Automated detection of the HER2 gene amplification status in Fluorescence in situ hybridization images for the diagnostics of cancer tissues.

The human epidermal growth factor receptor 2 (HER2) gene amplification status is a crucial marker for evaluating clinical therapies of breast or gastric cancer. We propose a deep learning-based pipeline for the detection, localization and classification of interphase nuclei depending on their HER2 gene amplification state in Fluorescence in situ hybridization (FISH) images. Our pipeline combines two RetinaNet-based object localization networks which are trained (1) to detect and classify interphase nuclei into distinct classes normal, low-grade and high-grade and (2) to detect and classify FISH signals into distinct classes HER2 or centromere of chromosome 17 (CEN17). By independently classifying each nucleus twice, the two-step pipeline provides both robustness and interpretability for the automated detection of the HER2 amplification status. The accuracy of our deep learning-based pipeline is on par with that of three pathologists and a set of 57 validation images containing several hundreds of nuclei are accurately classified. The automatic pipeline is a first step towards assisting pathologists in evaluating the HER2 status of tumors using FISH images, for analyzing FISH images in retrospective studies, and for optimizing the documentation of each tumor sample by automatically annotating and reporting of the HER2 gene amplification specificities.

Targeted capture-based NGS is superior to multiplex PCR-based NGS for hereditary BRCA1 and BRCA2 gene analysis in FFPE tumor samples.

BACKGROUND: With the introduction of Olaparib treatment for BRCA-deficient recurrent ovarian cancer, testing for somatic and/or germline mutations in BRCA1/2 genes in tumor tissues became essential for treatment decisions. In most cases only formalin-fixed paraffin-embedded (FFPE) samples, containing fragmented and chemically modified DNA of minor quality, are available. Thus, multiplex PCR-based sequencing is most commonly applied in routine molecular testing, which is predominantly focused on the identification of known hot spot mutations in oncogenes. METHODS: We compared the overall performance of an adjusted targeted capture-based enrichment protocol and a multiplex PCR-based approach for calling of pathogenic SNVs and InDels using DNA extracted from 13 FFPE tissue samples. We further applied both strategies to seven blood samples and five matched FFPE tumor tissues of patients with known germline exon-spanning deletions and gene-wide duplications in BRCA1/2 to evaluate CNV detection based solely on panel NGS data. Finally, we analyzed DNA from FFPE tissues of 11 index patients from families suspected of having hereditary breast and ovarian cancer, of whom no blood samples were available for testing, in order to identify underlying pathogenic germline BRCA1/2 mutations. RESULTS: The multiplex PCR-based protocol produced inhomogeneous coverage among targets of each sample and between samples as well as sporadic amplicon drop out, leading to insufficiently or non-covered nucleotides, which subsequently hindered variant detection. This protocol further led to detection of PCR-artifacts that could easily have been misinterpreted as pathogenic mutations. No such limitations were observed by application of an adjusted targeted capture-based protocol, which allowed for CNV calling with 86% sensitivity and 100% specificity. All pathogenic CNVs were confirmed in the five matched FFPE tumor samples from patients carrying known pathogenic germline mutations and we additionally identified somatic loss of the second allele in BRCA1/2. Furthermore we detected pathogenic BRCA1/2 variants in four the eleven FFPE samples from patients of whom no blood was available for analysis. CONCLUSIONS: We demonstrate that an adjusted targeted capture-based enrichment protocol is superior to commonly applied multiplex PCR-based protocols for reliable BRCA1/2 variant detection, including CNV-detection, using FFPE tumor samples.

Human gastric cancer modelling using organoids.

OBJECTIVE: Gastric cancer is the second leading cause of cancer-related deaths and the fifth most common malignancy worldwide. In this study, human and mouse gastric cancer organoids were generated to model the disease and perform drug testing to delineate treatment strategies. DESIGN: Human gastric cancer organoid cultures were established, samples classified according to their molecular profile and their response to conventional chemotherapeutics tested. Targeted treatment was performed according to specific druggable mutations. Mouse gastric cancer organoid cultures were generated carrying molecular subtype-specific alterations. RESULTS: Twenty human gastric cancer organoid cultures were established and four selected for a comprehensive in-depth analysis. Organoids demonstrated divergent growth characteristics and morphologies. Immunohistochemistry showed similar characteristics to the corresponding primary tissue. A divergent response to 5-fluoruracil, oxaliplatin, irinotecan, epirubicin and docetaxel treatment was observed. Whole genome sequencing revealed a mutational spectrum that corresponded to the previously identified microsatellite instable, genomic stable and chromosomal instable subtypes of gastric cancer. The mutational landscape allowed targeted therapy with trastuzumab for ERBB2 alterations and palbociclib for CDKN2A loss. Mouse cancer organoids carrying Kras and Tp53 or Apc and Cdh1 mutations were characterised and serve as model system to study the signalling of induced pathways. CONCLUSION: We generated human and mouse gastric cancer organoids modelling typical characteristics and altered pathways of human gastric cancer. Successful interference with activated pathways demonstrates their potential usefulness as living biomarkers for therapy response testing.

Whole exome sequencing identifies mTOR and KEAP1 as potential targets for radiosensitization of HNSCC cells refractory to EGFR and ß1 integrin inhibition.

Intrinsic and acquired resistances are major obstacles in cancer therapy. Genetic characterization is commonly used to identify predictive or prognostic biomarker signatures and potential cancer targets in samples from therapy-naïve patients. By far less common are such investigations to identify specific, predictive and/or prognostic gene signatures in patients or cancer cells refractory to a specific molecular-targeted intervention. This, however, might have a great value to foster the development of tailored, personalized cancer therapy. Based on our identification of a differential radiosensitization by single and combined ß1 integrin (AIIB2) and EGFR (Cetuximab) targeting in more physiological, three-dimensional head and neck squamous cell carcinoma (HNSCC) cell cultures, we performed comparative whole exome sequencing, phosphoproteome analyses and RNAi knockdown screens in responder and non-responder cell lines. We found a higher rate of gene mutations with putative protein-changing characteristics in non-responders and different mutational profiles of responders and non-responders. These profiles allow stratification of HNSCC patients and identification of potential targets to address treatment resistance. Consecutively, pharmacological inhibition of mTOR and KEAP1 effectively diminished non-responder insusceptibility to ß1 integrin and EGFR targeting for radiosensitization. Our data pinpoint the added value of genetic biomarker identification after selection for cancer subgroup responsiveness to targeted therapies.