Precision Cancer Medicine Research Articles

1235P Enrichment of rare cancers in pragmatic precision cancer medicine trial: Experience from IMPRESS-Norway

1235P Enrichment of rare cancers in pragmatic precision cancer medicine trial: Experience from IMPRESS-Norway

174TiP A pivotal clinical trial of a functional ex vivo organ culture assay for cancer precision medicine

174TiP A pivotal clinical trial of a functional ex vivo organ culture assay for cancer precision medicine

A cell-level discriminative neural network model for diagnosis of blood cancers.

Precise identification of cancer cells in patient samples is essential for accurate diagnosis and clinical monitoring but has been a significant challenge in machine learning approaches for cancer precision medicine. In most scenarios, training data are only available with disease annotation at the subject or sample level. Traditional approaches separate the classification process into multiple steps that are optimized independently. Recent methods either focus on predicting sample-level diagnosis without identifying individual pathologic cells or are less effective for identifying heterogeneous cancer cell phenotypes. We developed a generalized end-to-end differentiable model, the Cell Scoring Neural Network (CSNN), which takes sample-level training data and predicts the diagnosis of the testing samples and the identity of the diagnostic cells in the sample, simultaneously. The cell-level density differences between samples are linked to the sample diagnosis, which allows the probabilities of individual cells being diagnostic to be calculated using backpropagation. We applied CSNN to two independent clinical flow cytometry datasets for leukemia diagnosis. In both qualitative and quantitative assessments, CSNN outperformed preexisting neural network modeling approaches for both cancer diagnosis and cell-level classification. Post hoc decision trees and 2D dot plots were generated for interpretation of the identified cancer cells, showing that the identified cell phenotypes match the cancer endotypes observed clinically in patient cohorts. Independent data clustering analysis confirmed the identified cancer cell populations. The source code of CSNN and datasets used in the experiments are publicly available on GitHub (http://github.com/erobl/csnn). Raw FCS files can be downloaded from FlowRepository (ID: FR-FCM-Z6YK).

The TRIPLEX study: use of patient-derived tumor organoids as an innovative tool for precision medicine in triple-negative breast cancer

BackgroundTriple negative breast cancers (TNBC) account for approximately 15% of all breast cancers and are associated with a shorter median survival mainly due to locally advanced tumor and high risk of metastasis. The current neoadjuvant treatment for TNBC consists of a regimen of immune checkpoint blocker and chemotherapy (chemo-ICB). Despite the frequent use of this combination for TNBC treatment, moderate results are observed and its clinical benefit in TNBC remains difficult to predict. Patient-derived tumor organoids (PDTO) are 3D in vitro cellular structures obtained from patient’s tumor samples. More and more evidence suggest that these models could predict the response of the tumor from which they are derived. PDTO may thus be used as a tool to predict chemo-ICB efficacy in TNBC patients.MethodThe TRIPLEX study is a single-center observational study conducted to investigate the feasibility of generating PDTO from TNBC and to evaluate their ability to predict clinical response. PDTO will be obtained after the dissociation of biopsies and embedding into extra cellular matrix. PDTO will be cultured in a medium supplemented with growth factors and signal pathway inhibitors. Molecular and histological analyses will be performed on established PDTO lines to validate their phenotypic proximity with the original tumor. Response of PDTO to chemo-ICB will be assessed using co-cultures with autologous immune cells collected from patient blood samples. PDTO response will finally be compared with the response of the patient to evaluate the predictive potential of the model.DiscussionThis study will allow to assess the feasibility of using PDTO as predictive tools for the evaluation of the response of TNBC patients to treatments. In the event that PDTO could faithfully predict patient response in clinically relevant time frames, a prospective clinical trial could be designed to use PDTO to guide clinical decision. This study will also permit the establishment of a living biobank of TNBC PDTO usable for future innovative strategies evaluation.Trial registrationThe clinical trial (version 1.2) has been validated by local research ethic committee on December 30th 2021 and registered at ClinicalTrials.gov with the identifier NCT05404321 on June 3rd 2022, version 1.2.

