Explaining Multiclass Compound Activity Predictions Using Counterfactuals and Shapley Values. [PDF]
Molecules, 2023 Most machine learning (ML) models produce black box predictions that are difficult, if not impossible, to understand. In pharmaceutical research, black box predictions work against the acceptance of ML models for guiding experimental work.
Lamens A, Bajorath J.
europepmc +2 more sources
Explaining multivariate molecular diagnostic tests via Shapley values. [PDF]
BMC Med Inform Decis Mak, 2021 Background Machine learning (ML) can be an effective tool to extract information from attribute-rich molecular datasets for the generation of molecular diagnostic tests.
Roder J +3 more
europepmc +2 more sources
Model independent feature attributions: Shapley values that uncover non-linear dependencies. [PDF]
PeerJ Comput Sci, 2021 Shapley values have become increasingly popular in the machine learning literature, thanks to their attractive axiomatisation, flexibility, and uniqueness in satisfying certain notions of ‘fairness’. The flexibility arises from the myriad potential forms
Fryer DV, Strumke I, Nguyen H.
europepmc +3 more sources
Explaining a series of models by propagating Shapley values. [PDF]
Nat Commun, 2022 Series of machine learning models, relevant for tasks in biology, medicine, and finance, usually involve complex feature attribution techniques. The authors introduce a tractable method to compute local feature attributions for a series of machine ...
Chen H, Lundberg SM, Lee SI.
europepmc +2 more sources
Enhancing Omics Analyses Through Coalitional Games and Shapley Values. [PDF]
Methods ProtocWe describe a comprehensive methodology for the application of game theory to omics data analysis, with a particular focus on coalitional games and Shapley values.
Vargas E, de la Torre I, Esteban FJ.
europepmc +2 more sources
Data analysis with Shapley values for automatic subject selection in Alzheimer's disease data sets using interpretable machine learning. [PDF]
Alzheimers Res Ther, 2021 Background For the recruitment and monitoring of subjects for therapy studies, it is important to predict whether mild cognitive impaired (MCI) subjects will prospectively develop Alzheimer’s disease (AD).
Bloch L +2 more
europepmc +2 more sources
Shapley Values for Feature Selection: The Good, the Bad, and the Axioms
IEEE Access, 2021 The Shapley value has become popular in the Explainable AI (XAI) literature, thanks, to a large extent, to a solid theoretical foundation, including four “favourable and fair” axioms for attribution in transferable utility games.
Daniel Fryer +2 more
exaly +3 more sources
LLpowershap: logistic loss-based automated Shapley values feature selection method. [PDF]
BMC Med Res MethodolBackground Shapley values have been used extensively in machine learning, not only to explain black box machine learning models, but among other tasks, also to conduct model debugging, sensitivity and fairness analyses and to select important features ...
Madakkatel I, Hyppönen E.
europepmc +2 more sources
Enhancing Transcriptomic Insights into Neurological Disorders Through the Comparative Analysis of Shapley Values. [PDF]
Curr Issues Mol BiolNeurological disorders such as Autism Spectrum Disorder (ASD), Schizophrenia (SCH), Bipolar Disorder (BD), and Major Depressive Disorder (MDD) affect millions of people worldwide, yet their molecular mechanisms remain poorly understood.
Castro-Martínez JA +3 more
europepmc +2 more sources
Protocol to calculate and compare exact Shapley values for different kernels in support vector machine models using binary features. [PDF]
STAR ProtocSummary: The Shapley value formalism from cooperative game theory was adapted to explain predictions of machine learning models. Here, we present a protocol to calculate and compare exact Shapley values for support vector machine models with commonly ...
Roth JP, Bajorath J.
europepmc +2 more sources