RAGPPI: New Benchmark Dataset for AI-Assisted Protein Interaction Analysis in Drug Discovery
Researchers have published RAGPPI, a benchmark of 4,420 question-answer pairs designed to evaluate Retrieval-Augmented Generation (RAG) systems on the biological impacts of protein-protein interactions (PPIs) in drug discovery. The dataset includes a 500-pair gold standard annotated by domain experts and a 3,720-pair silver standard built using an ensemble LLM auto-evaluator. The benchmark addresses a gap in tools for assessing AI-assisted target identification, a critical and time-intensive step in pharmaceutical development.
RAGPPI (RAG Benchmark for Protein-Protein Interactions) is a new factual question-answer benchmark introduced to support the evaluation of large language model (LLM) and RAG-based systems applied to drug discovery. The dataset comprises 4,420 QA pairs focused on the biological impacts of PPIs, which are central to identifying therapeutic targets. A gold-standard subset of 500 pairs was constructed through expert-driven annotation informed by interviews with domain specialists who defined criteria for question type and sourcing. The remaining 3,720 pairs form a silver-standard dataset, generated using an ensemble auto-evaluation LLM that incorporates expert labeling characteristics alongside two similarity metrics: average fact-abstract similarity (F1) and low-similarity fact counts (F2). The benchmark was accepted to the Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026). The authors have committed to maintaining RAGPPI as an ongoing community resource to advance RAG systems for drug discovery question-answering.
What's missing
Inter-annotator agreement statistics for the gold-standard annotation process are not described in the abstract, leaving the reliability of expert labeling unclear.
What different sources said
- arXiv cs.CLCenter
RAGPPI: RAG Benchmark for Protein-Protein Interactions in Drug Discovery
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.