DNA methylation profiling reliably distinguishes pulmonary enteric adenocarcinoma from metastatic colorectal cancer

The Role of DNA Methylation in Gastrointestinal Disease: An Expanded Review of Malignant and Nonmalignant Gastrointestinal Diseases

Esophageal, colorectal, pancreatic, hepatocellular, and gastric cancer together impact millions of patients worldwide each year, with high overall mortality rates, and are increasing in incidence. Additionally, premalignant gastrointestinal diseases, such as Barrett's esophagus and inflammatory bowel disease, are also increasing in incidence. However, involvement of aberrant DNA methylation in these diseases is incompletely understood, especially given recent research advancements in this field. Here, we review knowledge of this epigenetic mechanism in gastrointestinal preneoplasia and neoplasia, considering mechanisms of action, genetic and environmental factors, and 5'-C-phosphate-G-3' island methylator phenotype. We also highlight developments in translational research, focusing on genomic-wide data, methylation-based biomarkers and diagnostic tests, machine learning, and therapeutic epigenetic strategies.

Accurate identification of primary site in tumors of unknown origin (TUO) using DNA methylation

Tumors of unknown origin (TUO) generally result in poor patient survival and are clinically difficult to address. Identification of the site of origin in TUO patients is paramount to their improved treatment and survival but is difficult to obtain with current methods. Here, we develop a random forest machine learning TUO methylation classifier using a large number of primary and metastatic tumor samples. Our classifier achieves high accuracy in primary site identification when applied to both publicly available and internal validation samples, with 97% of samples classified correctly and 85% receiving high probability scores (≥0.9). Moreover, by employing pathologist expertise and t-SNE visualization, the TUO classifier can assign samples to 46 different sites of origin/disease classes. This strategy also revealed multiple classes of yet unknown significance for future exploration. Overall, the presented TUO classifier represents a significant step forward in the diagnosis of TUO tumors.

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.

Lung enteric-type adenocarcinoma with gastric metastasis: a rare case report and literature review

Lung enteric-type adenocarcinoma (ETAC) is a rare subtype of non-small cell lung cancer (NSCLC), comprising approximately 0.6% of all primary lung adenocarcinomas. It is characterized by a tendency for early metastasis and a prognosis comparable to that of common lung adenocarcinoma. This case report described a patient with lung-ETAC who developed gastric metastasis. The patient underwent treatment with chemotherapy and a PD-1 inhibitor, resulting in disease remission with a progression-free survival (PFS) of 8 months. The follow-up time was 13 months. This case report was aimed to enhance understanding of the biological behavior of this rare tumor and provide insights into potential future treatment strategies.

Case report: 18F-FDG PET/CT in pulmonary enteric adenocarcinoma

Pulmonary enteric adenocarcinoma (PEAC), an uncommon variant of lung cancer, presents significant diagnostic challenges due to its overlapping characteristics with colorectal adenocarcinomas. We present a case of a 55-year-old non-smoking female patient diagnosed with PEAC. The patient's initial symptoms included fever, cough, and sputum production, with air space consolidation on CT, leading to an initial diagnosis of pneumonia. Sputum culture after admission showed no growth of bacteria and fungi. Anti-inflammatory therapy was not ideal. Subsequent bronchoscopy with endobronchial ultrasound and biopsy confirmed the diagnosis of PEAC. Gastroscopy and colonoscopy yielded negative results, and a PET/CT scan revealed an FDG-avid lesion in the right middle lobe, with no other significant hypermetabolic gastrointestinal lesions, thereby excluding an extrapulmonary primary gastrointestinal malignancy. The patient was ultimately staged as PEAC (T4N1M0, stage IIIb). She declined anti-tumor therapy and experienced clinical deterioration during follow-up. This case report expands the radiological spectrum of PEAC, adds to the limited literature, and emphasizes the role of 18F-FDG PET/CT in diagnosing such diseases. It also underscores the importance of a multidisciplinary approach in the management of PEAC.

Deep learning and machine learning approaches to classify stomach distant metastatic tumors using DNA methylation profiles

Distant metastasis of cancer is a significant contributor to cancer-related complications, and early identification of unidentified stomach adenocarcinoma is crucial for a positive prognosis. Changes inDNA methylation are being increasingly recognized as a crucial factor in predicting cancer progression. Within this research, we developed machine learning and deep learning models for distinguishing distant metastasis in samples of stomach adenocarcinoma based on DNA methylation profile. Employing deep neural networks (DNN), support vector machines (SVM), random forest (RF), Naive Bayes (NB) and decision tree (DT), and models for forecasting distant metastasis in stomach adenocarcinoma. The results show that the performance of DNN is better than that of other models, AUC and AUPR achieving 99.9 % and 99.5 % respectively. Additionally, a weighted random sampling technique was utilized to address the issue of imbalanced datasets, enabling the identification of crucial methylation markers associated with functionally significant genes in stomach distant metastasis tumors with greater performance.

Proteomics-Derived Biomarker Panel Facilitates Distinguishing Primary Lung Adenocarcinomas With Intestinal or Mucinous Differentiation From Lung Metastatic Colorectal Cancer

