The web is increasingly accessed by AI agents rather than humans. Every agent needs knowledge, especially in the life-sciences, where agentic pipelines are growing fast. Access to the literature is a crucial part of that need, and resources such as Europe PMC, with over 40M indexed records, are widely used to meet it. Yet these resources were not built for AI agents: they take keywords and complex syntax and return whole papers, so every agent must learn the syntax, issue several searches, and read full papers to find the evidence it needs. We introduce EMBL AI Librarian, a knowledge layer that upgrades the Europe PMC interface for AI agents: an agent asks in natural language and receives evidence that answers it. A single LLM orchestrates the whole knowledge retrieval process: it plans complementary subqueries executed by the live Europe PMC search engine, then reads the selected papers and locates the relevant evidence. We evaluate Librarian across four benchmarks: literature synthesis, claim verification, open-domain question answering, and downstream biology tasks such as protocol questions and sequence manipulation. On ScholarQABench, Librarian improves Citation F1 by more than $16$ points over strong recently published baselines. Used as the retrieval layer of an existing claim-verification pipeline, it increases agreement with expert consensus; and on the open-form LitQA2 benchmark, a GPT-5.4 agent scores about $8$ points higher when grounded in Librarian than with web search. Overall, our results show that equipping life-science agents with the Librarian knowledge layer improves performance across a range of tasks. We release our code publicly at https://github.com/petroni-lab/librarian
Luigi Sigillo, M. Silvestri, Francesco Tabaro et al.· 0 citations
BACKGROUND
Precision oncology aims to tailor treatment according to tumor-specific molecular alterations, but the success of aberration-guided therapies has been limited in clinical trials. Here, we develop an integrated whole-genome and transcriptome workflow to systematically distinguish functionally credible, predictive driver aberrations from non-functional alterations across all classes of genomic events.
METHODS
We applied the integrated omics workflow to 335 patients with ovarian high-grade serous carcinoma (HGSC) enrolled in the observational DECIDER study. Tumor samples were collected from multiple cancer sites as part of the standard cancer care. DNA and RNA were extracted together from snap-frozen tumor samples and sent to whole-genome and transcriptome sequencing. Sequencing data were processed with the Anduril 2 pipeline for detection and validation of short somatic changes and with the HMW toolkit and the nf-core/rnafusion pipeline for assessment of structural changes. Aberration-specific drug sensitivity was tested in patient-derived organoids with a drug screen combining targeted agents and chemotherapy.
RESULTS
Using an agnostic integrated omics analysis, we identified clinically relevant ESCAT Tier II-III alterations in more than 40% of the patients, even though 58% of all nominally pathogenic variants proved to be false positives. Credible aberrations were predominantly clonal, detected across anatomical sites, and preserved from diagnosis to relapse, indicating early establishment during tumor evolution. The most recurrent actionable event was NF1 deficiency, which was associated with a robust transcriptional footprint and marked sensitivity to KRAS- and MEK-inhibition in patient-derived organoids. Notably, integrated DNA-RNA analysis enabled discrimination of treatment-guiding aberrations from false-positive findings that would otherwise misinform treatment selection and confound clinical trial outcomes.
CONCLUSIONS
Our findings provide a strategy for more reliable biomarker detection in precision oncology, inform biomarker-guided clinical trial design, and reveal unexploited therapeutic vulnerabilities in HGSC.
T. Muranen, A. Hainari, D. Afenteva et al.· Genome Medicine· 0 citations