Precision Medicine In Oncology Research Articles

Transforming oral cancer care: The promise of deep learning in diagnosis

The diagnosis and treatment of oral cancer present significant challenges, including delayed diagnosis at advanced stages and limited access to healthcare. Deep learning (DL), a subset of artificial intelligence, holds promise for transforming medical image analysis and predictive analytics. In this perspective, we examine the applications of DL in oral cancer. Specifically, we explore the efficacy of convolutional neural networks (CNNs) and recurrent neural networks (RNNs) in diagnosing and predicting the prognosis of oral cancer in the last five years. Additionally, we underscore the importance of oral cancer databases in advancing research and clinical practice. However, DL methods face constraints related to input variability and model interpretability. Addressing these issues is crucial to harnessing the full potential of DL in oral cancer treatment. In summary, this article underscores the innovative contributions of DL in revolutionizing oral cancer management and advocating for precision medicine in oncology.

Targeting KRAS Diversity: Covalent Modulation of G12X and Beyond in Cancer Therapy.

The GTPase KRAS acts as a switch in cellular signaling, transitioning between inactive GDP-bound and active GTP-bound states. In about 20% of human cancers, oncogenic RAS mutations disrupt this balance, favoring the active form and promoting proliferative signaling, thus rendering KRAS an appealing target for precision medicine in oncology. In 2013, Shokat and co-workers achieved a groundbreaking feat by covalently targeting a previously undiscovered allosteric pocket (switch II pocket (SWIIP)) of KRASG12C. This breakthrough led to the development and approval of sotorasib (AMG510) and adagrasib (MRTX849), revolutionizing the treatment of KRASG12C-dependent lung cancer. Recent achievements in targeting various KRASG12X mutants, using SWIIP as a key binding pocket, are discussed. Insights from successful KRASG12C targeting informed the design of molecules addressing other mutations, often in a covalent manner. These findings offer promise for innovative approaches in addressing commonly occurring KRAS mutations such as G12D, G12V, G12A, G12S, and G12R in various cancers.

Abstract LB396: The power of NetraAI: Precision medicine in oncology through sub-insight learning from small data sets

Abstract The capabilities of artificial intelligence (AI) and machine learning (ML) are pivotal for refining patient stratification and subtype discrimination in clinical trials. Conventional ML methods often rely on large data sets for meaningful discoveries. NetraAI is a novel ML approach designed and trained to work with smaller data sets. The challenge with smaller data sets is that they do not reflect the totality of the disease that they represent. NetraAI employs a novel approach termed “Sub-Insight Learning”, utilizing validated mathematical methods to analyze even small patient data sets. This allows the system to decompose the data sets into high and low confidence patient subpopulations, enhancing predictive model accuracy and reducing overfitting. Further, the system explains what variables are driving the etiology defining the subpopulations of patients. Using two non-small cell lung cancer (NSCLC) data sets (GSE18842 and GSE10245) consisting of only 104 samples from adenocarcinoma (ADC) and squamous cell carcinoma (SCC), NetraAI distinguished the two subtypes through unique genetic signatures. Notably, nine of the ten variables identified correlate with known NSCLC markers, with PIGX emerging as a novel target. Leveraging protein-protein interaction networks (PPI) revealed connections between PIGX and BACE1. BACE1 has been implicated as a driver of NSCLC brain metastasis. These findings shed light on the biology of membrane proteins and their post-translational modifications, a factor implicated in various diseases, prompting further exploration. NetraAI demonstrates a significant breakthrough in precision medicine for oncology, capable of generating meaningful insights from small data sets. The discovery of novel biomarkers and their implications in cancer and other diseases underline the potential of this AI-driven approach in advancing current research paradigms and patient-specific treatments. Citation Format: Bessi Qorri, Mike J. Tsay, Paul Leonchyk, Larry Alphs, Luca Pani, Joseph Geraci. The power of NetraAI: Precision medicine in oncology through sub-insight learning from small data sets [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(7_Suppl):Abstract nr LB396.

Abstract 1470: Advancing cancer research: A novel PanCancer digital PCR tool for simultaneous detection of multiple hallmark mutations in BRAF and EGFR