The diagnosis of primary lung adenocarcinomas with intestinal or mucinous differentiation (PAIM) remains challenging due to the overlapping histomorphological, immunohistochemical (IHC), and genetic characteristics with lung metastatic colorectal cancer (lmCRC). This study aimed to explore the protein biomarkers that could distinguish between PAIM and lmCRC. To uncover differences between the two diseases, we used tandem mass tagging-based shotgun proteomics to characterize proteomes of formalin-fixed, paraffin-embedded tumor samples of PAIM (n = 22) and lmCRC (n = 17).Then three machine learning algorithms, namely support vector machine (SVM), random forest, and the Least Absolute Shrinkage and Selection Operator, were utilized to select protein features with diagnostic significance. These candidate proteins were further validated in an independent cohort (PAIM, n = 11; lmCRC, n = 19) by IHC to confirm their diagnostic performance. In total, 105 proteins out of 7871 proteins were significantly dysregulated between PAIM and lmCRC samples and well-separated two groups by Uniform Manifold Approximation and Projection. The upregulated proteins in PAIM were involved in actin cytoskeleton organization, platelet degranulation, and regulation of leukocyte chemotaxis, while downregulated ones were involved in mitochondrial transmembrane transport, vasculature development, and stem cell proliferation. A set of ten candidate proteins (high-level expression in lmCRC: CDH17, ATP1B3, GLB1, OXNAD1, LYST, FABP1; high-level expression in PAIM: CK7 (an established marker), NARR, MLPH, S100A14) was ultimately selected to distinguish PAIM from lmCRC by machine learning algorithms. We further confirmed using IHC that the five protein biomarkers including CDH17, CK7, MLPH, FABP1 and NARR were effective biomarkers for distinguishing PAIM from lmCRC. Our study depicts PAIM-specific proteomic characteristics and demonstrates the potential utility of new protein biomarkers for the differential diagnosis of PAIM and lmCRC. These findings may contribute to improving the diagnostic accuracy and guide appropriate treatments for these patients.

EpiDiP/NanoDiP: a versatile unsupervised machine learning edge computing platform for epigenomic tumour diagnostics

DNA methylation analysis based on supervised machine learning algorithms with static reference data, allowing diagnostic tumour typing with unprecedented precision, has quickly become a new standard of care. Whereas genome-wide diagnostic methylation profiling is mostly performed on microarrays, an increasing number of institutions additionally employ nanopore sequencing as a faster alternative. In addition, methylation-specific parallel sequencing can generate methylation and genomic copy number data. Given these diverse approaches to methylation profiling, to date, there is no single tool that allows (1) classification and interpretation of microarray, nanopore and parallel sequencing data, (2) direct control of nanopore sequencers, and (3) the integration of microarray-based methylation reference data. Furthermore, no software capable of entirely running in routine diagnostic laboratory environments lacking high-performance computing and network infrastructure exists. To overcome these shortcomings, we present EpiDiP/NanoDiP as an open-source DNA methylation and copy number profiling suite, which has been benchmarked against an established supervised machine learning approach using in-house routine diagnostics data obtained between 2019 and 2021. Running locally on portable, cost- and energy-saving system-on-chip as well as gpGPU-augmented edge computing devices, NanoDiP works in offline mode, ensuring data privacy. It does not require the rigid training data annotation of supervised approaches. Furthermore, NanoDiP is the core of our public, free-of-charge EpiDiP web service which enables comparative methylation data analysis against an extensive reference data collection. We envision this versatile platform as a useful resource not only for neuropathologists and surgical pathologists but also for the tumour epigenetics research community. In daily diagnostic routine, analysis of native, unfixed biopsies by NanoDiP delivers molecular tumour classification in an intraoperative time frame.

Pulmonary invasive mucinous adenocarcinoma

Invasive mucinous adenocarcinoma (IMA) is a relatively rare subtype of lung adenocarcinoma, composed of goblet and/or columnar tumour cells containing abundant intracytoplasmic mucin vacuoles. While a majority of IMAs are driven by KRAS mutations, recent studies have identified distinct genomic alterations, such as NRG1 and ERBB2 fusions. IMAs also more frequently present as a pneumonic-like pattern with multifocal and multilobar involvement, and comparative genomic profiling predominantly shows a clonal relationship, suggesting intrapulmonary metastases rather than synchronous primary tumours. Accordingly, these unique features require different therapeutic approaches when compared to nonmucinous adenocarcinomas in general. In this article, we review recent updates on the histopathological, clinical, and molecular features of IMAs, and also highlight some unresolved issues for future studies.

Frequent nuclear β-catenin expression in pulmonary enteric-type adenocarcinoma according to the current World Health Organization criteria

Based on the current World Health Organization classification criteria, five of 3895 consecutive cases of surgically resected primary lung carcinomas (0.13%) categorized as enteric-type were analyzed. Three cases completely comprised tumor cells that resemble colorectal adenocarcinoma, while the other two cases exhibited features of conventional adenocarcinomas admixed with enteric components. Immunohistochemically, all patients expressed at least three of the five intestinal markers: CDX2, CK20, HNF4α, MUC2, and SATB2. None of the patients expressed TTF-1 and NKX3.1. Three cases showed nuclear accumulation of β-catenin, indicating activation of the Wnt/β-catenin signaling pathway; APC mutations were detected in one of these cases. TP53 mutations were detected in three cases. Mutated EGFR or ALK fusions were not detected. Our study demonstrates that pulmonary enteric-type adenocarcinomas share immunohistochemical features and genetic alterations with colorectal adenocarcinomas, which are characterized by frequent activation of the Wnt/β-catenin signaling pathway and a lack of actionable mutations.

Distinguishing Gastric/Esophageal Adenocarcinoma from Pancreatic Adenocarcinoma Using Methylation-Based Droplet Digital PCR

The goal of this study was to develop a methylation-based droplet digital PCR to separate 2 cancer classes that do not have sensitive and specific immunohistochemical stains: gastric/esophageal and pancreatic adenocarcinomas. The assay used methylation-independent primers and methylation-dependent probes to assess a single differentially methylated CpG site; analyses of array data from The Cancer Genome Atlas network showed that high methylation at the cg06118999 probe supports the presence of cells originating from the stomach or esophagus (eg, as in gastric metastasis), whereas low methylation suggests that these cells are rare to absent (eg, pancreatic metastasis). On validation using formalin-fixed paraffin-embedded primary and metastatic samples from our institution, methylation-based droplet digital PCR targeting the corresponding CpG dinucleotide generated evaluable data for 60 of the 62 samples (97%) and correctly classified 50 of the 60 evaluable cases (83.3%), mostly adenocarcinomas from the stomach or pancreas. This ddPCR was created to be easy-to-interpret, rapid, inexpensive, and compatible with existing platforms at many clinical laboratories. We suggest that similarly accessible PCRs could be developed for other differentials in pathology that do not have sensitive and specific immunohistochemical stains.

