eXplainable Artificial Intelligence (XAI) for the identification of biologically relevant gene expression patterns in longitudinal human studies, insights from obesity research

Abstract

Until date, several machine learning approaches have been proposed for the dynamic modeling of temporal omics data. Although they have yielded impressive results in terms of model accuracy and predictive ability, most of these applications are based on "Black-box" algorithms and more interpretable models have been claimed by the research community. The recent eXplainable Artificial Intelligence (XAI) revolution offers a solution for this issue, were rule-based approaches are highly suitable for explanatory purposes. The further integration of the data mining process along with functional-annotation and pathway analyses is an additional way towards more explanatory and biologically soundness models. In this paper, we present a novel rule-based XAI strategy (including pre-processing, knowledgeextraction and functional validation) for finding biologically relevant sequential patterns from longitudinal human gene expression data (GED). To illustrate the performance of our pipeline, we work on in vivo temporal GED collected within the course of a long-term dietary intervention in 57 subjects with obesity (GSE77962). As validation populations, we employ three independent datasets following the same experimental design. As a result, we validate primarily extracted gene patterns and prove the goodness of our strategy for the mining of biologically relevant gene-gene temporal relations. Our whole pipeline has been gathered under open-source software and could be easily extended to other human temporal GED applications.

Integrative Analysis of Next-Generation Sequencing for Next-Generation Cancer Research toward Artificial Intelligence

“…In the work by Augusto et al, sequential rule mining was proposed as one of the solutions to understand the 'black-box' machine learning model. Their pipeline was able to find biologically relevant genes in six different datasets [157]. Other approaches include the calibration of machine learning models by making the predictions probabilistically interpretable [158].…”

Deep Learning-Based Breast Cancer Diagnosis at Ultrasound: Initial Application of Weakly-Supervised Algorithm Without Image Annotation Original Research

“…GAP used in our study can enforce the feature maps to preserve spatial information relevant to the classes, so that they can be used to interpret the decision of the CNN models 8,28 . This method for identifying areas that are attributed to differential diagnosis using GAP with CAM leads toward the concept of eXplainable AI (XAI) 29,30 . XAI or responsible AI is an emerging paradigm to overcome the inherent "black box problem" brought by deep frameworks, wherein it is impossible for us to understand how decisions are furnished.…”

Artificial Intelligence for Mental Health Care: Clinical Applications, Barriers, Facilitators, and Artificial Wisdom

“…Despite the clear trade-off between accuracy and explainability, explainable models are needed to ensure safety of the patients and establish trust in the AI models. Recent developments in AI include recurrent neural network (RNN) variant models that can control data inputs at various stages and self-evaluate which timepoints and data inputs are most predictive of the outcome, visualizing techniques, association rule mining (using biologically-based relationships between data elements), and functional validation of the results (117,119).…”