Abstract The paradigm shift towards precision medicine in oncology emphasizes the importance of identifying specific genetic mutations driving cancer. Some hallmark mutations in cancer-associated genes, such as BRAF and EGFR, are important in analyzing many cancer types. With the emergence of digital PCR (dPCR) technology, high-sensitivity and quantitative mutation analysis can be performed, lending valuable support to cancer research. In this work, we introduce a new and innovative dPCR method, the dPCR PanCancer assays (RUO), designed for concurrently detecting multiple hallmark mutations in BRAF and EGFR. This work includes two novel PanCancer assays for BRAF and EGFR, each tailored to target a spectrum of mutations associated with these genes, facilitating a comprehensive mutation analysis. The dPCR assay for BRAF targets multiple V600 hallmark mutations, and the dPCR assay for EGFR targets various important deletions on exon 19. This also includes a reference gene as a control for PCR efficiency in the duplex reaction. Here, we present our initial data from various sample types, including blood, plasma and FFPE samples. Through a meticulously optimized dPCR setup, we achieved exceptional sensitivity and specificity, enabling the detection of multiple mutations in a single channel at allelic frequencies below 1%. Both dPCR PanCancer Kits (RUO) have potential use in research for pre-screening samples (e.g., prior to next-generation sequencing) or monitoring cancer cells. They simultaneously assess the mutations, reducing time and costs and saving sample material. Additionally, our technology is adaptable to other cancer-associated genes, where similar assays can potentially be developed. Overall, we have demonstrated that our dPCR PanCancer Kits (RUO) provide a robust, fast and efficient technology to identify critical mutations, ultimately enhancing our understanding of BRAF and EGFR-driven cancers. The dPCR PanCancer Kit is for research use only. Not for the diagnosis, prevention, or treatment of a disease. Citation Format: Claudia Kappmeier, Sherina Edward, Corinna Hochstein, Ellen Inga Bruske, Francesca Di Pasquale, Ronny Kellner. Advancing cancer research: A novel PanCancer digital PCR tool for simultaneous detection of multiple hallmark mutations in BRAF and EGFR [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 1470.

A Review on Patient-Derived 3D Micro Cancer Approach for Drug Screen in Personalized Cancer Medicine.

Precision medicine in oncology aims to identify an individualized treatment plan based on genomic alterations in a patient's tumor. It helps to select the most beneficial therapy for an individual patient. As it is now known that no patient's cancer is the same, and therefore, different patients may respond differently to conventional treatments, precision medicine, which replaces the one-size-fits-all approach, supports the development of tailored treatments for specific cancers of different patients. Patient-specific organoid or spheroid models as 3D cell culture models are very promising for predicting resistance to anti-cancer drugs and for identifying the most effective cancer therapy for high-throughput drug screening combined with genomic analysis in personalized medicine. Because tumor spheroids incorporate many features of solid tumors and reflect resistance to drugs and radiation, as in human cancers, they are widely used in drug screening studies. Testing patient-derived 3D cancer spheroids with some anticancer drugs based on information from molecular profiling can reveal the sensitivity of tumor cells to drugs and provide the right compounds to be effective against resistant cells. Given that many patients do not respond to standard treatments, patient-specific treatments will be more effective, less toxic. They will affect survival better compared to the standard approach used for all patients.

Use of next-generation sequencing in daily routine practice

Developments in molecular diagnosis and implementation of mutation-driven targeted therapy marked a milestone in cancer treatment. Next-generation sequencing allows sequencing of a high number of nucleotides in a short time and from a limited quantity of pathology or cytology specimens. This is a review of actual indications, utility of next-generation sequencing, and availability of targeted therapies in different neoplasms. We present the European Society for Medical Oncology Precision Medicine Working Group recommendations for tumor multigene sequencing use with the Scale for Clinical Actionability of molecular Targets ranking determined for each alteration.

Latest trends in cancer clinical trials using genomics

Background: Recent advances in molecular biology and genomics have revolutionized the understanding of the intricate molecular underpinnings of cancer. Next-generation sequencing analysis now allows identification of specific actionable genetic alterations. This breakthrough has paved the way for precision medicine in oncology, redefining the conventional clinical trial landscape and enabling personalized approaches to cancer treatment.Current Concepts: The shift toward precision medicine involves a fundamental departure from the traditional Phases 1–4 clinical trial protocols. Instead of using uniform treatment pathways, personalized therapies are designed based on the genetic profiles of individual patients. Tumor-agnostic clinical trials are becoming as a prominent concept, encompassing innovative adaptive designs that adapt treatments to specific genetic variations. Master protocols such as umbrella studies, basket trials, platform studies, and master observational trials exemplify this transformation.Discussion and Conclusion: International precision medicine research is characterized by exemplar studies such as the NCI-MATCH study in the United States, the Drug Rediscovery Protocol study in the Netherlands, and the Targeted Agent and Profiling Utilization Registry study in the United States. Korean oncology research also contributed to the international effort in precision medicine through initiatives like K-MASTER and the Korean Precision Medicine Networking Group, which is making commendable contributions to the global precision medicine movements.

[Precision medicine in oncology].

