Machine learning evaluation of immune infiltrate through digital tumour score allows prediction of survival outcome in a pooled analysis of three international stage III colon cancer cohorts.

BACKGROUND: T-cell immune infiltrates are robust prognostic variables in localised colon cancer. Evaluation of prognosis using artificial intelligence is an emerging field. We evaluated whether machine learning analysis improved prediction of patient outcome in comparison with analysis of T cell infiltrate only or in association with clinical variables. METHODS: We used data from two phase III clinical trials (Prodige-13 and PETACC08) and one retrospective Italian cohort (HARMONY). Cohorts were split into training (N = 692), internal validation (N = 297) and external validation (N = 672) sets. Tumour slides were stained with CD3mAb. CD3 Machine Learning (CD3ML) score was computed using graphical parameters within the tumour tiles obtained from CD3 slides. CD3 infiltrates in tumour core and invasive margin were automatically detected. Associations of CD3 infiltrates and CD3ML with 5-year Disease-Free Survival (DFS) were examined using univariate and multivariable survival models by Cox regression. FINDINGS: CD3 density both in the invasive margin and the tumour core were significantly associated with DFS in the different sets. Similarly, CD3ML score was significantly associated with DFS in all sets. CD3 assessment did not provide added value on top of CD3ML assessment (Likelihood Ratio Test (LRT), p = 0.13). In contrast, CD3ML improved prediction of DFS when combined with a clinical risk stage (LRT, p = 0.001). Stratified by clinical risk score (High or Low), patients with low CD3ML score had better DFS. INTERPRETATION: In all tested sets, machine learning analysis of tumour cells improved prediction of prognosis compared to clinical parameters. Adding tumour-infiltrating lymphocytes assessment did not improve prognostic determination. FUNDING: This research received no external funding.

CD3-CD8 immune score associated with a clinical score stratifies PDAC prognosis regardless of adjuvant or neoadjuvant chemotherapy.

Stratification of the prognosis of pancreatic cancer (PDAC) patients treated by surgery is based solely on clinical variables, such as tumor stage and node status. The development of biomarkers of relapse is needed, especially to drive administration of adjuvant therapy in this at-risk population. Our study evaluates the prognostic performance of a CD3- and CD8-based immune score. CD3, CD8 and Foxp3 expression were evaluated on whole slides in two retrospective PDAC cohorts totaling 334 patients. For this study, we developed an immune score to estimate CD3 and CD8 infiltration in both tumor core and invasive margin using computer-guided analysis with QuPath software. Variables were combined in a dichotomous immune score. The association between immune and clinical scores, and both PFS and OS was investigated. We observed that a dichotomous immune score predicts both PFS and OS of localized PDAC. By univariate and multivariate analysis, immune score, tumor grade, adjuvant therapy, lymph node status, and adjuvant chemotherapy administration were associated with PFS and OS. We subsequently associated the PDAC immune score and clinical variables in a combined score. This combined score predicted patient outcomes independently of adjuvant or neoadjuvant treatment, and improved patient prognostic prediction compared to clinical variables or immune score alone.

Evaluation of immune infiltrate according to the HER2 status in colorectal cancer.

BACKGROUND AND AIMS: In colorectal cancer (CRC), HER2 targeting is a promising treatment and immune infiltrate is an important area of research and strategy. Data regarding HER2 status and immune infiltrate are lacking. The aim of this study was to compare the immune infiltrate between HER2 amplified and non-amplified categories in proficient MisMatchRepair (pMMR)/microsatellite stable (MSS) CRC. METHODS: HER2 immunohistochemistry (IHC) and fluorescence in situ hybridization were performed in a retrospective series of 654 CRC. Lymphocyte infiltrate was analysed by anti-CD3, CD8 and CD4 IHC and evaluated digitally using QuPath software. RESULTS: Among the 654 CRC, we first observed a decreased CD3+ and CD8+ infiltrate between HER2 amplified (all IHC 3+ except one 2+) and non-amplified HER2 2+ IHC CRC (p = 0.059 and 0.072 respectively). A supplementary analysis of 258 pMMR/MSS CRC from the previous cohort, displaying all the IHC scores (0, 1+, 2+, 3+), showed a lower CD3+ infiltrate between HER2 amplified versus HER2 0 (p = 0.002), 1+ (p = 0.088) and non-amplified 2+ (p = 0.081) IHC cases. CONCLUSIONS: Our original findings suggest that in pMMR/MSS CRC, the immune infiltrate is reduced in HER2 amplified versus other HER2 categories. These data might be useful for future strategies combining anti-HER2 treatments and immune checkpoint inhibitors and need to be confirmed in larger CRC cohorts.