DNA methylation-based classifier differentiates intrahepatic pancreato-biliary tumours

BACKGROUND

Differentiating intrahepatic cholangiocarcinomas (iCCA) from hepatic metastases of pancreatic ductal adenocarcinoma (PAAD) is challenging. Both tumours have similar morphological and immunohistochemical pattern and share multiple driver mutations. We hypothesised that DNA methylation-based machine-learning algorithms may help perform this task.

METHODS

We assembled genome-wide DNA methylation data for iCCA (n = 259), PAAD (n = 431), and normal bile duct (n = 70) from publicly available sources. We split this cohort into a reference (n = 399) and a validation set (n = 361). Using the reference cohort, we trained three machine learning models to differentiate between these entities. Furthermore, we validated the classifiers on the technical validation set and used an internal cohort (n = 72) to test our classifier.

FINDINGS

On the validation cohort, the neural network, support vector machine, and the random forest classifiers reached accuracies of 97.68%, 95.62%, and 96.5%, respectively. Filtering by anomaly detection and thresholds improved the accuracy to 99.07% (37 samples excluded by filtering), 96.22% (17 samples excluded), and 100% (44 samples excluded) for the neural network, support vector machine and random forest, respectively. Because of best balance between accuracy and number of predictable cases we tested the neural network with applied filters on the in-house cohort, obtaining an accuracy of 95.45%.

INTERPRETATION

We developed a classifier that can differentiate between iCCAs, intrahepatic metastases of a PAAD, and normal bile duct tissue with high accuracy. This tool can be used for improving the diagnosis of pancreato-biliary cancers of the liver.

FUNDING

This work was supported by Berlin Institute of Health (JCS Program), DKTK Berlin (Young Investigator Grant 2022), German Research Foundation (493697503 and 314905040 - SFB/TRR 209 Liver Cancer B01), and German Cancer Aid (70113922).

erarchical tumor artificial intelligence classifier traces tissue of origin and tumor type in primary and metastasized tumors using DNA methylation

Human cancers are heterogenous by their cell composition and origination site. Cancer metastasis generates the conundrum of the unknown origin of migrated tumor cells. Tracing tissue of origin and tumor type in primary and metastasized cancer is vital for clinical significance. DNA methylation alterations play a crucial role in carcinogenesis and mark cell fate differentiation, thus can be used to trace tumor tissue of origin. In this study, we employed a novel tumor-type-specific hierarchical model using genome-scale DNA methylation data to develop a multilayer perceptron model, HiTAIC, to trace tissue of origin and tumor type in 27 cancers from 23 tissue sites in data from 7735 tumors with high resolution, accuracy, and specificity. In tracing primary cancer origin, HiTAIC accuracy was 99% in the test set and 93% in the external validation data set. Metastatic cancers were identified with a 96% accuracy in the external data set. HiTAIC is a user-friendly web-based application through https://sites.dartmouth.edu/salaslabhitaic/. In conclusion, we developed HiTAIC, a DNA methylation-based algorithm, to trace tumor tissue of origin in primary and metastasized cancers. The high accuracy and resolution of tumor tracing using HiTAIC holds promise for clinical assistance in identifying cancer of unknown origin.

Deciphering Lung Adenocarcinoma Heterogeneity: An Overview of Pathological and Clinical Features of Rare Subtypes

Lung cancer is one of the most frequently diagnosed cancers worldwide and the leading cause of cancer-related death. The 2021 World Health Organization (WHO) classification provided a detailed and updated categorization of lung adenocarcinomas with a special focus on rare histological types, including enteric, fetal and colloid types, as well as not otherwise specified adenocarcinoma, overall accounting for about 5-10% of all cases. However, rare entities are nowadays difficult to diagnose in most centers, and evidence of optimal therapeutic management for these patients is still lacking. In recent years, increasing knowledge about the mutational profile of lung cancer, in addition to the spreading diffusion of next-generation sequencing (NGS) in different centers, have been helpful in the identification of rare variants of lung cancer. Hence, the hope is that several new drugs will be available in the near future to treat these rare lung tumors, such as in targeted therapy and immunotherapy, which are often used in clinical practice for several malignancies. The aim of this review is to summarize the current knowledge about the molecular pathology and clinical management of the most common rare adenocarcinoma subtypes in order to provide a concise and updated report that can drive clinicians' choices in their routine practice.

Expression of paired box 9 defines an aggressive subset of lung adenocarcinoma preferentially occurring in smokers

AIMS

A distinct subset of lung adenocarcinomas (LADs), arising from a series of peripheral lung cells defined as the terminal respiratory unit (TRU), is characterised by thyroid transcription factor 1 (TTF-1) expression. The clinical relevance of transcription factors (TFs) other than TTF-1 remains unknown in LAD and was explored in the present study.

METHODS AND RESULTS

Seventy-one LAD samples were subjected to high-throughput transcriptome screening of LAD using cap analysis gene expression (CAGE) sequencing data; CAGE provides genome-wide expression levels of the transcription start sites (TSSs). In total, 1083 invasive LAD samples were subjected to immunohistochemical examination for paired box 9 (PAX9) and TTF-1 expression levels. PAX9 is an endoderm development-associated TF that most strongly and inversely correlates with the expression of TTF-1 TSS subsets. Immunohistochemically, PAX9 expression was restricted to the nuclei of ciliated epithelial and basal cells in the bronchi and bronchioles and the nuclei of epithelial cells of the bronchial glands; moreover, PAX9 expression was observed in 304 LADs (28%). PAX9-positive LADs were significantly associated with heavy smoking, non-lepidic subtype, EGFR wild-type tumours and PD-L1 expression (all P < 0.0001). All these characteristics were opposite to those of TRU-type LADs with TTF-1 expression. PAX9 expression was an independent prognostic factor for decreased overall survival (P = 0.022).

CONCLUSIONS

Our results revealed that PAX9 expression defines an aggressive subset of LADs preferentially occurring in smokers that may arise from bronchial or bronchiolar cells.

