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

arXiv: https://arxiv.org/abs/2604.21508 · HTML: https://mlsanity.com/paper/2604.21508/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 81 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Builds on (most cited first, 18 of 18)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [E(n) Equivariant Graph Neural Networks](https://mlsanity.com/paper/2102.09844/) (2021)
- [YOLOv11: An Overview of the Key Architectural Enhancements](https://mlsanity.com/paper/2410.17725/) (2024)
- [DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking](https://mlsanity.com/paper/2210.01776/) (2022)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [Deep Learning is Robust to Massive Label Noise](https://mlsanity.com/paper/1705.10694/) (2017)
- [EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction](https://mlsanity.com/paper/2202.05146/) (2022)
- [ChatGPT Chemistry Assistant for Text Mining and Prediction of MOF Synthesis](https://mlsanity.com/paper/2306.11296/) (2023)
- [MolScribe: Robust Molecular Structure Recognition with Image-To-Graph Generation](https://mlsanity.com/paper/2205.14311/) (2022)
- [MolParser: End-to-end Visual Recognition of Molecule Structures in the Wild](https://mlsanity.com/paper/2411.11098/) (2024)
- [MolNexTR: A Generalized Deep Learning Model for Molecular Image Recognition](https://mlsanity.com/paper/2403.03691/) (2024)
- [MolMiner: You only look once for chemical structure recognition](https://mlsanity.com/paper/2205.11016/) (2022)

## Built on by (most cited first, 1 of 1)

- [MolParser-Mobile: Ultrafast OCSR System for Large-Scale Chemical Literature Mining](https://mlsanity.com/paper/2609.05807/) (2026)

## Abstract (arXiv)

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.