Tumor necrosis factor superfamily signaling: life and death in cancer.

Immune checkpoint inhibitors have shaped the landscape of cancer treatment. However, many patients either do not respond or suffer from later progression. Numerous proteins can control immune system activity, including multiple tumor necrosis factor (TNF) superfamily (TNFSF) and TNF receptor superfamily (TNFRSF) members; these proteins play a complex role in regulating cell survival and death, cellular differentiation, and immune system activity. Notably, TNFSF/TNFRSF molecules may display either pro-tumoral or anti-tumoral activity, or even both, depending on tumor type. Therefore, TNF is a prototype of an enigmatic two-faced mediator in oncogenesis. To date, multiple anti-TNF agents have been approved and/or included in guidelines for treating autoimmune disorders and immune-related toxicities after immune checkpoint blockade for cancer. A confirmed role for the TNFSF/TNFRSF members in treating cancer has proven more elusive. In this review, we highlight the cancer-relevant TNFSF/TNFRSF family members, focusing on the death domain-containing and co-stimulation members and their signaling pathways, as well as their complicated role in the life and death of cancer cells.

Constructing a personalized prognostic risk model for colorectal cancer using machine learning and multi-omics approach based on epithelial-mesenchymal transition-related genes.

The progression and the metastatic potential of colorectal cancer (CRC) are intricately linked to the epithelial-mesenchymal transition (EMT) process. The present study harnesses the power of machine learning combined with multi-omics data to develop a risk stratification model anchored on EMT-associated genes. The aim is to facilitate personalized prognostic assessments in CRC. We utilized publicly accessible gene expression datasets to pinpoint EMT-associated genes, employing a CoxBoost algorithm to sift through these genes for prognostic significance. The resultant model, predicated on gene expression levels, underwent rigorous independent validation across various datasets. Our model demonstrated a robust capacity to segregate CRC patients into distinct high- and low-risk categories, each correlating with markedly different survival probabilities. Notably, the risk score emerged as an independent prognostic indicator for CRC. High-risk patients were characterized by an immunosuppressive tumor milieu and a heightened responsiveness to certain chemotherapeutic agents, underlining the model's potential in steering tailored oncological therapies. Moreover, our research unearthed a putative repressive interaction between the long non-coding RNA PVT1 and the EMT-associated genes TIMP1 and MMP1, offering new insights into the molecular intricacies of CRC. In essence, our research introduces a sophisticated risk model, leveraging machine learning and multi-omics insights, which accurately prognosticates outcomes for CRC patients, paving the way for more individualized and effective oncological treatment paradigms.

TP53_PROF: a machine learning model to predict impact of missense mutations in TP53.

Correctly identifying the true driver mutations in a patient's tumor is a major challenge in precision oncology. Most efforts address frequent mutations, leaving medium- and low-frequency variants mostly unaddressed. For TP53, this identification is crucial for both somatic and germline mutations, with the latter associated with the Li-Fraumeni syndrome (LFS), a multiorgan cancer predisposition. We present TP53_PROF (prediction of functionality), a gene specific machine learning model to predict the functional consequences of every possible missense mutation in TP53, integrating human cell- and yeast-based functional assays scores along with computational scores. Variants were labeled for the training set using well-defined criteria of prevalence in four cancer genomics databases. The model's predictions provided accuracy of 96.5%. They were validated experimentally, and were compared to population data, LFS datasets, ClinVar annotations and to TCGA survival data. Very high accuracy was shown through all methods of validation. TP53_PROF allows accurate classification of TP53 missense mutations applicable for clinical practice. Our gene specific approach integrated machine learning, highly reliable features and biological knowledge, to create an unprecedented, thoroughly validated and clinically oriented classification model. This approach currently addresses TP53 mutations and will be applied in the future to other important cancer genes.

Current Status and Challenges in Rare Genitourinary Cancer Research and Future Directions.