Clinical features and prognosis of pulmonary enteric adenocarcinoma: A retrospective study in China and the SEER database

Objective

Pulmonary enteric adenocarcinoma (PEAC) is a rare subtype of pulmonary adenocarcinoma that lacks effective treatment. The purpose of this research was to investigate the clinical characteristics, treatment, and prognosis of PEAC, as well as the impact of relevant factors on survival, thus providing a reference for the clinical management of patients with this disease.

Methods

For this study, we gathered clinical data from 26 patients with PEAC in the Affiliated Cancer Hospital of Zhengzhou University from June 2014 to June 2021. We used SEER*Stat software V8.3.5 to download the PEAC patients from the Surveillance, Epidemiology, and End Results (SEER) database. In total, 20 patients were identified. Clinical data, including general information, imaging findings, and treatment protocols, were obtained, together with a follow-up of disease regression. The relevant clinical data were then analyzed.

Results

It included 12 males and 14 females out of 26 patients from China, whose mean age was (62.73 ± 11.89) years; 20 were in the lower lung, 11 were stage I-II, and 15 were stage III-IV. Five had EGFR mutations, and four had KRAS mutations. In terms of treatment, patients with stage I-II were primarily treated by surgery, and patients with stage III-IV were treated mostly by chemotherapy. We extended the follow-up date to January 2022. On completion of the follow-up visit, 11 patients died, and the remaining 15 patients survived. The overall survival (OS) of 26 patients was 2.0-76.0 months, while the mean was 53.1 months, and the median OS (mOS) was 38.0 months (95% CI:1.727-74.273). In the case of progression-free survival (PFS) times, it was 2.0-76.0 months, with a mean PFS of 31.0 months and a median PFS (mPFS) of 8.0 months (95% CI:4.333-11.667). The PFS of the 15 patients in stage III-IV was 2.0-17 months, while the mean PFS was 6.5 months and the mPFS was 6.0 months (95% CI:4.512-7.488). Out of the 20 patients identified in the SEER database, the average age was 69.9 years, with 14 males and 6 females. Of these patients, 8 were diagnosed with stage I-II, while the remaining 11 were diagnosed with stage III-IV. 10 underwent surgery, 4 received radiation therapy, and 9 received chemotherapy. The mean OS of the 20 patients was 67.5 months, mOS was 28.0 months (95% CI: 9.664- 46.336). For patients diagnosed with stage III-IV, the mean OS was 14.8 months and mOS was 20 months (95% CI: 4.713-35.287).

Conclusion

PEAC is rare, and the prognosis is determined mainly by the stage; patients who undergo surgery in stage I-II have a better prognosis.

Genomic and transcriptomic insights into the precision treatment of pulmonary enteric adenocarcinoma

BACKGROUND

Pulmonary enteric adenocarcinoma (PEAC) is a rare subtype of lung adenocarcinoma. More investigations about precision therapy in PEAC were required to improve the prognosis.

METHODS

Twenty-four patients with PEAC were enrolled in this study. Tumor tissue samples were available from 17 patients for both DNA and RNA based next-generation sequencing, PD-L1 IHC staining and PCR-based microsatellite instability (MSI) analysis.

RESULTS

TP53 (70.6%) and KRAS (47.1%) were the most frequently mutated genes in PEAC. For KRAS mutations, the prevalence of G12D (37.5%) and G12V (37.5%) was higher than G12A (12.5%) and G12C (12.5%). Actionable mutations in receptor tyrosine kinase (including one EGFR and two ALK mutations), PI3K/mTOR, RAS/RAF/MEK, homologous recombination repair (HRR) and cell cycle signaling pathways were identified in 94.1% of patients with PEAC. While PD-L1 expression was observed in 17.6% (3/17) patients, no MSI-H patients were identified. Transcriptomic data showed that two patients with positive PD-L1 expression had relatively high immune infiltration. In addition, prolonged survival was obtained with the treatment of osimertinib, ensartinib, and immunotherapy combined with chemotherapy in two EGFR-mutated, one ALK-rearranged, and one PD-L1 expressed patients, respectively.

CONCLUSION

PEAC is a disease of genetic heterogeneity. The administration of EGFR and ALK inhibitors was effective in patients with PEAC. PD-L1 expression and KRAS mutation type may be used as predictive biomarkers for immunotherapy in PEAC. This study provided both theoretical basis and clinical evidence for PEAC.

A pulmonary enteric adenocarcinoma patient harboring a rare EGFR exon 19 P753S mutation: Case report and review

Pulmonary enteric adenocarcinoma (PEAC) is a rare subtype of non–small cell lung cancer (NSCLC), accounting for about 0.6% of all primary lung adenocarcinoma. Although epidermal growth factor receptor (EGFR) mutation is common in primary lung adenocarcinoma, it is rarely reported in PEAC. This case report describes a PEAC patient with co-mutations of EGFR, Kirsten rat sarcoma viral oncogene (KRAS), and TP53, being treated with immunotherapy combined with chemotherapy. A 69-year-old man complained of cough and expectoration with bloody sputum for 2 weeks. The lung-enhanced CT scan showed a massive soft tissue shadow, about 46 × 35 mm in the lower lobe of the right lung. The neoplasm sample in the lower lobe of the right lung was obtained using CT-guided fine-needle aspiration (FNA). Immunohistochemical assays showed that the tumor was positive for CK7, CDX-2, C-MET, and villin. Gastroscopy and rectal colonoscopy had been performed respectively to exclude a diagnosis of colorectal adenocarcinoma. The patient was finally diagnosed with pulmonary intestinal adenocarcinoma. Next-generation sequencing (NGS) analysis showed a rare EGFR exon 19 missense mutation (c.2257C>T, p.P753S), KRAS exon 2 missense mutation (c.35G>T, p.G12V), and TP53 exon 5 missense mutation (c.401T>C, p.F134S). The lung-enhanced CT scan showed that the tumor shrank after four cycles of chemotherapy combined with immunotherapy. We hope that this case report can increase the understanding of this rare type of tumor and provide new molecular indications for diagnosis and individualized treatment. Furthermore, the combination of chemotherapy and immunotherapy seems to be an effective therapy for PEAC. Whether the use of immunotherapy can provide clinical benefits needs to be further explored with more samples in future studies.

