RESUMEN

The massive amount of human biological, imaging, and clinical data produced by multiple and diverse sources necessitates integrative modeling approaches able to summarize all this information into answers to specific clinical questions. In this paper, we present a hypermodeling scheme able to combine models of diverse cancer aspects regardless of their underlying method or scale. Describing tissue-scale cancer cell proliferation, biomechanical tumor growth, nutrient transport, genomic-scale aberrant cancer cell metabolism, and cell-signaling pathways that regulate the cellular response to therapy, the hypermodel integrates mutation, miRNA expression, imaging, and clinical data. The constituting hypomodels, as well as their orchestration and links, are described. Two specific cancer types, Wilms tumor (nephroblastoma) and non-small cell lung cancer, are addressed as proof-of-concept study cases. Personalized simulations of the actual anatomy of a patient have been conducted. The hypermodel has also been applied to predict tumor control after radiotherapy and the relationship between tumor proliferative activity and response to neoadjuvant chemotherapy. Our innovative hypermodel holds promise as a digital twin-based clinical decision support system and as the core of future in silico trial platforms, although additional retrospective adaptation and validation are necessary.

RESUMEN

Despite the remarkable advances in cancer diagnosis, treatment, and management over the past decade, malignant tumors remain a major public health problem. Further progress in combating cancer may be enabled by personalizing the delivery of therapies according to the predicted response for each individual patient. The design of personalized therapies requires the integration of patient-specific information with an appropriate mathematical model of tumor response. A fundamental barrier to realizing this paradigm is the current lack of a rigorous yet practical mathematical theory of tumor initiation, development, invasion, and response to therapy. We begin this review with an overview of different approaches to modeling tumor growth and treatment, including mechanistic as well as data-driven models based on big data and artificial intelligence. We then present illustrative examples of mathematical models manifesting their utility and discuss the limitations of stand-alone mechanistic and data-driven models. We then discuss the potential of mechanistic models for not only predicting but also optimizing response to therapy on a patient-specific basis. We describe current efforts and future possibilities to integrate mechanistic and data-driven models. We conclude by proposing five fundamental challenges that must be addressed to fully realize personalized care for cancer patients driven by computational models.

Asunto(s)

RESUMEN

Mutationsin epidermal growth factor receptor (EGFR) are found in approximately 48% of Asian and 19% of Western patients with lung adenocarcinoma (LUAD), leading to aggressive tumor growth. While tyrosine kinase inhibitors (TKIs) like gefitinib and osimertinib target this mutation, treatments often face challenges such as metastasis and resistance. To address this, we developed physiologically based pharmacokinetic (PBPK) models for both drugs, simulating their distribution within the primary tumor and metastases following oral administration. These models, combined with a mechanistic knowledge-based disease model of EGFR-mutated LUAD, allow us to predict the tumor's behavior under treatment considering the diversity within the tumor cells due to different mutations. The combined model reproduces the drugs' distribution within the body, as well as the effects of both gefitinib and osimertinib on EGFR-activation-induced signaling pathways. In addition, the disease model encapsulates the heterogeneity within the tumor through the representation of various subclones. Each subclone is characterized by unique mutation profiles, allowing the model to accurately reproduce clinical outcomes, including patients' progression, aligning with RECIST criteria guidelines (version 1.1). Datasets used for calibration came from NEJ002 and FLAURA clinical trials. The quality of the fit was ensured with rigorous visual predictive checks and statistical tests (comparison metrics computed from bootstrapped, weighted log-rank tests: 98.4% (NEJ002) and 99.9% (FLAURA) similarity). In addition, the model was able to predict outcomes from an independent retrospective study comparing gefitinib and osimertinib which had not been used within the model development phase. This output validation underscores mechanistic models' potential in guiding future clinical trials by comparing treatment efficacies and identifying patients who would benefit most from specific TKIs. Our work is a step towards the design of a powerful tool enhancing personalized treatment in LUAD. It could support treatment strategy evaluations and potentially reduce trial sizes, promising more efficient and targeted therapeutic approaches. Following its consecutive prospective validations with the FLAURA2 and MARIPOSA trials (validation metrics computed from bootstrapped, weighted log-rank tests: 94.0% and 98.1%, respectively), the model could be used to generate a synthetic control arm.