PURPOSE OF REVIEW: In contemporary urological practice, managing rare genitourinary (GU) malignancies presents significant challenges, necessitating a comprehensive understanding of their unique characteristics and tailored treatment approaches. RECENT FINDINGS: Rare GU malignancies, whether per se, variants of common histologies, or common tumors in uncommon locations, often lack widely available clinical guidelines. Consequently, treatment decisions are frequently based on empirical evidence, risking suboptimal outcomes. However, recent advances in molecular profiling, targeted therapies, and immunotherapy offer promising avenues for improving management strategies and patient outcomes. This review provides a comprehensive overview of some rare GU malignancies encountered in clinical practice, including their distinct pathological features, current management approaches, and ongoing research directions. Understanding the complexities of these rare tumors and implementing multidisciplinary treatment strategies are essential for optimizing patient care and improving survival outcomes.

The personalized cancer network explorer (PeCaX) as a visual analytics tool to support molecular tumor boards.

BACKGROUND: Personalized oncology represents a shift in cancer treatment from conventional methods to target specific therapies where the decisions are made based on the patient specific tumor profile. Selection of the optimal therapy relies on a complex interdisciplinary analysis and interpretation of these variants by experts in molecular tumor boards. With up to hundreds of somatic variants identified in a tumor, this process requires visual analytics tools to guide and accelerate the annotation process. RESULTS: The Personal Cancer Network Explorer (PeCaX) is a visual analytics tool supporting the efficient annotation, navigation, and interpretation of somatic genomic variants through functional annotation, drug target annotation, and visual interpretation within the context of biological networks. Starting with somatic variants in a VCF file, PeCaX enables users to explore these variants through a web-based graphical user interface. The most protruding feature of PeCaX is the combination of clinical variant annotation and gene-drug networks with an interactive visualization. This reduces the time and effort the user needs to invest to get to a treatment suggestion and helps to generate new hypotheses. PeCaX is being provided as a platform-independent containerized software package for local or institution-wide deployment. PeCaX is available for download at https://github.com/KohlbacherLab/PeCaX-docker .

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.

Methods for the Detection of Circulating Biomarkers in Cancer Patients.

Liquid biopsy has emerged as one of the main pillars for personalized oncology. The term englobes body-fluid samples which contain tumor-derived material such as circulating tumor DNA (ctDNA), circulating tumor cells (CTCs), and circulating extracellular vesicles (cEVs). Potential clinical application of liquid biopsy analyses includes cancer screening, detection of minimal residual disease and recurrence, therapy selection, and evaluation of acquired resistance. Despite the great developments of technology focused on circulating biomarkers characterization only cfDNA testing is nowadays implemented for the therapy selection in some advanced tumors. This can be partially explained by the fact that there is still a lack of global standardization of procedures both in the pre-analytical and analytical steps. In the present chapter, we summarize the different strategies for addressing the study of liquid biopsy taking into account their pros and cons to be applied in a clinical context and we also discuss the main technical and clinical challenges in the field of circulating biomarkers and personalized oncology.

Patient-Derived Tumor Organoids for Guidance of Personalized Drug Therapies in Recurrent Glioblastoma.

An obstacle to effective uniform treatment of glioblastoma, especially at recurrence, is genetic and cellular intertumoral heterogeneity. Hence, personalized strategies are necessary, as are means to stratify potential targeted therapies in a clinically relevant timeframe. Functional profiling of drug candidates against patient-derived glioblastoma organoids (PD-GBO) holds promise as an empirical method to preclinically discover potentially effective treatments of individual tumors. Here, we describe our establishment of a PD-GBO-based functional profiling platform and the results of its application to four patient tumors. We show that our PD-GBO model system preserves key features of individual patient glioblastomas in vivo. As proof of concept, we tested a panel of 41 FDA-approved drugs and were able to identify potential treatment options for three out of four patients; the turnaround from tumor resection to discovery of treatment option was 13, 14, and 15 days, respectively. These results demonstrate that this approach is a complement and, potentially, an alternative to current molecular profiling efforts in the pursuit of effective personalized treatment discovery in a clinically relevant time period. Furthermore, these results warrant the use of PD-GBO platforms for preclinical identification of new drugs against defined morphological glioblastoma features.

Personalized Immuno-Oncology.