Personalized oncology according to current practice is primarily based on tumor biology, which is translated into genomic biomarkers. Mutations in oncogenes and tumor suppressor genes are targeted by rationally designed drugs and, conversely, are used to inform tailored treatment strategies. Faster and cheaper technologies for DNA sequencing enable genomic medicine in aclinical routine setting. Genomic features, tumor biology and clinical implications are integrated into individual therapy recommendations by molecular tumor boards, which have been established at many cancer centers in Germany and worldwide throughout recent years. This article discusses the promises and limitations of genomics-centered precision oncology and highlights future avenues and alternative approaches to individualize cancer treatment.

Applications of CRISPR-Cas9 for advancing precision medicine in oncology: from target discovery to disease modeling.

The clustered regularly interspaced short palindromic repeats (CRISPR) and CRISPR-associated protein 9 (Cas9) (CRISPR/Cas9) system is a powerful tool that enables precise and efficient gene manipulation. In a relatively short time, CRISPR has risen to become the preferred gene-editing system due to its high efficiency, simplicity, and programmability at low costs. Furthermore, in the recent years, the CRISPR toolkit has been rapidly expanding, and the emerging advancements have shown tremendous potential in uncovering molecular mechanisms and new therapeutic strategies for human diseases. In this review, we provide our perspectives on the recent advancements in CRISPR technology and its impact on precision medicine, ranging from target identification, disease modeling, and diagnostics. We also discuss the impact of novel approaches such as epigenome, base, and prime editing on preclinical cancer drug discovery.

RNA-Based Strategies for Cancer Therapy: In Silico Design and Evaluation of ASOs for Targeted Exon Skipping.

Precision medicine in oncology has made significant progress in recent years by approving drugs that target specific genetic mutations. However, many cancer driver genes remain challenging to pharmacologically target ("undruggable"). To tackle this issue, RNA-based methods like antisense oligonucleotides (ASOs) that induce targeted exon skipping (ES) could provide a promising alternative. In this work, a comprehensive computational procedure is presented, focused on the development of ES-based cancer treatments. The procedure aims to produce specific protein variants, including inactive oncogenes and partially restored tumor suppressors. This novel computational procedure encompasses target-exon selection, in silico prediction of ES products, and identification of the best candidate ASOs for further experimental validation. The method was effectively employed on extensively mutated cancer genes, prioritized according to their suitability for ES-based interventions. Notable genes, such as NRAS and VHL, exhibited potential for this therapeutic approach, as specific target exons were identified and optimal ASO sequences were devised to induce their skipping. To the best of our knowledge, this is the first computational procedure that encompasses all necessary steps for designing ASO sequences tailored for targeted ES, contributing with a versatile and innovative approach to addressing the challenges posed by undruggable cancer driver genes and beyond.

P10.10.B BIRC3 AS A PREDICTOR OF OUTCOME AND A NEW THERAPEUTIC TARGET IN TMZ RESISTANT GLIOBLASTOMA TUMORS

Abstract BACKGROUND Glioblastoma (GB) is the most aggressive malignant tumor of the central nervous system, with a highly unfavorable prognosis with a median survival of 15 months. The standard treatment consists of surgical resection, chemotherapy, and radiotherapy. Despite intense research, overall survival remains stagnant, with very few approved therapeutic agents. Understanding the mutational profile of a tumor is important to inform diagnosis and guide therapeutic options, as well as identify patients that may not respond to treatment. The key advantage of precision medicine in oncology is the ability to match the right drug to the right patient to help improve patient outcomes. Aside from MGMT promoter methylation and TMZ response, molecular biomarkers associated with therapeutic response or prognostic of survival are still lacking in GB. In a recent study, using NADH-fluorescence lifetime imaging (NADH-FLIM), as a new drug screening precision medicine ex-vivo approach, we perturbed IDH1/2 WT GB patients-derived vital tumors by TMZ treatment and obtained a stratification in TMZ sensitive (S) and non-sensitive (NS) tumors, identifying several genes differentially expressed between the two groups. MATERIAL AND METHODS In this study, we enlarged our previous glioblastoma case study by performing NADH-FLIM metabolic approach to test TMZ drug tumor response on several primary and recurrent ex-vivo live GB tumors. Transcriptome analysis was performed to molecularly characterize TMZ S and NS cases. Moreover, functional cellular experiments were carried on to explore biomarkers' efficiency. RESULTS The majority of the genes, found dysregulated in the previous study, showed the same directional regulation of expression and we confirmed, in TMZ-resistant samples, the statistically significant upregulation of BIRC3, a strong inhibitor of apoptosis. The large public TCGA data set provided an opportunity to fully assess the BIRC3 mRNA expression complementarity with the MGMT status as a predictor of outcome in several cohorts analyzed with different RNA analysis approaches. BIRC3 functioned as a prognostic factor of survival also in a French and Italian private glioblastoma cohort analyzed by RNAseq and RT-PCR, respectively. In addition, most importantly, we show that the drug AZD5582, which is a specific antagonist of BIRC3, combined with TMZ treatment, is able to revert TMZ resistance, by restoring apoptosis, in glioblastoma cell lines and in patients derived organoids that are non-sensitive to TMZ-treatment. Higher levels of BIRC3 mRNA expression are associated with AZD5582 efficacy. CONCLUSION Investigating the mRNA expression levels of BIRC3 in GB tumors can be used as a tool to predict survival and response to TMZ. Moreover, the presence of high levels of BIRC3 mRNA is indicative of a new therapeutic target in glioblastoma tumors that are resistant to standard TMZ therapy.

