DianShi-RxnDB: A Large-Scale, Fine-Grained Organic Reaction Data Platform Built via a Fully Automated Pipeline for Researchers and AI Agents
Summary
DianShi-RxnDB is a large-scale data platform that extracts and normalizes millions of organic reaction data from patents via an automated pipeline to support AI-driven chemistry research.
View Cached Full Text
Cached at: 09/10/26, 06:10 AM
Paper page - DianShi-RxnDB: A Large-Scale, Fine-Grained Organic Reaction Data Platform Built via a Fully Automated Pipeline for Researchers and AI Agents
Source: https://huggingface.co/papers/2609.06703 Authors:
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Abstract
DianShi-RxnDB is an automated platform that extracts and normalizes millions of structured organic reactions from patents to support AI-driven chemistry research.
High-quality structured organic reaction data are essential for developing artificial intelligence for chemistry (AI4Chem), yet much of this knowledge remains dispersed across patent text, images, and reaction schemes. We presentDianShi-RxnDB, a large-scale, fine-grained organic reaction data platform built via a fully automated extraction andnormalization pipelineintegrating patent text, images, and reaction schemes. Its corpus covers organic synthesis patents from the USPTO and EPO published between 1976 and 2025, yielding approximately 24 million reaction instances, of which approximately 14.8 million (61.7%) pass automated qualification checks. Each instance represents a specific single-step experiment recording participants, roles, quantities, temperatures, reaction times, yields, experimental procedures, and provenance links to source patents. In a manual evaluation of 1,300 sampled qualified instances, the micro-averaged field-level accuracy was 92.95%. A matched comparison with Pistachio further indicated advantages in deduplicated record counts, representation granularity, and field-level exact agreement. The platform provides a Web research workbench for searching, filtering, comparing, and source-verifying records, and aModel Context Protocol(MCP) service offering AI agents composable structured retrieval tools.DianShi-RxnDBis available at https://dianshi.opendatalab.org.cn/ .
View arXiv pageView PDFProject pageAdd to collection
Get this paper in your agent:
hf papers read 2609\.06703
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2609.06703 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2609.06703 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2609.06703 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
@rasyn_lab: Today, we are launching Analyst Agent, an AI that does analytical chemistry from the raw instrument file. You give it t…
Analyst Agent is an AI system that processes raw instrument files in analytical chemistry, answering questions in plain language with evidence, and it performs best on blind benchmarks across different base models.
Folding, Reasoning, and Scaling with Open-source Drug Discovery Engine
Introduces OpenDDE, an open-source all-atom biomolecular foundation model that uses co-folding as a shared structural reasoning layer for drug discovery, achieving high accuracy and identifying scaling laws for further improvement.
@johnsonshi86: https://x.com/johnsonshi86/status/2072112215097024961
Describes DR-DCI, an optimization that combines RAG with bash commands on a virtual filesystem to enable agents to perform precise corpus retrieval, and discusses scaling to distributed systems for inference providers.
ReactionAtlas: Ab origine exploration of chemical reaction networks with machine learning
ReactionAtlas is a machine learning framework that automatically constructs chemical reaction networks from seed molecules by generating and validating transition states, discovering approximately 47,000 reactions and 12,000 compounds in prebiotic carbohydrate chemistry.
DDIAgents: Mechanism-Conditioned Context Flow for Drug-Drug Interaction Prediction
Proposes DDIAgents, a mechanism-conditioned multi-agent framework for drug-drug interaction prediction that dynamically routes relevant biomedical knowledge to specialized expert agents and aggregates their analyses, outperforming existing feature-based, graph-based, and LLM-based methods.