Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 6 min ago
Peer-reviewedCC BY 4.0Frontiers in Oncology

Beyond XAI: a claim-specific translation matrix for cancer biomarkers and therapeutic targets

  • Vijayachitra Modhukur1,2
  • Naisarg Patel1
  • Prakash Lingasamy3,4
4 affiliations
  1. 1Celvia CC AS
  2. 2Department of Obstetrics and Gynecology, Institute of Clinical Medicine, University of Tartu
  3. 3Laboratory of Precision and Nanomedicine, Institute of Biomedicine and Translational Medicine, University of Tartu
  4. 4Nalam Biosciences OÜ
Open at sourceDOICite

Abstract

Explainable artificial intelligence (XAI) is increasingly used in molecular and multimodal oncology to identify features that influence machine-learning predictions. A model-important feature may subsequently be described as a biomarker, mechanistic driver or therapeutic target, although these labels represent distinct scientific claims requiring different evidence. We propose the XAI Biomarker Translation Matrix, a claim-specific conceptual framework separating explanation evidence (E), biological evidence (B) and translational evidence (T). A claim gate routes XAI-prioritised candidates into three validation pathways: diagnostic, prognostic or treatment-predictive biomarkers; mechanistic therapeutic targets; and tumour-selective delivery targets. The explanation dimension is XAI-specific and addresses whether attribution is defined, stable, faithful and reproducible, whereas the biological and translational dimensions connect the attributed feature to claim-appropriate evidence. Claim-evidence concordance requires terminology to remain no stronger than the evidence demonstrated for the intended use, and falsification-first translation asks investigators to prespecify the observation most capable of challenging the proposed interpretation. Complementing established AI-reporting, biomarker-validation and target-assessment standards, the matrix adds an XAI-specific explanation-evidence layer and an explicit claim gate linking attribution to claim-specific evidence and terminology: XAI prioritises candidates; the claim determines the validation pathway.

Related

  1. Metastasis Pattern-Specific Biomarkers and Therapeutic Targets in Gastric Cancer: From Surgical Specimens to Clinical Translation.
    Mitsuro Kanda
    Annals of gastroenterological surgeryPeer-reviewedCC BYFull textGeneral medicineEurope PMCPMC
  2. Skin-Derived Non-Coding RNAs as Potential Biomarkers and Therapeutic Targets
    Non-coding RNAPeer-reviewedCC BYFull textMolecular biology & gene regulationOncologyEurope PMC
  3. Circulating Biomarkers with Artificial Intelligence for Clinical Risk Assessment and Therapeutic Monitoring: Evidence, Limitations, and Translation
    Wenyuan Wei, Rui Zhang, Zhiying Zhang
    Therapeutics and Clinical Risk ManagementPeer-reviewedCC BY-NC 4.0Full textOncologyPMC
  4. Growth Hormone-Related Gene Signatures Reveal Diagnostic Biomarkers, Immune Landscapes, and Potential Therapeutic Targets in Sepsis Through WGCNA and Machine Learning Analyses.
    Xiuhua Li, Ang Liu, Yingwei Ding +2
    Immunity, inflammation and diseasePeer-reviewedCC BYFull textEpidemiology & public healthEurope PMCPMC
  5. Red Blood Cells Beyond Oxygen Transport: Dynamic Regulators, Disease Biomarkers and Therapeutic Platforms—A Narrative Review
    Joan-Lluis Vives-Corrons
    International Journal of Molecular SciencesPeer-reviewedCC BY 4.0Full textPhysiologyCrossrefEurope PMC

Cite

BibTeXRIS
BibTeX
@article{modhukur2026beyond,
  title = {{Beyond XAI: a claim-specific translation matrix for cancer biomarkers and therapeutic targets}},
  author = {Vijayachitra Modhukur and Naisarg Patel and Prakash Lingasamy},
  journal = {Frontiers in Oncology},
  year = {2026},
  month = oct,
  doi = {10.3389/fonc.2026.1994216},
  url = {https://www.frontiersin.org/articles/10.3389/fonc.2026.1994216/full},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Beyond XAI: a claim-specific translation matrix for cancer biomarkers and therapeutic targets
AU  - Vijayachitra Modhukur
AU  - Naisarg Patel
AU  - Prakash Lingasamy
PY  - 2026
DA  - 2026/10/29
JO  - Frontiers in Oncology
DO  - 10.3389/fonc.2026.1994216
UR  - https://www.frontiersin.org/articles/10.3389/fonc.2026.1994216/full
AB  - Explainable artificial intelligence (XAI) is increasingly used in molecular and multimodal oncology to identify features that influence machine-learning predictions. A model-important feature may subsequently be described as a biomarker, mechanistic driver or therapeutic target, although these labels represent distinct scientific claims requiring different evidence. We propose the XAI Biomarker Translation Matrix, a claim-specific conceptual framework separating explanation evidence (E), biological evidence (B) and translational evidence (T). A claim gate routes XAI-prioritised candidates into three validation pathways: diagnostic, prognostic or treatment-predictive biomarkers; mechanistic therapeutic targets; and tumour-selective delivery targets. The explanation dimension is XAI-specific and addresses whether attribution is defined, stable, faithful and reproducible, whereas the biological and translational dimensions connect the attributed feature to claim-appropriate evidence. Claim-evidence concordance requires terminology to remain no stronger than the evidence demonstrated for the intended use, and falsification-first translation asks investigators to prespecify the observation most capable of challenging the proposed interpretation. Complementing established AI-reporting, biomarker-validation and target-assessment standards, the matrix adds an XAI-specific explanation-evidence layer and an explicit claim gate linking attribution to claim-specific evidence and terminology: XAI prioritises candidates; the claim determines the validation pathway.
SN  - 2234-943X
ER  -