Hopes, concerns, satisfaction and regret in a precision medicine trial for childhood cancer: a mixed-methods study of parent and patient perspectives

BackgroundPaediatric precision oncology aims to match therapeutic agents to driver gene targets. We investigated whether parents and patients regret participation in precision medicine trials, particularly when their hopes are unfulfilled.MethodsParents and adolescent patients completed questionnaires at trial enrolment (T0) and after receiving results (T1). Parents opted-in to an interview at T1. Bereaved parents completed a questionnaire 6-months post-bereavement (T1B). We analysed quantitative data with R and qualitative data thematically with NVivo, before integrating all data for interpretation.Results182 parents and 23 patients completed T0; 108/182 parents and 8/23 patients completed T1; 27/98 bereaved parents completed T1B; and 45/108 parents were interviewed. At enrolment, participants held concurrent hopes that precision medicine would benefit future children and their child. Participants expressed concern regarding wait-times for receipt of results. Most participants found the trial beneficial and not burdensome, including bereaved parents. Participants reported high trial satisfaction (median scores: parents: 93/100; patients: 80/100). Participants expressed few regrets (parent median scores: parents: 10/100; bereaved parents: 15/100; patient regret: 2/8 expressed minimal regret).ConclusionsEven when trial outcomes did not match their hopes, parents and patients rarely regretted participating in a childhood cancer precision medicine trial. These data are critical for integrating participants’ views into future precision medicine delivery.

A biobank of pediatric patient-derived-xenograft models in cancer precision medicine trial MAPPYACTS for relapsed and refractory tumors

Pediatric patients with recurrent and refractory cancers are in most need for new treatments. This study developed patient-derived-xenograft (PDX) models within the European MAPPYACTS cancer precision medicine trial (NCT02613962). To date, 131 PDX models were established following heterotopical and/or orthotopical implantation in immunocompromised mice: 76 sarcomas, 25 other solid tumors, 12 central nervous system tumors, 15 acute leukemias, and 3 lymphomas. PDX establishment rate was 43%. Histology, whole exome and RNA sequencing revealed a high concordance with the primary patient’s tumor profile, human leukocyte-antigen characteristics and specific metabolic pathway signatures. A detailed patient molecular characterization, including specific mutations prioritized in the clinical molecular tumor boards are provided. Ninety models were shared with the IMI2 ITCC Pediatric Preclinical Proof-of-concept Platform (IMI2 ITCC-P4) for further exploitation. This PDX biobank of unique recurrent childhood cancers provides an essential support for basic and translational research and treatments development in advanced pediatric malignancies.

Biomarker-Directed Therapy in Black and White Men With Metastatic Castration-Resistant Prostate Cancer