Advancing precision oncology through systematic germline and tumor genetic analysis: The oncogenetic point of view on findings from a prospective multicenter clinical trial of 666 patients.

INTRODUCTION: With the emergence of targeted therapies, there is a need to accurately identify more tumor biomarkers. The EXOMA trial was designed to offer tumor and germline exome sequencing (ES) to patients with solid malignant tumors and facing therapeutic failure. As hereditary cancer predispositions could be identified, with genetic counseling and health management implications, a genetic consultation was systematically established. This design needs to be discussed as genetic human resources are limited and indication of theranostic tests will increase. METHODS: Genetic counseling was conducted within 15 days following inclusion in the study for patients recruited between December 2015 and July 2019. In silico analyses from theranostic ES were limited to 317 genes involved in oncogenesis, from both tumor and blood DNA. RESULTS: Six hundred and sixty six patients had a genetic consultation before ES. In 65/666 patients, 66 germline pathogenic or likely pathogenic (P/LP) variants were identified in 16 actionable genes and seven non-actionable genes according to French guidelines. 24/65 patients had previously received genetic analysis for diagnostic purposes, and for 17 of them, a P/LP variant had already been identified. Among the 48/65 remaining cases for which the EXOMA protocol revealed a previously unknown P/LP variant, only 19 met the criteria for genetic testing for inherited cancer risk after familial survey. These criteria had not been identified by the oncologist in 10 cases. In 21/65 cases, the variant was considered incidental. DISCUSSION: In 7.4% of patients, an undiagnosed hereditary genetic predisposition was identified, whether or not related to the clinical presentation, and germline analysis impacted oncological management for only 6.3% of the cohort. This low percentage should be weighed against the burden of systematic genetic consultation and urgent circuits. Information or training tools to form oncologists to the prescription of germline genetic analyses should be explored, as well as information supports and patient preferences.

First-line durvalumab and tremelimumab with chemotherapy in RAS-mutated metastatic colorectal cancer: a phase 1b/2 trial.

Although patients with microsatellite instable metastatic colorectal cancer (CRC) benefit from immune checkpoint blockade, chemotherapy with targeted therapies remains the only therapeutic option for microsatellite stable (MSS) tumors. The single-arm, phase 1b/2 MEDITREME trial evaluated the safety and efficacy of durvalumab plus tremelimumab combined with mFOLFOX6 chemotherapy in first line, in 57 patients with RAS-mutant unresectable metastatic CRC. Safety was the primary objective of phase Ib; no safety issue was observed. The phase 2 primary objective of efficacy in terms of 3-month progression-free survival (PFS) in patients with MSS tumors was met, with 3-month PFS of 90.7% (95% confidence interval (CI): 79.2-96%). For secondary objectives, response rate was 64.5%; median PFS was 8.2 months (95% CI: 5.9-8.6); and overall survival was not reached in patients with MSS tumors. We observed higher tumor mutational burden and lower genomic instability in responders. Integrated transcriptomic analysis underlined that high immune signature and low epithelial-mesenchymal transition were associated with better outcome. Immunomonitoring showed induction of neoantigen and NY-ESO1 and TERT blood tumor-specific T cell response associated with better PFS. The combination of durvalumab-tremelimumab with mFOLFOX6 was tolerable with promising clinical activity in MSS mCRC. Clinicaltrials.gov identifier: NCT03202758 .

GTN Enhances Antitumor Effects of Doxorubicin in TNBC by Targeting the Immunosuppressive Activity of PMN-MDSC.

