Citations

Spatially resolved sequencing technologies help us dissect how cells are organized in space. Several available computational approaches focus on the identification of spatially variable genes (SVGs), genes whose expression patterns vary in space. The detection of SVGs is analogous to the identification of differentially expressed genes and permits us to understand how genes and associated molecular processes are spatially distributed within cellular niches. However, the expression activities of SVGs fail to encode all information inherent in the spatial distribution of cells. Here, we devised a deep learning model, Spatially Informed Artificial Intelligence (SPIN-AI), to identify spatially predictive genes (SPGs), whose expression can predict how cells are organized in space. We used SPIN-AI on spatial transcriptomic data from squamous cell carcinoma (SCC) as a proof of concept. Our results demonstrate that SPGs not only recapitulate the biology of SCC but also identify genes distinct from SVGs. Moreover, we found a substantial number of ribosomal genes that were SPGs but not SVGs. Since SPGs possess the capability to predict spatial cellular organization, we reason that SPGs capture more biologically relevant information for a given cellular niche than SVGs. Thus, SPIN-AI has broad applications for detecting SPGs and uncovering which biological processes play important roles in governing cellular organization.

Anticipating and understanding cancers’ need for specific gene activities is key for novel therapeutic development. Here we utilized DepMap, a cancer gene dependency screen, to demonstrate that machine learning combined with network biology can produce robust algorithms that both predict what genes a cancer is dependent on and what network features coordinate such gene dependencies. Using network topology and biological annotations, we constructed four groups of novel engineered machine learning features that produced high accuracies when predicting binary gene dependencies. We found that in all examined cancer types, F1 scores were greater than 0.90, and model accuracy remained robust under multiple hyperparameter tests. We then deconstructed these models to identify tumor type-specific coordinators of gene dependency and identified that in certain cancers, such as thyroid and kidney, tumors’ dependencies are highly predicted by gene connectivity. In contrast, other histologies relied on pathway-based features such as lung, where gene dependencies were highly predictive by associations with cell death pathway genes. In sum, we show that biologically informed network features can be a valuable and robust addition to predictive pharmacology models while simultaneously providing mechanistic insights.

Abstract High grade glioma (HGG) represents a group of devastating diseases with dismal prognosis. Surgical resection of the contrast enhancing (CE) region of HGG remains the mainstay of treatment, but recurrence inevitably arises from the unresected non-contrast enhancing (NE) region, surgically inaccessible due to cancer cell invasion into healthy brain tissue. Due to its critical role in recurrence, understanding of the NE region is central to the improvement of clinical outcomes. We reveal the biological characteristics of this region through image localized multi-regional sampling. We linked microenvironmental characteristics measured by multi-parametric MRI to genomic mutations and transcriptional phenotypes using mixed effect modeling which allowed us to control for individualized patient effects. We first confirmed that T2 is a significant indicator of IDH mutation status in the NE region, being the first description of such a relationship in a HGG cohort. We found the combination of EGFR amplification and CDKN2A homozygous loss was associated with a significantly lower mean diffusivity (MD) compared to double wild type tumors in the NE region, indicating the presence of greater cellular packing and proliferation in EGFR amplification/CDKN2A loss regions. Finally, using single cell pathway based tumor classifications, we showed that nK2, a DSC-MRI metric representing cell size heterogeneity, correlated positively with neuronal signature and negatively with glycolytic/plurimetabolic signature within the NE tumor, indicating that glycolytic/plurimetobolic tumors possessed a high amount of cell size heterogeneity compared to neuronal samples. This hypothesis was supported using digital reference object (DRO) modeling which confirmed that cell size and heterogeneity drove the differential nK2 signal between neuronal and glycolytic/plurimetabolic samples. We identified immune cell infiltrate as one possible mechanism of increased cell size heterogeneity using transcriptomic signature analysis which found more immune cell signatures within glycolytic/plurimetobolic tumors compared to neuronal. Collectively this study demonstrates the central role of multi-parametric MRI as a non-invasive measure of tumor biology and a tool for understanding the clinically critical NE region which can then inform new therapies targeting this region of HGG recurrence. Citation Format: Matthew Flick, Taylor Weiskittel, Kevin Meng-Lin, Fulvio D'Angelo, Francesca Caruso, Shannon Ensign, Mylan Blomquist, Luija Wang, Christopher Sereduk, Gustavo De Leon, Ashley Nespodzany, Javier Urcuyo, Ashlynn Gonzalez, Lee Curtin, Kyle Singleton, Aliya Anil, Natenael Simmineh, Erika Lewis, Teresa Noviello, Reyna Patel, Panwen Wang, Junwen Wang, Jennifer Eschbacher, Andrea Hawkins-Daarud, Pamela Jackson, Kris Smith, Peter Nakaji, Bernard Bendok, Richard Zimmerman, Chandan Krishna, Devi Patra, Naresh Patel, Mark Lyons, Matthew Neal, Kliment Donev, Maciej Mrugala, Alyx Porter, Scott Beeman, Yuxiang Zhou, Leslie Baxter, Christopher Plaisier, Jing Li, Hu Li, Anna Lasorella, Chad Quarles, Kristin Swanson, Michele Ceccarelli, Antonio Iavarone, Nhan Tran, Leland Hu. Multi-parametric MRI maps regional heterogeneity of high grade glioma phenotypes. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5621.