Black men have higher incidence and mortality from prostate cancer. Whether precision oncology disparities affect Black men with metastatic castration-resistant prostate cancer (mCRPC) is unknown. To compare precision medicine data and outcomes between Black and White men with mCRPC. This retrospective cohort study used data collected by the Prostate Cancer Precision Medicine Multi-Institutional Collaborative Effort (PROMISE) consortium, a multi-institutional registry with linked clinicogenomic data, from April 2020 to December 2021. Participants included Black and White patients with mCRPC with molecular data. Data were analyzed from December 2021 to May 2023. Database-reported race and ethnicity. The primary outcome was the frequency of actionable molecular data, defined as the presence of mismatch repair deficiency (MMRD) or high microsatellite instability (MSI-H), homologous recombination repair deficiency, or tumor mutational burden of 10 mutations per megabase or greater. Secondary outcomes included the frequency of other alterations, the type and timing of genomic testing performed, and use of targeted therapy. Efficacy outcomes were prostate-specific antigen response rate, site-reported radiographic response, and overall survival. A total of 962 eligible patients with mCRPC were identified, including 204 Black patients (21.2%; median [IQR] age at diagnosis, 61 [55-67] years; 131 patients [64.2%] with Gleason scores 8-10; 92 patients [45.1%] with de novo metastatic disease) and 758 White patients (78.8%; median [IQR] age, 63 [57-69] years; 445 patients [58.7%] with Gleason scores 8-10; 310 patients [40.9%] with de novo metastatic disease). Median (IQR) follow-up from mCRPC was 26.6 (14.2-44.7) months. Blood-based molecular testing was more common in Black men (111 men [48.7%]) than White men (317 men [36.4%]; P < .001). Rates of actionable alterations were similar between groups (65 Black men [32.8%]; 215 White men [29.1%]; P = .35), but MMRD or MSI-H was more common in Black men (18 men [9.1]) than White men (36 men [4.9%]; P = .04). PTEN alterations were less frequent in Black men than White men (31 men [15.7%] vs 194 men [26.3%]; P = .003), as were TMPRSS alterations (14 men [7.1%] vs 155 men [21.0%]; P < .001). No other differences were seen in the 15 most frequently altered genes, including TP53, AR, CDK12, RB1, and PIK3CA. Matched targeted therapy was given less frequently in Black men than White men (22 men [33.5%] vs 115 men [53.5%]; P = .008). There were no differences in response to targeted therapy or survival between the two cohorts. This cohort study of men with mCRPC found higher frequency of MMRD or MSI-H and lower frequency of PTEN and TMPRSS alterations in Black men compared with White men. Although Black men received targeted therapy less frequently than White men, no differences were observed in clinical outcomes.

Precision Medicine for Gastric Cancer: Applicability from the Perspective of Helicobacter pylori Infection

Precision Medicine for Gastric Cancer: Applicability from the Perspective of Helicobacter pylori Infection

Current status and issues in genomic analysis using EUS-FNA/FNB specimens in hepatobiliary-pancreatic cancers.

Comprehensive genomic profiling based on next-generation sequencing has recently been used to provide precision medicine for various advanced cancers. Endoscopic ultrasound (EUS)-guided fine-needle aspiration (EUS-FNA) and EUS-guided fine-needle biopsy (EUS-FNB) play essential roles in the diagnosis of abdominal masses, mainly pancreatic cancers. In recent years, CGP analysis using EUS-FNA/FNB specimens for hepatobiliary-pancreatic cancers has increased; however, the success rate of CGP analysis is not clinically satisfactory, and many issues need to be resolved to improve the success rate of CGP analysis. In this article, we review the transition from EUS-FNA to FNB, compare each test, and discuss the current status and issues in genomic analysis of hepatobiliary-pancreatic cancers using EUS-FNA/FNB specimens.

Pharmacogenetic and liquid biopsy: The new tools of precision medicine in cancer

The main difficulty in the treatment of cancer lies in the already known mechanism of resistance to conventional chemotherapy. It is mainly due to the expression of the multidrug transport systems known as ABC transporters, both in neoplastic cells and in excretory organs that reduce the chemotherapeutic concentration. The cancer cell proliferation by activation of growth factor receptors induces their intrinsic tyrosine kinase activity, and their intracellular signaling pathways involved in such activation. Tumor proliferation can respond to the direct action of growth factors on their respective receptors, or due to somatic mutations in different steps of their signaling pathway, in an independent manner of growth factor stimulus. Pharmacogenetics studies have been performed to identify these drivers&amp;rsquo; mutations and their detection enables targeted inhibitory therapies against their abnormal proteins. The design of new molecules capable of inhibiting these signals has opened a new line of treatment for each type of tumor, thereby enabling tumor growth control and giving rise to the precision medicine approach. It is possible that mutations of sensitive and resistant to these targeted therapies coexist in the same tumor, from the start of therapy or as a consequence of the first-line treatment. The mutations in circulating DNA in body fluids, which are detected and quantified by droplet digital polymerase chain reaction-assisted liquid biopsy, are the ideal biomarkers for the evaluation of pharmacological response, which is crucial for facilitating the change of therapeutic strategy involving second- or third-generation drugs. The quantification of these mutations can be used to assess minimal residual disease in the therapeutic follow-up of each case.