Framework for Implementing Individualised Dosing of Anti-Cancer Drugs in Routine Care: Overcoming the Logistical Challenges

Precision medicine in oncology involves identifying the ‘right drug’, at the ‘right dose’, for the right person. Currently, many orally administered anti-cancer drugs, particularly kinase inhibitors (KIs), are prescribed at a standard fixed dose. Identifying the right dose remains one of the biggest challenges to optimal patient care. Recently the Precision Dosing Group established the Accurate Dosing of Anti-cancer Patient-centred Therapies (ADAPT) Program to address individualised dosing; thus, use existing anti-cancer drugs more safely and efficiently. In this paper, we outline our framework, based on the Medical Research Council (MRC) framework, with a simple 6-step process and strategies which have led to the successful implementation of the ADAPT program in South Australia. Implementation strategies in our 6-step process involve: (1) Evaluate the evidence and identify the cancer drugs: Literature review, shadowing other experts, establishing academic partnerships, adaptability/flexibility; (2) Establishment of analytical equipment for drug assays for clinical purposes: assessment for readiness, accreditation, feasibility, obtaining formal commitments, quality assurance to all stakeholders; (3) Clinical preparation and education: educational material, conducted educational meetings, involve opinion leaders, use of mass media, promote network weaving, conduct ongoing training; (4) Blood collection, sample preparation and analyses: goods received procedures, critical control points (transport time); (5) Interpret and release results with recommendations: facilitate the relay of clinical data to providers; (6) Clinical application: providing ongoing consultation, identify early adopters, identify, and prepare champions. These strategies were selected from the 73 implementation strategies outlined in the Expert Recommendations for Implementing Change (ERIC) study. The ADAPT program currently provides routine plasma concentrations for patients on several orally administered drugs in South Australia and is currently in its evaluation phase soon to be published. Our newly established framework could provide great potential and opportunities to advance individualised dosing of oral anti-cancer drugs in routine clinical care.

How can we deliver on the promise of precision medicine in oncology and beyond? A practical roadmap for action.

Precision medicine (PM) is a form of personalized medicine that recognizes that individuals with the same condition may have different underlying factors and uses molecular information to provide tailored treatments. This approach can improve treatment outcomes and transform lives through favorable risk/benefit ratios, avoidance of ineffective interventions, and possible cost savings, as evidenced in the field of lung cancer and other oncology/therapeutic settings, including cardiac disease, diabetes, and rare diseases. However, the potential benefits of PM have yet to be fully realized. There are many barriers to the implementation of PM in clinical practice, including fragmentation of the PM landscape, siloed approaches to address shared challenges, unwarranted variation in availability and access to PM, lack of standardization, and limited understanding of patients'experience and needs throughout the PM pathway. We believe that a diverse, intersectoral multistakeholder collaboration, with three main pillars of activity: generation of data to demonstrate the benefit of PM, education to support informed decision-making, and addressing barriers across the patient pathway, is necessary to reach the shared goal of making PM an accessible and sustainable reality. Besides healthcare providers, researchers, policymakers/regulators/payers, and industry representatives, patients in particular must be equal partners and should be central to the PM approach-from early research through to clinical trials and approval of new treatments-to ensure it represents their entire experience and identifies barriers, solutions, and opportunities at the point of delivery. We propose a practical and iterative roadmap to advance PM and call for all stakeholders across the healthcare system to employ a collaborative, cocreated, patient-centered methodology to close gaps and fully realize the potential of PM.

[Precision medicine in oncology: what contribution to clinical practice?]

The concept of precision medicine refers to strategies that are designed to provide prevention and treatment based on the characteristics of each patient and the disease. One of the fields where the process of personalization has been very successful is oncology. The path between theory and clinical practice is, however, long and might be shortened by switching methodology, diagnostics, data collection and analysis, and placing a focus on patient-centered care.

HOPE (SOLTI-1903) breast cancer study: real-world, patient-centric, clinical practice study to assess the impact of genomic data on next treatment decision-choice in patients with locally advanced or metastatic breast cancer.