Combination of Pembrolizumab With Platinum-containing Chemotherapy for Pulmonary Enteric Adenocarcinoma

BACKGROUND/AIM

Pulmonary enteric adeno-carcinoma (PEAC) is a rare type of non-small cell lung cancer (NSCLC), for which no established standard treatment exists. Combination therapy with the anti-programmed cell death protein 1 antibody pembrolizumab and platinum-containing chemotherapy is the standard treatment for NSCLC patients, but its effectiveness in PEAC is uncertain.

CASE REPORT

We present a 68-year-old man with chemotherapy-naïve advanced PEAC who responded to a combination of pembrolizumab and platinum-containing chemotherapy.

CONCLUSION

The number of PEAC cases is small, and no clinical trials have been conducted to determine an optimal chemotherapy regimen. In this case, we showed that pembrolizumab combined with platinum-containing chemotherapy might effectively treat PEAC.

Genetic mutation profiles and immune microenvironment analysis of pulmonary enteric adenocarcinoma

BACKGROUND

Pulmonary enteric adenocarcinoma (PEAC) has distinctive clinical outcomes, radiographic, pathological and molecular characteristics. The prognosis of patients with PEAC was poor. However, molecular profiles and therapeutic biomarkers of PEAC remain elusive.

METHODS

In the present study, the hospitalized patients with PEAC admitted to Tongji Hospital in Wuhan from January 1, 2014 to November 20, 2020 were retrospectively enrolled and followed until December 10, 2020. Comprehensive genomic profiling of tumor tissue from the PEAC patients were performed and compared with lung adenocarcinoma, colorectal cancer and metastatic colorectal carcinoma. Tumor immune microenvironment analysis were evaluated.

RESULTS

There were 10 patients with PEAC enrolled. 70% of patients were male and the median age of onset was 63 years (interquartile range, 55-72). There were six early-stage patients (Stage IA to IIB) and four stage IV patients. Molecular analysis revealed the most common gene mutations included TP53 (57%, 4/7) and KRAS (57%, 4/7) mutations. There were 40% mutations occurred in genes encoding receptor tyrosine kinases (RTKs). 100% of patients (8/8) were microsatellite stability (MSS). The median level of TMB was 6.0 (interquartile range, 4.5-7.0) mutations/Mb. Three of 10 patients showed low PD-L1 expression (tumor proportion score < 10%) and the others were PD-L1 negative. A small subset of CD8+, CD3+, CD68+ T cells were observed and were mainly distributed in the cancer stroma.

CONCLUSION

This study demonstrated that PEAC was characterized by low-frequency RTK gene mutation, high KRAS mutation, low PD-L1 expression, low TMB, and low CD8+ T cells infiltration.

An Integrated Epigenomic and Genomic View on Phyllodes and Phyllodes-like Breast Tumors

Fibroepithelial lesions (FL) of the breast, in particular, phyllodes tumors (PT) and fibroadenomas, pose a significant diagnostic challenge. There are no generally accepted criteria that distinguish benign, borderline, malignant PT and fibroadenomas. Combined genome-wide DNA methylation and copy number variant (CNV) profiling is an emerging strategy to classify tumors. We compiled a series of patient-derived archival biopsy specimens reflecting the FL spectrum and histological mimickers including clinical follow-up data. DNA methylation and CNVs were determined by well-established microarrays. Comparison of the patterns with a pan-cancer dataset assembled from public resources including "The Cancer Genome Atlas" (TCGA) and "Gene Expression Omnibus" (GEO) suggests that FLs form a methylation class distinct from both control breast tissue as well as common breast cancers. Complex CNVs were enriched in clinically aggressive FLs. Subsequent fluorescence in situ hybridization (FISH) analysis detected respective aberrations in the neoplastic mesenchymal component of FLs only, confirming that the epithelial component is non-neoplastic. Of note, our approach could lead to the elimination of the diagnostically problematic category of borderline PT and allow for optimized prognostic patient stratification. Furthermore, the identified recurrent genomic aberrations such as 1q gains (including MDM4), CDKN2a/b deletions, and EGFR amplifications may inform therapeutic decision-making.

Mucosal melanomas of different anatomic sites share a common global DNA methylation profile with cutaneous melanoma but show location-dependent patterns of genetic and epigenetic alterations

Cutaneous, ocular, and mucosal melanomas are histologically indistinguishable tumors that are driven by a different spectrum of genetic alterations. With current methods, identification of the site of origin of a melanoma metastasis is challenging. DNA methylation profiling has shown promise for the identification of the site of tumor origin in various settings. Here we explore the DNA methylation landscape of melanomas from different sites and analyze if different melanoma origins can be distinguished by their epigenetic profile. We performed DNA methylation analysis, next generation DNA panel sequencing, and copy number analysis of 82 non-cutaneous and 25 cutaneous melanoma samples. We further analyzed eight normal melanocyte cell culture preparations. DNA methylation analysis separated uveal melanomas from melanomas of other primary sites. Mucosal, conjunctival, and cutaneous melanomas shared a common global DNA methylation profile. Still, we observed location-dependent DNA methylation differences in cancer-related genes, such as low frequencies of RARB (7/63) and CDKN2A promoter methylation (6/63) in mucosal melanomas, or a high frequency of APC promoter methylation in conjunctival melanomas (6/9). Furthermore, all investigated melanomas of the paranasal sinus showed loss of PTEN expression (9/9), mainly caused by promoter methylation. This was less frequently seen in melanomas of other sites (24/98). Copy number analysis revealed recurrent amplifications in mucosal melanomas, including chromosomes 4q, 5p, 11q and 12q. Most melanomas of the oral cavity showed gains of chromosome 5p with TERT amplification (8/10), while 11q amplifications were enriched in melanomas of the nasal cavity (7/16). In summary, mucosal, conjunctival, and cutaneous melanomas show a surprisingly similar global DNA methylation profile and identification of the site of origin by DNA methylation testing is likely not feasible. Still, our study demonstrates tumor location-dependent differences of promoter methylation frequencies in specific cancer-related genes together with tumor site-specific enrichment for specific chromosomal changes and genetic mutations. © 2021 The Authors. The Journal of Pathology published by John Wiley & Sons, Ltd. on behalf of The Pathological Society of Great Britain and Ireland.