Cancer immunotherapy, which aims to control the immune system to eradicate cancer cells and prevent their spread, needs to be personalized because anticancer immune responses can be inhibited in several ways that vary from patient to patient. Cancer immunotherapy includes pharmaceuticals such as immune checkpoint inhibitors and monoclonal antibodies (MAbs) as well as cell therapy, immunogene therapy, and vaccines. Combination of programmed cell death protein 1 (PD-1)/programmed cell death protein ligand 1 (PD-L1) drugs with other immunotherapy drugs, for example, antibody-drug conjugates, as well as combination of PD-1/PD-L1 drugs with other therapies, for example, chemotherapy and radiation therapy, are being explored. Biomarkers are important for predicting the response to immunotherapy. Molecular diagnostics and sequencing are important technologies for guiding treatment in immuno-oncology. Genomic profiling of tumor mutational burden may enhance the predictive utility of PD-L1 expression and facilitate personalized combination immunotherapy. Optimization of personalized immuno-oncology requires integration of several technologies and selection of those best suited for an individual patient. Advances in immuno-oncology are also attributed to technologies for targeted delivery of anticancer therapeutics such as antigen-capturing nanoparticles for precision targeting and selective delivery. A breakthrough in cell therapy of cancer is a chimeric antigen receptors-T cell, which combines the antigen-binding site of a MAb with the signal activating machinery of a T cell, freeing antigen recognition from major histocompatibility complex restriction. Gene-editing tools such as clustered regularly interspaced short palindromic repeats have a promising application for removing alloreactivity and decreasing immunogenicity of third-party T cells. In conclusion, personalized immuno-oncology is one of the most promising approaches to management of cancer.

Leveraging TCGA gene expression data to build predictive models for cancer drug response.

BACKGROUND: Machine learning has been utilized to predict cancer drug response from multi-omics data generated from sensitivities of cancer cell lines to different therapeutic compounds. Here, we build machine learning models using gene expression data from patients' primary tumor tissues to predict whether a patient will respond positively or negatively to two chemotherapeutics: 5-Fluorouracil and Gemcitabine. RESULTS: We focused on 5-Fluorouracil and Gemcitabine because based on our exclusion criteria, they provide the largest numbers of patients within TCGA. Normalized gene expression data were clustered and used as the input features for the study. We used matching clinical trial data to ascertain the response of these patients via multiple classification methods. Multiple clustering and classification methods were compared for prediction accuracy of drug response. Clara and random forest were found to be the best clustering and classification methods, respectively. The results show our models predict with up to 86% accuracy; despite the study's limitation of sample size. We also found the genes most informative for predicting drug response were enriched in well-known cancer signaling pathways and highlighted their potential significance in chemotherapy prognosis. CONCLUSIONS: Primary tumor gene expression is a good predictor of cancer drug response. Investment in larger datasets containing both patient gene expression and drug response is needed to support future work of machine learning models. Ultimately, such predictive models may aid oncologists with making critical treatment decisions.

Use of Fluorescence In Situ Hybridization (FISH) in Diagnosis and Tailored Therapies in Solid Tumors.

Fluorescence in situ hybridization (FISH) is a standard technique used in routine diagnostics of genetic aberrations. Thanks to simple FISH procedure is possible to recognize tumor-specific abnormality. Its applications are limited to designed probe type. Gene rearrangements e.g., ALK, ROS1 reflecting numerous translocational partners, deletions of critical regions e.g., 1p and 19q, gene fusions e.g., COL1A1-PDGFB, genomic imbalances e.g., 6p, 6q, 11q and amplifications e.g., HER2 are targets in personalized oncology. Confirmation of genetic marker is frequently a direct indication to start specific, targeted treatment. In other cases, detected aberration helps pathologists to better distinguish soft tissue sarcomas, or to state a final diagnosis. Our main goal is to show that applying FISH to formalin-fixed paraffin-embedded tissue sample (FFPE) enables assessing genomic status in the population of cells deriving from a primary tumor or metastasis. Although many more sophisticated techniques are available, like Real-Time PCR or new generation sequencing, FISH remains a commonly used method in many genetic laboratories.

VIST - a Variant-Information Search Tool for precision oncology.

