Learning the rules of peptide self-assembly through data mining with large language models
Peptides are ubiquitous and important biologically derived molecules, that have been found to self-assemble to form a wide array of structures. Extensive research has explored the impacts of both internal chemical composition and external environmental stimuli on the self-assembly behaviour of these...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | |
container_volume | |
creator | Yang, Zhenze Yorke, Sarah K Knowles, Tuomas P. J Buehler, Markus J |
description | Peptides are ubiquitous and important biologically derived molecules, that
have been found to self-assemble to form a wide array of structures. Extensive
research has explored the impacts of both internal chemical composition and
external environmental stimuli on the self-assembly behaviour of these systems.
However, there is yet to be a systematic study that gathers this rich
literature data and collectively examines these experimental factors to provide
a global picture of the fundamental rules that govern protein self-assembly
behavior. In this work, we curate a peptide assembly database through a
combination of manual processing by human experts and literature mining
facilitated by a large language model. As a result, we collect more than 1,000
experimental data entries with information about peptide sequence, experimental
conditions and corresponding self-assembly phases. Utilizing the collected
data, ML models are trained and evaluated, demonstrating excellent accuracy
(>80\%) and efficiency in peptide assembly phase classification. Moreover, we
fine-tune our GPT model for peptide literature mining with the developed
dataset, which exhibits markedly superior performance in extracting information
from academic publications relative to the pre-trained model. We find that this
workflow can substantially improve efficiency when exploring potential
self-assembling peptide candidates, through guiding experimental work, while
also deepening our understanding of the mechanisms governing peptide
self-assembly. In doing so, novel structures can be accessed for a range of
applications including sensing, catalysis and biomaterials. |
doi_str_mv | 10.48550/arxiv.2411.05421 |
format | Article |
fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2411_05421</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2411_05421</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2411_054213</originalsourceid><addsrcrecordid>eNqFjjsOwjAQRN1QIOAAVOwFEuJ8JHoEoqCkookWZeNY8idaO0BuT4joaWameCM9IbYyS8tDVWV75Ld-pnkpZZpVZS6X4n4lZKedgtgR8GAogG-hpz7qhiCQaRMMgezDjBPCflAdNBgRrJ5vLx07MMiKpnRqwGlY35AJa7Fo0QTa_HoldufT7XhJZou6Z22Rx_prU882xX_iA9QnQIk</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Learning the rules of peptide self-assembly through data mining with large language models</title><source>arXiv.org</source><creator>Yang, Zhenze ; Yorke, Sarah K ; Knowles, Tuomas P. J ; Buehler, Markus J</creator><creatorcontrib>Yang, Zhenze ; Yorke, Sarah K ; Knowles, Tuomas P. J ; Buehler, Markus J</creatorcontrib><description>Peptides are ubiquitous and important biologically derived molecules, that
have been found to self-assemble to form a wide array of structures. Extensive
research has explored the impacts of both internal chemical composition and
external environmental stimuli on the self-assembly behaviour of these systems.
However, there is yet to be a systematic study that gathers this rich
literature data and collectively examines these experimental factors to provide
a global picture of the fundamental rules that govern protein self-assembly
behavior. In this work, we curate a peptide assembly database through a
combination of manual processing by human experts and literature mining
facilitated by a large language model. As a result, we collect more than 1,000
experimental data entries with information about peptide sequence, experimental
conditions and corresponding self-assembly phases. Utilizing the collected
data, ML models are trained and evaluated, demonstrating excellent accuracy
(>80\%) and efficiency in peptide assembly phase classification. Moreover, we
fine-tune our GPT model for peptide literature mining with the developed
dataset, which exhibits markedly superior performance in extracting information
from academic publications relative to the pre-trained model. We find that this
workflow can substantially improve efficiency when exploring potential
self-assembling peptide candidates, through guiding experimental work, while
also deepening our understanding of the mechanisms governing peptide
self-assembly. In doing so, novel structures can be accessed for a range of
applications including sensing, catalysis and biomaterials.</description><identifier>DOI: 10.48550/arxiv.2411.05421</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Computation and Language ; Physics - Disordered Systems and Neural Networks ; Physics - Mesoscale and Nanoscale Physics ; Physics - Soft Condensed Matter</subject><creationdate>2024-11</creationdate><rights>http://creativecommons.org/licenses/by-nc-nd/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2411.05421$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2411.05421$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Yang, Zhenze</creatorcontrib><creatorcontrib>Yorke, Sarah K</creatorcontrib><creatorcontrib>Knowles, Tuomas P. J</creatorcontrib><creatorcontrib>Buehler, Markus J</creatorcontrib><title>Learning the rules of peptide self-assembly through data mining with large language models</title><description>Peptides are ubiquitous and important biologically derived molecules, that
have been found to self-assemble to form a wide array of structures. Extensive
research has explored the impacts of both internal chemical composition and
external environmental stimuli on the self-assembly behaviour of these systems.