Metastatic breast cancer (mBC) causes nearly all BC-related deaths. Next-generation sequencing (NGS) technologies allow for the application of personalized medicine using targeted therapies that could improve patients' outcomes. However, NGS is not routinely used in the clinical practice and its cost induces access-inequity among patients. We hypothesized that promoting active patient participation in the management of their disease offering access to NGS testing and to the subsequent medical interpretation and recommendations provided by a multidisciplinary molecular advisory board (MAB) could contribute to progressively overcome this challenge. We designed HOPE (SOLTI-1903) breast cancer trial, a study where patients voluntarily lead their inclusion through a digital tool (DT). The main objectives of HOPE study are to empower mBC patients, gather real-world data on the use of molecular information in the management of mBC and to generate evidence to assess the clinical utility for healthcare systems. After self-registration through the DT, the study team validates eligibility criteria and assists patients with mBC in the subsequent steps. Patients get access to the information sheet and sign the informed consent form through an advanced digital signature. Afterwards, they provide the most recent (preferably) metastatic archival tumor sample for DNA-sequencing and a blood sample obtained at the time of disease progression for ctDNA analysis. Paired results are reviewed by the MAB, considering patient's medical history. The MAB provides a further interpretation of molecular results and potential treatment recommendations, including ongoing clinical trials and further (germline) genetic testing. Participants self-document their treatment and disease evolution for the next 2 years. Patients are encouraged to involve their physicians in the study. HOPE also includes a patient empowerment program with educational workshops and videos about mBC and precision medicine in oncology. The primary endpoint of the study was to describe the feasibility of a patient-centric precision oncology program in mBC patients when a comprehensive genomic profile is available to decide on a subsequent line of treatment. www.soltihope.com, identifier NCT04497285.

Multi-omics fusion analysis models with machine learning predict survival of HER2-negative metastatic breast cancer: a multicenter prospective observational study.

