Search

Machine learning tools are increasingly used to improve the quality of care and the soundness of a treatment plan. Explainable AI (XAI) helps users in understanding the inner mechanisms of opaque machine learning models and is a driver of trust and adoption. Explanation methods for black-box models exist, but there is a lack of user studies on the interpretability of the provided explanations. We used a Think Aloud Protocol (TAP) to explore oncologists' assessment of a lung cancer relapse prediction system with the aim of refining the purpose-built explanation model for better credibility and utility. Novel to this context, TAP is used as a neutral methodology to elicit experts' thought processes and judgements of the AI system, without explicit prompts. TAP aims to elicit the factors which influenced clinicians' perception of credibility and usefulness of the system. Ten oncologists took part in the study. We conducted a thematic analysis of their verbalized responses, generating five themes that help us to understand the context within which oncologists' may (or may not) integrate an explainable AI system into their working day., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2023 Anjara et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Phosphorylation of specific substrates by protein kinases is a key control mechanism for vital cell-fate decisions and other cellular processes. However, discovering specific kinase-substrate relationships is time-consuming and often rather serendipitous. Computational predictions alleviate these challenges, but the current approaches suffer from limitations like restricted kinome coverage and inaccuracy. They also typically utilise only local features without reflecting broader interaction context. To address these limitations, we have developed an alternative predictive model. It uses statistical relational learning on top of phosphorylation networks interpreted as knowledge graphs, a simple yet robust model for representing networked knowledge. Compared to a representative selection of six existing systems, our model has the highest kinome coverage and produces biologically valid high-confidence predictions not possible with the other tools. Specifically, we have experimentally validated predictions of previously unknown phosphorylations by the LATS1, AKT1, PKA and MST2 kinases in human. Thus, our tool is useful for focusing phosphoproteomic experiments, and facilitates the discovery of new phosphorylation reactions. Our model can be accessed publicly via an easy-to-use web interface (LinkPhinder)., Competing Interests: The authors have declared that no competing interests exist.