ALBERT

Description: Building an effective Machine Learning (ML) model for a data set is a difficult task involving various steps. One of the most important steps is to compare a substantial amount of generated ML models to find the optimal one for deployment. It is challenging to compare such models with a dynamic number of features. Comparison is more than only finding differences of ML model performance, as users are also interested in the relations between features and model performance such as feature importance for ML explanations. This paper proposes RadialNet Chart, a novel visualisation approach, to compare ML models trained with a different number of features of a given data set while revealing implicit dependent relations. In RadialNet Chart, ML models and features are represented by lines and arcs, respectively. These lines are generated effectively using a recursive function. The dependence of ML models with a dynamic number of features is encoded into the structure of visualisation, where ML models and their dependent features are directly revealed from related line connections. ML model performance information is encoded with colour and line width in RadialNet Chart. Taken together with the structure of visualisation, feature importance can be directly discerned in RadialNet Chart for ML explanations. Compared with other commonly used visualisation approaches, RadialNet Chart can help to simplify the ML model comparison process with different benefits such as the following: more efficient in terms of helping users to focus their attention to find visual elements of interest and easier to compare ML performance to find optimal ML model and discern important features visually and directly instead of through complex algorithmic calculations for ML explanations.

Description: This paper estimates the yields of DNA double-strand breaks (DSBs) induced by ultrasoft X-rays and uses the DSB yields and the repair outcomes to evaluate the relative biological effectiveness (RBE) of ultrasoft X-rays. We simulated the yields of DSB induction and predicted them in the presence and absence of oxygen, using a Monte Carlo damage simulation (MCDS) software, to calculate the RBE. Monte Carlo excision repair (MCER) simulations were also performed to calculate the repair outcomes (correct repairs, mutations, and DSB conversions). Compared to 60Co γ-rays, the RBE values for ultrasoft X-rays (titanium K-shell, aluminum K-shell, copper L-shell, and carbon K-shell) for DSB induction were respectively 1.3, 1.9, 2.3, and 2.6 under aerobic conditions and 1.3, 2.1, 2.5, and 2.9 under a hypoxic condition (2% O2). The RBE values for enzymatic DSBs were 1.6, 2.1, 2.3, and 2.4, respectively, indicating that the enzymatic DSB yields are comparable to the yields of DSB induction. The synergistic effects of DSB induction and enzymatic DSB formation further facilitate cell killing and the advantage in cancer treatment.