Loading
Life sciences · Preprint
arXiv · September 3, 2026
Raises a question worth testing. It does not answer one.
Hakken is a transformer-based computational system that predicts undocumented relationships between biomedical concepts by fusing knowledge graphs with LLM semantics. Two predicted relationships (TP53–BAMBI and RAF1–TNF) were confirmed in wet-lab, but the validation sample is small, methods are incompletely specified, and the work remains unrefereed.
Computational prediction model applied to temporal knowledge graphs; qualitative expert review and partial empirical validation. Biomedical concepts and relationships extracted from research publications; validation performed with biologists and wet-lab experiments.. Intervention: Hakken prediction and explanation system applied to biomedical knowledge graphs to generate novel relationship hypotheses.
1.5 million above-confidence-threshold hypotheses related to aging were generated Two predicted relationships (TP53–BAMBI and RAF1–TNF interactions) were confirmed via wet-lab validation Model establishes new benchmark for time-aware multi-label relation prediction on biomedical knowledge graphs
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
If validated at scale, computational prediction of undocumented biomedical relationships could accelerate drug discovery and repurposing efforts. However, the current work shows only proof-of-concept; clinicians and researchers should not act on predicted relationships without independent empirical validation.
This is a computational prediction system demonstrating proof-of-concept in biomedical discovery with qualitative validation of selected hypotheses, not a rigorous empirical test of predicted relationships.
As stated by the source record.
Quoted from the source exactly as published.
If validated at scale, computational prediction of undocumented biomedical relationships could accelerate drug discovery and repurposing efforts. However, the current work shows only proof-of-concept; clinicians and researchers should not act on predicted relationships without independent empirical validation.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
We present Hakken, a domain-agnostic prediction and explanation system performing knowledge prediction, i.e., growing scientific knowledge by establishing novel relationships, ones that are not limited to the deductive hull of previous knowledge. Hakken uses a transformer-based prediction model built on temporal sequences of knowledge graphs extracted from vast bodies of research publications, fused with an LLM's semantic knowledge, to predict the presence and define the type of as-yet undocumented relationships between scientific concepts. It then calls a model-agnostic explanation framework to provide accompanying information for each prediction that allows scientists to evaluate the suggested new relationship. While general purpose, we demonstrate Hakken's practical capabilities by applying it to the biomedical domain. There, Hakken's prediction model establishes a new benchmark for time-aware multi-label relation prediction, and we show that the model's output stays coherent and informative over extended time spans in historic data. In addition, we scored 1.5 million above-confidence-threshold hypotheses related to aging, qualitatively validated batches of these predictions with biologists and progressed three of them for empirical validation in wet-lab. Two predictions with potentially significant impact in the context of drug discovery and repurposing were confirmed, introducing previously undocumented interactions between TP53 and BAMBI, and between RAF1 and TNF, to biomedical science.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.