Suman, Vera

Abstract The OmicsFootPrint framework addresses the need for advanced multi-omics data analysis methodologies by transforming data into intuitive two-dimensional circular images and facilitating the interpretation of complex diseases. Utilizing deep neural networks and incorporating the SHapley Additive exPlanations algorithm, the framework enhances model interpretability. Tested with The Cancer Genome Atlas data, OmicsFootPrint effectively classified lung and breast cancer subtypes, achieving high area under the curve (AUC) scores—0.98 ± 0.02 for lung cancer subtype differentiation and 0.83 ± 0.07 for breast cancer PAM50 subtypes, and successfully distinguished between invasive lobular and ductal carcinomas in breast cancer, showcasing its robustness. It also demonstrated notable performance in predicting drug responses in cancer cell lines, with a median AUC of 0.74, surpassing nine existing methods. Furthermore, its effectiveness persists even with reduced training sample sizes. OmicsFootPrint marks an enhancement in multi-omics research, offering a novel, efficient and interpretable approach that contributes to a deeper understanding of disease mechanisms.

Purpose The majority of patients with cancer receive treatments that are minimally informed by omics data. We propose a precision medicine computational framework, PANOPLY (Precision Cancer Genomic Report: Single Sample Inventory), to identify and prioritize drug targets and cancer therapy regimens. Materials and Methods The PANOPLY approach integrates clinical data with germline and somatic features obtained from multiomics platforms and applies machine learning and network analysis approaches in the context of the individual patient and matched controls. The PANOPLY workflow uses the following four steps: selection of matched controls to the patient of interest; identification of patient-specific genomic events; identification of suitable drugs using the driver-gene network and random forest analyses; and provision of an integrated multiomics case report of the patient with prioritization of anticancer drugs. Results The PANOPLY workflow can be executed on a stand-alone virtual machine and is also available for download as an R package. We applied the method to an institutional breast cancer neoadjuvant chemotherapy study that collected clinical and genomic data as well as patient-derived xenografts to investigate the prioritization offered by PANOPLY. In a chemotherapy-resistant patient-derived xenograft model, we found that that the prioritized drug, olaparib, was more effective than placebo in treating the tumor ( P < .05). We also applied PANOPLY to in-house and publicly accessible multiomics tumor data sets with therapeutic response or survival data available. Conclusion PANOPLY shows promise as a means to prioritize drugs on the basis of clinical and multiomics data for an individual patient with cancer. Additional studies are needed to confirm this approach.

Abstract Purpose: Hyperactivation of AKT is common and associated with endocrine resistance in estrogen receptor–positive (ER+) breast cancer. The allosteric pan-AKT inhibitor MK-2206 induced apoptosis in PIK3CA-mutant ER+ breast cancer under estrogen-deprived condition in preclinical studies. This neoadjuvant phase II trial was therefore conducted to test the hypothesis that adding MK-2206 to anastrozole induces pathologic complete response (pCR) in PIK3CA mutant ER+ breast cancer. Experimental Design: Potential eligible patients with clinical stage II/III ER+/HER2− breast cancer were preregistered and received anastrozole (goserelin if premenopausal) for 28 days in cycle 0 pending tumor PIK3CA sequencing. Patients positive for PIK3CA mutation in the tumor were eligible to start MK-2206 (150 mg orally weekly, with prophylactic prednisone) on cycle 1 day 2 (C1D2) and to receive a maximum of four 28-day cycles of combination therapy before surgery. Serial biopsies were collected at preregistration, C1D1 and C1D17. Results: Fifty-one patients preregistered and 16 of 22 with PIK3CA-mutant tumors received study drug. Three patients went off study due to C1D17 Ki67 &gt;10% (n = 2) and toxicity (n = 1). Thirteen patients completed neoadjuvant therapy followed by surgery. No pCRs were observed. Rash was common. MK-2206 did not further suppress cell proliferation and did not induce apoptosis on C1D17 biopsies. Although AKT phosphorylation was reduced, PRAS40 phosphorylation at C1D17 after MK-2206 persisted. One patient acquired an ESR1 mutation at surgery. Conclusions: MK-2206 is unlikely to add to the efficacy of anastrozole alone in PIK3CA-mutant ER+ breast cancer and should not be studied further in the target patient population. Clin Cancer Res; 23(22); 6823–32. ©2017 AACR.

Abstract Significant endocrine therapy–resistant tumor proliferation is present in ≥20% of estrogen receptor–positive (ER+) primary breast cancers and is associated with disease recurrence and death. Here, we uncover a link between intrinsic endocrine therapy resistance and dysregulation of the MutL mismatch repair (MMR) complex (MLH1/3, PMS1/2), and demonstrate a direct role for MutL complex loss in resistance to all classes of endocrine therapy. We find that MutL deficiency in ER+ breast cancer abrogates CHK2-mediated inhibition of CDK4, a prerequisite for endocrine therapy responsiveness. Consequently, CDK4/6 inhibitors (CDK4/6i) remain effective in MutL-defective ER+ breast cancer cells. These observations are supported by data from a clinical trial where a CDK4/6i was found to strongly inhibit aromatase inhibitor–resistant proliferation of MutL-defective tumors. These data suggest that diagnostic markers of MutL deficiency could be used to direct adjuvant CDK4/6i to a population of patients with breast cancer who exhibit marked resistance to the current standard of care. Significance: MutL deficiency in a subset of ER+ primary tumors explains why CDK4/6 inhibition is effective against some de novo endocrine therapy–resistant tumors. Therefore, markers of MutL dysregulation could guide CDK4/6 inhibitor use in the adjuvant setting, where the risk benefit ratio for untargeted therapeutic intervention is narrow. Cancer Discov; 7(10); 1168–83. ©2017 AACR. This article is highlighted in the In This Issue feature, p. 1047