Precision Medicine in Head and Neck Cancer: Tailoring Therapies to Molecular Profiles

Head and neck cancer refers to a diverse range of cancers with intricate molecular profiles that require individualised treatment strategies. Oncology is being revolutionised by precision medicine, which provides customised medicines based on unique tumour features. The aim of this review is to examine the state of precision medicine in head and neck cancer and its future prospects. Molecular profiling, biomarker-driven therapy, developing technologies, obstacles, and clinical consequences are highlighted. To compile the most recent research findings and trends in precision oncology for head and neck tumours, a thorough study of the PubMed literature was carried out. A variety of genetic changes and signalling pathways have been revealed by molecular characterisation, underscoring the importance of biomarkers such as EGFR and PD-L1 in directing targeted therapy. Liquid biopsy and genomic sequencing are two emerging technologies that have the potential to improve molecular profiling. Widespread use is hampered by issues such tumour heterogeneity, tissue sample accessibility, and cost-effective deployment. In conclusion, there is potential for improving precision medicine for head and neck cancer through the combination of cutting-edge technologies, biomarker-driven treatments, and patient-centric methods. Reaching the most benefit of customised care requires overcoming obstacles and improving accessibility.

Precision cancer medicine: Concepts, current practice, and future developments.

Precision cancer medicine is a multidisciplinary team effort that requires involvement and commitment of many stakeholders including the society at large. Building on the success of significant advances in precision therapy for oncological patients over the last two decades, future developments will be significantly shaped by improvements in scalable molecular diagnostics in which increasingly complex multilayered datasets require transformation into clinically useful information guiding patient management at fast turnaround times. Adaptive profiling strategies involving tissue- and liquid-based testing that account for the immense plasticity of cancer during the patient's journey and also include early detection approaches are already finding their way into clinical routine and will become paramount. A second major driver is the development of smart clinical trials and trial concepts which, complemented by real-world evidence, rapidly broaden the spectrum of therapeutic options. Tight coordination with regulatory agencies and health technology assessment bodies is crucial in this context. Multicentric networks operating nationally and internationally are key in implementing precision oncology in clinical practice and support developing and improving the ecosystem and framework needed to turn invocation into benefits for patients. The review provides an overview of the diagnostic tools, innovative clinical studies, and collaborative efforts needed to realize precision cancer medicine.

Molecular biomarkers for facilitating genome‑directed precision medicine in gynecological cancer (Review).

Prominent recent advancements in cancer treatment include the development and clinical application of next-generation sequencing (NGS) technologies, alongside a diverse array of novel molecular targeting therapeutics. NGS has enabled the high-speed and low-cost sequencing of whole genomes in individual patients, which has opened the era of genome-based precision medicine. The development of numerous molecular targeting agents, including anti-VEGF antibodies, poly (ADP-ribose) polymerase inhibitors and immune checkpoint inhibitors, have all improved the efficacy of systemic cancer therapy. Accumulating bench and translational research evidence has led to identification of various cancer-related biomarker profiles. In particular, companion diagnostics have been developed for some of these biomarkers, which can be clinically applied and are now widely used for guiding cancer therapies. Selecting biomarkers accurately will improve therapeutic efficacy, avoid overtreatment, enable earlier diagnosis and reduce the cost of preventing and treating gynecological cancer. Therefore, biomarkers are fast becoming indispensable tools in the practice of genome-directed precision medicine. In the present review, the current evidence of cancer-related biomarkers in the field of gynecological oncology, their molecular interpretations and future perspectives are outlined. The aim of the present review is to provide potentially useful information for the formulation of clinical trials.

