Epidemiological models with constant parameters may not capture satisfactory infection patterns in the presence of pharmaceutical and non-pharmaceutical mitigation measures during a pandemic, since infectiousness is a function of time. In this paper, an Epidemiology-Informed Neural Network algorithm is introduced to learn the time-varying transmission rate for the COVID-19 pandemic in the presence of various mitigation scenarios. There are asymptomatic infectives, mostly unreported, and the proposed algorithm learns the proportion of the total infective individuals that are asymptomatic infectives. Using cumulative and daily reported cases of the symptomatic infectives, we simulate the impact of non-pharmaceutical mitigation measures such as early detection of infectives, contact tracing, and social distancing on the basic reproduction number. We demonstrate the effectiveness of vaccination on the transmission of COVID-19. The accuracy of the proposed algorithm is demonstrated using error metrics in the data-driven simulation for COVID-19 data of Italy, South Korea, the United Kingdom, and the United States.

Tumor ploidy is increasingly recognized as a determinant of therapeutic response, but the mechanisms by which ploidy shapes sensitivity to specific cytotoxic agents remain unclear. Here, we investigated the relationship between ploidy and gemcitabine response using pharmacogenomic reanalysis, isogenic cancer cell systems, live-cell imaging, intracellular pharma-cokinetic/pharmacodynamic (PKPD) measurements, and mathematical modeling. Across public pharmacogenomic datasets, gemcitabine emerged as a low-ploidy-selective cytotoxic agent. In matched isogenic low- and high-ploidy cell systems, higher-ploidy cells were consistently less sensitive to gemcitabine across multiple lineages. Focused live-cell imaging and PKPD measurements in near-diploid and near-tetraploid SUM-159 cells showed that both states formed intracellular dFdCTP, but high-ploidy cells exhibited weaker and slower treatment responses, with delayed accumulation of cell death. To quantify these differences, we developed a delay-aware live/dead model driven by intracellular dFdCTP exposure. The best-fit model identified both reduced effective gemcitabine potency and a substantially longer delay from intracellular drug action to observed death in high-ploidy cells. Specifically, the inferred mean delay was approximately 17.5 hours in near-diploid cells versus 42.5 hours in near-tetraploid cells. The model also supported a thresholded, nonlinear, and ploidy-dependent mapping from administered gemcitabine dose to effective intracellular drug action. Together, these results establish ploidy as a determinant of both the magnitude and timing of gemcitabine response and provide a quantitative framework for linking intracellular drug exposure to delayed cytotoxic outcomes across ploidy states.

Identification of minimally invasive biomarkers of cancer-associated cachexia may help to recognize high risk patients for progression to more severe cachectic stages. We developed a machine learning-based Mo del for Ca chectic P atients S tratification (MoCaPS) to determine the sets of blood biomarkers that differentiate between noncachectic (NCa), precachectic (PCa), or cachectic (Ca) patients. The model was applied to data collected from treatment-naïve patients with pancreatic ductal adenocarcinoma through the Florida Pancreas Collaborative multi-institutional cohort study and biobanking initiative. Cachexia status of all participants was classified according to modified criteria by Vigano and colleagues. The MoCaPS model pipeline was designed to work effectively with datasets of moderate size to robustly select predictive data features, and to efficiently handle data imbalance. MoCaPS identified between 4 and 5 biomarkers out of 37 candidates that distinguished precachectic and cachectic stages, and demonstrated accuracies near or greater than 75% for predictors of NCa, PCa, and Ca.

Adoptive cell therapy (ACT) with tumor-infiltrating lymphocytes (TIL) is a form of personalized immunotherapy that requires ex vivo expansion of autologous TILs and their reinfusion back into the patient. Predicting TIL expansion at the time of diagnosis may improve selection of patients that can benefit from ACT-TIL. It can also prevent high treatment-related costs and delays in treatment of patients whose cancer specimens would not yield successful TIL growth. We developed PETIL, a machine-learning model optimized for data of a medium size to determine a minimal combination of features (demographic, clinical, and biological specimen-based) that is predictive of expansion of TILs from a resected bladder cancer. We used a retrospectively identified set of data from bladder cancer patients at Moffitt Cancer Center for the training and testing cohorts. Additionally, we used data from a recent feasibility clinical trial at Moffitt Cancer Center as a blinded validation cohort. PETIL uses random forest method to identify a combination of robust predictive features, support vector machine model to determine the optimal classification hyperparameters, and Matthews correlation coefficient method to adjust the decision-boundary threshold for imbalanced data. Our model yielded AUC=0.740 for the testing cohort and AUC=0.857 for blinded validation cohort. Thus, our PETIL model optimized for data of medium size has favorable performance metrics for predicting TIL expansion from a given tumor. Authors Summary: Treatment with autologous tumor-infiltrating lymphocytes (TIL) that are expanded ex vivo from a given tumor and then reinfused into the patient is a promising personalized immunotherapy. However, the TIL expansion takes about 4-6 weeks, thus developing tools that predict whether TIL growth will be successful can help to avoid delays in treatment of patients whose cancer specimens would not yield successful TIL expansion. Our Predictor of Expansion of TIL (PETIL) is a machine-learning model that uses patients’ demographic information, clinical tumor classification, and biological tumor specimen-based measurements to determine a minimal set of these data features that are predictive of TIL expansion outcome. We applied this model to data from bladder cancer patients collected at Moffitt Cancer Center and showed that PETIL has favorable performance metrics for the dataset of a moderate size. This computational predictor can support clinicians in determining which patients are candidates for TIL immunotherapy. The developed PETIL pipeline can also be adjusted to data from other solid tumors.

Epidemiological models with constant parameters may not capture satisfactory infection patterns in the presence of pharmaceutical and non-pharmaceutical mitigation measures during a pandemic, since infectiousness is a function of time. In this paper, an Epidemiology-Informed Neural Network algorithm is introduced to learn the time-varying transmission rate for the COVID-19 pandemic in the presence of various mitigation scenarios. There are asymptomatic infectives, mostly unreported, and the proposed algorithm learns the proportion of the total infective individuals that are asymptomatic infectives. Using cumulative and daily reported cases of the symptomatic infectives, we simulate the impact of non-pharmaceutical mitigation measures such as early detection of infectives, contact tracing, and social distancing on the basic reproduction number. We demonstrate the effectiveness of vaccination on the transmission of COVID-19. The accuracy of the proposed algorithm is demonstrated using error metrics in the data-driven simulation for COVID-19 data of Italy, South Korea, the United Kingdom, and the United States.

Mutating variants of COVID-19 have been reported across many US states since 2021. In the fight against COVID-19, it has become imperative to study the heterogeneity in the time-varying transmission rates for each variant in the presence of pharmaceutical and non-pharmaceutical mitigation measures. We develop a Susceptible-Exposed-Infected-Recovered mathematical model to highlight the differences in the transmission of the B.1.617.2 delta variant and the original SARS-CoV-2. Theoretical results for the well-posedness of the model are discussed. A Deep neural network is utilized and a deep learning algorithm is developed to learn the time-varying heterogeneous transmission rates for each variant. The accuracy of the algorithm for the model is shown using error metrics in the data-driven simulation for COVID-19 variants in the US states of Florida, Alabama, Tennessee, and Missouri. Short-term forecasting of daily cases is demonstrated using long short term memory neural network and an adaptive neuro-fuzzy inference system.