To the Editor: Oncology precision medicine aims to identify patients most likely to respond effectively to therapies. Efforts to establish a survival prediction model using a single platform have not yet met the precision medicine goals.[1] Circulating tumor DNA (ctDNA), assessed by liquid biopsy, is representative of tumor heterogeneity, and ctDNA levels hold the potential for monitoring treatment response.[2] Moreover, circulating tumor cells (CTCs) in the metastatic cascade have been identified as clinical factors associated with poor prognosis.[3] The added value obtained from multi-omics fusion analysis to improve predictive models requires further investigation.[4] This study was approved by the Independent Ethics Committee of the National Cancer Center (CH-BC-023), and written informed consent was obtained from all patients before their enrolment. In this study, we characterized the biological parameters extracted from a subset of enrolled patients with human epithelial growth factor receptor-2 (HER2) negative metastatic breast cancer (MBC) in the CAMELLIA study (ClinicalTrials.gov: NCT01917279). Seventy patients were treated with the docetaxel plus capecitabine (TX) chemotherapy regimen during the initial period, that is, capecitabine (1000 mg/m2, twice daily, days 1–14, every three weeks) in combination with docetaxel (75 mg/m2, day 1, every three weeks) for six cycles [Supplementary Table 1, https://links.lww.com/CM9/B458]. All patients underwent contrast-enhanced Computer Tomography (CT) (Discovery CT750/ GoldSeal Optima CT660, GE HealthCare Life Sciences, Chicago, IL, United States) with a scanning layer thickness of 5 mm and an interval of 0. Peripheral blood samples (5 mL, two tubes) were prospectively collected at baseline to perform next-generation sequencing of ctDNA and CTC analyses. We optimized CanPatrol®CTC enrichment technology (SurExam Bio-Tech Co., Ltd, Guangzhou, China) to detect CTC clusters. Targeted region capture and next-generation sequencing customized probes (Integrated DNA Technologies, Coralville, IA, United States) covering −1.5 Mbp genome and 1021 cancer-related genes were used to detect somatic variants in ctDNA [Supplementary Table 2, https://links.lww.com/CM9/B458]. Mutations were enriched using R package clusterProfiler (version 3.18.1, https://www.r-project.org) by querying the following annotated databases: Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) [Supplementary Figures 1 and 2, https://links.lww.com/CM9/B458]. We combined ctDNA and CTC features by a fusion method based on canonical correlation analysis (CCA) to obtain a single feature matrix. corr(X*,Y*)=cov(X*,Y*)var(X*)⋅var(Y*) where X*=WxTX, Y*=WyTY. X and Y are two feature matrices; Wx and Wy are transformation matrices; cov(X*,Y*)=WxTSxyWy, var(X*)=WxTSxxWx, var(Y*)=WyTSyyWy. In this study, we used the summation method to obtain the fused feature vectors with the minimum rank of the original feature matrices: Z=X*+Y*=WxTX+WyTY where Z denotes the canonical correlation discriminant features. A total of 1218 quantitative CT radiomic features were extracted from regions of interest and manually segmented using Pyradiomics (version 3.0.1, https://github.com/Radiomics/pyradiomics) in Python (Python Software Foundation. Python Language Reference, version 2.7, available at http://www.python.org). Each patient feature was normalized to Z-scores, and dimension reduction was ensured by limiting the variance to a 0.010 threshold. We selected the features using the Wilcoxon–Mann–Whitney test with P value < 0.20, then conducted single-factor Cox regression, and selected the features with a concordance index (C-index) value >0.50. We performed a descriptive analysis of progression-free survival and overall survival (OS) as valid survival endpoints. Considering the restricted sample size, we performed leave-one-out cross-validation. The Youden index was chosen to divide the risk scores into high or low signatures. The Harrell C-index and time-dependent receiver operating characteristic (TD-ROC) curves, with quantified areas under the curves (AUCs), were calculated to evaluate and verify model performance. A flowchart of the process is shown in Supplementary Figure 3A, https://links.lww.com/CM9/B458. Seventy patients were enrolled in the study. Clinical characteristics are summarized in Supplementary Table 1, https://links.lww.com/CM9/B458. A total of 180 mutations were identified. GO and KEGG enrichment analysis showed 25 dimensions of breast cancer-associated genes with P = 1.91 × 10–18; Padjust = 3.96 × 10–16 [Supplementary Figure 4, https://links.lww.com/CM9/B458]. In the entire cohort, 950 CTCs were detected. Correlation analysis of CTCs showed more textural features than first-order and shaped features [Supplementary Table 3, https://links.lww.com/CM9/B458]. Supplementary Figure 5, https://links.lww.com/CM9/B458 shows the close association between the selected radiomic features and CTC/ctDNA genetic alterations. A series of prediction models were developed: (1) clinical features only, (2) clinical + CCA model, and (3) multi-omics fusion model. The C-index of the multi-omics fusion model was 0.725 (Hazard ratio [HR] 3.812, 95% confidence interval [CI] 2.245–6.472, P < 0.0001), which was superior to that of the other two models (P = 0.0086 and P = 0.0137, respectively) [Supplementary Tables 4–6 and Supplementary Figure 3B, https://links.lww.com/CM9/B458]. TD-ROC analysis assessed the accuracy of prognosis at specific time points of 1, 2, and 3 years, with an AUC ranging between 0.866 and 0.918 [Supplementary Figure 3B, https://links.lww.com/CM9/B458]. For OS prediction, the multi-omics fusion model also showed statistically significantly better performance, with a C-index of 0.811 (HR 5.992, 95% CI 3.145–11.419, P < 0.0001) [Supplementary Table 4 and Supplementary Figure 3B, https://links.lww.com/CM9/B458]. C-index comparison was performed to statistically validate the improvement of the multi-omics fusion model over the other two models (P < 0.0001, P < 0.0001) [Supplementary Tables 5–6, https://links.lww.com/CM9/B458]. In the TD-ROC analysis, the AUC of OS of multi-omics model was 0.815–0.989 [Supplementary Table 4 and Supplementary Figure 3B, https://links.lww.com/CM9/B458]. Further evaluation of the multi-omics fusion model also showed good predictive ability in the following subgroups: age <50 years, regardless of the number of metastatic organs, liver and lung metastases, and those who received prior adjuvant therapy and first-line endocrine therapy for metastasis [Supplementary Figures 6–8 https://links.lww.com/CM9/B458]. The response to treatment is modulated by a tumor ecosystem whose multi-omics landscape can be integrated into a predictive model by machine learning. Previously, efforts to identify predictive characteristics largely ignored this issue.[1] Taking advantage of important breakthroughs in CTC/ctDNA detection,[2,3] our pilot study features the innovative application of radiomics combined with liquid biopsy technique (ctDNA/CTC assay) to noninvasively provide more comprehensive information beyond visual perception. In the clinical workflow, predictive models can advance the clinical management of MBC and guide therapeutic strategies, ultimately leading to improved survival outcomes.[4] The tumor evolution in patients can be precisely predicted at a macroscopic level, represented by clinicopathological phenotypes and radiomics, as well as at the cellular level, represented by CTCs in liquid-based biopsies, and at the molecular level, represented by ctDNA. Although ctDNA and CTCs are seldom used simultaneously,[3] we hypothesized that serial analysis of both peripheral biomarkers would appeal more to patients. Here, we optimized the data fusion process, and established an efficient and accurate survival prediction algorithm model. These multi-omics fusion predictive models can help identify MBC candidates who may benefit from palliative chemotherapy. This study has some limitations. First, it was limited by its small sample size. A larger cohort study would help to optimize the cutoff values. Second, the prediction model may require further external prospective intervention studies to validate. In conclusion, our pretreatment multi-omics fusion models with machine learning effectively predicted the survival of HER2− MBC patients with good discrimination power and outperformed conventional clinicopathological models. This framework highlights the importance of data integration with machine learning and is widely used to generate predictors by including various newer features. Acknowledgements We sincerely thank the patients who participated and all the staff who assisted in this study. Funding This study was supported by the National Key Research and Development Program of China (2021YFF1201300 and 2021YFF1201003), the National Natural Science Foundation of China (Nos. 81971662, 92259301, 92159301 and 92059103), the Natural Science Foundation of Beijing City (7202105), and the Key Project of Beijing Hope Marathon Special Fund from the China Cancer Foundation (LC2018A20). Conflicts of interest None.

