Purpose: Human papillomavirus (HPV) in oropharyngeal squamous cell carcinoma (OPSCC) is tumorigenic and has been associated with a favorable prognosis compared with OPSCC caused by tobacco, alcohol, and other carcinogens. Meanwhile, machine learning has evolved as a powerful tool to predict molecular and cellular alterations of medical images of various sources. Experimental Design: We generated a deep learning–based HPV prediction score (HPV-ps) on regular hematoxylin and eosin (H&E) stains and assessed its performance to predict HPV association using 273 patients from two different sites (OPSCC; Giessen, n = 163; Cologne, n = 110). Then, the prognostic relevance in a total of 594 patients (Giessen, Cologne, HNSCC TCGA) was evaluated. In addition, we investigated whether four board-certified pathologists could identify HPV association (n = 152) and compared the results to the classifier. Results: Although pathologists were able to diagnose HPV association from H&E-stained slides (AUC = 0.74, median of four observers), the interrater reliability was minimal (Light Kappa = 0.37; P = 0.129), as compared with AUC = 0.8 using the HPV-ps within two independent cohorts (n = 273). The HPV-ps identified individuals with a favorable prognosis in a total of 594 patients from three cohorts (Giessen, OPSCC, HR = 0.55, P < 0.0001; Cologne, OPSCC, HR = 0.44, P = 0.0027; TCGA, non-OPSCC head and neck, HR = 0.69, P = 0.0073). Interestingly, the HPV-ps further stratified patients when combined with p16 status (Giessen, HR = 0.06, P < 0.0001; Cologne, HR = 0.3, P = 0.046). Conclusions: Detection of HPV association in OPSCC using deep learning with help of regular H&E stains may either be used as a single biomarker, or in combination with p16 status, to identify patients with OPSCC with a favorable prognosis, potentially outperforming combined HPV-DNA/p16 status as a biomarker for patient stratification.

Background: Helicobacter pylori, a 2 × 1 μm spiral-shaped bacterium, is the most common risk factor for gastric cancer worldwide. Clinically, patients presenting with symptoms of gastritis, routinely undergo gastric biopsies. The following histo-morphological evaluation dictates therapeutic decisions, where antibiotics are used for H. pylori eradication. There is a strong rational to accelerate the detection process of H. pylori on histological specimens, using novel technologies, such as deep learning. Methods: We designed a deep-learning-based decision support algorithm that can be applied on regular whole slide images of gastric biopsies. In detail, we can detect H. pylori both on Giemsa- and regular H&E stained whole slide images. Results: With the help of our decision support algorithm, we show an increased sensitivity in a subset of 87 cases that underwent additional PCR- and immunohistochemical testing to define a sensitive ground truth of HP presence. For Giemsa stained sections, the decision support algorithm achieved a sensitivity of 100% compared to 68.4% (microscopic diagnosis), with a tolerable specificity of 66.2% for the decision support algorithm compared to 92.6 (microscopic diagnosis). Conclusion: Together, we provide the first evidence of a decision support algorithm proving as a sensitive screening option for H. pylori that can potentially aid pathologists to accurately diagnose H. pylori presence on gastric biopsies.

Macrophage polarization is a process whereby macrophages acquire distinct effector states (M1 or M2) to carry out multiple and sometimes opposite functions. We show here that translational reprogramming occurs during macrophage polarization and that this relies on the Elongator complex subunit Elp3, an enzyme that modifies the wobble uridine base U34 in cytosolic tRNAs. Elp3 expression is downregulated by classical M1‐activating signals in myeloid cells, where it limits the production of pro‐inflammatory cytokines via FoxO1 phosphorylation, and attenuates experimental colitis in mice. In contrast, alternative M2‐activating signals upregulate Elp3 expression through a PI3K‐ and STAT6‐dependent signaling pathway. The metabolic reprogramming linked to M2 macrophage polarization relies on Elp3 and the translation of multiple candidates, including the mitochondrial ribosome large subunit proteins Mrpl3, Mrpl13, and Mrpl47. By promoting translation of its activator Ric8b in a codon‐dependent manner, Elp3 also regulates mTORC2 activation. Elp3 expression in myeloid cells further promotes Wnt‐driven tumor initiation in the intestine by maintaining a pool of tumor‐associated macrophages exhibiting M2 features. Collectively, our data establish a functional link between tRNA modifications, mTORC2 activation, and macrophage polarization.