RESUMEN

The use of data-driven high-throughput analytical techniques, which has given rise to computational oncology, is undisputed. The widespread use of machine learning (ML) and mathematical modeling (MM)-based techniques is widely acknowledged. These two approaches have fueled the advancement in cancer research and eventually led to the uptake of telemedicine in cancer care. For diagnostic, prognostic, and treatment purposes concerning different types of cancer research, vast databases of varied information with manifold dimensions are required, and indeed, all this information can only be managed by an automated system developed utilizing ML and MM. In addition, MM is being used to probe the relationship between the pharmacokinetics and pharmacodynamics (PK/PD interactions) of anti-cancer substances to improve cancer treatment, and also to refine the quality of existing treatment models by being incorporated at all steps of research and development related to cancer and in routine patient care. This review will serve as a consolidation of the advancement and benefits of ML and MM techniques with a special focus on the area of cancer prognosis and anticancer therapy, leading to the identification of challenges (data quantity, ethical consideration, and data privacy) which are yet to be fully addressed in current studies.

RESUMEN

The early detection of colorectal cancer (CRC) through medical image analysis is a pivotal concern in healthcare, with the potential to significantly reduce mortality rates. Current Domain Adaptation (DA) methods strive to mitigate the discrepancies between different imaging modalities that are critical in identifying CRC, yet they often fall short in addressing the complexity of cancer's presentation within these images. These conventional techniques typically overlook the intricate geometrical structures and the local variations within the data, leading to suboptimal diagnostic performance. This study introduces an innovative application of the Discriminative Manifold Distribution Alignment (DMDA) method, which is specifically engineered to enhance the medical image diagnosis of colorectal cancer. DMDA transcends traditional DA approaches by focusing on both local and global distribution alignments and by intricately learning the intrinsic geometrical characteristics present in manifold space. This is achieved without depending on the potentially misleading pseudo-labels, a common pitfall in existing methodologies. Our implementation of DMDA on three distinct datasets, involving several unique DA tasks, has consistently demonstrated superior classification accuracy and computational efficiency. The method adeptly captures the complex morphological and textural nuances of CRC lesions, leading to a significant leap in domain adaptation technology. DMDA's ability to reconcile global and local distributional disparities, coupled with its manifold-based geometrical structure learning, signals a paradigm shift in medical imaging analysis. The results obtained are not only promising in terms of advancing domain adaptation theory but also in their practical implications, offering the prospect of substantially improved diagnostic accuracy and faster clinical workflows. This heralds a transformative approach in personalized oncology care, aligning with the pressing need for early and accurate CRC detection.

Asunto(s)

RESUMEN

Single cell computational analysis has emerged as a powerful tool in the field of oncology, enabling researchers to decipher the complex cellular heterogeneity that characterizes cancer. By leveraging computational algorithms and bioinformatics approaches, this methodology provides insights into the underlying genetic, epigenetic and transcriptomic variations among individual cancer cells. In this paper, we present a comprehensive overview of single cell computational analysis in oncology, discussing the key computational techniques employed for data processing, analysis, and interpretation. We explore the challenges associated with single cell data, including data quality control, normalization, dimensionality reduction, clustering, and trajectory inference. Furthermore, we highlight the applications of single cell computational analysis, including the identification of novel cell states, the characterization of tumor subtypes, the discovery of biomarkers, and the prediction of therapy response. Finally, we address the future directions and potential advancements in the field, including the development of machine learning and deep learning approaches for single cell analysis. Overall, this paper aims to provide a roadmap for researchers interested in leveraging computational methods to unlock the full potential of single cell analysis in understanding cancer biology with the goal of advancing precision oncology. For this purpose, we also include a notebook that instructs on how to apply the recommended tools in the Preprocessing and Quality Control section.