Abstract 5452: Complimentary use of DNA- and RNA-based NGS assays optimizes detection of clinically relevant translocations for comprehensive genomic profiling

Abstract Introduction: Detection of gene translocations is a key component of clinical diagnostics to enable precision medicine in oncology. Several methods such as fluorescence in situ hybridization or RT-PCR have historically been employed, however, next-generation sequencing (NGS)-based comprehensive genomic profiling (CGP) including DNA and RNA sequencing approaches have been validated for this purpose. Here we explore the complimentary nature of these methods to enable detection of clinically relevant translocations to guide patient care. Methods: We utilized Endeavor, a 505 gene DNA-based CGP assay developed by Personal Genome Diagnostics, to assess single nucleotide variants, insertion/deletions, amplifications, translocations, microsatellite instability, and tumor mutation burden as well as a 53 gene RNA-based Invitae NGS FusionPlex Solid Tumor v1 assay. 151 patients with advanced or metastatic solid tumors, including lung, colorectal, esophageal, breast, brain, bladder, and prostate cancers, were consecutively enrolled and only overlapping target regions were evaluated to compare performance. Results: Of the 151 cases selected for the study, failure rates were 2.0% and 9.9% for Endeavor and FusionPlex, respectively. Translocations were detected in 21/151 (13.9%) cases by Endeavor and 17/105 (11.3%) cases by FusionPlex. For the 133 cases where data was available from both assays, 12 (9.0%) concordant translocation positive cases were detected involving ALK, RET, NTRK1, NTRK3, MET exon 14 skipping, EGFRvIII, and EWSR1 with 109 (82.0%) cases translocation negative by both assays achieving a concordance rate of 91%. For 7 (5.3%) cases, Endeavor detected translocations events in FGFR1, FGFR2, ETV4, ETV6, MYC, and NTRK3 that were not detected by FusionPlex. Conversely, FusionPlex identified 5 (3.8%) cases with translocations in ROS1, NTRK2, and EGFRvIII that were not detected by Endeavor (Table 1). Discrepancies in translocation detection were attributed to variability in assay failure rates, panel design, and underlying biological differences in detectability associated with DNA- and RNA-based methods. Conclusions: In this study, comparison of translocation detection using DNA and RNA-based NGS approaches revealed a high concordance between the two assays and were equally valuable for identifying actionable targets. These findings provide confirmatory support for the complimentary use of DNA- and RNA-based NGS approaches to most accurately identify clinically relevant translocations thereby providing more comprehensive results to help guide cancer treatment strategies. Citation Format: Rongqin Ren, Jennifer Jackson, Jacob Kames, David Riles, Christopher Coldren, Scott Wheeler, Pranil Chandra, Michelle Shiller. Complimentary use of DNA- and RNA-based NGS assays optimizes detection of clinically relevant translocations for comprehensive genomic profiling. [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 5452.

Abstract 6403: A self-replicating RNA precision medicine approach to overcoming resistance to endocrine therapy in ER+BC