Next-Generation Sequencing in Breast Cancer Patients: Real-World Data for Precision Medicine.

Breast cancer is one of the most common causes of cancer-related death in females. Numerous drug-targetable biomarkers and predictive biomarkers have been developed. Some researchers have expressed doubts about the need for next-generation sequencing (NGS) studies in daily practice. This study analyzed the results of NGS studies on breast cancer at a single institute and evaluated the real-world applications of NGS data to precision medicine for breast cancer. We retrospectively collected the results of NGS studies and analyzed the histopathologic features and genetic profiles of patients treated for breast cancer from 2010 to 2021. Seventy cases had data from CancerSCAN, a customized panel of 375 cancer-associated genes, and 110 cases had data from TruSight Oncology 500. The most frequently detected single nucleotide variant was the TP53 mutation (123/180, 68.3%), followed by PIK3CA mutations (51/180, 28.3%). Estrogen receptor 1 (ESR1) mutation was detected in 11 patients (6.1%), of whom 10 had hormone receptor-positive, human epidermal growth factor receptor 2-negative breast cancer, and two had no history of prior endocrine therapy. Based on their NGS study results, 13 patients (7.2%) received target therapy. Among them, four patients had a BRCA1 or BRCA2 germline mutation, and nine patients had a PIK3CA mutation. NGS can provide information about predictive biomarkers and drug-targetable biomarkers that can enable treatment and participation in clinical trials based on precision medicine. Further studies should be conducted to excavate novel drug-targetable biomarkers and develop additional target therapies.

Deciphering the Biology of Circulating Tumor Cells through Single-Cell RNA Sequencing: Implications for Precision Medicine in Cancer.

Circulating tumor cells (CTCs) hold unique biological characteristics that directly involve them in hematogenous dissemination. Studying CTCs systematically is technically challenging due to their extreme rarity and heterogeneity and the lack of specific markers to specify metastasis-initiating CTCs. With cutting-edge technology, single-cell RNA sequencing (scRNA-seq) provides insights into the biology of metastatic processes driven by CTCs. Transcriptomics analysis of single CTCs can decipher tumor heterogeneity and phenotypic plasticity for exploring promising novel therapeutic targets. The integrated approach provides a perspective on the mechanisms underlying tumor development and interrogates CTCs interactions with other blood cell types, particularly those of the immune system. This review aims to comprehensively describe the current study on CTC transcriptomic analysis through scRNA-seq technology. We emphasize the workflow for scRNA-seq analysis of CTCs, including enrichment, single cell isolation, and bioinformatic tools applied for this purpose. Furthermore, we elucidated the translational knowledge from the transcriptomic profile of individual CTCs and the biology of cancer metastasis for developing effective therapeutics through targeting key pathways in CTCs.

The future of lymphoma diagnosis, prognosis, and treatment monitoring in countries with limited access to pathology services

The world is moving towards precision medicine for cancer. This movement goes hand in hand with the development of newer advanced technologies for early, precise diagnosis of cancer and personalized treatment plans with fewer adverse effects for the patient. Liquid biopsy is one such advancement. At the same time, it has the advantage of minimal invasion and avoids serial invasive biopsies. In countries with limited access to pathology services, such as sub-Saharan Africa, liquid biopsy may provide an opportunity for early detection and prognostication of lymphoma. We discuss the current diagnostic modalities for lymphoma, highlighting the existing challenges with tissue biopsy, and how feasible it is for countries with limited pathology resources to leverage advancements made in the clinical application of liquid biopsy to improve lymphoma care.

Personalized K-Track assay to detect actionable mutations and minimal residual disease in solid tumors.