RESUMEN

Intraperitoneal (IP) chemotherapy is a promising treatment approach for patients diagnosed with peritoneal carcinomatosis, allowing the direct delivery of therapeutic agents to the tumor site within the abdominal cavity. Nevertheless, limited drug penetration into the tumor remains a primary drawback of this method. The process of delivering drugs to the tumor entails numerous complications, primarily stemming from the specific pathophysiology of the tumor. Investigating drug delivery during IP chemotherapy and studying the parameters affecting it are challenging due to the limitations of experimental studies. In contrast, mathematical modeling, with its capabilities such as enabling single-parameter studies, and cost and time efficiency, emerges as a potent tool for this purpose. In this study, we developed a numerical model to investigate IP chemotherapy by incorporating an actual image of a tumor with heterogeneous vasculature. The tumor's geometry is reconstructed using image processing techniques. The model also incorporates drug binding and uptake by cancer cells. After 60 min of IP treatment with Doxorubicin, the area under the curve (AUC) of the average free drug concentration versus time curve, serving as an indicator of drug availability to the tumor, reached 295.18 mol·m-3·s-1. Additionally, the half-width parameter W1/2, which reflects drug penetration into the tumor, ranged from 0.11 to 0.14 mm. Furthermore, the treatment resulted in a fraction of killed cells reaching 20.4% by the end of the procedure. Analyzing the spatial distribution of interstitial fluid velocity, pressure, and drug concentration in the tumor revealed that the heterogeneous distribution of tumor vasculature influences the drug delivery process. Our findings underscore the significance of considering the specific vascular network of a tumor when modeling intraperitoneal chemotherapy. The proposed methodology holds promise for application in patient-specific studies.

RESUMEN

We propose that an information technology and computational framework that would unify access to hospital digital information silos, and enable integration of this information using machine learning methods, would bring a new paradigm to patient management and research. This is the core principle of Integrated Diagnostics (ID): the amalgamation of multiple analytical modalities, with evolved information technology, applied to a defined patient cohort, and resulting in a synergistic effect in the clinical value of the individual diagnostic tools. This has the potential to transform the practice of personalized oncology at a time at which it is very much needed. In this article we present different models from the literature that contribute to the vision of ID and we provide published exemplars of ID tools. We briefly describe ongoing efforts within a universal healthcare system to create national clinical datasets. Following this, we argue the case to create "hospital units" to leverage this multi-modal analysis, data integration and holistic clinical decision-making. Finally, we describe the joint model created in our institutions.

RESUMEN

We employed supervised machine learning algorithms to a cohort of colorectal cancer patients from the NCI to differentiate and classify the heterogenous disease based on anatomical laterality and multi-omics stratification, in a first of its kind. Multi-omics integrative analysis shows distinct clustering of left and right colorectal cancer with disentangled representation of methylome and delineation of transcriptome and genome. We present novel multi-omics findings consistent with augmented hypermethylation of genes in right CRC, epigenomic biomarkers on the right in conjunction with immune-mediated pathway signatures, and lymphocytic invasion which unlocks unique therapeutic avenues. Contrarily, left CRC multi-omics signature is found to be marked by angiogenesis, cadherins, and epithelial-mesenchymal transition (EMT). An integrated multi-omics molecular signature of RNF217-AS1, hsa-miR-10b, and panel of FBX02, FBX06, FBX044, MAD2L2, and MIIP copy number altered genes have been found by the study. Overall survival analysis reveals genomic biomarkers ABCA13 and TTN in 852 LCRC cases, and SOX11 in 170 RCRC cases that predicts a significant survival benefit. Our study exemplifies the translational competence and robustness of machine learning in effective translational bridging of research and clinic. Supplementary Information: The online version contains supplementary material available at 10.1007/s13193-023-01760-6.

