Loading…

Large Language Model-Guided Prediction Toward Quantum Materials Synthesis

The synthesis of inorganic crystalline materials is essential for modern technology, especially in quantum materials development. However, designing efficient synthesis workflows remains a significant challenge due to the precise experimental conditions and extensive trial and error. Here, we presen...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-10
Main Authors: Okabe, Ryotaro, West, Zack, Chotrattanapituk, Abhijatmedhi, Cheng, Mouyang, Denisse Córdova Carrizales, Xie, Weiwei, Cava, Robert J, Li, Mingda
Format: Article
Language:English
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Okabe, Ryotaro
West, Zack
Chotrattanapituk, Abhijatmedhi
Cheng, Mouyang
Denisse Córdova Carrizales
Xie, Weiwei
Cava, Robert J
Li, Mingda
description The synthesis of inorganic crystalline materials is essential for modern technology, especially in quantum materials development. However, designing efficient synthesis workflows remains a significant challenge due to the precise experimental conditions and extensive trial and error. Here, we present a framework using large language models (LLMs) to predict synthesis pathways for inorganic materials, including quantum materials. Our framework contains three models: LHS2RHS, predicting products from reactants; RHS2LHS, predicting reactants from products; and TGT2CEQ, generating full chemical equations for target compounds. Fine-tuned on a text-mined synthesis database, our model raises accuracy from under 40% with pretrained models, to under 80% using conventional fine-tuning, and further to around 90% with our proposed generalized Tanimoto similarity, while maintaining robust to additional synthesis steps. Our model further demonstrates comparable performance across materials with varying degrees of quantumness quantified using quantum weight, indicating that LLMs offer a powerful tool to predict balanced chemical equations for quantum materials discovery.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3121793822</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3121793822</sourcerecordid><originalsourceid>FETCH-proquest_journals_31217938223</originalsourceid><addsrcrecordid>eNqNissKwjAQRYMgWLT_EHBdaCfW1rX4ggqK3ZfBjDWlJpoH4t_bhR_g6h7OuSMWgRBZUi4AJix2rkvTFJYF5LmI2KFC2xKvULcBBzgaSX2yC0qS5CdLUl29MprX5o1W8nNA7cODH9GTVdg7fvlofyen3IyNb4Og-LdTNt9u6vU-eVrzCuR805lg9ZAakUFWrEQJIP57fQFqeTxS</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3121793822</pqid></control><display><type>article</type><title>Large Language Model-Guided Prediction Toward Quantum Materials Synthesis</title><source>ProQuest Publicly Available Content database</source><creator>Okabe, Ryotaro ; West, Zack ; Chotrattanapituk, Abhijatmedhi ; Cheng, Mouyang ; Denisse Córdova Carrizales ; Xie, Weiwei ; Cava, Robert J ; Li, Mingda</creator><creatorcontrib>Okabe, Ryotaro ; West, Zack ; Chotrattanapituk, Abhijatmedhi ; Cheng, Mouyang ; Denisse Córdova Carrizales ; Xie, Weiwei ; Cava, Robert J ; Li, Mingda</creatorcontrib><description>The synthesis of inorganic crystalline materials is essential for modern technology, especially in quantum materials development. However, designing efficient synthesis workflows remains a significant challenge due to the precise experimental conditions and extensive trial and error. Here, we present a framework using large language models (LLMs) to predict synthesis pathways for inorganic materials, including quantum materials. Our framework contains three models: LHS2RHS, predicting products from reactants; RHS2LHS, predicting reactants from products; and TGT2CEQ, generating full chemical equations for target compounds. Fine-tuned on a text-mined synthesis database, our model raises accuracy from under 40% with pretrained models, to under 80% using conventional fine-tuning, and further to around 90% with our proposed generalized Tanimoto similarity, while maintaining robust to additional synthesis steps. Our model further demonstrates comparable performance across materials with varying degrees of quantumness quantified using quantum weight, indicating that LLMs offer a powerful tool to predict balanced chemical equations for quantum materials discovery.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Chemical compounds ; Chemical synthesis ; Inorganic materials ; Large language models</subject><ispartof>arXiv.org, 2024-10</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/3121793822?