110 Background: Minimal residual disease (MRD) refers to a small number of cancer cells that remain in the body after curative-intent treatment, causing relapse and metastasis. Current tumor biomarkers and imaging methods have limited sensitivity and specificity to monitor MRD for solid tumors. Circulating tumor DNA (ctDNA) in liquid biopsy has emerged as a promising biomarker to detect MRD but current ctDNA assays remain mostly inaccessible and unaffordable for developing countries. Methods: In this prospective multi-center study, 441 Vietnamese patients diagnosed with breast, colorectal, gastric, lung, liver and ovarian cancers, eligible for curative-intent surgery were recruited. Genomic DNA from tumor tissue and paired white blood cells were sequenced to profile all tumor-derived genomic alterations including actionable mutations in 95 cancer-associated genes. Our bioinformatic algorithm then ranked top alterations unique for individual patient, which were then used to monitor ctDNA presence in serial plasma samples collected before surgery and at scheduled visits after surgery by multiplex PCR and ultra-deep sequencing. Results: The assay had limit of detection for somatic mutations down to at least 0.05% variant allele frequency in liquid biopsy.The sensitivity to detect ctDNA in the pre-operative plasma was 91%, 95%, 70%, 77%, 69% and 47% for colorectal, liver, lung, ovarian, high-risk breast cancer and gastric cancer respectively; the specificity was &gt;99%. After 18-month follow-up, our interim analysis revealed a promising 89% detection rate of post-operative ctDNA in all patients that had metastasis and recurrence (31/35), with the lead time of 2.5-13 months ahead of clinical diagnosis. Conclusions: The K-Track assay is streamlined and affordable with dual clinical utilities in residual cancer surveillance and actionable mutation profiling for targeted therapies. The assay could lay foundation to empower precision cancer medicine in Vietnam and developing countries.

Predicting anticancer drug sensitivity on distributed data sources using federated deep learning

Drug sensitivity prediction plays a crucial role in precision cancer therapy. Collaboration among medical institutions can lead to better performance in drug sensitivity prediction. However, patient privacy and data protection regulation remain a severe impediment to centralized prediction studies. For the first time, we proposed a federated drug sensitivity prediction model with high generalization, combining distributed data sources while protecting private data. Cell lines are first classified into three categories using the waterfall method. Focal loss for solving class imbalance is then embedded into the horizontal federated deep learning framework, i.e., HFDL-fl is presented. Applying HFDL-fl to homogeneous and heterogeneous data, we obtained HFDL-Cross and HFDL-Within. Our comprehensive experiments demonstrated that (i) collaboration by HFDL-fl outperforms private model on local data, (ii) focal loss function can effectively improve model performance to classify cell lines in sensitive and resistant categories, and (iii) HFDL-fl is not significantly affected by data heterogeneity. To summarize, HFDL-fl provides a valuable solution to break down the barriers between medical institutions for privacy-preserving drug sensitivity prediction and therefore facilitates the development of cancer precision medicine and other privacy-related biomedical research.

Application of the Multi-Omics Liquid Biopsy Method M2P-HCC in Early Liver Cancer Screening for High-Risk Individuals with Hepatitis B-Related Liver Cancer.