(1) Background: Immunosuppression is a key barrier to effective anti-cancer therapies, particularly in triple-negative breast cancer (TNBC), an aggressive and difficult to treat form of breast cancer. We investigated here whether the combination of doxorubicin, a standard chemotherapy in TNBC with glyceryltrinitrate (GTN), a nitric oxide (NO) donor, could overcome chemotherapy resistance and highlight the mechanisms involved in a mouse model of TNBC. (2) Methods: Balb/C-bearing subcutaneous 4T1 (TNBC) tumors were treated with doxorubicin (8 mg/Kg) and GTN (5 mg/kg) and monitored for tumor growth and tumor-infiltrating immune cells. The effect of treatments on MDSCs reprogramming was investigated ex vivo and in vitro. (3) Results: GTN improved the anti-tumor efficacy of doxorubicin in TNBC tumors. This combination increases the intra-tumor recruitment and activation of CD8+ lymphocytes and dampens the immunosuppressive function of PMN-MDSCs PD-L1low. Mechanistically, in PMN-MDSC, the doxorubicin/GTN combination reduced STAT5 phosphorylation, while GTN +/- doxorubicin induced a ROS-dependent cleavage of STAT5 associated with a decrease in FATP2. (4) Conclusion: We have identified a new combination enhancing the immune-mediated anticancer therapy in a TNBC mouse model through the reprograming of PMN-MDSCs towards a less immunosuppressive phenotype. These findings prompt the testing of GTN combined with chemotherapies as an adjuvant in TNBC patients experiencing treatment failure.

Exome-Based Genomic Markers Could Improve Prediction of Checkpoint Inhibitor Efficacy Independently of Tumor Type.

Immune checkpoint inhibitors (ICIs) have improved the care of patients in multiple cancer types. However, PD-L1 status, high Tumor Mutational Burden (TMB), and mismatch repair deficiency are the only validated biomarkers of efficacy for ICIs. These markers remain imperfect, and new predictive markers represent an unmet medical need. Whole-exome sequencing was carried out on 154 metastatic or locally advanced cancers from different tumor types treated by immunotherapy. Clinical and genomic features were investigated using Cox regression models to explore their capacity to predict progression-free survival (PFS). The cohort was split into training and validation sets to assess validity of observations. Two predictive models were estimated using clinical and exome-derived variables, respectively. Stage at diagnosis, surgery before immunotherapy, number of lines before immunotherapy, pleuroperitoneal, bone or lung metastasis, and immune-related toxicity were selected to generate a clinical score. KRAS mutations, TMB, TCR clonality, and Shannon entropy were retained to generate an exome-derived score. The addition of the exome-derived score improved the prediction of prognosis compared with the clinical score alone. Exome-derived variables could be used to predict responses to ICI independently of tumor type and might be of value in improving patient selection for ICI therapy.

Preliminary evaluation of deep learning for first-line diagnostic prediction of tumor mutational status.

The detection of tumour gene mutations by DNA or RNA sequencing is crucial for the prescription of effective targeted therapies. Recent developments showed promising results for tumoral mutational status prediction using new deep learning based methods on histopathological images. However, it is still unknown whether these methods can be useful aside from sequencing methods for efficient population diagnosis. In this retrospective study, we use a standard prediction pipeline based on a convolutional neural network for the detection of cancer driver genomic alterations in The Cancer Genome Atlas (TCGA) breast (BRCA, n = 719), lung (LUAD, n = 541) and colon (COAD, n = 459) cancer datasets. We propose 3 diagnostic strategies using deep learning methods as first-line diagnostic tools. Focusing on cancer driver genes such as KRAS, EGFR or TP53, we show that these methods help reduce DNA sequencing by up to 49.9% with a high sensitivity (95%). In a context of limited resources, these methods increase sensitivity up to 69.8% at a 30% capacity of DNA sequencing tests, up to 85.1% at a 50% capacity, and up to 91.8% at a 70% capacity. These methods can also be used to prioritize patients with a positive predictive value up to 90.6% in the 10% patient most at risk of being mutated. Limitations of this study include the lack of external validation on non-TCGA data, dependence on prevalence of mutations in datasets, and use of a standard DL method on a limited dataset. Future studies using state-of-the-art methods and larger datasets are needed for better evaluation and clinical implementation.

PIK3CA and PIK3R1 tumor mutational landscape in a pan-cancer patient cohort and its association with pathway activation and treatment efficacy.

