Grading of lung adenocarcinomas with simultaneous segmentation by artificial intelligence (GLASS-AI)

Preclinical genetically engineered mouse models (GEMMs) of lung adenocarcinoma are invaluable for investigating molecular drivers of tumor formation, progression, and therapeutic resistance. However, histological analysis of these GEMMs requires significant time and training to ensure accuracy and consistency. To achieve a more objective and standardized analysis, we used machine learning to create GLASS-AI, a histological image analysis tool that the broader cancer research community can utilize to grade, segment, and analyze tumors in preclinical models of lung adenocarcinoma. GLASS-AI demonstrates strong agreement with expert human raters while uncovering a significant degree of unreported intratumor heterogeneity. Integrating immunohistochemical staining with high-resolution grade analysis by GLASS-AI identified dysregulation of Mapk/Erk signaling in high-grade lung adenocarcinomas and locally advanced tumor regions. Our work demonstrates the benefit of employing GLASS-AI in preclinical lung adenocarcinoma models and the power of integrating machine learning and molecular biology techniques for studying the molecular pathways that underlie cancer progression.

Comprehensive Metabolic Tracing Reveals the Origin and Catabolism of Cysteine in Mammalian Tissues and Tumors

Cysteine plays critical roles in cellular biosynthesis, enzyme catalysis, and redox metabolism. The intracellular cysteine pool can be sustained by cystine uptake or de novo synthesis from serine and homocysteine. Demand for cysteine is increased during tumorigenesis for generating glutathione to deal with oxidative stress. While cultured cells have been shown to be highly dependent on exogenous cystine for proliferation and survival, how diverse tissues obtain and use cysteine in vivo has not been characterized. We comprehensively interrogated cysteine metabolism in normal murine tissues and cancers that arise from them using stable isotope 13C1-serine and 13C6-cystine tracing. De novo cysteine synthesis was highest in normal liver and pancreas and absent in lung tissue, while cysteine synthesis was either inactive or downregulated during tumorigenesis. In contrast, cystine uptake and metabolism to downstream metabolites was a universal feature of normal tissues and tumors. However, differences in glutathione labeling from cysteine were evident across tumor types. Thus, cystine is a major contributor to the cysteine pool in tumors, and glutathione metabolism is differentially active across tumor types.

SIGNIFICANCE

Stable isotope 13C1-serine and 13C6-cystine tracing characterizes cysteine metabolism in normal murine tissues and its rewiring in tumors using genetically engineered mouse models of liver, pancreas, and lung cancers.

Transcriptome annotation reveals minimal immunogenetic diversity among Wyoming toads, Anaxyrus baxteri

Briefly considered extinct in the wild, the future of the Wyoming toad (Anaxyrus baxteri) continues to rely on captive breeding to supplement the wild population. Given its small natural geographic range and history of rapid population decline at least partly due to fungal disease, investigation of the diversity of key receptor families involved in the host immune response represents an important conservation need. Population decline may have reduced immunogenetic diversity sufficiently to increase the vulnerability of the species to infectious diseases. Here we use comparative transcriptomics to examine the diversity of toll-like receptors and major histocompatibility complex (MHC) sequences across three individual Wyoming toads. We find reduced diversity at MHC genes compared to bufonid species with a similar history of bottleneck events. Our data provide a foundation for future studies that seek to evaluate the genetic diversity of Wyoming toads, identify biomarkers for infectious disease outcomes, and guide breeding strategies to increase genomic variability and wild release successes.

Mutant p53s and chromosome 19 microRNA cluster overexpression regulate cancer testis antigen expression and cellular transformation in hepatocellular carcinoma

A subset of hepatocellular carcinoma (HCC) overexpresses the chromosome 19 miRNA cluster (C19MC) and is associated with an undifferentiated phenotype marked by overexpression of cancer testis antigens (CTAs) including anti-apoptotic melanoma-A antigens (MAGEAs). However, the regulation of C19MC miRNA and MAGEA expression in HCCs are not understood. Here we show that, C19MC overexpression is tightly linked to a sub-set of HCCs with transcription-incompetent p53. Using next-generation and Sanger sequencing we found that, p53 in Hep3B cells is impaired by TP53-FXR2 fusion, and that overexpression of the C19MC miRNA-520G in Hep3B cells promotes the expression of MAGEA-3, 6 and 12 mRNAs. Furthermore, overexpression of p53-R175H and p53-R273H mutants promote miR-520G and MAGEA RNA expression and cellular transformation. Moreover, IFN-γ co-operates with miR-520G to promote MAGEA expression. On the other hand, metals such as nickel and zinc promote miR-526B but not miR-520G, to result in the suppression of MAGEA mRNA expression, and evoke cell death through mitochondrial membrane depolarization. Therefore our study demonstrates that a MAGEA-promoting network involving miR-520G, p53-defects and IFN-γ that govern cellular transformation and cell survival pathways, but MAGEA expression and survival are counteracted by nickel and zinc combination.