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Okabe, Ryotaro</creatorcontrib><creatorcontrib>West, Zack</creatorcontrib><creatorcontrib>Chotrattanapituk, Abhijatmedhi</creatorcontrib><creatorcontrib>Cheng, Mouyang</creatorcontrib><creatorcontrib>Denisse Córdova Carrizales</creatorcontrib><creatorcontrib>Xie, Weiwei</creatorcontrib><creatorcontrib>Cava, Robert J</creatorcontrib><creatorcontrib>Li, Mingda</creatorcontrib><title>Large Language Model-Guided Prediction Toward Quantum Materials Synthesis</title><title>arXiv.org</title><description>The synthesis of inorganic crystalline materials is essential for modern technology, especially in quantum materials development. However, designing efficient synthesis workflows remains a significant challenge due to the precise experimental conditions and extensive trial and error. Here, we present a framework using large language models (LLMs) to predict synthesis pathways for inorganic materials, including quantum materials. Our framework contains three models: LHS2RHS, predicting products from reactants; RHS2LHS, predicting reactants from products; and TGT2CEQ, generating full chemical equations for target compounds. Fine-tuned on a text-mined synthesis database, our model raises accuracy from under 40% with pretrained models, to under 80% using conventional fine-tuning, and further to around 90% with our proposed generalized Tanimoto similarity, while maintaining robust to additional synthesis steps. Our model further demonstrates comparable performance across materials with varying degrees of quantumness quantified using quantum weight, indicating that LLMs offer a powerful tool to predict balanced chemical equations for quantum materials discovery.</description><subject>Chemical compounds</subject><subject>Chemical synthesis</subject><subject>Inorganic materials</subject><subject>Large language models</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNissKwjAQRYMgWLT_EHBdaCfW1rX4ggqK3ZfBjDWlJpoH4t_bhR_g6h7OuSMWgRBZUi4AJix2rkvTFJYF5LmI2KFC2xKvULcBBzgaSX2yC0qS5CdLUl29MprX5o1W8nNA7cODH9GTVdg7fvlofyen3IyNb4Og-LdTNt9u6vU-eVrzCuR805lg9ZAakUFWrEQJIP57fQFqeTxS</recordid><startdate>20241028</startdate><enddate>20241028</enddate><creator>Okabe, Ryotaro</creator><creator>West, Zack</creator><creator>Chotrattanapituk, Abhijatmedhi</creator><creator>Cheng, Mouyang</creator><creator>Denisse Córdova Carrizales</creator><creator>Xie, Weiwei</creator><creator>Cava, Robert J</creator><creator>Li, Mingda</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20241028</creationdate><title>Large Language Model-Guided Prediction Toward Quantum Materials Synthesis</title><author>Okabe, Ryotaro ; West, Zack ; Chotrattanapituk, Abhijatmedhi ; Cheng, Mouyang ; Denisse Córdova Carrizales ; Xie, Weiwei ; Cava, Robert J ; Li, Mingda</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_31217938223</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Chemical compounds</topic><topic>Chemical synthesis</topic><topic>Inorganic materials</topic><topic>Large language models</topic><toplevel>online_resources</toplevel><creatorcontrib>Okabe, Ryotaro</creatorcontrib><creatorcontrib>West, Zack</creatorcontrib><creatorcontrib>Chotrattanapituk, Abhijatmedhi</creatorcontrib><creatorcontrib>Cheng, Mouyang</creatorcontrib><creatorcontrib>Denisse Córdova Carrizales</creatorcontrib><creatorcontrib>Xie, Weiwei</creatorcontrib><creatorcontrib>Cava, Robert J</creatorcontrib><creatorcontrib>Li, Mingda</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>ProQuest Publicly Available Content database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Okabe, Ryotaro</au><au>West, Zack</au><au>Chotrattanapituk, Abhijatmedhi</au><au>Cheng, Mouyang</au><au>Denisse Córdova Carrizales</au><au>Xie, Weiwei</au><au>Cava, Robert J</au><au>Li, Mingda</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Large Language Model-Guided Prediction Toward Quantum Materials Synthesis</atitle><jtitle>arXiv.org</jtitle><date>2024-10-28</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>The synthesis of inorganic crystalline materials is essential for modern technology, especially in quantum materials development. However, designing efficient synthesis workflows remains a significant challenge due to the precise experimental conditions and extensive trial and error. Here, we present a framework using large language models (LLMs) to predict synthesis pathways for inorganic materials, including quantum materials. Our framework contains three models: LHS2RHS, predicting products from reactants; RHS2LHS, predicting reactants from products; and TGT2CEQ, generating full chemical equations for target compounds. Fine-tuned on a text-mined synthesis database, our model raises accuracy from under 40% with pretrained models, to under 80% using conventional fine-tuning, and further to around 90% with our proposed generalized Tanimoto similarity, while maintaining robust to additional synthesis steps. Our model further demonstrates comparable performance across materials with varying degrees of quantumness quantified using quantum weight, indicating that LLMs offer a powerful tool to predict balanced chemical equations for quantum materials discovery.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2024-10
issn 2331-8422
language eng
recordid cdi_proquest_journals_3121793822
source ProQuest Publicly Available Content database
subjects Chemical compounds
Chemical synthesis
Inorganic materials
Large language models
title Large Language Model-Guided Prediction Toward Quantum Materials Synthesis
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T12%3A57%3A35IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Large%20Language%20Model-Guided%20Prediction%20Toward%20Quantum%20Materials%20Synthesis&rft.jtitle=arXiv.org&rft.au=Okabe,%20Ryotaro&rft.date=2024-10-28&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3121793822%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_31217938223%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3121793822&rft_id=info:pmid/&rfr_iscdi=true