There is little data concerning the implications of PIK3CA mutations outside of the known hotspots described in ER+/HER2- metastatic breast cancer (mBC). Similarly, PIK3R1 mutations could also lead to activation of PI3K pathway, but are poorly described. We determined the incidence and type of all somatic PIK3CA and PIK3R1 mutations by whole exome sequencing (WES) in a pan-cancer cohort of 1200 patients. Activation of the PI3K pathway was studied using phospho-AKT immunohistochemistry. Associations between PIK3CA/PIK3R1 mutations and response to chemotherapy were studied in mBC cases. We found 141 patients (11.8%) with a PIK3CA and/or PIK3R1 mutation across 20 different cancer types. The main cancer subtype was mBC (45.4%). Eighty-four mutations (62.2%) occurred in the three described hotspots; 51 mutations occurred outside of these hotspots. In total, 78.4% were considered activating or probably activating. Among PIK3R1 mutations, 20% were loss of function mutations, leading to a constitutional activation of the pathway. Phospho-AKT quantification in tumor samples was in favor of activation of the PI3K pathway in the majority of mutated tumors, regardless of mutation type. In ER+/HER2- mBC, first line chemotherapy efficacy was similar for PIK3CA-mutated and PIK3CA-WT tumors, whereas in triple negative mBC, chemotherapy appeared to be more effective in PIK3CA-WT tumors. In this large, real-life pan-cancer patient cohort, our results indicate that PIK3CA/PIK3R1 mutations are widely spread, and plead in favour of evaluating the efficacy of PI3K inhibitors outside of ER+/HER2- mBC and outside of hotspot mutations.

Molecular intrinsic subtypes, genomic, and immune landscapes of BRCA-proficient but HRD-high ER-positive/HER2-negative early breast cancers.

PURPOSE: The vast majority of research studies that have described the links between DNA damage repair or homologous recombination deficiency (HRD) score, and tumor biology, have concerned either triple negative breast cancers or cancers with mutation of BRCA 1/2. We hypothesized that ER + /HER2- early breast tumors without BRCA 1/2 mutation could have high HRD score and aimed to describe their genomic, transcriptomic, and immune landscapes. PATIENTS AND METHODS: In this study, we reported BRCA 1/2 mutational status, HRD score, and mutational signature 3 (S3) expression, in all early breast cancer (eBC) subtypes from the TCGA database, with a particular focus in ER + /HER2-. In this subtype, bioinformatics analyses of tumor transcriptomic, immune profile, and mutational landscape were performed, according to HRD status. Overall survival (OS), progression free-interval (PFI), and variables associated with outcome were also evaluated. RESULTS: Among the 928 tumor samples analyzed, 46 harbored BRCA 1/2 mutations, and 606 were ER + /HER2- (of which 24 were BRCA 1/2 mutated). We found a subset of BRCA-proficient ER + /HER2- eBC, with high HRD score. These tumors displayed significantly different immune, mutational, and tumor molecular signatures landscapes, compared to BRCA-mutated and BRCA-proficient HRD-low tumors. Outcome did not significantly differ between these 3 groups, but biological factors associated with survival are not the same across the 3 entities. CONCLUSION: This study highlights possible novel biological differences among ER + /HER2- breast cancer related to HRD status. Our results could have important implications for translational research and/or the design of future clinical trials, but require prospective clinical evaluation.

Downregulation of Elovl5 promotes breast cancer metastasis through a lipid-droplet accumulation-mediated induction of TGF-ß receptors.

Metastatic breast cancer cannot be cured, and alteration of fatty acid metabolism contributes to tumor progression and metastasis. Here, we were interested in the elongation of very long-chain fatty acids protein 5 (Elovl5) in breast cancer. We observed that breast cancer tumors had a lower expression of Elovl5 than normal breast tissues. Furthermore, low expression of Elovl5 is associated with a worse prognosis in ER+ breast cancer patients. In accordance with this finding, decrease of Elovl5 expression was more pronounced in ER+ breast tumors from patients with metastases in lymph nodes. Although downregulation of Elovl5 expression limited breast cancer cell proliferation and cancer progression, suppression of Elovl5 promoted EMT, cell invasion and lung metastases in murine breast cancer models. The loss of Elovl5 expression induced upregulation of TGF-ß receptors mediated by a lipid-droplet accumulation-dependent Smad2 acetylation. As expected, inhibition of TGF-ß receptors restored proliferation and dampened invasion in low Elovl5 expressing cancer cells. Interestingly, the abolition of lipid-droplet formation by inhibition of diacylglycerol acyltransferase activity reversed induction of TGF-ß receptors, cell invasion, and lung metastasis triggered by Elovl5 knockdown. Altogether, we showed that Elovl5 is involved in metastasis through lipid droplets-regulated TGF-ß receptor expression and is a predictive biomarker of metastatic ER+ breast cancer.

