Clinical Features Predicting COVID-19 Severity Risk at the Time of Hospitalization.

The global spread of COVID-19 has led to significant mortality and morbidity worldwide. Early identification of COVID-19 patients who are at high risk of developing severe disease can help in improved patient management, care, and treatment, as well as in the effective allocation of hospital resources. The severity prediction at the time of hospitalization can be extremely helpful in deciding the treatment of COVID-19 patients. To this end, this study presents an interpretable artificial intelligence (AI) model, named COVID-19 severity predictor (CoSP) that predicts COVID-19 severity using the clinical features at the time of hospital admission. We utilized a dataset comprising 64 demographic and laboratory features of 7,416 confirmed COVID-19 patients that were collected at the time of hospital admission. The proposed hierarchical CoSP model performs four-class COVID severity risk prediction into asymptomatic, mild, moderate, and severe categories. CoSP yielded better performance with good interpretability, as observed via Shapley analysis on COVID severity prediction compared to the other popular ML methods, with an area under the received operating characteristic curve (AUC-ROC) of 0.95, an area under the precision-recall curve (AUPRC) of 0.91, and a weighted F1-score of 0.83. Out of 64 initial features, 19 features were inferred as predictive of the severity of COVID-19 disease by the CoSP model. Therefore, an AI model predicting COVID-19 severity may be helpful for early intervention, optimizing resource allocation, and guiding personalized treatments, potentially enabling healthcare professionals to save lives and allocate resources effectively in the fight against the pandemic.

Physics-Guided Deep Generative Model for New Ligand Discovery.

Structure-based drug discovery aims to identify small molecules that can attach to a specific target protein and change its functionality. Recently, deep learning has shown great promise in generating drug-like molecules with specific biochemical features and conditioned with structural features. However, they usually fail to incorporate an essential factor: the underlying physics which guides molecular formation and binding in real-world scenarios. In this work, we describe a physics-guided deep generative model for new ligand discovery, conditioned not only on the binding site but also on physics-based features that describe the binding mechanism between a receptor and a ligand. The proposed hybrid model has been tested on large protein-ligand complexes and small host-guest systems. Using the top-N methodology, on average more than 75% of the generated structures by our hybrid model were stronger binders than the original reference ligand. All of them had higher ΔGbind (affinity) values than the ones generated by the previous state-of-the-art method by an average margin of 1.88 kcal/mol. The visualization of the top-5 ligands generated by the proposed physics-guided model and the reference deep learning model demonstrate more feasible conformations and orientations by the former. The future directions include training and testing the hybrid model on larger datasets, adding more relevant physics-based features, and interpreting the deep learning outcomes from biophysical perspectives.

GCRS: A hybrid graph convolutional network for risk stratification in multiple myeloma cancer patients.

In this study, we present an efficient Graph Convolutional Network based Risk Stratification system (GCRS) for cancer risk-stage prediction of newly diagnosed multiple myeloma (NDMM) patients. GCRS is a hybrid graph convolutional network consisting of a fusion of multiple connectivity graphs that are used to learn the latent representation of topological structures among patients. This proposed risk stratification system integrates these connectivity graphs prepared from the clinical and laboratory characteristics of NDMM cancer patients for partitioning them into three cancer risk groups: low, intermediate, and high. Extensive experiments demonstrate that GCRS outperforms the existing state-of-the-art methods in terms of C-index and hazard ratio on two publicly available datasets of NDMM patients. We have statistically validated our results using the Cox Proportional-Hazards model, Kaplan-Meier analysis, and log-rank test on progression-free survival (PFS) and overall survival (OS). We have also evaluated the contribution of various clinical parameters as utilized by the GCRS risk stratification system using the SHapley Additive exPlanations (SHAP) analysis, an interpretability algorithm for validating AI methods. Our study reveals the utility of the deep learning approach in building a robust system for cancer risk stage prediction.