Machine Learning Models Predict the Primary Sites of Head and Neck Squamous Cell Carcinoma Metastases Based on DNA Methylation

In head and neck squamous cell cancers (HNSCs) that present as metastases with an unknown primary (HNSC-CUPs), the identification of a primary tumor improves therapy options and increases patient survival. However, the currently available diagnostic methods are laborious and do not offer a sufficient detection rate. Predictive machine learning models based on DNA methylation profiles have recently emerged as a promising technique for tumor classification. We applied this technique to HNSC to develop a tool that can improve the diagnostic workup for HNSC-CUPs. On a reference cohort of 405 primary HNSC samples, we developed four classifiers based on different machine learning models (random forest (RF), neural network (NN), elastic net penalized logistic regression (LOGREG), support vector machine (SVM)) that predict the primary site of HNSC tumors from their DNA methylation profile. The classifiers achieved high classification accuracies (RF=83%, NN=88%, LOGREG=SVM=89%) on an independent cohort of 64 HNSC metastases. Further, the NN, LOGREG, and SVM models significantly outperformed p16 status as a marker for an origin in the oropharynx. In conclusion, the DNA methylation profiles of HNSC metastases are characteristic for their primary sites and the classifiers developed in this study, which are made available to the scientific community, can provide valuable information to guide the diagnostic workup of HNSC-CUP. This article is protected by copyright. All rights reserved.

DNA Methylation-Based Classification of Small B-Cell Lymphomas: A Proof-of-Principle Study

Although most small B-cell lymphomas (SBCLs) can be diagnosed using routine methods, challenges exist. For example, marginal zone lymphomas (MZLs) can be difficult to rule-in, in large part because no widely-used, sensitive, and specific biomarker is available for the marginal zone cell of origin. In this study, it was hypothesized that DNA methylation array profiling can assist with the classification of SBCLs, including MZLs. Extramedullary SBCLs, including challenging cases, were reviewed internally for pathology consensus and profiled. By combining the resulting array data set with data sets from other groups, a set of 26 informative probes was selected and used to train machine learning models to classify 4 common SBCLs: chronic lymphocytic leukemia/small lymphocytic lymphoma, follicular lymphoma, mantle cell lymphoma, and MZL. Prediction probability cutoff was used to separate classifiable from unclassifiable cases, and show that the trained model was able to classify 95% of independent test cases (n = 264/279). The concordance between model predictions and pathology diagnoses was 99.6% (n = 262/263) among classifiable test cases. One validation reference test case was reclassified based on model prediction. The model was also used to predict the diagnoses of two challenging SBCLs. Although the differential examined and data on difficult cases are limited, these results support accurate methylation-based classification of SBCLs. Furthermore, high specificities of predictions suggest that methylation signatures can be used to rule-in MZLs.

Tumour Genome Characterization of a Rare Case of Pulmonary Enteric Adenocarcinoma and Prior Colon Adenocarcinoma

Pulmonary enteric adenocarcinoma (PEAC) is a rare variant of lung adenocarcinoma first described in the early 1990s in a lung tumour with overlapping lung and small intestine features. It is a rare tumour with fewer than 300 cases described in the published literature and was only formally classified in 2011. Given these characteristics the diagnosis is challenging, but even more so in a patient with prior gastrointestinal malignancy. A 68-year-old Caucasian female presented with a cough and was found to have a right upper lobe mass. Her history was significant for a pT3N1 colon adenocarcinoma. The resected lung tumour showed invasive lung adenocarcinoma but also features of colorectal origin. Immuno-stains were strongly and diffusely positive for lung and enteric markers. Multi-region, whole-exome sequencing of the mass and archival tissue from the prior colorectal cancer showed distinct genomic signatures with higher mutational burden in the PEAC and very minimal overlap in mutations between the two tumours. This case highlights the challenge of diagnosing rare lung tumours, but more specifically PEAC in a patient with prior gastro-intestinal cancer. Our use of multi-region, next-generation sequencing revealed distinct genomic signatures between the two tumours further supporting our diagnosis, and evidence of PEAC intra-tumour heterogeneity.

Pulmonary enteric adenocarcinoma

•

Synthetically expounded the clinical characteristics of PEAC.

•

Systematically described the differentiation of PEAC from primary lung adenocarcinoma and MCRC.

•

Found patients with PEAC may have high frequencies of HER2 and MMR mutations.

•

Proposed a new conjecture that patients with PEAC might benefit from anti-HER2 therapy and immune checkpoint inhibitors.

Pulmonary enteric adenocarcinoma (PEAC) is an exceptionally rare subtype of non–small cell lung cancer (NSCLC). It is characterized by pathological features similar to those of colorectal adenocarcinoma. Most patients with PEAC have almost no special clinical manifestations, and it is often difficult to differentiate from metastatic colorectal adenocarcinoma (MCRC). As a special type of lung adenocarcinoma, PEAC has unique mutation expression and immune characteristics; its mutation profile shows higher Kirsten rat sarcoma viral oncogene (KRAS), human epidermal growth factor receptor-2 (HER2) , DNA mismatch repair(MMR) mutation rates, and much lower epidermal growth factor receptor (EGFR) rate. So in the future, targeted therapy may tend to be a new light in the treatment of PEAC. As for immunohistochemistry (IHC), CDX-2, villin, and CK7 are significantly positive in PEAC. This review focuses on the pathologic features, immunohistochemical examination, mutation analysis, diagnosis, treatment, and prognosis of PEAC.