Combination of CDX2 H-score quantitative analysis with CD3 AI-guided analysis identifies patients with a good prognosis only in stage III colon cancer.

AIM: Stratification of colon cancer (CC) of patients with stage II and III for risk of relapse is still needed especially to drive adjuvant therapy administration. Our study evaluates the prognostic performance of two known biomarkers, CDX2 and CD3, standalone or their combined information in stage II and III CC. PATIENTS AND METHODS: CDX2 and CD3 expression was evaluated in Prodige-13 study gathering 443 stage II and 398 stage III primary CC on whole slide colectomy. We developed for this study an H-score to quantify CDX2 expression and used our artificial intelligence (AI)-guided tissue analysis ColoClass to detect CD3 in tumour core and invasive margin. Association between biomarkers and relapse-free survival was investigated. RESULTS: Univariate analysis showed that the combined variable CD3-TC and CD3-IM was associated with prognosis in both stage II and stage III. CDX2, on the contrary, was associated with prognosis only in stage III. We subsequently associated CDX2 and combined immune parameters only in stage III. This multivariate analysis allowed us to distinguish a proportion of stage III CC harbouring a high CDX2 expression and a high immune infiltration with a particularly good prognosis compared to their counterpart. CONCLUSION: This study validated the prognostic role of CDX2 and CD3 evaluated with immunohistochemistry procedures in stage III but not in stage II. This association would be conceivable in a routine pathology laboratory and could help oncologist to consider chemotherapy de-escalation for a part of stage III patients.

Hematopoietic Prostaglandin D2 Synthase Controls Tfh/Th2 Communication and Limits Tfh Antitumor Effects.

T follicular helper (Tfh) cells are a subset of CD4+ T cells essential in immunity and have a role in helping B cells produce antibodies against pathogens. However, their role during cancer progression remains unknown. The mechanism of action of Tfh cells remains elusive because contradictory data have been reported on their protumor or antitumor responses in human and murine tumors. Like Tfh cells, Th2 cells are also involved in humoral immunity and are regularly associated with tumor progression and poor prognosis, mainly through their secretion of IL4. Here, we showed that Tfh cells expressed hematopoietic prostaglandin D2 (PGD2) synthase in a pSTAT1/pSTAT3-dependent manner. Tfh cells produced PGD2, which led to recruitment of Th2 cells via the PGD2 receptor chemoattractant receptor homologous molecule expressed on Th type 2 cells (CRTH2) and increased their effector functions. This cross-talk between Tfh and Th2 cells promoted IL4-dependent tumor growth. Correlation between Th2 cells, Tfh cells, and hematopoietic PGD2 synthase was observed in different human cancers and associated with outcome. This study provides evidence that Tfh/Th2 cross-talk through PGD2 limits the antitumor effects of Tfh cells and, therefore, could serve as a therapeutic target.

Efficacy of platinum-based chemotherapy in metastatic breast cancer and HRD biomarkers: utility of exome sequencing.

