Predicting EGFR mutational status from pathology images using a real-world dataset.

Treatment of non-small cell lung cancer is increasingly biomarker driven with multiple genomic alterations, including those in the epidermal growth factor receptor (EGFR) gene, that benefit from targeted therapies. We developed a set of algorithms to assess EGFR status and morphology using a real-world advanced lung adenocarcinoma cohort of 2099 patients with hematoxylin and eosin (H&E) images exhibiting high morphological diversity and low tumor content relative to public datasets. The best performing EGFR algorithm was attention-based and achieved an area under the curve (AUC) of 0.870, a negative predictive value (NPV) of 0.954 and a positive predictive value (PPV) of 0.410 in a validation cohort reflecting the 15% prevalence of EGFR mutations in lung adenocarcinoma. The attention model outperformed a heuristic-based model focused exclusively on tumor regions, and we show that although the attention model also extracts signal primarily from tumor morphology, it extracts additional signal from non-tumor tissue regions. Further analysis of high-attention regions by pathologists showed associations of predicted EGFR negativity with solid growth patterns and higher peritumoral immune presence. This algorithm highlights the potential of deep learning tools to provide instantaneous rule-out screening for biomarker alterations and may help prioritize the use of scarce tissue for biomarker testing.

Genomic Profiling of Combined Hepatocellular Cholangiocarcinoma Reveals Genomics Similar to Either Hepatocellular Carcinoma or Cholangiocarcinoma.

PURPOSE: Combined hepatocellular cholangiocarcinoma (cHCC-CCA) is a rare, aggressive primary liver carcinoma, with morphologic features of both hepatocellular carcinomas (HCC) and liver cholangiocarcinomas (CCA). METHODS: The genomic profiles of 4,975 CCA, 1,470 HCC, and 73 cHCC-CCA cases arising from comprehensive genomic profiling in the course of clinical care were reviewed for genomic alterations (GA), tumor mutational burden, microsatellite instability status, genomic loss of heterozygosity, chromosomal aneuploidy, genomic ancestry, and hepatitis B virus status. RESULTS: In cHCC-CCA, GA were most common in TP53 (65.8%), TERT (49.3%), and PTEN (9.6%), and 24.6% cHCC-CCA harbored potentially targetable GA. Other GA were predominantly associated with either HCC or CCA, including, but not limited to, TERT, FGFR2, IDH1, and presence of hepatitis B virus. On the basis of these features, a machine learning (ML) model was trained to classify a cHCC-CCA case as CCA-like or HCC-like. Of cHCC-CCA cases, 16% (12/73) were ML-classified as CCA-like and 58% (42/73) cHCC-CCA were ML-classified as HCC-like. The ML model classified more than 70% of cHCC-CCA as CCA-like or HCC-like on the basis of genomic profiles, without additional clinico-pathologic input. CONCLUSION: These findings demonstrate the use of ML for classification as based on a targeted exome panel used during routine clinical care. Classification of cHCC-CCA by genomic features alone creates insights into the biology of the disease and warrants further investigation for relevance to clinical care.

IGF1R- and ROR1-Specific CAR T Cells as a Potential Therapy for High Risk Sarcomas.

Patients with metastatic or recurrent and refractory sarcomas have a dismal prognosis. Therefore, new targeted therapies are urgently needed. This study was designed to evaluate chimeric antigen receptor (CAR) T cells targeting the type I insulin-like growth factor receptor (IGF1R) or tyrosine kinase-like orphan receptor 1 (ROR1) molecules for their therapeutic potential against sarcomas. Here, we report that IGF1R (15/15) and ROR1 (11/15) were highly expressed in sarcoma cell lines including Ewing sarcoma, osteosarcoma, alveolar or embryonal rhabdomyosarcoma, and fibrosarcoma. IGF1R and ROR1 CAR T cells derived from eight healthy donors using the Sleeping Beauty (SB) transposon system were cytotoxic against sarcoma cells and produced high levels of IFN-γ, TNF-α and IL-13 in an antigen-specific manner. IGF1R and ROR1 CAR T cells generated from three sarcoma patients released significant amounts of IFN-γ in response to sarcoma stimulation. The adoptive transfer of IGF1R and ROR1 CAR T cells derived from a sarcoma patient significantly reduced tumor growth in pre-established, systemically disseminated and localized osteosarcoma xenograft models in NSG mice. Infusion of IGF1R and ROR1 CAR T cells also prolonged animal survival in a localized sarcoma model using NOD/scid mice. Our data indicate that both IGF1R and ROR1 can be effectively targeted by SB modified CAR T cells and that such CAR T cells may be useful in the treatment of high risk sarcoma patients.

Overexpression of Arabidopsis thaliana PTEN caused accumulation of autophagic bodies in pollen tubes by disrupting phosphatidylinositol 3-phosphate dynamics.

Autophagy is a pathway in eukaryotes by which nutrient remobilization occurs through bulk protein and organelle turnover. Autophagy not only aides cells in coping with harsh environments but also plays a key role in many physiological processes that include pollen germination and tube growth. Most autophagic components are conserved among eukaryotes, but phylum-specific molecular components also exist. We show here that Arabidopsis thaliana PTEN, a protein and lipid dual phosphatase homologous to animal PTENs (phosphatase and tensin homologs deleted on chromosome 10), regulates autophagy in pollen tubes by disrupting the dynamics of phosphatidylinositol 3-phosphate (PI3P). The pollen-specific PTEN bound PI3P in vitro and was localized at PI3P-positive vesicles. Overexpression of PTEN caused accumulation of autophagic bodies and resulted in gametophytic male sterility. Such an overexpression effect was dependent upon its lipid phosphatase activity and was inhibited by exogenous PI3P or by expression of a class III phosphatidylinositol 3-kinase (PI3K) that produced PI3P. Overexpression of PTEN disrupted the dynamics of autophagosomes and a subpopulation of endosomes, as shown by altered localization patterns of respective fluorescent markers. Treatment with wortmannin, an inhibitor of class III PI3K, mimicked the effects by PTEN overexpression, which implied a critical role for PI3P dynamics in these processes. Despite sharing evolutionarily conserved catalytic domains, plant PTENs contain regulatory sequences that are distinct from those of animal PTENs, which might underlie their differing membrane association and thereby function. Our results show that PTEN regulates autophagy through phylum-specific molecular mechanisms.