Concept-Oriented Self-Explaining Neural Networks

Park, Min Sue; Hwang, Hyung Ju

doi:10.1007/s11063-023-11355-5

Cited by 1 publication

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SENNs aim to enhance transparency and interpretability in complex ML systems. Usually comprising two main components-a prediction network for making predictions and an explanation network for generating human-readable justifications-SENNs provide attention maps or feature importance scores highlighting influential parts of the input (Park and Hwang, 2023). Trained concurrently to optimize accurate predictions and meaningful explanations, SENNs find applications in crucial domains such as healthcare, finance, and natural language processing (Ren et al, 2023).…”

Section: Self-explaining Approachesmentioning

confidence: 99%

Interpretable and explainable predictive machine learning models for data-driven protein engineering

Medina-Ortiz,

Khalifeh,

Anvari-Kazemabad

et al. 2024

Preprint

View full text Add to dashboard Cite

Protein engineering using directed evolution and (semi)rational design has emerged as a powerful strategy for optimizing and enhancing enzymes or proteins with desired properties. Integrating artificial intelligence methods has further enhanced and accelerated protein engineering through predictive models developed in data-driven strategies. However, the lack of explainability and interpretability in these models poses challenges. Explainable Artificial Intelligence addresses the interpretability and explainability of machine learning models, providing transparency and insights into predictive processes. Nonetheless, there is a growing need to incorporate explainable techniques in predicting protein properties in machine learning-assisted protein engineering. This work explores incorporating explainable artificial intelligence in predicting protein properties, emphasizing its role in trustworthiness and interpretability. It assesses different machine learning approaches, introduces diverse explainable methodologies, and proposes strategies for seamless integration, improving trust-worthiness. Practical cases demonstrate the explainable model’s effectiveness in identifying DNA binding proteins and optimizing Green Fluorescent Protein brightness. The study highlights the utility of explainable artificial intelligence in advancing computationally assisted protein design, fostering confidence in model reliability.

show abstract

Section: Self-explaining Approachesmentioning

confidence: 99%