Metastatic breast cancer (MBC) is frequently managed by platinum-based chemotherapy during the disease course. The real benefit of these treatments is uncertain at advanced stages of the disease and in non-triple-negative subtypes. Since homologous recombination deficiency (HRD) could inform about tumor sensitivity to DNA-damaging agents, we aimed to determine biomarkers of genomic instability, and their link with platinum efficacy. In this single-center study, we report BRCA1/2 mutational status, HRD score and signature 3 levels, all obtained by tumor exome sequencing, in 86 patients with various subtypes of MBC and who received platinum-based chemotherapy. Overall response rate, disease control rate, PFS and PFS2/PFS1 ratio were evaluated to assess platinum-based chemotherapy efficacy. Among the 86 tumor samples analyzed, 7 harbored BRCA1/2 mutations. We found a subset of BRCA-proficient MBC with high HRD score or high S3 levels, comparable to BRCA-mutated tumors. However, these patients with high HRD score or high S3 tumor level do not seem to benefit more from platinum-based chemotherapy than the others, in terms of response rates and/or PFS, regardless of BC molecular subtype. By multivariate analysis, only the absence of liver metastases was independently associated with significantly better PFS on platinum-based chemotherapy. However, some of our exploratory analyses reveal that certain methods, when optimized, seem to associate with platinum benefit. Tumor exome sequencing methodology for quantifying HRD has to be approached systematically, and further validated and standardized prior to its clinical use. Further studies are warranted to confirm these results to guide platinum use in MBC.

Custom multi­tumor next­generation sequencing panel for routine molecular diagnosis of solid tumors: Validation and results from three­year clinical use.

Molecular testing is extremely important in cancer care, starting as early as at diagnosis. In order to address the challenge of providing reliable results within the timeframe adapted to patient management and suitable to guide clinical decisions, a capture­based next­generation sequencing (NGS) panel focusing on ten genes known to harbor genetic variations which may be targeted by approved drugs in patients with cancer was designed and validated. Very favorable analytical performances were obtained for both solid and liquid biopsies. For solid biopsies, a low read depth (80X per nucleotide) led to the genotype detection accuracy of 100%. The read of raw data for liquid biopsies resulted in the 91.19% result concordance between paired solid and liquid samples. The present method met all the requirements for the ISO15189 certification. During our three­year experience of routinely using this panel, almost 2,300 samples from lung and colorectal cancers, melanomas and gastrointestinal stromal tumors have been analyzed. It was found that our panel detected slightly more gain­of­function variants than described in the literature. Surprisingly, loss­of­function variants were also detected in certain of the analyzed genes. Finally, liquid biopsy data revealed statistically different mutated allele frequencies between tumor types, but also between mutated genes and variants themselves. In conclusion, the use of our capture­based NGS panel is perfectly adapted to perform relevant molecular diagnosis in a time frame compatible with patient care.

Association of Anti-EGFR Antibody and MEK Inhibitor in Gynecological Cancer Harboring RAS Mutation: A Case Series.

Low-grade serous carcinoma represents a minority of serous carcinoma. Although they have better prognosis than high-grade serous carcinoma, they respond poorly to chemotherapy. Thus, it appears necessary to find other treatments such as targeted therapies. Since RAS or RAF mutations occur frequently in low-grade serous carcinoma and lead to constitutively activated MAPK cascade, MEK inhibition should be effective in the treatment of low-grade serous carcinoma. So, we wanted to evaluate the clinical benefit of MEK inhibitors in the management of advanced-stage low-grade serous carcinoma harboring KRAS or NRAS mutation. We report a case series of three women with advanced-stage low-grade serous carcinoma harboring RAS mutation who had stabilization of their disease during several months under targeted therapy combining anti-EGFR antibody and MEK inhibitor. We performed in vitro experiments, confirming the effectiveness of MEK inhibitor on the KRAS-mutated OVCAR-5 cell line, and the constitutively activation of MAPK cascade in RAS-mutated carcinoma. However, it seems that the anti-EGFR antibody does not provide any additional benefit. After whole exome analysis is carried out on the patient with the shortest response, we observed the appearance of RB1 loss-of-function mutation that could be a mechanism of resistance to MEK inhibitors in RAS- of RAF-mutated cancers. The MEK inhibitor is effective in the advanced stages of low-grade serous carcinoma harboring RAS mutation with acceptable tolerance. RB1 loss could be a mechanism of resistance to MEK inhibitors in RAS-mutated low-grade serous carcinoma.

MEK inhibition overcomes chemoimmunotherapy resistance by inducing CXCL10 in cancer cells.