Non-small cell lung cancer (NSCLC) is the most common cause of cancer-related deaths worldwide and is primarily treated with radiation, surgery, and platinum-based drugs like cisplatin and carboplatin. The major challenge in the treatment of NSCLC patients is intrinsic or acquired resistance to chemotherapy. Molecular markers predicting the outcome of the patients are urgently needed. Here, we employed patient-derived xenografts (PDXs) to detect predictive methylation biomarkers for platin-based therapies. We used MeDIP-Seq to generate genome-wide DNA methylation profiles of 22 PDXs, their parental primary NSCLC, and their corresponding normal tissues and complemented the data with gene expression analyses of the same tissues. Candidate biomarkers were validated with quantitative methylation-specific PCRs (qMSP) in an independent cohort. Comprehensive analyses revealed that differential methylation patterns are highly similar, enriched in PDXs and lung tumor-specific when comparing differences in methylation between PDXs versus primary NSCLC. We identified a set of 40 candidate regions with methylation correlated to carboplatin response and corresponding inverse gene expression pattern even before therapy. This analysis led to the identification of a promoter CpG island methylation of LDL receptor-related protein 12 (LRP12) associated with increased resistance to carboplatin. Validation in an independent patient cohort (n = 35) confirmed that LRP12 methylation status is predictive for therapeutic response of NSCLC patients to platin therapy with a sensitivity of 80% and a specificity of 84% (p < 0.01). Similarly, we find a shorter survival time for patients with LRP12 hypermethylation in the TCGA data set for NSCLC (lung adenocarcinoma). Using an epigenome-wide sequencing approach, we find differential methylation patterns from primary lung cancer and PDX-derived cancers to be very similar, albeit with a lower degree of differential methylation in primary tumors. We identify LRP12 DNA methylation as a powerful predictive marker for carboplatin resistance. These findings outline a platform for the identification of epigenetic therapy resistance biomarkers based on PDX NSCLC models.

Patients with metastasized malignant melanomas (MM) are regularly treated with immune checkpoint inhibitors (CPI). Within our study, we evaluated the predictive value of tumor infiltrating lymphocyte (TIL) clusters in primary MM and its association to molecular subtypes to predict response to CPI treatment. A cohort of 90 MM patients who received CPI treatment were collected from a single center, as well as a validation cohort of 351 patients from the TCGA database (SKCM) who received standard of care. A deep-convolutional-neural network (U-Net) was trained to detect viable tumor areas on H&E whole-slide-images, following a quantitative detection of TILs with help of a separate additional neural network. The number of TIL clusters was associated with response to CPI in 90 MM patients (AUC = 0.6), even more pronounced within the sub-cohort of BRAF V600^E/K-mutated MM patients (AUC = 0.7, n = 32). Interestingly, the TIL clusters in NRAS-mutated as well as wildtype MM (BRAF-wt, NRAS-wt) tumors, did not demonstrate a predictive value of CPI response (AUC = 0.5, n = 25). Moreover, PD-L1 expression had a limited predictive value within our cohort. In parallel, within an independent cohort of MM patients (TCGA, n = 351), the number of TIL clusters was associated with improved survival in BRAF V600^E/K mutated MM (p < 0.0001, n = 164) but neither in NRAS-mutated (55.7 months vs. 63.0 months, respectively, p = 0.590, n = 85) nor BRAF/NRAS-wildtype MM patients (52.4 months vs. 47.4 months, respectively, p = 0.581, n = 104). While TILs in MM have been associated with improved survival, we show—for the first time—that TIL clusters are associated with response to immunotherapy in BRAF V600^E/K mutated MM.

Pathologic examination of prostate biopsies is time consuming due to the large number of slides per case. In this retrospective study, we validate a deep learning-based classifier for prostate cancer (PCA) detection and Gleason grading (AI tool) in biopsy samples. Five external cohorts of patients with multifocal prostate biopsy were analyzed from high-volume pathology institutes. A total of 5922 H&E sections representing 7473 biopsy cores from 423 patient cases (digitized using three scanners) were assessed concerning tumor detection. Two tumor-bearing datasets (core n = 227 and 159) were graded by an international group of pathologists including expert urologic pathologists (n = 11) to validate the Gleason grading classifier. The sensitivity, specificity, and NPV for the detection of tumor-bearing biopsies was in a range of 0.971–1.000, 0.875–0.976, and 0.988–1.000, respectively, across the different test cohorts. In several biopsy slides tumor tissue was correctly detected by the AI tool that was initially missed by pathologists. Most false positive misclassifications represented lesions suspicious for carcinoma or cancer mimickers. The quadratically weighted kappa levels for Gleason grading agreement for single pathologists was 0.62–0.80 (0.77 for AI tool) and 0.64–0.76 (0.72 for AI tool) for the two grading datasets, respectively. In cases where consensus for grading was reached among pathologists, kappa levels for AI tool were 0.903 and 0.855. The PCA detection classifier showed high accuracy for PCA detection in biopsy cases during external validation, independent of the institute and scanner used. High levels of agreement for Gleason grading were indistinguishable between experienced genitourinary pathologists and the AI tool.