Variantscape: Retrospective Study of Large Language Model-Based Extraction of Variant-Treatment-Cancer Associations from Published Oncology Abstracts
- 1University of Pavia
Abstract
Objectives: Precision oncology relies on accurate interpretation of tumour-detected gene variants, to guide personalised treatment decisions. However, interpretation of variants in context requires extensive information that is often buried within unstructured biomedical literature and obscured by inconsistent nomenclature, making manual retrieval labour-intensive and prone to omissions. In this study, our aim was to evaluate the potential of large language models to extract variant-treatment-cancer associations at scale from published abstracts. Design: We developed Variantscape, a large-scale, automated pipeline and open-access web tool. It integrates traditional natural language processing methods with state-of-the-art large language models to extract, standardise, and analyse co-associations between genetic variants, cancer types, and therapeutic interventions from published biomedical abstracts. Results: From over 3.7 million abstracts published between January 2014 and October 2026, 886,195 articles containing gene names were eligible for extraction. Among these, 37,895 (4.3%) mentioned a variant, cancer type, and therapeutic agent together, covering 11,985 unique variants across 197 cancer types and 547 therapeutic agents. LLM verification against the abstract text confirmed at least one association in 35,224 papers, giving a literature-derived graph of 10,571 nodes and 44,644 verified edges. Canonical alterations in well-studied cancers (e.g., BRAF V600E in melanoma) were strongly linked to established treatments, while several rare variants also emerged with high-confidence literature support. Conclusions: By applying large language models to biomedical literature, Variantscape enables scalable, context-aware extraction of trilateral variant-treatment-cancer relationships. This approach supports early evidence synthesis/hypothesis generation, highlights underrecognized or rare associations for MTB preparation, and offers a practical resource for accelerating discovery and supporting precision oncology research and translation.
Related
- Distinct clinical associations of baseline and treatment-emergent hypogammaglobulinemia in diffuse large B-cell lymphoma: a retrospective real-world cohort study
- Associations of Cancer Rehabilitation During Hospitalization for Cancer Treatment With Survival and Post–Discharge Healthcare Utilization: A Multicenter Retrospective Cohort Study
- Association of Mandibular Morphological and Trabecular Bone Characteristics with Long-Term Outcomes Following First Permanent Molar Extraction: A Retrospective Study
- Comparative outcomes of natural orifice specimen extraction surgery versus conventional minilaparotomy-assisted specimen extraction in colorectal cancer: A single-center retrospective study.
- Clinical outcomes of the crown separation–dislocation–re-segmentation technique for high-risk impacted mandibular third molar extraction: a single-center retrospective cohort study
BibTeX
@misc{wosny2026variantscape,
title = {{Variantscape: Retrospective Study of Large Language Model-Based Extraction of Variant-Treatment-Cancer Associations from Published Oncology Abstracts}},
author = {M. Wosny and A. S. Blindu and M. Boesch and T. Peres and T. Niederhauser and M. Fruh and C. Rothermundt and J. Hastings},
howpublished = {medRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.02.26359492},
url = {https://www.medrxiv.org/content/10.64898/2026.08.02.26359492v2},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Variantscape: Retrospective Study of Large Language Model-Based Extraction of Variant-Treatment-Cancer Associations from Published Oncology Abstracts
AU - M. Wosny
AU - A. S. Blindu
AU - M. Boesch
AU - T. Peres
AU - T. Niederhauser
AU - M. Fruh
AU - C. Rothermundt
AU - J. Hastings
PY - 2026
DA - 2026/08/02
PB - medRxiv
DO - 10.64898/2026.08.02.26359492
UR - https://www.medrxiv.org/content/10.64898/2026.08.02.26359492v2
AB - Objectives: Precision oncology relies on accurate interpretation of tumour-detected gene variants, to guide personalised treatment decisions. However, interpretation of variants in context requires extensive information that is often buried within unstructured biomedical literature and obscured by inconsistent nomenclature, making manual retrieval labour-intensive and prone to omissions. In this study, our aim was to evaluate the potential of large language models to extract variant-treatment-cancer associations at scale from published abstracts. Design: We developed Variantscape, a large-scale, automated pipeline and open-access web tool. It integrates traditional natural language processing methods with state-of-the-art large language models to extract, standardise, and analyse co-associations between genetic variants, cancer types, and therapeutic interventions from published biomedical abstracts. Results: From over 3.7 million abstracts published between January 2014 and October 2026, 886,195 articles containing gene names were eligible for extraction. Among these, 37,895 (4.3%) mentioned a variant, cancer type, and therapeutic agent together, covering 11,985 unique variants across 197 cancer types and 547 therapeutic agents. LLM verification against the abstract text confirmed at least one association in 35,224 papers, giving a literature-derived graph of 10,571 nodes and 44,644 verified edges. Canonical alterations in well-studied cancers (e.g., BRAF V600E in melanoma) were strongly linked to established treatments, while several rare variants also emerged with high-confidence literature support. Conclusions: By applying large language models to biomedical literature, Variantscape enables scalable, context-aware extraction of trilateral variant-treatment-cancer relationships. This approach supports early evidence synthesis/hypothesis generation, highlights underrecognized or rare associations for MTB preparation, and offers a practical resource for accelerating discovery and supporting precision oncology research and translation.
ER -