However, there is yet to be a systematic study that gathers this rich
literature data and collectively examines these experimental factors to provide
a global picture of the fundamental rules that govern protein self-assembly
behavior. In this work, we curate a peptide assembly database through a
combination of manual processing by human experts and literature mining
facilitated by a large language model. As a result, we collect more than 1,000
experimental data entries with information about peptide sequence, experimental
conditions and corresponding self-assembly phases. Utilizing the collected
data, ML models are trained and evaluated, demonstrating excellent accuracy
(>80\%) and efficiency in peptide assembly phase classification. Moreover, we
fine-tune our GPT model for peptide literature mining with the developed
dataset, which exhibits markedly superior performance in extracting information
from academic publications relative to the pre-trained model. We find that this
workflow can substantially improve efficiency when exploring potential
self-assembling peptide candidates, through guiding experimental work, while
also deepening our understanding of the mechanisms governing peptide
self-assembly. In doing so, novel structures can be accessed for a range of
applications including sensing, catalysis and biomaterials.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computation and Language</subject><subject>Physics - Disordered Systems and Neural Networks</subject><subject>Physics - Mesoscale and Nanoscale Physics</subject><subject>Physics - Soft Condensed Matter</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNqFjjsOwjAQRN1QIOAAVOwFEuJ8JHoEoqCkookWZeNY8idaO0BuT4joaWameCM9IbYyS8tDVWV75Ld-pnkpZZpVZS6X4n4lZKedgtgR8GAogG-hpz7qhiCQaRMMgezDjBPCflAdNBgRrJ5vLx07MMiKpnRqwGlY35AJa7Fo0QTa_HoldufT7XhJZou6Z22Rx_prU882xX_iA9QnQIk</recordid><startdate>20241108</startdate><enddate>20241108</enddate><creator>Yang, Zhenze</creator><creator>Yorke, Sarah K</creator><creator>Knowles, Tuomas P. J</creator><creator>Buehler, Markus J</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20241108</creationdate><title>Learning the rules of peptide self-assembly through data mining with large language models</title><author>Yang, Zhenze ; Yorke, Sarah K ; Knowles, Tuomas P. J ; Buehler, Markus J</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2411_054213</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computation and Language</topic><topic>Physics - Disordered Systems and Neural Networks</topic><topic>Physics - Mesoscale and Nanoscale Physics</topic><topic>Physics - Soft Condensed Matter</topic><toplevel>online_resources</toplevel><creatorcontrib>Yang, Zhenze</creatorcontrib><creatorcontrib>Yorke, Sarah K</creatorcontrib><creatorcontrib>Knowles, Tuomas P. J</creatorcontrib><creatorcontrib>Buehler, Markus J</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Yang, Zhenze</au><au>Yorke, Sarah K</au><au>Knowles, Tuomas P. J</au><au>Buehler, Markus J</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Learning the rules of peptide self-assembly through data mining with large language models</atitle><date>2024-11-08</date><risdate>2024</risdate><abstract>Peptides are ubiquitous and important biologically derived molecules, that
have been found to self-assemble to form a wide array of structures. Extensive
research has explored the impacts of both internal chemical composition and
external environmental stimuli on the self-assembly behaviour of these systems.
However, there is yet to be a systematic study that gathers this rich
literature data and collectively examines these experimental factors to provide
a global picture of the fundamental rules that govern protein self-assembly
behavior. In this work, we curate a peptide assembly database through a
combination of manual processing by human experts and literature mining
facilitated by a large language model. As a result, we collect more than 1,000
experimental data entries with information about peptide sequence, experimental
conditions and corresponding self-assembly phases. Utilizing the collected
data, ML models are trained and evaluated, demonstrating excellent accuracy
(>80\%) and efficiency in peptide assembly phase classification. Moreover, we
fine-tune our GPT model for peptide literature mining with the developed
dataset, which exhibits markedly superior performance in extracting information
from academic publications relative to the pre-trained model. We find that this
workflow can substantially improve efficiency when exploring potential
self-assembling peptide candidates, through guiding experimental work, while
also deepening our understanding of the mechanisms governing peptide
self-assembly. In doing so, novel structures can be accessed for a range of
applications including sensing, catalysis and biomaterials.</abstract><doi>10.48550/arxiv.2411.05421</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | DOI: 10.48550/arxiv.2411.05421 |
ispartof | |
issn | |
language | eng |
recordid | cdi_arxiv_primary_2411_05421 |
source | arXiv.org |
subjects | Computer Science - Artificial Intelligence Computer Science - Computation and Language Physics - Disordered Systems and Neural Networks Physics - Mesoscale and Nanoscale Physics Physics - Soft Condensed Matter |
title | Learning the rules of peptide self-assembly through data mining with large language models |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T04%3A53%3A37IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Learning%20the%20rules%20of%20peptide%20self-assembly%20through%20data%20mining%20with%20large%20language%20models&rft.au=Yang,%20Zhenze&rft.date=2024-11-08&rft_id=info:doi/10.48550/arxiv.2411.05421&rft_dat=%3Carxiv_GOX%3E2411_05421%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |