EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY-NC 4.0

Explainable/interpretable artificial intelligence and knowledge graph neural network for synthetic lethality prediction: overview, challenges, and future directions

Salsabil Felloussi, Fatima El Haoussi, Hamid Tairi, Noura Aherrahrou iD

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag564 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Salsabil Felloussi und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, L3IA Laboratory, Faculty of Sciences Dhar El Mahraz, University Sidi Mohamed Ben Abdellah, B.P. 1796 - Atlas, 30003, …. Hauptthemen laut MEDLINE: Graph Neural Networks, Synthetic Lethal Mutations, Artificial Intelligence, Computational Biology. Die Arbeit nennt 145 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Synthetic lethality (SL) provides a powerful foundation for targeted oncology by identifying gene pairs whose simultaneous disruption is fatal to cancer cells while sparing healthy tissue. However, mapping these interactions experimentally across the human genome is restricted by massive combinatorial scale and high costs. To address this, computational approaches specifically graph neural networks (GNNs) have become the standard for modeling these complex biological relationships. Hence, by integrating heterogeneous knowledge graph (KG) and multi-omics data, GNNs can effectively capture the topological and molecular context required for accurate SL prediction. This review systematically evaluates the computational SL landscape across three core dimensions. First, we examine how diverse GNN architectures integrate multi-layered biological data. Second, we address model interpretability, contrasting intrinsically transparent architectures with post-hoc explanation methods, as a requirement for clinical trust. Finally, we explore the emerging role of Generative AI and large language models to leverage their zero-shot reasoning and broad biomedical knowledge.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Graph Neural NetworksSynthetic Lethal MutationsArtificial IntelligenceComputational BiologyNeoplasmsHumansGenerative Artificial IntelligenceLarge Language Models

Stichwörter der Autor:innen

LLMsexplainabilitygenerative AIinterpretabilityknowledge graphsynthetic lethality

Autor:innen und Institutionen

  • Department of Computer Science, L3IA Laboratory, Faculty of Sciences Dhar El Mahraz, University Sidi Mohamed Ben Abdellah, B.P. 1796 - Atlas, 30003, Fez, Morocco.

ORCID-Profile: Noura Aherrahrou

Zitieren

APA

Felloussi, S., El Haoussi, F., Tairi, H., & Aherrahrou, N. (2026). Explainable/interpretable artificial intelligence and knowledge graph neural network for synthetic lethality prediction: overview, challenges, and future directions. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag564

Vancouver

Felloussi S, El Haoussi F, Tairi H, Aherrahrou N. Explainable/interpretable artificial intelligence and knowledge graph neural network for synthetic lethality prediction: overview, challenges, and future directions. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag564

BibTeX
@article{Felloussi2026,
  author = {Felloussi, Salsabil and El Haoussi, Fatima and Tairi, Hamid and Aherrahrou, Noura},
  title = {Explainable/interpretable artificial intelligence and knowledge graph neural network for synthetic lethality prediction: overview, challenges, and future directions},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag564}
}
Kostenlos starten →