Abstract Acquired PARP inhibitor (PARPi) resistance in BRCA1- or BRCA2-mutant ovarian cancer often results from secondary mutations that restore expression of functional protein. RAD51C is a less commonly studied ovarian cancer susceptibility gene whose promoter is sometimes methylated, leading to homologous recombination (HR) deficiency and PARPi sensitivity. For this study, the PARPi-sensitive patient-derived ovarian cancer xenograft PH039, which lacks HR gene mutations but harbors RAD51C promoter methylation, was selected for PARPi resistance by cyclical niraparib treatment in vivo. PH039 acquired PARPi resistance by the third treatment cycle and grew through subsequent treatment with either niraparib or rucaparib. Transcriptional profiling throughout the course of resistance development showed widespread pathway level changes along with a marked increase in RAD51C mRNA, which reflected loss of RAD51C promoter methylation. Analysis of ovarian cancer samples from the ARIEL2 Part 1 clinical trial of rucaparib monotherapy likewise indicated an association between loss of RAD51C methylation prior to on-study biopsy and limited response. Interestingly, the PARPi resistant PH039 model remained platinum sensitive. Collectively, these results not only indicate that PARPi treatment pressure can reverse RAD51C methylation and restore RAD51C expression, but also provide a model for studying the clinical observation that PARPi and platinum sensitivity are sometimes dissociated.

Abstract A key resistance mechanism to platinum-based chemotherapies and PARP inhibitors in BRCA-mutant cancers is the acquisition of BRCA reversion mutations that restore protein function. To estimate the prevalence of BRCA reversion mutations in high-grade ovarian carcinoma (HGOC), we performed targeted next-generation sequencing of circulating cell-free DNA (cfDNA) extracted from pretreatment and postprogression plasma in patients with deleterious germline or somatic BRCA mutations treated with the PARP inhibitor rucaparib. BRCA reversion mutations were identified in pretreatment cfDNA from 18% (2/11) of platinum-refractory and 13% (5/38) of platinum-resistant cancers, compared with 2% (1/48) of platinum-sensitive cancers (P = 0.049). Patients without BRCA reversion mutations detected in pretreatment cfDNA had significantly longer rucaparib progression-free survival than those with reversion mutations (median, 9.0 vs. 1.8 months; HR, 0.12; P < 0.0001). To study acquired resistance, we sequenced 78 postprogression cfDNA, identifying eight additional patients with BRCA reversion mutations not found in pretreatment cfDNA. Significance: BRCA reversion mutations are detected in cfDNA from platinum-resistant or platinum-refractory HGOC and are associated with decreased clinical benefit from rucaparib treatment. Sequencing of cfDNA can detect multiple BRCA reversion mutations, highlighting the ability to capture multiclonal heterogeneity. This article is highlighted in the In This Issue feature, p. 151

