Charles N Landen, Luciana Molinero, Habib Hamidi, Jalid Sehouli, Austin Miller, Kathleen N Moore, Cagatay Taskiran, Michael Bookman, Kristina Lindemann, Charles Anderson, Regina Berger, Tashanna Myers, Mario Beiner, Thomas Reid, Els Van Nieuwenhuysen, Andrew Green, Aikou Okamoto, Carol Aghajanian, Premal H Thaker, Stephanie V Blank, Victor K Khor, Ching-Wei Chang, Yvonne G Lin, Sandro Pignata <<<

PURPOSE: To explore whether patients with BRCA1/2-mutated or homologous recombination deficient (HRD) ovarian cancers benefitted from atezolizumab in the phase III IMagyn050 (NCT03038100) trial.PATIENTS AND METHODS: Patients with newly diagnosed ovarian cancer were randomized to either atezolizumab or placebo with standard chemotherapy and bevacizumab. Programmed death-ligand 1 (PD-L1) status of tumor-infiltrating immune cells (IC) was determined centrally (VENTANA SP142 assay). Genomic alterations, including deleterious BRCA1/2 alterations, genomic loss of heterozygosity (gLOH), tumor mutation burden (TMB), and microsatellite instability (MSI), were evaluated using the FoundationOne assay. HRD was defined as gLOH ≥ 16%, regardless of BRCA1/2 mutation status. Potential associations between progression-free survival (PFS) and genomic biomarkers were evaluated using standard correlation analyses and log-rank of Kaplan-Meier estimates.RESULTS: Among biomarker-evaluable samples, 22% (234/1,050) harbored BRCA1/2 mutations and 46% (446/980) were HRD. Median TMB was low irrespective of BRCA1/2 or HRD. Only 3% (29/1,024) had TMB ≥10 mut/Mb, and 0.3% (3/1,022) were MSI-high. PFS was better in BRCA2-mutated versus BRCA2-non-mutated tumors and in HRD versus proficient tumors. PD-L1 positivity (≥1% expression on ICs) was associated with HRD but not BRCA1/2 mutations. PFS was not improved by adding atezolizumab in BRCA2-mutated or HRD tumors; there was a trend toward enhanced PFS with atezolizumab in BRCA1-mutated tumors.CONCLUSIONS: Most ovarian tumors have low TMB despite BRCA1/2 mutations or HRD. Neither BRCA1/2 mutation nor HRD predicted enhanced benefit from atezolizumab. This is the first randomized double-blind trial in ovarian cancer demonstrating that genomic instability triggered by BRCA1/2 mutation or HRD is not associated with improved sensitivity to immune checkpoint inhibitors. See related commentary by Al-Rawi et al., p. 1645. <<<

Identifying robust survival subgroups of hepatocellular carcinoma (HCC) will significantly improve patient care. Currently, endeavor of integrating multi-omics data to explicitly predict HCC survival from multiple patient cohorts is lacking. To fill this gap, we present a deep learning (DL)-based model on HCC that robustly differentiates survival subpopulations of patients in six cohorts. We built the DL-based, survival-sensitive model on 360 HCC patients' data using RNA sequencing (RNA-Seq), miRNA sequencing (miRNA-Seq), and methylation data from The Cancer Genome Atlas (TCGA), which predicts prognosis as good as an alternative model where genomics and clinical data are both considered. This DL-based model provides two optimal subgroups of patients with significant survival differences ( = 7.13e-6) and good model fitness [concordance index (C-index) = 0.68]. More aggressive subtype is associated with frequent inactivation mutations, higher expression of stemness markers ( and ) and tumor marker , and activated Wnt and Akt signaling pathways. We validated this multi-omics model on five external datasets of various omics types: LIRI-JP cohort ( = 230, C-index = 0.75), NCI cohort ( = 221, C-index = 0.67), Chinese cohort ( = 166, C-index = 0.69), E-TABM-36 cohort ( = 40, C-index = 0.77), and Hawaiian cohort ( = 27, C-index = 0.82). This is the first study to employ DL to identify multi-omics features linked to the differential survival of patients with HCC. Given its robustness over multiple cohorts, we expect this workflow to be useful at predicting HCC prognosis prediction. . <<<

To develop and validate a radiomics model for evaluating pathologic complete response (pCR) to neoadjuvant chemoradiotherapy in patients with locally advanced rectal cancer (LARC). We enrolled 222 patients (152 in the primary cohort and 70 in the validation cohort) with clinicopathologically confirmed LARC who received chemoradiotherapy before surgery. All patients underwent T2-weighted and diffusion-weighted imaging before and after chemoradiotherapy; 2,252 radiomic features were extracted from each patient before and after treatment imaging. The two-sample test and the least absolute shrinkage and selection operator regression were used for feature selection, whereupon a radiomics signature was built with support vector machines. Multivariable logistic regression analysis was then used to develop a radiomics model incorporating the radiomics signature and independent clinicopathologic risk factors. The performance of the radiomics model was assessed by its calibration, discrimination, and clinical usefulness with independent validation. The radiomics signature comprised 30 selected features and showed good discrimination performance in both the primary and validation cohorts. The individualized radiomics model, which incorporated the radiomics signature and tumor length, also showed good discrimination, with an area under the receiver operating characteristic curve of 0.9756 (95% confidence interval, 0.9185-0.9711) in the validation cohort, and good calibration. Decision curve analysis confirmed the clinical utility of the radiomics model. Using pre- and posttreatment MRI data, we developed a radiomics model with excellent performance for individualized, noninvasive prediction of pCR. This model may be used to identify LARC patients who can omit surgery after chemoradiotherapy. . <<<