Artificial intelligence and pathology: From principles to practice and future applications in histomorphology and molecular profiling

The complexity of diagnostic (surgical) pathology has increased substantially over the last decades with respect to histomorphological and molecular profiling. Pathology has steadily expanded its role in tumor diagnostics and beyond from disease entity identification via prognosis estimation to precision therapy prediction. It is therefore not surprising that pathology is among the disciplines in medicine with high expectations in the application of artificial intelligence (AI) or machine learning approaches given their capabilities to analyze complex data in a quantitative and standardized manner to further enhance scope and precision of diagnostics. While an obvious application is the analysis of histological images, recent applications for the analysis of molecular profiling data from different sources and clinical data support the notion that AI will enhance both histopathology and molecular pathology in the future. At the same time, current literature should not be misunderstood in a way that pathologists will likely be replaced by AI applications in the foreseeable future. Although AI will transform pathology in the coming years, recent studies reporting AI algorithms to diagnose cancer or predict certain molecular properties deal with relatively simple diagnostic problems that fall short of the diagnostic complexity pathologists face in clinical routine. Here, we review the pertinent literature of AI methods and their applications to pathology, and put the current achievements and what can be expected in the future in the context of the requirements for research and routine diagnostics.

DNA methylation subtypes for ovarian cancer prognosis

Ovarian cancer is one of three major malignancies of the female reproductive system. DNA methylation (MET) is closely related to ovarian cancer occurrence and development, and as such, elucidation of effective MET subtype markers may guide individualized treatment and improve ovarian cancer prognosis. To identify potential markers, we downloaded a total of 571 ovarian cancer MET samples from The Cancer Genome Atlas (TCGA), and established a Cox proportional hazards model using the MET spectrum and clinical pathological parameters. A total of 250 prognosis-related MET loci were obtained by Cox regression, and six molecular subtypes were screened by consensus clustering of CpG loci with a significant difference in both univariate and multivariate analyses. There was a remarkable MET difference between most subtypes. Cluster 2 had the highest MET level and demonstrated the best prognosis, while Clusters 4 and 5 had MET levels significantly lower than those of the other subtypes and demonstrated very poor prognosis. All Cluster 5 samples were at a high grade, while the percentage of stage IV samples in Cluster 4 was greater than in the other subtypes. We obtained five CpG loci using a coexpression network: cg27625732, cg00431050, cg22197830, cg03152385, and cg22809047. Our cluster analysis showed that prognosis in patients with hypomethylation was significantly worse than in patients with hypermethylation. These MET molecular subtypes can be used not only to evaluate ovarian cancer prognosis, but also to fully distinguish the tumor stage and histological grade in patients with ovarian cancer.

Pulmonary enteric adenocarcinoma: a literature review

Pulmonary enteric adenocarcinoma (PEAC) is an extremely rare type of non-small cell lung cancer (NSCLC) with a histologic pattern that mimics metastatic colorectal cancer (MCC). The main clinical symptoms in PEAC patients are dyspnoea, coughing, hemoptysis, and chest and back pain. The first article about PEAC appeared in 1991 in the form of a case report. As a variant of invasive lung carcinoma, only a small number of case reports and clinical research studies have been carried out, and the only one guidance on diagnosis and treatment is the WHO Tumor Classification book. It is important for doctors to distinguish PEAC from MCC to extend survival time and improve the quality of life. We reviewed the existing literature regarding the diagnosis, treatment, and prognosis of PEAC to provide some valuable clinical references.

Pulmonary enteric adenocarcinoma: an overview

Most commonly described as sporadic, pulmonary adenocarcinoma with enteric differentiation (PAED) is a rare variant of invasive lung cancer recently established and recognised by the World Health Organization. This tumour is highly heterogeneous and shares several morphological features with pulmonary and colorectal adenocarcinomas. Our objective is to summarise current research on PAED, focusing on its immunohistochemical and molecular features as potential tools for differential diagnosis from colorectal cancer, as well as prognosis definition and therapeutic choice. PAED exhibits an 'entero-like' pathological morphology in more than half cases, expressing at least one of the typical immunohistochemical markers of enteric differentiation, namely CDX2, CK20 or MUC2. For this reason, this malignancy appears often indistinguishable from a colorectal cancer metastasis, making the differential diagnosis laborious. Although standard diagnostic criteria have not been established yet, in the past few years, a number of approaches have been addressed, aimed at defining specific immunohistochemical and molecular signatures. Based on previously published literature, we have collected and analysed molecular and immunohistochemical data on this rare neoplasm, and have described the state of the art on diagnostic criteria as well as major clinical and therapeutic implications.The analysis of data from 295 patients from 58 published articles allowed us to identify the most represented immunohistochemical and molecular markers, as well as major differences between Asian PAEDs and those diagnosed in European/North American countries. The innovative molecular approaches, exploring driver mutations or new gene alterations, could help to identify rare prognostic factors and guide future tailored therapeutic approaches to this rare neoplasm.

Machine learning analysis of exome trios to contrast the genomic architecture of autism and schizophrenia

BACKGROUND

Machine learning (ML) algorithms and methods offer great tools to analyze large complex genomic datasets. Our goal was to compare the genomic architecture of schizophrenia (SCZ) and autism spectrum disorder (ASD) using ML.

METHODS

In this paper, we used regularized gradient boosted machines to analyze whole-exome sequencing (WES) data from individuals SCZ and ASD in order to identify important distinguishing genetic features. We further demonstrated a method of gene clustering to highlight which subsets of genes identified by the ML algorithm are mutated concurrently in affected individuals and are central to each disease (i.e., ASD vs. SCZ "hub" genes).

RESULTS

In summary, after correcting for population structure, we found that SCZ and ASD cases could be successfully separated based on genetic information, with 86-88% accuracy on the testing dataset. Through bioinformatic analysis, we explored if combinations of genes concurrently mutated in patients with the same condition ("hub" genes) belong to specific pathways. Several themes were found to be associated with ASD, including calcium ion transmembrane transport, immune system/inflammation, synapse organization, and retinoid metabolic process. Moreover, ion transmembrane transport, neurotransmitter transport, and microtubule/cytoskeleton processes were highlighted for SCZ.

CONCLUSIONS

Our manuscript introduces a novel comparative approach for studying the genetic architecture of genetically related diseases with complex inheritance and highlights genetic similarities and differences between ASD and SCZ.

