ChemQuery: A Natural Language Query‐Driven Service for Comprehensive Exploration of Chemistry Patent Literature

ABSTRACT Patents are integral to our shared scientific knowledge, requiring companies and inventors to stay informed about them to conduct research, find licensing opportunities, and manage legal risks. However, the rising rate of filings has made this task increasingly challenging over the years. T...

Full description

Saved in:
Bibliographic Details
Main Authors: Shubham Gupta, Rafael Teixeira de Lima, Lokesh Mishra, Cesar Berrospi, Panagiotis Vagenas, Nikolaos Livathinos, Christoph Auer, Michele Dolfi, Peter Staar
Format: Article
Language:English
Published: Wiley 2025-04-01
Series:Applied AI Letters
Subjects:
Online Access:https://doi.org/10.1002/ail2.124
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849330282528768000
author Shubham Gupta
Rafael Teixeira de Lima
Lokesh Mishra
Cesar Berrospi
Panagiotis Vagenas
Nikolaos Livathinos
Christoph Auer
Michele Dolfi
Peter Staar
author_facet Shubham Gupta
Rafael Teixeira de Lima
Lokesh Mishra
Cesar Berrospi
Panagiotis Vagenas
Nikolaos Livathinos
Christoph Auer
Michele Dolfi
Peter Staar
author_sort Shubham Gupta
collection DOAJ
description ABSTRACT Patents are integral to our shared scientific knowledge, requiring companies and inventors to stay informed about them to conduct research, find licensing opportunities, and manage legal risks. However, the rising rate of filings has made this task increasingly challenging over the years. To address this issue, we introduce ChemQuery, a tool for easily exploring chemistry‐related patents using natural language questions. Traditional systems rely on simplistic keyword‐based searches to find patents that might be relevant to a user's request. In contrast, ChemQuery uses up‐to‐date information to return specific answers, along with their sources. It also offers a more comprehensive search experience to the users, thanks to capabilities like extracting molecules from diagrams, integrating information from PubChem, and allowing complex queries about molecular structures. We conduct a thorough empirical evaluation of ChemQuery and compare it with several baseline approaches. The results highlight the practical utility and limitations of our tool.
format Article
id doaj-art-3b92a23fe34547089ff9bce70801115c
institution Kabale University
issn 2689-5595
language English
publishDate 2025-04-01
publisher Wiley
record_format Article
series Applied AI Letters
spelling doaj-art-3b92a23fe34547089ff9bce70801115c2025-08-20T03:46:58ZengWileyApplied AI Letters2689-55952025-04-0162n/an/a10.1002/ail2.124ChemQuery: A Natural Language Query‐Driven Service for Comprehensive Exploration of Chemistry Patent LiteratureShubham Gupta0Rafael Teixeira de Lima1Lokesh Mishra2Cesar Berrospi3Panagiotis Vagenas4Nikolaos Livathinos5Christoph Auer6Michele Dolfi7Peter Staar8IBM Research Paris‐Saclay Orsay FranceIBM Research Paris‐Saclay Orsay FranceIBM Research Zurich Rüschlikon SwitzerlandIBM Research Zurich Rüschlikon SwitzerlandIBM Research Zurich Rüschlikon SwitzerlandIBM Research Zurich Rüschlikon SwitzerlandIBM Research Zurich Rüschlikon SwitzerlandIBM Research Zurich Rüschlikon SwitzerlandIBM Research Zurich Rüschlikon SwitzerlandABSTRACT Patents are integral to our shared scientific knowledge, requiring companies and inventors to stay informed about them to conduct research, find licensing opportunities, and manage legal risks. However, the rising rate of filings has made this task increasingly challenging over the years. To address this issue, we introduce ChemQuery, a tool for easily exploring chemistry‐related patents using natural language questions. Traditional systems rely on simplistic keyword‐based searches to find patents that might be relevant to a user's request. In contrast, ChemQuery uses up‐to‐date information to return specific answers, along with their sources. It also offers a more comprehensive search experience to the users, thanks to capabilities like extracting molecules from diagrams, integrating information from PubChem, and allowing complex queries about molecular structures. We conduct a thorough empirical evaluation of ChemQuery and compare it with several baseline approaches. The results highlight the practical utility and limitations of our tool.https://doi.org/10.1002/ail2.124chemistry patentsmolecule searchnatural language queriespatent searchquestion answering
spellingShingle Shubham Gupta
Rafael Teixeira de Lima
Lokesh Mishra
Cesar Berrospi
Panagiotis Vagenas
Nikolaos Livathinos
Christoph Auer
Michele Dolfi
Peter Staar
ChemQuery: A Natural Language Query‐Driven Service for Comprehensive Exploration of Chemistry Patent Literature
Applied AI Letters
chemistry patents
molecule search
natural language queries
patent search
question answering
title ChemQuery: A Natural Language Query‐Driven Service for Comprehensive Exploration of Chemistry Patent Literature
title_full ChemQuery: A Natural Language Query‐Driven Service for Comprehensive Exploration of Chemistry Patent Literature
title_fullStr ChemQuery: A Natural Language Query‐Driven Service for Comprehensive Exploration of Chemistry Patent Literature
title_full_unstemmed ChemQuery: A Natural Language Query‐Driven Service for Comprehensive Exploration of Chemistry Patent Literature
title_short ChemQuery: A Natural Language Query‐Driven Service for Comprehensive Exploration of Chemistry Patent Literature
title_sort chemquery a natural language query driven service for comprehensive exploration of chemistry patent literature
topic chemistry patents
molecule search
natural language queries
patent search
question answering
url https://doi.org/10.1002/ail2.124
work_keys_str_mv AT shubhamgupta chemqueryanaturallanguagequerydrivenserviceforcomprehensiveexplorationofchemistrypatentliterature
AT rafaelteixeiradelima chemqueryanaturallanguagequerydrivenserviceforcomprehensiveexplorationofchemistrypatentliterature
AT lokeshmishra chemqueryanaturallanguagequerydrivenserviceforcomprehensiveexplorationofchemistrypatentliterature
AT cesarberrospi chemqueryanaturallanguagequerydrivenserviceforcomprehensiveexplorationofchemistrypatentliterature
AT panagiotisvagenas chemqueryanaturallanguagequerydrivenserviceforcomprehensiveexplorationofchemistrypatentliterature
AT nikolaoslivathinos chemqueryanaturallanguagequerydrivenserviceforcomprehensiveexplorationofchemistrypatentliterature
AT christophauer chemqueryanaturallanguagequerydrivenserviceforcomprehensiveexplorationofchemistrypatentliterature
AT micheledolfi chemqueryanaturallanguagequerydrivenserviceforcomprehensiveexplorationofchemistrypatentliterature
AT peterstaar chemqueryanaturallanguagequerydrivenserviceforcomprehensiveexplorationofchemistrypatentliterature