Hammarlund, E. U. | bioRxiv Science

bioRxiv2023

Cell Types or Cell States? An Investigation of Adrenergic and Mesenchymal Cell Phenotypes in Neuroblastoma

Neuroblastoma is a pediatric cancer that exhibits two cellular phenotypes: adrenergic (ADRN) and mesenchymal (MES). ADRN is differentiated and therapy-sensitive, while MES is less differentiated with elevated therapy resistance. To understand neuroblastoma and its treatment response, it is important to elucidate how these phenotypes impact the eco-evolutionary dynamics of cancer cell populations and whether they represent distinct cell types or dynamic cell states. Here, we show that neuroblastoma cells undergo an ADRN to a MES phenotypic switch under chemotherapy treatment. We use a strong inference approach to generate four hypotheses on how this switch may occur: cell types without resistance, cell types with resistance, cell states without resistance, and cell states with resistance. For each of these hypotheses, we create theoretical models to make qualitative predictions about their resulting eco-evolutionary dynamics. Our results provide a framework to further experimentally determine whether ADRN and MES phenotypes are distinct cell types or dynamic cell states.

cancer biology↗

bioRxiv2023

A Clear, Legible, Explainable, Transparent, and Elucidative (CLETE) Binary Classification Platform for Tabular Data

Therapeutic resistance continues to impede overall survival rates for those affected by cancer. Although driver genes are associated with diverse cancer types, a scarcity of instrumental methods for predicting therapy response or resistance persists. Therefore, the impetus for designing predictive tools for therapeutic response is crucial and tools based on machine learning open new opportunities. Here, we present an easily accessible platform dedicated to Clear, Legible, Explainable, Transparent, and Elucidative (CLETE) yet wholly modifiable binary classification models. Our platform encompasses both unsupervised and supervised feature selection options, hyperparameter search methodologies, under-sampling and over-sampling methods, and normalization methods, along with fifteen machine learning algorithms. The platform furnishes a k-fold receiver operating curve (ROC) - area under the curve (AUC) and accuracy plots, permutation feature importance, SHapley Additive exPlanations (SHAP) plots, and Local Interpretable Model-agnostic Explanations (LIME) plots to interpret the model and individual predictions. We have deployed a unique custom metric for hyperparameter search, which considers both training and validation scores, thus ensuring a check on under or over-fitting. Moreover, we introduce an innovative scoring method, NegLog2RMSL, which incorporates both training and test scores for model evaluation that facilitates the evaluation of models via multiple parameters. In a bid to simplify the user interface, we provide a graphical interface that sidesteps programming expertise and is compatible with both Windows and Mac OS. Platform robustness has been validated using pharmacogenomic data for 23 drugs across four diseases and holds the potential for utilization with any form of tabular data.

bioinformatics↗