RESUMEN

T-cell-based immunotherapies hold tremendous potential in the fight against cancer, thanks to their capacity to specifically targeting diseased cells. Nevertheless, this potential has been tempered with safety concerns regarding the possible recognition of unknown off-targets displayed by healthy cells. In a notorious example, engineered T-cells specific to MAGEA3 (EVDPIGHLY) also recognized a TITIN-derived peptide (ESDPIVAQY) expressed by cardiac cells, inducing lethal damage in melanoma patients. Such off-target toxicity has been related to T-cell cross-reactivity induced by molecular mimicry. In this context, there is growing interest in developing the means to avoid off-target toxicity, and to provide safer immunotherapy products. To this end, we present CrossDome, a multi-omics suite to predict the off-target toxicity risk of T-cell-based immunotherapies. Our suite provides two alternative protocols, i) a peptide-centered prediction, or ii) a TCR-centered prediction. As proof-of-principle, we evaluate our approach using 16 well-known cross-reactivity cases involving cancer-associated antigens. With CrossDome, the TITIN-derived peptide was predicted at the 99+ percentile rank among 36,000 scored candidates (p-value < 0.001). In addition, off-targets for all the 16 known cases were predicted within the top ranges of relatedness score on a Monte Carlo simulation with over 5 million putative peptide pairs, allowing us to determine a cut-off p-value for off-target toxicity risk. We also implemented a penalty system based on TCR hotspots, named contact map (CM). This TCR-centered approach improved upon the peptide-centered prediction on the MAGEA3-TITIN screening (e.g., from 27th to 6th, out of 36,000 ranked peptides). Next, we used an extended dataset of experimentally-determined cross-reactive peptides to evaluate alternative CrossDome protocols. The level of enrichment of validated cases among top 50 best-scored peptides was 63% for the peptide-centered protocol, and up to 82% for the TCR-centered protocol. Finally, we performed functional characterization of top ranking candidates, by integrating expression data, HLA binding, and immunogenicity predictions. CrossDome was designed as an R package for easy integration with antigen discovery pipelines, and an interactive web interface for users without coding experience. CrossDome is under active development, and it is available at https://github.com/AntunesLab/crossdome.

Asunto(s)

RESUMEN

Mathematical models are a core component in the foundation of cancer theory and have been developed as clinical tools in precision medicine. Modeling studies for clinical applications often assume an individual's characteristics can be represented as parameters in a model and are used to explain, predict, and optimize treatment outcomes. However, this approach relies on the identifiability of the underlying mathematical models. In this study, we build on the framework of an observing-system simulation experiment to study the identifiability of several models of cancer growth, focusing on the prognostic parameters of each model. Our results demonstrate that the frequency of data collection, the types of data, such as cancer proxy, and the accuracy of measurements all play crucial roles in determining the identifiability of the model. We also found that highly accurate data can allow for reasonably accurate estimates of some parameters, which may be the key to achieving model identifiability in practice. As more complex models required more data for identification, our results support the idea of using models with a clear mechanism that tracks disease progression in clinical settings. For such a model, the subset of model parameters associated with disease progression naturally minimizes the required data for model identifiability.

RESUMEN

The computer simulation of organ-scale biomechanistic models of cancer personalized via routinely collected clinical and imaging data enables to obtain patient-specific predictions of tumor growth and treatment response over the anatomy of the patient's affected organ. These patient-specific computational forecasts have been regarded as a promising approach to personalize the clinical management of cancer and derive optimal treatment plans for individual patients, which constitute timely and critical needs in clinical oncology. However, the computer simulation of the underlying spatiotemporal models can entail a prohibitive computational cost, which constitutes a barrier to the successful development of clinically-actionable computational technologies for personalized tumor forecasting. To address this issue, here we propose to utilize dynamic-mode decomposition (DMD) to construct a low-dimensional representation of cancer models and accelerate their simulation. DMD is an unsupervised machine learning method based on the singular value decomposition that has proven useful in many applications as both a predictive and a diagnostic tool. We show that DMD may be applied to Fisher-Kolmogorov models, which constitute an established formulation to represent untreated solid tumor growth that can further accommodate other relevant cancer phenomena (e.g., therapeutic effects, mechanical deformation). Our results show that a DMD implementation of this model over a clinically relevant parameter space can yield promising predictions, with short to medium-term errors remaining under 1% and long-term errors remaining under 20%, despite very short training periods. In particular, we have found that, for moderate to high tumor cell diffusivity and low to moderate tumor cell proliferation rate, DMD reconstructions provide accurate, bounded-error reconstructions for all tested training periods. Additionally, we also show that the three-dimensional DMD reconstruction of the tumor field can be leveraged to accurately reconstruct the displacement fields of the tumor-induced deformation of the host tissue. Thus, we posit the proposed data-driven approach has the potential to greatly reduce the computational overhead of personalized simulations of cancer models, thereby facilitating tumor forecasting, parameter identification, uncertainty quantification, and treatment optimization.