Abstract Drug resistance remains the major driving factor behind the clinical failure of targeted therapeutics. Current oncology precision medicine approaches rely on targeting known acquired resistance mutations, such as EGFR T790M or ALK/ROS mutations in NSCLC with 2nd and 3rd generation molecules designed to overcome or prevent resistance. These next generation targeted therapeutic approaches have increasingly long and complex drug development timelines and burdensome toxicities from off target effects (e.g. wild-type receptor targeting) or drug-drug interactions (DDI). The toxicities limit tolerability, compliance and combinability of different targeted therapeutics. RNA-based immunotherapy approaches offer an increasingly attractive alternative to next generation small molecule targeted therapeutics approaches: (1) RNA-based approaches only require a known acquired resistance sequence, (2) drug development timelines, cost and complexity can be meaningfully condensed, and (3) multiple acquired resistance mutations can be targeted with the same candidate. RBI-1000 is a candidate using a novel type of self-replicating RNA (srRNA) to generate robust immunity directed against acquired resistance mutations that develop in ER+ breast cancer (ER+ BC) in response to endocrine therapy. RBI-1000 includes on-target mutations within the estrogen receptor ligand binding domain, and bypass mutations either in the form of activating mutations in the PI3K kinase domain or amplifications of HER2/HER3. Here, we demonstrate that this srRNA encapsulated in a lipid nanoparticle primes polyfunctional CD4 and CD8 T cells leading to tumor growth inhibition and improved survival in a mouse model expressing the targeted acquired resistance mutation. Priming of T cells against acquired mutations is also confirmed in human HLA-transgenic mice. The immune cell-mediated elimination of clones expressing the acquired resistance mutations is predicted to prolong endocrine control of ER+BC, in an analogous manner to small molecule or monoclonal antibody targeted therapies, but with a more favorable dosing and adverse event profile due to precise immunologic targeting and no DDI. Citation Format: Zelanna Goldberg, Christian Maine, Gabrielle P. Dailey, Christine Domingo, Gaelle Picarda, Hunter Little, Annie Chou, Jessica Sparks, Darina Spasova, Shigeki Miyake-Stoner, Zachary C. Hartman, Christopher A. Rabiola, Erika J. Crosby, Herbert K. Lyerly, Nathaniel Wang, Parinaz Aliahmad. A self-replicating RNA precision medicine approach to overcoming resistance to endocrine therapy in ER+BC. [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 6403.

From Personalized to Precision Medicine in Oncology: A Model-Based Dosing Approach to Optimize Achievement of Imatinib Target Exposure.

Imatinib is a targeted cancer therapy that has significantly improved the care of patients with chronic myeloid leukemia (CML) and gastrointestinal stromal tumor (GIST). However, it has been shown that the recommended dosages of imatinib are associated with trough plasma concentration (Cmin) lower than the target value in many patients. The aims of this study were to design a novel model-based dosing approach for imatinib and to compare the performance of this method with that of other dosing methods. Three target interval dosing (TID) methods were developed based on a previously published PK model to optimize the achievement of a target Cmin interval or minimize underexposure. We compared the performance of those methods to that of traditional model-based target concentration dosing (TCD) as well as fixed-dose regimen using simulated patients (n = 800) as well as real patients' data (n = 85). Both TID and TCD model-based approaches were effective with about 65% of Cmin achieving the target imatinib Cmin interval of 1000-2000 ng/mL in 800 simulated patients and more than 75% using real data. The TID approach could also minimize underexposure. The standard 400 mg/24 h dosage of imatinib was associated with only 29% and 16.5% of target attainment in simulated and real conditions, respectively. Some other fixed-dose regimens performed better but could not minimize over- or underexposure. Model-based, goal-oriented methods can improve initial dosing of imatinib. Combined with subsequent TDM, these approaches are a rational basis for precision dosing of imatinib and other drugs with exposure-response relationships in oncology.

DJ-1 Oncogene as a Potential Diagnostic and Prognostic Biomarker for Head and Neck Cancer.

Background Current methods used to diagnose and prognosticate oropharyngeal cancer have contributed to unfavorable patientsurvival rates that have not significantly improved for the last several decades. Precision medicine oncology relies on molecular diagnostics and biomarkers to supplement existing methods of detecting and prognosticating cancers. This study evaluated the expression of DJ-1, an oncogene that is implicated in the pathogenesis of oral squamous cell carcinoma (OSCC), the most common type of head and neck cancer, to determine its utility as a diagnostic and prognostic biomarker. Methodology Immunohistochemistry (IHC) was performed on 13 normal oral mucosa tissue samples and 143 OSCC tissue samples of varying histopathological grades. Computer-assisted image analysis was performed using the Aperio ImageScope software from Leica Biosystems (Buffalo Grove, IL), which utilizes an algorithm of positive pixel counting for the quantification of immunoreactivity and the percentage of positive cell staining, generating a histo-score (H-score). The comparisons of the average H-scores of the different groups were made using a two-tailed T-test with P ≤ 0.05 set as the level of significance. Results The study found a significant increase in DJ-1 expression in oral squamous cell carcinoma tissue samples in comparison to the normal oral mucosa tissue samples. Additionally, the study documented a significant upregulation in DJ-1 expression in the OSCC tissue samples with high histopathological grades compared to the OSCC tissue samples with low histopathological grades. Conclusions DJ-1 expression patterns were able to reliably differentiate between oral squamous cell carcinoma and the normal counterpart tissues of the oral mucosa, thereby highlighting its role as a potential diagnostic biomarker. Moreover, DJ-1 expression significantly correlates with the OSCC histological grade, which serves as an indicator of the differentiation status and a predictor of the biological behavior of malignant neoplasms, adding to DJ-1's potential utility as a prognostic biomarker for this common type of head and neck cancer.