BACKGROUND: Diagnosis and treatment decisions in cancer increasingly depend on a detailed analysis of the mutational status of a patient's genome. This analysis relies on previously published information regarding the association of variations to disease progression and possible interventions. Clinicians to a large degree use biomedical search engines to obtain such information; however, the vast majority of scientific publications focus on basic science and have no direct clinical impact. We develop the Variant-Information Search Tool (VIST), a search engine designed for the targeted search of clinically relevant publications given an oncological mutation profile. RESULTS: VIST indexes all PubMed abstracts and content from ClinicalTrials.gov. It applies advanced text mining to identify mentions of genes, variants and drugs and uses machine learning based scoring to judge the clinical relevance of indexed abstracts. Its functionality is available through a fast and intuitive web interface. We perform several evaluations, showing that VIST's ranking is superior to that of PubMed or a pure vector space model with regard to the clinical relevance of a document's content. CONCLUSION: Different user groups search repositories of scientific publications with different intentions. This diversity is not adequately reflected in the standard search engines, often leading to poor performance in specialized settings. We develop a search engine for the specific case of finding documents that are clinically relevant in the course of cancer treatment. We believe that the architecture of our engine, heavily relying on machine learning algorithms, can also act as a blueprint for search engines in other, equally specific domains. VIST is freely available at https://vist.informatik.hu-berlin.de/.

Prognostic value of Osteopontin (SPP1) in colorectal carcinoma requires a personalized molecular approach.

Stratification of colorectal cancer for better management and tangible clinical outcomes is lacking in clinical practice. To reach this goal, the identification of reliable biomarker(s) is a prerequisite to deliver personalized colorectal cancer theranostics. Osteopontin (SPP1) is a key extracellular matrix protein involved in several pathophysiological processes including cancer progression and metastasis. However, the exact molecular mechanisms regulating its expression, localization, and molecular functions in cancer are still poorly understood. This study was designed to investigate the SPP1 expression profiles in Saudi colorectal cancer patients, and to assess its prognostic value. Hundred thirty-four (134) archival paraffin blocks of colorectal cancer were collected from King Abdulaziz University Hospital, Saudi Arabia. Tissue microarrays were constructed, and automated immunohistochemistry was performed to evaluate SPP1 protein expression patterns in colorectal cancer. About 20% and 23% of our colorectal cancer samples showed high SPP1 cytoplasmic and nuclear expression patterns, respectively. Cytoplasmic SPP1 did not correlate with age, gender, tumor size, and location. However, significant correlations were observed with tumor grade (p = 0.008), tumor invasion (p = 0.01), and distant metastasis (p = 0.04). Kaplan-Meier survival analysis showed a significantly lower recurrence rate in patients with higher SPP1 cytoplasmic expression (p = 0.05). At multivariate analysis, high SPP1 cytoplasmic expression was an independent favorable prognostic marker (p = 0.02). However, nuclear SPP1 expression did not show any prognostic value (p = 0.712). Our results showed a particular SPP1 prognostic relevance that is not in line with most colorectal cancer previous studies that may be attributed to the molecular pathophysiology of our colorectal cancer cohort. Saudi Arabia has both specific genomic makeup and particular environment that could lead to distinctive molecular roots of cancer. SPP1 has several isoforms, tissue localizations and molecular functions, signaling pathways, and downstream molecular functions. Therefore, a more individualized approach for CRC studies and particularly SPP1 prognosis outcomes' assessment is highly recommended toward precision oncology.

Targeting the undruggable: immunotherapy meets personalized oncology in the genomic era.

Owing to recent advances in genomic technologies, personalized oncology is poised to fundamentally alter cancer therapy. In this paradigm, the mutational and transcriptional profiles of tumors are assessed, and personalized treatments are designed based on the specific molecular abnormalities relevant to each patient's cancer. To date, such approaches have yielded impressive clinical responses in some patients. However, a major limitation of this strategy has also been revealed: the vast majority of tumor mutations are not targetable by current pharmacological approaches. Immunotherapy offers a promising alternative to exploit tumor mutations as targets for clinical intervention. Mutated proteins can give rise to novel antigens (called neoantigens) that are recognized with high specificity by patient T cells. Indeed, neoantigen-specific T cells have been shown to underlie clinical responses to many standard treatments and immunotherapeutic interventions. Moreover, studies in mouse models targeting neoantigens, and early results from clinical trials, have established proof of concept for personalized immunotherapies targeting next-generation sequencing identified neoantigens. Here, we review basic immunological principles related to T-cell recognition of neoantigens, and we examine recent studies that use genomic data to design personalized immunotherapies. We discuss the opportunities and challenges that lie ahead on the road to improving patient outcomes by incorporating immunotherapy into the paradigm of personalized oncology.

