniques have been shown to effectively overcome the limitations of a single feature in prediction by combining multiple features. The rapid development of Big Data and advanced algorithms may facilitate the roles of utility in predicting response to immunotherapy.
Although immunotherapy has revolutionized cancer treatment, the assessment of whether an individual patient might benefit from immunotherapy usually remains confusing. Manual assessment is difficult to ensure its efficiency and accuracy. Artificial intelligence, on the other hand, can be employed to standardize assessments across institutions rather than relying on clinicians' interpretations, which are occasionally inherently subjective. Artificial intelligence techniques can integrate the large-scale data to optimally match immunotherapy to patients, evaluate the target epitope antigen of tumor vaccine, and predict the risk of irAEs. Thus, artificial intelligence techniques will effectively accelerate tumor immunotherapy's prediction and screening process based on bioengineering technology so that more patients can benefit from immunotherapy.
Currently, only a small proportion of patients could benefit from immunotherapy. Although researchers have tried to develop new treatment options or biomarkers to improve the clinical outcomes of immunotherapy, the results are not satisfactory. With the great advances in artificial intelligence and bioinformatics, it is necessary to develop novel models and biomarkers for immunotherapy.
We invite authors to submit original research and review articles that will help improve the prediction of immunotherapeutic efficacy across multiple cancer types. Potential topics can include, but are not limited to:
• Developing new targets, drugs, neoantigens, and cancer vaccines through artificial intelligence.
• Artificial intelligence to predict response to immunotherapy.
• Application of artificial intelligence in identifying genetic and epigenetic factors that influence response to therapy.
• Impact of artificial intelligence on immunotherapy of novel molecular subtypes of cancer.
• Molecular profiling of genetic and epigenetic biomarkers to identify prognostic and therapeutic targets.
• Use of artificial intelligence and Big Data (including clinical features, genomics, radiomics, histological features, and single-cell sequencing data) in the development of novel biomarkers and models.
With the continuing advances of biotechnology and molecular biology of tumors, immunotherapy has become a vital therapeutic modality in cancer treatment. Nevertheless, only a small fraction of patients have been able to achieve clinical benefits. Moreover, the high cost and immune-related adverse events (irAEs) hinder its effective use in clinical practice. Therefore, clinical satisfaction with immunotherapy might be achieved by improving diagnostic accuracy and distinguishing patients with increased potential to benefit from immunotherapy.
Artificial intelligence, especially machine learning, can robustly solve classification or regression tasks by integrating multiple features. Scientists have developed many powerful predictive tools or novel molecular markers for immunotherapy through machine learning combined with clinical features, genomics, radiomics, histological features, or single-cell sequencing data. Machine learning techniques have been shown to effectively overcome the limitations of a single feature in prediction by combining multiple features. The rapid development of Big Data and advanced algorithms may facilitate the roles of utility in predicting response to immunotherapy.
Although immunotherapy has revolutionized cancer treatment, the assessment of whether an individual patient might benefit from immunotherapy usually remains confusing. Manual assessment is difficult to ensure its efficiency and accuracy. Artificial intelligence, on the other hand, can be employed to standardize assessments across institutions rather than relying on clinicians' interpretations, which are occasionally inherently subjective. Artificial intelligence techniques can integrate the large-scale data to optimally match immunotherapy to patients, evaluate the target epitope antigen of tumor vaccine, and predict the risk of irAEs. Thus, artificial intelligence techniques will effectively accelerate tumor immunotherapy's prediction and screening process based on bioengineering technology so that more patients can benefit from immunotherapy.
Currently, only a small proportion of patients could benefit from immunotherapy. Although researchers have tried to develop new treatment options or biomarkers to improve the clinical outcomes of immunotherapy, the results are not satisfactory. With the great advances in artificial intelligence and bioinformatics, it is necessary to develop novel models and biomarkers for immunotherapy.
We invite authors to submit original research and review articles that will help improve the prediction of immunotherapeutic efficacy across multiple cancer types. Potential topics can include, but are not limited to:
• Developing new targets, drugs, neoantigens, and cancer vaccines through artificial intelligence.
• Artificial intelligence to predict response to immunotherapy.
• Application of artificial intelligence in identifying genetic and epigenetic factors that influence response to therapy.
• Impact of artificial intelligence on immunotherapy of novel molecular subtypes of cancer.
• Molecular profiling of genetic and epigenetic biomarkers to identify prognostic and therapeutic targets.
• Use of artificial intelligence and Big Data (including clinical features, genomics, radiomics, histological features, and single-cell sequencing data) in the development of novel biomarkers and models.
