The tumour histopathology "glossary" for AI developers.

The applications of artificial intelligence (AI) and deep learning (DL) are leading to significant advances in cancer research, particularly in analysing histopathology images for prognostic and treatment-predictive insights. However, effective translation of these computational methods requires computational researchers to have at least a basic understanding of histopathology. In this work, we aim to bridge that gap by introducing essential histopathology concepts to support AI developers in their research.

Plasticity in metastatic colorectal cancer.

Genetic mutations cause colorectal cancer (CRC) initiation, but their contribution to metastasis and therapy resistance is less clear. In a recent issue of Nature, Moorman et al. use single-cell transcriptome sequencing to map the changes in cancer cell state (cell phenotypes) that occur through CRC progression.

Deep Learning for Biomarker Discovery in Cancer Genomes.

Background: Genomic data is essential for clinical decision-making in precision oncology. Bioinformatic algorithms are widely used to analyze next-generation sequencing (NGS) data, but they face two major challenges. First, these pipelines are highly complex, involving multiple steps and the integration of various tools.

Study protocol for Adaptive ChemoTherapy for Ovarian cancer (ACTOv): a multicentre phase II randomised controlled trial to evaluate the efficacy of adaptive therapy (AT) with carboplatin, based on changes in CA125, in patients with relapsed platinum-sensitive high-grade serous or high-grade endometrioid ovarian cancer.

Introduction: Adaptive ChemoTherapy for Ovarian cancer (ACTOv) is a phase II, multicentre, randomised controlled trial, evaluating an adaptive therapy (AT) regimen with carboplatin in women with relapsed, platinum-sensitive high-grade serous or high-grade endometrioid cancer of the ovary, fallopian tube and peritoneum whose disease has progressed at least 6 months after day 1 of the last cycle of platinum-based chemotherapy. AT is a novel, evolutionarily informed approach to cancer treatment, which aims to exploit intratumoral competition between drug-sensitive and drug-resistant tumour subpopulations by modulating drug dose according to a patient's own response to the last round of treatment. ACTOv is the first clinical trial of AT in this disease setting.

Surprising features of nuclear receptor interaction networks revealed by live-cell single-molecule imaging.

Type II nuclear receptors (T2NRs) require heterodimerization with a common partner, the retinoid X receptor (RXR), to bind cognate DNA recognition sites in chromatin. Based on previous biochemical and overexpression studies, binding of T2NRs to chromatin is proposed to be regulated by competition for a limiting pool of the core RXR subunit. However, this mechanism has not yet been tested for endogenous proteins in live cells.