Tumour biomarkers articles from across Nature Portfolio

Cervical cancer remains a significant public health problem in many regions. Here, the authors perform a proteogenomic analysis of cervical cancer in Chinese patients; they reveal proteomic subgroups associated with clinical and biological features, and a potential biomarker of response to radiotherapy.

Genomic profiling of tumours can help tailer treatments to the patient, however, it often fails to accurately predict therapeutic outcomes. Here, the authors combine molecular and functional characterisation via BH3 profiling to identify therapeutically targetable vulnerabilities in glioma.

In this Journal Club, Sabarinathan discusses a study suggesting immunoproteasome expression as a potential biomarker of response to immune checkpoint inhibition in melanoma.

An analysis of histopathological data from mouse and human tumours via machine learning reveals that the densities of blood vessels and tumour-associated macrophages are predictive features of the degree of tumoural accumulation of polymeric and liposomal nanomedicines.

The development of clinically relevant artificial intelligence (AI) models has traditionally required access to extensive labelled datasets, which inevitably centre AI advances around large centres and private corporations. Data availability has also dictated the development of AI applications: most studies focus on common cancer types, and leave rare diseases behind. However, this paradigm is changing with the advent of foundation models, which enable the training of more powerful and robust AI systems using much smaller datasets.