NICE Guidelines: management of colorectal cancer metastases

Machine-Learning Identifies a Strategy for Differentiation Therapy in Solid Tumors

BACKGROUND

Although differentiation therapy can cure some hematologic malignancies, its curative potential remains unrealized in solid tumors. This is because conventional computational approaches succumb to the thunderous noise of inter-/intratumoral heterogeneity. Using colorectal cancers (CRCs) as an example, here we outline a machine learning(ML)-based approach to track, differentiate, and selectively target cancer stem cells (CSCs).

METHODS

A transcriptomic network was built and validated using healthy colon and CRC tissues in diverse gene expression datasets (~5,000 human and >300 mouse samples). Therapeutic targets and perturbation strategies were prioritized using ML, with the goal of reinstating the expression of a transcriptional identifier of the differentiated colonocyte, CDX2, whose loss in poorly differentiated (CSC-enriched) CRCs doubles the risk of relapse/death. The top candidate target was then engaged with a clinical-grade drug and tested on 3 models: CRC lines in vitro, xenografts in mice, and in a prospective cohort of healthy (n = 3) and CRC (n = 23) patient-derived organoids (PDOs).

RESULTS

The drug shifts the network predictably, induces CDX2 and crypt differentiation, and shows cytotoxicity in all 3 models, with a high degree of selectivity towards all CDX2-negative cell lines, xenotransplants, and PDOs. The potential for effective pairing of therapeutic efficacy (IC50) and biomarker (CDX2-low state) is confirmed in PDOs using multivariate analyses. A 50-gene signature of therapeutic response is derived and tested on 9 independent cohorts (~1700 CRCs), revealing the impact of CDX2-reinstatement therapy could translate into a ~50% reduction in the risk of mortality/recurrence.

CONCLUSIONS

Findings not only validate the precision of the ML approach in targeting CSCs, and objectively assess its impact on clinical outcome, but also exemplify the use of ML in yielding clinical directive information for enhancing personalized medicine.

Current Perspectives on the Importance of Pathological Features in Prognostication and Guidance of Adjuvant Chemotherapy in Colon Cancer

There is not a clear consensus on which pathological features and biomarkers are important in guiding prognosis and adjuvant therapy in colon cancer. The Pathology in Colon Cancer, Prognosis and Uptake of Adjuvant Therapy (PiCC UP) Australia and New Zealand questionnaire was distributed to colorectal surgeons, medical oncologists and pathologists after institutional board approval. The aim of this study was to understand current specialist attitudes towards pathological features in the prognostication of colon cancer and adjuvant therapy in stage II disease. A 5-scale Likert score was used to assess attitudes towards 23 pathological features for prognosis and 18 features for adjuvant therapy. Data were analysed using a rating scale and graded response model in item response theory (IRT) on STATA (Stata MP, version 15; StataCorp LP). One hundred and sixty-four specialists (45 oncologists, 86 surgeons and 33 pathologists) participated. Based on IRT modelling, the most important pathological features for prognosis in colon cancer were distant metastases, lymph node metastases and liver metastases. Other features seen as important were tumour rupture, involved margin, radial margin, CRM, lymphovascular invasion and grade of differentiation. Size of tumour, location, lymph node ratio and EGFR status were considered less important. The most important features in decision making for adjuvant therapy in stage II colon cancer were tumour rupture, lymphovascular invasion and microsatellite instability. BRAF status, size of tumour, location, tumour budding and tumour infiltrating lymphocytes were factored as lesser importance. Biomarkers such as CDX2, EGFR, KRAS and BRAF status present areas for further research to improve precision oncology. This study provides the most current status on the importance of pathological features in prognostication and recommendations for adjuvant therapy in Australia and New Zealand. Results of this nationwide study may be useful to help in guiding prognosis and adjuvant treatment in colon cancer.

Pathological Features and Prognostication in Colorectal Cancer

The prognostication of colorectal cancer (CRC) has traditionally relied on staging as defined by the Union for International Cancer Control (UICC) and American Joint Committee on Cancer (AJCC) TNM staging classifications. However, clinically, there appears to be differences in survival patterns independent of stage, suggesting a complex interaction of stage, pathological features, and biomarkers playing a role in guiding prognosis, risk stratification, and guiding neoadjuvant and adjuvant therapies. Histological features such as tumour budding, perineural invasion, apical lymph node involvement, lymph node yield, lymph node ratio, and molecular features such as MSI, KRAS, BRAF, and CDX2 may assist in prognostication and optimising adjuvant treatment. This study provides a comprehensive review of the pathological features and biomarkers that are important in the prognostication and treatment of CRC. We review the importance of pathological features and biomarkers that may be important in colorectal cancer based on the current evidence in the literature.