Baseline mutational profiles of patients with carcinoma of unknown primary origin enrolled in the CUPISCO study

A machine learning-based method for feature reduction of methylation data for the classification of cancer tissue origin

BACKGROUND

Genome DNA methylation profiling is a promising yet costly method for cancer classification, involving substantial data. We developed an ensemble learning model to identify cancer types using methylation profiles from a limited number of CpG sites.

METHODS

Analyzing methylation data from 890 samples across 10 cancer types from the TCGA database, we utilized ANOVA and Gain Ratio to select the most significant CpG sites, then employed Gradient Boosting to reduce these to just 100 sites.

RESULTS

This approach maintained high accuracy across multiple machine learning models, with classification accuracy rates between 87.7% and 93.5% for methods including Extreme Gradient Boosting, CatBoost, and Random Forest. This method effectively minimizes the number of features needed without losing performance, helping to classify primary organs and uncover subgroups within specific cancers like breast and lung.

CONCLUSIONS

Using a gradient boosting feature selector shows potential for streamlining methylation-based cancer classification.

Molecularly guided therapy versus chemotherapy after disease control in unfavourable cancer of unknown primary (CUPISCO): an open-label, randomised, phase 2 study

BACKGROUND

Patients with unfavourable subset cancer of unknown primary (CUP) have a poor prognosis when treated with standard platinum-based chemotherapy. Whether first-line treatment guided by comprehensive genomic profiling (CGP) can improve outcomes is unknown. The CUPISCO trial was designed to inform a molecularly guided treatment strategy to improve outcomes over standard platinum-based chemotherapy in patients with newly diagnosed, unfavourable, non-squamous CUP. The aim of the trial was to compare the efficacy and safety of molecularly guided therapy (MGT) versus standard platinum-based chemotherapy in these patients. This was to determine whether the inclusion of CGP in the initial diagnostic work-up leads to improved outcomes over the current standard of care. We herein report the primary analysis.

METHODS

CUPISCO was a phase 2, prospective, randomised, open-label, active-controlled, multicentre trial done at 159 sites in 34 countries outside the USA. Patients with central eligibility review-confirmed disease (acceptable histologies included adenocarcinoma and poorly differentiated carcinoma) and an Eastern Cooperative Oncology Group performance status of 0 or 1, evaluated by CGP, who reached disease control after three cycles of standard first-line platinum-based chemotherapy were randomly assigned 3:1 via a block-stratified randomisation procedure to MGT versus chemotherapy continuation for at least three further cycles. The primary endpoint was investigator-assessed progression-free survival in the intention-to-treat population. The study is registered with ClinicalTrials.gov, NCT03498521, and follow-up is ongoing.

FINDINGS

From July 10, 2018, to Dec 9, 2022, 636 (42%) of 1505 screened patients were enrolled. Median follow-up in the treatment period was 24·1 months (IQR 11·6-35·6). Of 438 patients who reached disease control after induction chemotherapy, 436 were randomly assigned: 326 (75%) to the MGT group and 110 (25%) to the chemotherapy group. Median progression-free survival in the intention-to-treat population was 6·1 months (95% CI 4·7-6·5) in the MGT group versus 4·4 months (4·1-5·6) in the chemotherapy group (hazard ratio 0·72 [95% CI 0·56-0·92]; p=0·0079). Related adverse event rates per 100-patient-years at risk were generally similar or lower with MGT versus chemotherapy.

INTERPRETATION

In patients with previously untreated, unfavourable, non-squamous CUP who reached disease control after induction chemotherapy, CGP with subsequent MGTs resulted in longer progression-free survival than standard platinum-based chemotherapy. On the basis of these results, we recommend that CGP is performed at initial diagnosis in patients with unfavourable CUP.

FUNDING

F Hoffmann-La Roche.

Clinical practice guidelines for molecular tumor marker, 2nd edition review part 2

In recent years, rapid advancement in gene/protein analysis technology has resulted in target molecule identification that may be useful in cancer treatment. Therefore, "Clinical Practice Guidelines for Molecular Tumor Marker, Second Edition" was published in Japan in September 2021. These guidelines were established to align the clinical usefulness of external diagnostic products with the evaluation criteria of the Pharmaceuticals and Medical Devices Agency. The guidelines were scoped for each tumor, and a clinical questionnaire was developed based on a serious clinical problem. This guideline was based on a careful review of the evidence obtained through a literature search, and recommendations were identified following the recommended grades of the Medical Information Network Distribution Services (Minds). Therefore, this guideline can be a tool for cancer treatment in clinical practice. We have already reported the review portion of "Clinical Practice Guidelines for Molecular Tumor Marker, Second Edition" as Part 1. Here, we present the English version of each part of the Clinical Practice Guidelines for Molecular Tumor Marker, Second Edition.

Advances in Cancer Research: Current and Future Diagnostic and Therapeutic Strategies

Cancers of unknown primary (CUP) exhibit significant cellular heterogeneity and malignancy, which poses significant challenges for diagnosis and treatment. Recent years have seen deeper insights into the imaging, pathology, and genetic characteristics of CUP, driven by interdisciplinary collaboration and the evolution of diagnostic and therapeutic strategies. However, due to their insidious onset, lack of evidence-based medicine, and limited clinical understanding, diagnosing and treating CUP remain a significant challenge. To inspire more creative and fantastic research, herein, we report and highlight recent advances in the diagnosis and therapeutic strategies of CUP. Specifically, we discuss advanced diagnostic technologies, including 12-deoxy-2-[fluorine-18]fluoro-D-glucose integrated with computed tomography (18F-FDG PET/CT) or 68Ga-FAPI (fibroblast activation protein inhibitor) PET/CT, liquid biopsy, molecular diagnostics, self-assembling nanotechnology, and artificial intelligence (AI). In particular, the discussion will extend to the effective treatment techniques currently available, such as targeted therapies, immunotherapies, and bio-nanotechnology-based therapeutics. Finally, a novel perspective on the challenges and directions for future CUP diagnostic and therapeutic strategies is discussed.