Chemotherapy with anti PD-1/PD-L1 antibodies has become the standard of care for patients with metastatic non-small cell lung cancer (mNSCLC). Using lung tumor models, where pemetrexed and cisplatin (PEM/CDDP) chemotherapy remains unable to synergize with immune checkpoint inhibitors (ICIs), we linked the failure of this treatment with its inability to induce CXCL10 expression and CD8+ T cell recruitment. Using drug screening, we showed that combining a MEK inhibitor (MEKi) with PEM/CDDP triggers CXCL10 secretion by cancer cells and CD8+ T cell recruitment, sensitizing it to ICIs. PEM/CDDP plus a MEKi promotes optineurin (OPTN)-dependent mitophagy, resulting in CXCL10 production in a mitochondrial DNA- and TLR9-dependent manner. TLR9 or autophagy/mitophagy inhibition abolishes the anti-tumor efficacy of PEM/CDDP plus MEKi/anti-PD-L1 therapy. In human NSCLCs, high OPTN, TLR9, and CXCL10 expression is associated with a better response to ICIs. Our results underline the role of TLR9- and OPTN-dependent mitophagy in enhancing chemoimmunotherapy efficacy.

Using a convolutional neural network for classification of squamous and non-squamous non-small cell lung cancer based on diagnostic histopathology HES images.

Histological stratification in metastatic non-small cell lung cancer (NSCLC) is essential to properly guide therapy. Morphological evaluation remains the basis for subtyping and is completed by additional immunohistochemistry labelling to confirm the diagnosis, which delays molecular analysis and utilises precious sample. Therefore, we tested the capacity of convolutional neural networks (CNNs) to classify NSCLC based on pathologic HES diagnostic biopsies. The model was estimated with a learning cohort of 132 NSCLC patients and validated on an external validation cohort of 65 NSCLC patients. Based on image patches, a CNN using InceptionV3 architecture was trained and optimized to classify NSCLC between squamous and non-squamous subtypes. Accuracies of 0.99, 0.87, 0.85, 0.85 was reached in the training, validation and test sets and in the external validation cohort. At the patient level, the CNN model showed a capacity to predict the tumour histology with accuracy of 0.73 and 0.78 in the learning and external validation cohorts respectively. Selecting tumour area using virtual tissue micro-array improved prediction, with accuracy of 0.82 in the external validation cohort. This study underlines the capacity of CNN to predict NSCLC subtype with good accuracy and to be applied to small pathologic samples without annotation.

New Artificial Intelligence Score and Immune Infiltrates as Prognostic Factors in Colorectal Cancer With Brain Metastases.

Incidence of brain metastases has increased in patients with colorectal cancer (CRC) as their survival has improved. CD3 T-cells and, lately, DGMate (DiGital tuMor pArameTErs) score, have been identified as prognostic factors in locally advanced CRC. Until now, there is no data concerning the prognostic value of these markers in patients with CRC-derived brain metastases. All consecutive patients with CRC-derived brain metastases diagnosed between 2000 and 2017 were retrospectively included. Staining for CD3, CD8, PD-1, PD-L1 and DGMate analyses were performed using tissue micro-array from primary tumors and, if available, brain metastases. All in all, 83 patients were included with 80 primary tumor samples and 37 brain metastases samples available. CD3 and CD8 T-cell infiltration was higher in primary tumors compared to brain metastases. We observed a significant higher DGMate score in rectal tumors compared to colon tumors (p=0.03). We also noted a trend of higher CD3 T-cell infiltration in primary tumors when brain metastases were both supra and subtentorial compared to brain metastases that were only subtentorial or supratentorial (p=0.36 and p=0.03, respectively). No correlation was found between CD3 or CD8 infiltration or DGMate score in primary tumors or brain metastases and overall survival (OS) in the overall population. In patients with rectal tumors, a high DGMate score in brain metastases was associated with longer OS (13.4 ± 6.1 months versus 6.1 ± 1.4 months, p=0.02). High CD3 T-cell infiltration in brain metastases was associated with lower OS in patients with supratentorial brain metastases (9.8 ± 3.3 months versus 16.7 ± 5.9 months, p=0.03). PD-L1 overexpression was rare, both in primary tumors and brain metastases, but PD-L1 positive primary tumors were associated with worse OS (p=0.01). In contrast to breast and lung cancer derived brain metastases, CD3 and CD8 infiltration and DGMate score are not major prognostic factors in patients with CRC-derived brain metastases.