BioMiner: A Multi-modal System for Automated Mining of Protein-Ligand Bioactivity Data from Literature

• URL: http://arxiv.org/abs/2604.21508v1
• Date: Thu, 23 Apr 2026 10:11:56 GMT
• Title: BioMiner: A Multi-modal System for Automated Mining of Protein-Ligand Bioactivity Data from Literature
• Abstract summary: We introduce BioMiner, a multi-modal extraction framework for bioactivity data extraction.<n>Within BioMiner, bioactivity semantics are inferred through direct reasoning, while chemical structures are resolved via a chemical-structure-grounded visual semantic reasoning paradigm.<n>For rigorous evaluation and method development, we establish a benchmark comprising 16,457 bioactivity entries curated from 500 publications.
• Score: 53.894504720119805
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Protein-ligand bioactivity data published in the literature are essential for drug discovery, yet manual curation struggles to keep pace with rapidly growing literature. Automated bioactivity extraction remains challenging because it requires not only interpreting biochemical semantics distributed across text, tables, and figures, but also reconstructing chemically exact ligand structures (e.g., Markush structures). To address this bottleneck, we introduce BioMiner, a multi-modal extraction framework that explicitly separates bioactivity semantic interpretation from ligand structure construction. Within BioMiner, bioactivity semantics are inferred through direct reasoning, while chemical structures are resolved via a chemical-structure-grounded visual semantic reasoning paradigm, in which multi-modal large language models operate on chemically grounded visual representations to infer inter-structure relationships, and exact molecular construction is delegated to domain chemistry tools. For rigorous evaluation and method development, we further establish BioVista, a comprehensive benchmark comprising 16,457 bioactivity entries curated from 500 publications. BioMiner validates its extraction ability and provides a quantitative baseline, achieving an F1 score of 0.32 for bioactivity triplets. BioMiner's practical utility is demonstrated via three applications: (1) extracting 82,262 data from 11,683 papers to build a pre-training database that improves downstream models performance by 3.9%; (2) enabling a human-in-the-loop workflow that doubles the number of high-quality NLRP3 bioactivity data, helping 38.6% improvement over 28 QSAR models and identification of 16 hit candidates with novel scaffolds; and (3) accelerating protein-ligand complex bioactivity annotation, achieving a 5.59-fold speed increase and 5.75% accuracy improvement over manual workflows in PoseBusters dataset.

Related papers

• Self Driving Datasets: From 20 Million Papers to Nuanced Biomedical Knowledge at Scale [34.468123235616524]
  We show that PubMed can be autonomously and cost-effectively turned into larger, more nuanced, and more accurate structured datasets.<n>We present three contributions: (1) an entity-tagging pipeline, grounded in nine6.3 biomedical repositories; (2) hybrid retrieval supporting entity-targeted corpus repositories; and (3) Starling, a deep research system given only a natural-language description.
  arXiv  Detail & Related papers  (2026-05-07T23:08:18Z)
• Rep3Net: An Approach Exploiting Multimodal Representation for Molecular Bioactivity Prediction [0.8049701904919515]
  In early stage drug discovery, bioactivity prediction of molecules against target proteins plays a crucial role.<n>We propose Rep3Net, a unified deep learning architecture that not only incorporates descriptor data but also includes spatial and relational information.<n>Our model employing multimodald features produce reliable bioactivity prediction on Poly [ADP-ribose] polymerase 1 dataset.
  arXiv  Detail & Related papers  (2025-11-29T15:39:48Z)
• Learning Cell-Aware Hierarchical Multi-Modal Representations for Robust Molecular Modeling [74.25438319700929]
  We propose CHMR (Cell-aware Hierarchical Multi-modal Representations), a robust framework that models local-global dependencies between molecules and cellular responses.<n> evaluated on nine public benchmarks spanning 728 tasks, CHMR outperforms state-of-the-art baselines.<n>Results demonstrate the advantage of hierarchy-aware, multimodal learning for reliable and biologically grounded molecular representations.
  arXiv  Detail & Related papers  (2025-11-26T07:15:00Z)
• BioChemInsight: An Open-Source Toolkit for Automated Identification and Recognition of Optical Chemical Structures and Activity Data in Scientific Publications [25.764592266678132]
  Existing optical chemical structure recognition tools fail to autonomously associate molecular structures with their bioactivity profiles.<n>BioChemInsight is an open-source pipeline that integrates DECIMER and MolVec for chemical structure recognition, Qwen2.5-VL-32B for compound identifier association, and PaddleOCR for bioactivity extraction and unit normalization.<n>System generates ready-to-use SAR datasets, reducing data preprocessing time from weeks to hours.
  arXiv  Detail & Related papers  (2025-04-12T04:56:44Z)
• BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers [48.21255861863282]
  BMRetriever is a series of dense retrievers for enhancing biomedical retrieval. BMRetriever exhibits strong parameter efficiency, with the 410M variant outperforming baselines up to 11.7 times larger.
  arXiv  Detail & Related papers  (2024-04-29T05:40:08Z)
• Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Survey [75.47055414002571]
  The integration of biomolecular modeling with natural language (BL) has emerged as a promising interdisciplinary area at the intersection of artificial intelligence, chemistry and biology. We provide an analysis of recent advancements achieved through cross modeling of biomolecules and natural language.
  arXiv  Detail & Related papers  (2024-03-03T14:59:47Z)
• BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning [77.90250740041411]
  This paper introduces BioT5+, an extension of the BioT5 framework, tailored to enhance biological research and drug discovery. BioT5+ incorporates several novel features: integration of IUPAC names for molecular understanding, inclusion of extensive bio-text and molecule data from sources like bioRxiv and PubChem, the multi-task instruction tuning for generality across tasks, and a numerical tokenization technique for improved processing of numerical data.
  arXiv  Detail & Related papers  (2024-02-27T12:43:09Z)
• BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations [54.97423244799579]
  $mathbfBioT5$ is a pre-training framework that enriches cross-modal integration in biology with chemical knowledge and natural language associations. $mathbfBioT5$ distinguishes between structured and unstructured knowledge, leading to more effective utilization of information.
  arXiv  Detail & Related papers  (2023-10-11T07:57:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.