Abstract PO-082: Automated tumor segmentation, grading, and analysis of tumor heterogeneity in preclinical models of lung adenocarcinoma

Preclinical mouse models of lung adenocarcinoma are invaluable for the discovery of molecular drivers of tumor formation, progression, and therapeutic resistance. Histological analyses of these preclinical models require significant investments of time and training to ensure accuracy and consistency. Analysis by a clinical pathologist is the gold standard in this approach, but may be difficult to obtain due to the cost and availability of their services. As an alternative we have developed a digital pathology tool to identify, segment, grade, and analyze tumors in mouse models of lung adenocarcinoma. This convolutional neural network (CNN) model, based on ResNet18, was trained to classify normal lung tissue, normal airways, and the different grades (1 – 4) of lung adenocarcinoma from 100,000 224 × 224 pixel image patches (~16,000 patches per class). Our training dataset was constructed from whole slide images of hematoxylin and eosin stained lung sections from 4 different mouse models of lung adenocarcinoma with oncogenic Kras (KrasG12D/+), in combination with oncogenic p53 mutations (KrasG12D/+; p53R172H/+ and KrasG12D/+;p53R270H/+), or with the loss of the tumor suppressive TAp73 (KrasG12D/+;TAp7fltd/fltd). Our CNN demonstrated a strong correspondence with human pathologists on our holdout dataset, achieving a micro-F1 score of 0.81 on a pixel-by-pixel basis. As a test of our CNN, we analyzed two mouse models to better understand the role of TAp73 in lung adenocarcinoma: KrasG12D/+ (“K”) and KrasG12D/+;TAp73fltd/fltd (“TK”). Both human raters and our CNN reported a significant increase in the tumor burden of the compound mutant “TK” mice compared to the single mutant “K” mice. According to our CNN, this increased tumor burden was driven primarily by an increase in tumor size and not an increased number of tumors in “TK” mice. Because our CNN can assign different grades to regions within the same image patch and tumor, we also uncovered a high degree of intratumor heterogeneity that was not reported by the human pathologists, who are trained to assign one grade to a single tumor with a bias for the highest grade present in a given tumor. The finer grading resolution allowed our CNN to uncover the increased tumor size observed in the “TK” mice was due to expansion of Grade 2 regions (characterized by enlarged nuclei without irregular shape) within tumors that would be considered a higher grade by pathologists. Our CNN also provides a detailed map of tumor grades overlaid on the H&E images used for analysis, allowing for precise targeting of regions within tumors with other assays. We are currently utilizing these outputs in conjunction with other assays, such as spatial transcriptomic analysis and immunohistochemistry, to investigate the molecular mechanisms that underlie the expansion of Grade 2 tumor regions in “TK” mice. Future work will expand this tool into a multidimensional digital pathology pipeline that can accelerate current investigations and reveal new therapeutic targets and prognostic markers.

Citation Format: John H. Lockhart, Hayley D. Ackerman, Kyubum Lee, Mahmoud Abdalah, Andrew Davis, Nicole Montey, Theresa Boyle, James Saller, Ayensur Keske, Kay Hänggi, Brian Ruffell, Olya Stringfield, Aik Choon Tan, Elsa R. Flores. Automated tumor segmentation, grading, and analysis of tumor heterogeneity in preclinical models of lung adenocarcinoma [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-082.