Asunto(s)

RESUMEN

Immunotherapy has become a fourth pillar in the treatment of brain tumors and, when combined with radiation therapy, may improve patient outcomes and reduce the neurotoxicity. As with other combination therapies, the identification of a treatment schedule that maximizes the synergistic effect of radiation- and immune-therapy is a fundamental challenge. Mechanism-based mathematical modeling is one promising approach to systematically investigate therapeutic combinations to maximize positive outcomes within a rigorous framework. However, successful clinical translation of model-generated combinations of treatment requires patient-specific data to allow the models to be meaningfully initialized and parameterized. Quantitative imaging techniques have emerged as a promising source of high quality, spatially and temporally resolved data for the development and validation of mathematical models. In this review, we will present approaches to personalize mechanism-based modeling frameworks with patient data, and then discuss how these techniques could be leveraged to improve brain cancer outcomes through patient-specific modeling and optimization of treatment strategies.

Asunto(s)

RESUMEN

Intraperitoneal (IP) chemotherapy has emerged as a promising method for the treatment of peritoneal malignancies (PMs). However, microenvironmental barriers in the tumor limit the delivery of drug particles and their deep penetration into the tumor, leading to reduced efficiency of treatment. Therefore, new drug delivery systems should be developed to overcome these microenvironmental barriers. One promising technique is magnetically controlled drug targeting (MCDT) in which an external magnetic field is utilized to concentrate drug-coated magnetic nanoparticles (MNPs) to the desired area. In this work, a mathematical model is developed to investigate the efficacy of MCDT in IP chemotherapy. In this model, considering the mechanism of drug binding and internalization into cancer cells, the efficacy of drug delivery using MNPs is evaluated and compared with conventional IP chemotherapy. The results indicate that over 60 min of treatment with MNPs, drug penetration depth increased more than 13 times compared to conventional IPC. Moreover, the drug penetration area (DPA) increased more than 1.4 times compared to the conventional IP injection. The fraction of killed cells in the tumor in magnetic drug delivery was 6.5%, which shows an increase of more than 2.5 times compared to that of the conventional method (2.54%). Furthermore, the effects of magnetic strength, the distance of the magnet to the tumor, and the magnetic nanoparticles' size were evaluated. The results show that MDT can be used as an effective technique to increase the efficiency of IP chemotherapy.

RESUMEN

BACKGROUND: Evaluating histologic grade for breast cancer diagnosis is standard and associated with prognostic outcomes. Current challenges include the time required for manual microscopic evaluation and interobserver variability. This study proposes a computer-aided diagnostic (CAD) pipeline for grading tumors using artificial intelligence. METHODS: There were 138 patients included in this retrospective study. Breast core biopsy slides were prepared using standard laboratory techniques, digitized, and pre-processed for analysis. Deep convolutional neural networks (CNNs) were developed to identify the regions of interest containing malignant cells and to segment tumor nuclei. Imaging-based features associated with spatial parameters were extracted from the segmented regions of interest (ROIs). Clinical datasets and pathologic biomarkers (estrogen receptor, progesterone receptor, and human epidermal growth factor 2) were collected from all study subjects. Pathologic, clinical, and imaging-based features were input into machine learning (ML) models to classify histologic grade, and model performances were tested against ground-truth labels at the patient-level. Classification performances were evaluated using receiver-operating characteristic (ROC) analysis. RESULTS: Multiparametric feature sets, containing both clinical and imaging-based features, demonstrated high classification performance. Using imaging-derived markers alone, the classification performance demonstrated an area under the curve (AUC) of 0.745, while modeling these features with other pathologic biomarkers yielded an AUC of 0.836. CONCLUSION: These results demonstrate an association between tumor nuclear spatial features and tumor grade. If further validated, these systems may be implemented into pathology CADs and can assist pathologists to expeditiously grade tumors at the time of diagnosis and to help guide clinical decisions.

