Cancer is a disease with unique management complexity because it displays high heterogeneity of molecular phenotypes. This heterogeneity results in significant differences in drug sensitivity, survival prognosis, and other aspects between individual cancer patients, even between patients with the same cancer tissue origin. Therefore, inferring the molecular classification of cancer is a key issue to address in order to provide personalized cancer therapy. Currently, many studies have aimed to classify cancer subtypes through the understanding of tumor heterogeneity and have promoted precision treatment. The subtype of breast cancer is a prime example of this. However, current clinical treatment for cancer patients is too imprecise and there is much research required to fully understand cancer heterogeneity.

In today’s biomedical big data era, the application of computational methods and high-throughput technologies have accelerated the understanding of cancer mechanisms. Some of the molecular features of cancer have been identified through the analysis of omics data. Signatures identified mainly focus on certain malignant phenotypes, functional mechanisms, or on a certain tumor microenvironment. By defining immune subtypes of cancer, the components of the tumor-immune microenvironment and the functional state of anti-cancer immunity can be better identified to guide clinical treatment and predict clinical outcomes for patients. However, the molecular mechanisms in cancer are complex, and there is an urgent need to find more cancer-specific traits or to identify more precise cancer molecular classifications. In addition, the application of computational methods in the multi-omics study is particularly important in this field due to its ability to handle large-scale data.

This Special Issue aims to publish original research and review articles involving computational methods for inferring novel molecular classifications that can predict clinical outcomes for cancer patients and guide individualized treatment.

Potential topics include but are not limited to the following:

• Inferring molecular classification for specific cancers or pan-cancers based on multi-omics data
• Inferring molecular classification for specific cancers or pan-cancers based on liquid biopsy
• Single-cell analyses for cancer molecular classification
• Medical image-based methods in cancer molecular classification
• Artificial Intelligence in cancer molecular classification
• Bioinformatic tools for cancer molecular classification analysis and visualization
• Clinical applications of cancer molecular classification
• Identification of novel cancer molecular classification that can promote precision treatment
• Identification of novel cancer molecular classification related to patient clinical outcomes
• Identification of novel cancer molecular classification related to chemotherapy sensitivity and immunotherapy response
• The association between cancer molecular classification and other biomarkers like TMB, MSI, MMR, etc.
• Experimental validation of the above-mentioned sections