Individualizing breast cancer treatment-The dawn of personalized medicine.

Identification of breast cancer not being a single disease but backed by multiple heterogeneous oncogenic subpopulations is of growing interest in developing personalized therapies to provide optimal outcomes. Through this review, we bring attention to evolution of tumor and microenvironment heterogeneity as a predominant challenge in stratifying therapies. Establishment of a 'precancer niche' serves as a prerequisite for genetically initiated cells to survive and promote neoplastic evolution towards clinically established cancer through development of tumor and its microenvironment. Additionally, continuous evolutionary interplay between tumor and recruited stromal cells along with many other components in the tumor microenvironment adds up to further complexity in developing targeted therapies. However, through continued excellence in developing high throughput technologies including the advent of single-nucleus sequencing, which makes it possible to sequence individual tumor cells, leads to improved abilities in decoding the heterogenic perturbations through reconstruction of tumor evolutionary lineages. Furthermore, simple liquid-biopsies in form of enumeration/characterization of circulating tumor cells and tumor microvesicles found in peripheral circulation, shed from distinct tumor lesions, show great promise as prospective biomarkers towards better prognosis in tailoring individualized therapies to breast cancer patients. Lastly, by means of network medicinal approaches, it is seemingly possible to develop a map of the cell's intricate wiring network, helping to identify appropriate interconnected protein networks through which the disease spreads, offering a more patient-specific outcome. Although these therapeutic interventions through designing personalized oncology-based trials are promising, owing to continuous tumor evolution, targeting genome instability survival pathways might become an economically viable alternative.

Anticancer activity of combination targeted therapy using cetuximab plus vemurafenib for refractory BRAF (V600E)-mutant metastatic colorectal carcinoma.

Mismatch-repair-deficient colorectal cancers often contain kinase-activating V600E BRAF mutations, but no clinical utility has yet been demonstrated in this setting for monotherapy using oral braf kinase inhibitors such as vemurafenib or dabrafenib. Recent studies have indicated that tumour resistance to braf inhibition is mediated by upregulated epidermal growth factor receptor (egfr) signalling, disruption of which is a routine treatment strategy in KRAS wild-type colorectal cancer. In this report, we describe the clinical course of a heavily pretreated patient who elected to receive off-label dual-targeted braf- and egfr-inhibitory therapy with good tolerance and apparent clinical benefit.

Spatially fractionated GRID radiation potentiates immune-mediated tumor control.

BACKGROUND: Tumor-immune interactions shape a developing tumor and its tumor immune microenvironment (TIME) resulting in either well-infiltrated, immunologically inflamed tumor beds, or immune deserts with low levels of infiltration. The pre-treatment immune make-up of the TIME is associated with treatment outcome; immunologically inflamed tumors generally exhibit better responses to radio- and immunotherapy than non-inflamed tumors. However, radiotherapy is known to induce opposing immunological consequences, resulting in both immunostimulatory and inhibitory responses. In fact, it is thought that the radiation-induced tumoricidal immune response is curtailed by subsequent applications of radiation. It is thus conceivable that spatially fractionated radiotherapy (SFRT), administered through GRID blocks (SFRT-GRID) or lattice radiotherapy to create areas of low or high dose exposure, may create protective reservoirs of the tumor immune microenvironment, thereby preserving anti-tumor immune responses that are pivotal for radiation success. METHODS: We have developed an agent-based model (ABM) of tumor-immune interactions to investigate the immunological consequences and clinical outcomes after 2 Gy × 35 whole tumor radiation therapy (WTRT) and SFRT-GRID. The ABM is conceptually calibrated such that untreated tumors escape immune surveillance and grow to clinical detection. Individual ABM simulations are initialized from four distinct multiplex immunohistochemistry (mIHC) slides, and immune related parameter rates are generated using Latin Hypercube Sampling. RESULTS: In silico simulations suggest that radiation-induced cancer cell death alone is insufficient to clear a tumor with WTRT. However, explicit consideration of radiation-induced anti-tumor immunity synergizes with radiation cytotoxicity to eradicate tumors. Similarly, SFRT-GRID is successful with radiation-induced anti-tumor immunity, and, for some pre-treatment TIME compositions and modeling parameters, SFRT-GRID might be superior to WTRT in providing tumor control. CONCLUSION: This study demonstrates the pivotal role of the radiation-induced anti-tumor immunity. Prolonged fractionated treatment schedules may counteract early immune recruitment, which may be protected by SFRT-facilitated immune reservoirs. Different biological responses and treatment outcomes are observed based on pre-treatment TIME composition and model parameters. A rigorous analysis and model calibration for different tumor types and immune infiltration states is required before any conclusions can be drawn for clinical translation.