Asunto(s)

RESUMEN

The maintenance and function of tissues in health and disease depends on cell-cell communication. This work shows how high-level features, representing cell-cell communication, can be defined and used to associate certain signaling "axes" with clinical outcomes. We generated a scaffold of cell-cell interactions and defined a probabilistic method for creating per-patient weighted graphs based on gene expression and cell deconvolution results. With this method, we generated over 9,000 graphs for The Cancer Genome Atlas (TCGA) patient samples, each representing likely channels of intercellular communication in the tumor microenvironment (TME). It was shown that cell-cell edges were strongly associated with disease severity and progression, in terms of survival time and tumor stage. Within individual tumor types, there are predominant cell types, and the collection of associated edges were found to be predictive of clinical phenotypes. Additionally, genes associated with differentially weighted edges were enriched in Gene Ontology terms associated with tissue structure and immune response. Code, data, and notebooks are provided to enable the application of this method to any expression dataset (https://github.com/IlyaLab/Pan-Cancer-Cell-Cell-Comm-Net).

RESUMEN

PURPOSE: Metronomic chemotherapy (MC) is a promising approach where, in contrast to the conventional maximal tolerated dose (MTD) strategy, regular fractionated doses of the drug are used. This approach has proven its efficacy, although drug dosing and scheduling are often chosen empirically. Pharmacokinetic/pharmacodynamic (PK/PD) models provide a way to choose optimal protocols with computational methods. Existing models are usually too complicated and are valid for only a subset of drug schedules. To address this issue, we propose herein a simple model that can describe MC and MTD regimens simultaneously. METHODS: The minimal model comprises tumor suppression due to antiangiogenic drug effect together with a cell-kill term, responsible for its cytotoxicity. The model was tested on data obtained on tumor-bearing mice treated with gemcitabine in ether MTD, MC, or combined (MTD + MC) regimens. RESULTS: We conducted a number of tests in which data were divided in various ways into training and validation sets. The model successfully described different trends in the MTD and MC regimens. With parameters obtained by fitting the model to MTD data, the simulations correctly predicted trends in both the MC and combined therapy groups. CONCLUSION: Our results demonstrate that the proposed model presents a minimal yet efficient tool for modeling outcomes in different treatment regimens in mice. We hope that this model has the potential for use in clinical practice in the development of patient-specific chemotherapy scheduling protocols based on observed treatment response.

Asunto(s)

RESUMEN

Tumor-associated vasculature is responsible for the delivery of nutrients, removal of waste, and allowing growth beyond 2-3 mm3. Additionally, the vascular network, which is changing in both space and time, fundamentally influences tumor response to both systemic and radiation therapy. Thus, a robust understanding of vascular dynamics is necessary to accurately predict tumor growth, as well as establish optimal treatment protocols to achieve optimal tumor control. Such a goal requires the intimate integration of both theory and experiment. Quantitative and time-resolved imaging methods have emerged as technologies able to visualize and characterize tumor vascular properties before and during therapy at the tissue and cell scale. Parallel to, but separate from those developments, mathematical modeling techniques have been developed to enable in silico investigations into theoretical tumor and vascular dynamics. In particular, recent efforts have sought to integrate both theory and experiment to enable data-driven mathematical modeling. Such mathematical models are calibrated by data obtained from individual tumor-vascular systems to predict future vascular growth, delivery of systemic agents, and response to radiotherapy. In this review, we discuss experimental techniques for visualizing and quantifying vascular dynamics including magnetic resonance imaging, microfluidic devices, and confocal microscopy. We then focus on the integration of these experimental measures with biologically based mathematical models to generate testable predictions.