Invited Review: DNA methylation-based classification of paediatric brain tumours

DNA methylation-based machine learning algorithms represent powerful diagnostic tools that are currently emerging for several fields of tumour classification. For various reasons, paediatric brain tumours have been the main driving forces behind this rapid development and brain tumour classification tools are likely further advanced than in any other field of cancer diagnostics. In this review, we will discuss the main characteristics that were important for this rapid advance, namely the high clinical need for improvement of paediatric brain tumour diagnostics, the robustness of methylated DNA and the consequential possibility to generate high-quality molecular data from archival formalin-fixed paraffin-embedded pathology specimens, the implementation of a single array platform by most laboratories allowing data exchange and data pooling to an unprecedented extent, as well as the high suitability of the data format for machine learning. We will further discuss the four most central output qualities of DNA methylation profiling in a diagnostic setting (tumour classification, tumour sub-classification, copy number analysis and guidance for additional molecular testing) individually for the most frequent types of paediatric brain tumours. Lastly, we will discuss DNA methylation profiling as a tool for the detection of new paediatric brain tumour classes and will give an overview of the rapidly growing family of new tumours identified with the aid of this technique.

Cutaneous metastasis as a primary presentation of a pulmonary enteric adenocarcinoma

BACKGROUND

Primary pulmonary enteric adenocarcinoma (PEAC) is a rare non-small cell lung cancer subtype sharing morphologic and immunohistochemical features with colorectal adenocarcinoma. Given the frequency of lung metastases in colorectal cancer, the differential diagnosis of PEAC according to routine morphological and immunohistochemical findings may be difficult. Genome sequence by next-generation sequencing has recently introduced new perspectives to better define the diagnosis and tumor sensitivity to treatments, while the rarity of this subtype of cancer still limits the current knowledge of its molecular features and provides no information to address patients to tailored therapies.

METHODS

We diagnosed a rare case of subcutaneous metastasis as a first symptom of a PEAC. Formalin-fixed paraffin-embedded samples of the primary tumor and subcutaneous metastases were examined by immunohistochemistry, and subsequently by targeted next-generation sequencing analysis.

RESULTS

Morphological and immunohistochemical findings suggested a rare case of metastatic pulmonary adenocarcinoma with enteric aspects. Next-generation sequencing analysis performed on both the primary tumor sample and the cutaneous lesion identified two pathogenic variants on CDKN2A and KRAS in both of them. However, the metastasis showed two additional pathogenic mutations located in SMAD4 and FLT3 genes.

CONCLUSIONS

We describe for the first time an extensive molecular analysis on a rare case of PEAC with an unusual cutaneous metastasis. Our observation suggests that a specific pattern of mutations is harbored in this neoplasm, and that additional molecular studies may provide further information to identify prognostic and hopefully predictive genes of response to treatment.

Videira P, Valadão G. Artificial Intelligence (AI) in Rare Diseases: Is the Future Brighter?

The amount of data collected and managed in (bio)medicine is ever-increasing. Thus, there is a need to rapidly and efficiently collect, analyze, and characterize all this information. Artificial intelligence (AI), with an emphasis on deep learning, holds great promise in this area and is already being successfully applied to basic research, diagnosis, drug discovery, and clinical trials. Rare diseases (RDs), which are severely underrepresented in basic and clinical research, can particularly benefit from AI technologies. Of the more than 7000 RDs described worldwide, only 5% have a treatment. The ability of AI technologies to integrate and analyze data from different sources (e.g., multi-omics, patient registries, and so on) can be used to overcome RDs’ challenges (e.g., low diagnostic rates, reduced number of patients, geographical dispersion, and so on). Ultimately, RDs’ AI-mediated knowledge could significantly boost therapy development. Presently, there are AI approaches being used in RDs and this review aims to collect and summarize these advances. A section dedicated to congenital disorders of glycosylation (CDG), a particular group of orphan RDs that can serve as a potential study model for other common diseases and RDs, has also been included.

Next generation sequencing of lung adenocarcinoma subtypes with intestinal differentiation reveals distinct molecular signatures associated with histomorphology and therapeutic options

OBJECTIVES

We aim to provide a better understanding of the molecular landscape of primary lung adenocarcinomas with intestinal differentiation.

MATERIAL AND METHODS

Five invasive mucinous adenocarcinomas (IMA) and seven pulmonary enteric adenocarcinomas (PEAD) were included in this study. Furthermore, we analyzed six pulmonary colloid adenocarcinomas (CAD), including one primary tumor, one metastasis, and two sample pairs consisting of the primary colloid lung tumor and a matching metastasis and an acinar component, respectively. All samples were characterized using immunohistochemistry (TTF-1, CK7, CK20, CDX2, Ki-67, ALK and PD-L1) and a next generation sequencing panel covering 404 cancer-related genes (FoundationOne® gene panel).

RESULTS AND CONCLUSION

While Ki-67 expression was comparably low in IMA (range: 8-15%) and in primary CAD (range: 5-8%), we observed considerably higher proliferation rates in the non-colloid tumor compartment (16%) and metastases (72%) from CAD, as well as in the PEAD-group (36-71%). The overall tumor mutational burden was lowest in IMA (2.5 mutations per megabase), intermediate in CAD (5.8 mutations per megabase) and highest in PEAD (16.8 mutations per megabase). KRAS mutations were frequent in all three tumor subtypes, but TP53 mutations were mostly limited to PEAD. While chromosomal alterations were rare in IMA, we discovered MYC amplifications in three of four CAD. Comparing primary and metastatic CAD, we observed the acquisition of multiple mutations and chromosomal alterations. PEAD had a variety of chromosomal alterations, including two cases with RICTOR amplification. PD-L1 expression (20%, 50% and 80% of tumor cells) was limited to three PEAD samples, only. In conclusion, we provide a detailed insight into the molecular alterations across and within the different subtypes of pulmonary adenocarcinomas with intestinal differentiation. From a clinical perspective, we provide data on potential treatment strategies for patients with PEAD, including immunotherapy.