Abstract Background: Acquired PARP inhibitor (PARPi) resistance in high-grade serous ovarian cancer (HGSOC) as a result of restored homologous recombination has been observed following secondary mutations that restore full-length protein in BRCA1, BRCA2, RAD51C, and RAD51D. Additionally, loss of BRCA1 methylation has also been shown to confer resistance. However, little is known about the role of RAD51C methylation in acquired PARPi resistance. In ARIEL2 Part 1, a phase 2 study of the PARPi rucaparib in ovarian carcinoma, four (2%) tumors demonstrated RAD51C methylation. The present study utilizes HGSOC patient derived xenografts (PDXs) and recurrent samples from ARIEL2 to assess the role of RAD51C methylation in the development of PARPi resistance. Methods: To drive PARPi resistance, PDX039, an extremely PARPi-sensitive model lacking demonstrable mutations in DNA repair genes, was treated cyclically with niraparib (100 mg/kg) for 21 days, after which the tumor was allowed to regrow and re-established in new mice for the next treatment round. To evaluate the frequency of methylation change, RAD51C methylation was analyzed in 12 rucaparib-treated mice (300 or 450 mg/kg) harboring PDX183, a PARPi-sensitive model without mutations in DNA repair genes. Global changes in gene expression following development of PARPi resistance were assessed by RNA sequencing. RAD51C promoter methylation was evaluated by bisulfite sequencing. Subsequent functional analysis included qRT-PCR, IHC, and western blot. DNA damage response pathways are being evaluated by immunofluorescence ex vivo following niraparib, rucaparib, or IR. Results: PDX039 grew through PARPi treatment by the third and fourth cycle of therapy. RAD51C was the only DNA repair gene to show significant change in RNAseq analysis (log2 fold-change=8.43; p=2e-192), corresponding with a loss of RAD51C methylation. Moreover, after just one round of PARPi treatment, RAD51C methylation was lost in 1 of 12 PARPi-treated PDX183 xenografts. RAD51C methylation loss ultimately resulted in restoration of expression, for which functional analysis is ongoing. Analysis of patient samples is currently underway. Conclusions: In HGSOC PDX models, RAD51C methylation affords PARPi sensitivity in the absence of DNA repair gene mutations. Treatment pressure with PARPi can reverse RAD51C methylation and restore RAD51C expression. Isolated changes in methylation of the RAD51C locus are sufficient to restore HR and convey PARPi resistance. Citation Format: Rachel M. Hurley, Ksenija Nesic, Cordelia McGehee, Olga Kondrashova, Maria I. Harrell, Paula A. Schneider, Xiaonan Hou, Cristina Correia, Karen S. Flatten, Giada V. Zapparoli, Alexander Dobrovic, Kevin K. Lin, Thomas C. Harding, Andrea E. Wahner Hendrickson, Elizabeth M. Swisher, Matthew Wakefield, S. John Weroha, Clare L. Scott, Scott H. Kaufmann. Loss of RAD51C promoter hypermethylation confers PARP inhibitor resistance [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2018; 2018 Apr 14-18; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2018;78(13 Suppl):Abstract nr 5885.

Purpose Pancreatic cancer has a poor prognosis and limited treatment options. Approximately 9% of pancreatic cancers harbor a germline or somatic BRCA1 or BRCA2 ( BRCA1/2) mutation. Because poly (ADP-ribose) polymerase inhibitors have significant activity in BRCA1/2-mutant ovarian and breast cancers, RUCAPANC investigated the efficacy and safety of rucaparib in BRCA1/2-mutant pancreatic cancer. Patients and Methods RUCAPANC enrolled patients with measurable locally advanced/metastatic pancreatic cancer who had received one to two prior chemotherapy regimens. Patients received oral rucaparib (600 mg twice daily) until disease progression. The primary end point was objective response rate. Results Nineteen patients were enrolled. Sixteen of 19 BRCA1/2 mutations were germline; three were somatic. Patients had received a median of two prior chemotherapy regimens. Four patients achieved a response; two partial responses and one complete response (CR) were confirmed (objective response rate, 15.8%; 3 of 19), with an additional CR unconfirmed. The disease control rate (CR, partial response, or stable disease for ≥ 12 weeks) was 31.6% (6 of 19) in all patients and 44.4% (4 of 9) in those who had received one prior chemotherapy regimen. As prespecified in the protocol, enrollment was stopped because of an insufficient response rate among the first 15 patients. Treatment-emergent adverse events included nausea (63.2%) and anemia (47.4%). Grade ≥ 3 adverse events included anemia (31.6%), fatigue (15.8%), and ascites (15.8%). Secondary resistance mutations were detected in circulating free tumor DNA in two patients with a germline BRCA2 mutation. These mutations are predicted to lead to the reversion of a somatic—not germline—mutation. Conclusion Rucaparib provided clinical benefit to patients with advanced pancreatic cancer and a BRCA1/2 mutation, and demonstrated an acceptable safety profile. Additional trials of rucaparib in this population are warranted.