Hepatocellular carcinoma (HCC) is one of the most common malignant tumors worldwide, with low rates of early diagnosis and surgical resection. In recent years, with the rapid development of liquid biopsy technology, circulating tumor DNA (ctDNA) has emerged as a research hotspot in the field of precision medicine for liver cancer. Existing studies have demonstrated the suitability of ctDNA for combined detection with other liver cancer diagnostic markers, enabling a multi-index analysis. In recent years, a novel prediction model has been developed for early liver cancer screening based on ctDNA liquid biopsy, M2P-HCC (methylation, mutation, and protein-HCC), mainly incorporating methylation changes, gene mutations, and protein markers associated with liver cancer. Preliminary validation in the HCCscreenTM Investigational (HIT, ChiCTR1800020233) study, which focused on screening early liver cancer in communities with Hepatitis B surface antigen (HBsAg) positivity, yielded promising results with 100% sensitivity and 94% specificity. However, it remains uncertain whether M2P-HCC can be effectively applied in high-risk populations for Hepatitis B-associated liver cancer, warranting further research. Patients who were under long-term follow-up at the outpatient clinic of the Infectious Diseases Center of West China Hospital of Sichuan University from December 2020 to January 2023 were recruited in this prospective observational study and underwent the M2P-HCC test. The study population consisted of high-risk patients with Hepatitis B-related liver cancer who met the inclusion criteria. Patients with a history of previous malignancy, recent blood transfusion, autoimmune diseases, and human immunodeficiency virus (HIV) infection were excluded. Clinical data were collected at a baseline, and all patients underwent the M2P-HCC blood test. Based on the test results, they were categorized into positive, early-warning, and negative groups. Prospective cohort observation and regular follow-ups were performed for 6-8 months. 313 patients met the inclusion criteria and were included in the study. After 6-8 months of follow-up, HCC occurred in 41(13.1%) participants. The M2P-HCC test demonstrated good predictive performance with an area under the curve (AUC) of 0.88 (95% CI: 0.81-0.95, p < 0.001) and a cutoff value of 83 points (sensitivity 82.9% and specificity 85.7%). In contrast, the combination of alpha-fetoprotein (AFP) and ultrasound (US) yielded an inferior predictive performance (AUC 0.76 (95% CI: 0.69-0.84, p < 0.001), sensitivity 58.5%, and specificity 94.1%). Multivariate analyses revealed that M2P-HCC was an independent predictor of increased risk of HCC (OR = 1.16 [1.09-1.22], p < 0.001). M2P-HCC liquid biopsy demonstrated good performance for early liver cancer screening in high-risk populations of Hepatitis B-related liver cancer, exhibiting better sensitivity than the combination of AFP and US.

Ensemble learning model for identifying the hallmark genes of NFκB/TNF signaling pathway in cancers

BackgroundThe nuclear factor kappa B (NFκB) regulatory pathways downstream of tumor necrosis factor (TNF) play a critical role in carcinogenesis. However, the widespread influence of NFκB in cells can result in off-target effects, making it a challenging therapeutic target. Ensemble learning is a machine learning technique where multiple models are combined to improve the performance and robustness of the prediction. Accordingly, an ensemble learning model could uncover more precise targets within the NFκB/TNF signaling pathway for cancer therapy.MethodsIn this study, we trained an ensemble learning model on the transcriptome profiles from 16 cancer types in the TCGA database to identify a robust set of genes that are consistently associated with the NFκB/TNF pathway in cancer. Our model uses cancer patients as features to predict the genes involved in the NFκB/TNF signaling pathway and can be adapted to predict the genes for different cancer types by switching the cancer type of patients. We also performed functional analysis, survival analysis, and a case study of triple-negative breast cancer to demonstrate our model's potential in translational cancer medicine.ResultsOur model accurately identified genes regulated by NFκB in response to TNF in cancer patients. The downstream analysis showed that the identified genes are typically involved in the canonical NFκB-regulated pathways, particularly in adaptive immunity, anti-apoptosis, and cellular response to cytokine stimuli. These genes were found to have oncogenic properties and detrimental effects on patient survival. Our model also could distinguish patients with a specific cancer subtype, triple-negative breast cancer (TNBC), which is known to be influenced by NFκB-regulated pathways downstream of TNF. Furthermore, a functional module known as mononuclear cell differentiation was identified that accurately predicts TNBC patients and poor short-term survival in non-TNBC patients, providing a potential avenue for developing precision medicine for cancer subtypes.ConclusionsIn conclusion, our approach enables the discovery of genes in NFκB-regulated pathways in response to TNF and their relevance to carcinogenesis. We successfully categorized these genes into functional groups, providing valuable insights for discovering more precise and targeted cancer therapeutics.