Abstract PO-023: Spatial genomics coupled with machine learning to identify p53-driven molecular signatures that are predictive of lung adenocarcinoma progression

P53 is frequently mutated in a wide variety of tumors; yet, the regulation and expression of downstream targets during tumor progression and response to therapy is unknown. Here, we use Kras/p53-driven lung adenocarcinoma in the mouse as a model system to identify p53-driven molecular signatures that predict lung adenocarcinoma progression. Using these tumors, we have developed a digital pathology tool using machine learning to grade lung adenocarcinomas. To do this, we analyzed hematoxylin and eosin (H&E) from mouse models of lung adenocarcinoma with Kras (KrasG12D/+) and in combination with p53 mutations (KrasG12D/+; p53R172H/+ and KrasG12D/+; p53R270H/+) and loss of TAp73 (KrasG12D/+; TAp73Δtd/Δtd). After grading, slides were divided into approximately 100,000 patches with dimensions of 224 × 224 pixels (113 × 113 µm). A convolutional neural network (CNN) model based on ResNet18 was trained to classify normal lung tissue, normal airways, and the different grades (1–4) of lung adenocarcinoma using 16,000 patches of each class. The resulting classification maps were used for analyses of tumor burden and progression. Adjacent tissue sections used for immunohistochemistry were co-registered to mapped H&E sections to investigate correlation between protein expression and tumor grade. Our CNN demonstrated a strong correspondence with human pathologists on our holdout dataset (81% agreement). Because our CNN can assign different grades to different regions within an image patch, we also uncovered a high degree of intratumor heterogeneity that was missed by human pathologists who assigned grades to entire tumors in a homogeneous manner. Both the pathologists and the CNN reported a significant increase in the tumor burden of compound mutant mice (KrasG12D/+; p53R172H/+, KrasG12D/+; p53R270H/+, and KrasG12D/+; TAp73Δtd/Δtd) compared to KrasG12D/+ mice. In addition, compound mutant mice were noted to have a greater proportion of high-grade (3-4) tumors by both approaches. In conclusion, our CNN demonstrates a high degree of agreement with human pathologists. Furthermore, this computational approach drastically increases the resolution of tumor grading in our mouse models and can detect regions of different grades within a single tumor. We are currently using single cell transcriptome analysis to define p53-molecular signatures that predict lung adenocarcinoma progression and grade. Future work will expand this tool into a multidimensional digital pathology pipeline that can accelerate current investigations and reveal new therapeutic targets and prognostic markers.

Citation Format: John H. Lockhart, Kyubum Lee, Hayley D. Ackerman, Mahmoud Abdulah, Andrew Davis, Nicole Montey, Theresa Boyle, James Saller, Aysenur Keske, Kay Hanggi, Olya Stringfield, Aik Choon Tan, Elsa R. Flores. Spatial genomics coupled with machine learning to identify p53-driven molecular signatures that are predictive of lung adenocarcinoma progression [abstract]. In: Proceedings of the AACR Virtual Special Conference on Tumor Heterogeneity: From Single Cells to Clinical Impact; 2020 Sep 17-18. Philadelphia (PA): AACR; Cancer Res 2020;80(21 Suppl):Abstract nr PO-023.

Pan-cancer analysis reveals TAp63-regulated oncogenic lncRNAs that promote cancer progression through AKT activation

The most frequent genetic alterations across multiple human cancers are mutations in TP53 and the activation of the PI3K/AKT pathway, two events crucial for cancer progression. Mutations in TP53 lead to the inhibition of the tumour and metastasis suppressor TAp63, a p53 family member. By performing a mouse-human cross species analysis between the TAp63 metastatic mammary adenocarcinoma mouse model and models of human breast cancer progression, we identified two TAp63-regulated oncogenic lncRNAs, TROLL-2 and TROLL-3. Further, using a pan-cancer analysis of human cancers and multiple mouse models of tumour progression, we revealed that these two lncRNAs induce the activation of AKT to promote cancer progression by regulating the nuclear to cytoplasmic translocation of their effector, WDR26, via the shuttling protein NOLC1. Our data provide preclinical rationale for the implementation of these lncRNAs and WDR26 as therapeutic targets for the treatment of human tumours dependent upon mutant TP53 and/or the PI3K/AKT pathway.

Bile Acids in Neurodegenerative Disorders

Bile acids, a structurally related group of molecules derived from cholesterol, have a long history as therapeutic agents in medicine, from treatment for primarily ocular diseases in ancient Chinese medicine to modern day use as approved drugs for certain liver diseases. Despite evidence supporting a neuroprotective role in a diverse spectrum of age-related neurodegenerative disorders, including several small pilot clinical trials, little is known about their molecular mechanisms or their physiological roles in the nervous system. We review the data reported for their use as treatments for neurodegenerative diseases and their underlying molecular basis. While data from cellular and animal models and clinical trials support potential efficacy to treat a variety of neurodegenerative disorders, the relevant bile acids, their origin, and the precise molecular mechanism(s) by which they confer neuroprotection are not known delaying translation to the clinical setting.