Leveraging State-of-the-Art AI Algorithms in Personalized Oncology: From Transcriptomics to Treatment.

BACKGROUND: Continuous breakthroughs in computational algorithms have positioned AI-based models as some of the most sophisticated technologies in the healthcare system. AI shows dynamic contributions in advancing various medical fields involving data interpretation and monitoring, imaging screening and diagnosis, and treatment response and survival prediction. Despite advances in clinical oncology, more effort must be employed to tailor therapeutic plans based on each patient's unique transcriptomic profile within the precision/personalized oncology frame. Furthermore, the standard analysis method is not compatible with the comprehensive deciphering of significant data streams, thus precluding the prediction of accurate treatment options. METHODOLOGY: We proposed a novel approach that includes obtaining different tumour tissues and preparing RNA samples for comprehensive transcriptomic interpretation using specifically trained, programmed, and optimized AI-based models for extracting large data volumes, refining, and analyzing them. Next, the transcriptomic results will be scanned against an expansive drug library to predict the response of each target to the tested drugs. The obtained target-drug combination/s will be then validated using in vitro and in vivo experimental models. Finally, the best treatment combination option/s will be introduced to the patient. We also provided a comprehensive review discussing AI models' recent innovations and implementations to aid in molecular diagnosis and treatment planning. RESULTS: The expected transcriptomic analysis generated by the AI-based algorithms will provide an inclusive genomic profile for each patient, containing statistical and bioinformatics analyses, identification of the dysregulated pathways, detection of the targeted genes, and recognition of molecular biomarkers. Subjecting these results to the prediction and pairing AI-based processes will result in statistical graphs presenting each target's likely response rate to various treatment options. Different in vitro and in vivo investigations will further validate the selection of the target drug/s pairs. CONCLUSIONS: Leveraging AI models will provide more rigorous manipulation of large-scale datasets on specific cancer care paths. Such a strategy would shape treatment according to each patient's demand, thus fortifying the avenue of personalized/precision medicine. Undoubtedly, this will assist in improving the oncology domain and alleviate the burden of clinicians in the coming decade.

RNA biomarkers in cancer therapeutics: The promise of personalized oncology.

Cancer therapy is a rapidly evolving and constantly expanding field. Current approaches include surgery, conventional chemotherapy and novel biologic agents as in immunotherapy, that together compose a wide armamentarium. The plethora of choices can, however, be clinically challenging in prescribing the most suitable treatment for any given patient. Fortunately, biomarkers can greatly facilitate the most appropriate selection. In recent years, RNA-based biomarkers have proven most promising. These molecules that range from small noncoding RNAs to protein coding gene transcripts can be valuable in cancer management and especially in cancer therapeutics. Compared to their DNA counterparts which are stable throughout treatment, RNA-biomarkers are dynamic. This allows prediction of success prior to treatment start and can identify alterations in expression that could reflect response. Moreover, improved nucleic acid technology allows RNA to be extracted from practically every biofluid/matrix and evaluated with exceedingly high analytic sensitivity. In addition, samples are largely obtained by minimally invasive procedures and as such can be used serially to assess treatment response real-time. This chapter provides the reader insight on currently known RNA biomarkers, the latest research employing Artificial Intelligence in the identification of such molecules and in clinical decisions driving forward the era of personalized oncology.