Geometric Constraints in Probabilistic Manifolds: A Bridge from Molecular Dynamics to Structured Diffusion Processes

Understanding the macroscopic characteristics of biological complexes demands precision and specificity in statistical ensemble modeling. One of the primary challenges in this domain lies in sampling from particular subsets of the state-space, driven either by existing structural knowledge or specif...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Diamond, Justin, Lill, Markus
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 Diamond, Justin
Lill, Markus
description Understanding the macroscopic characteristics of biological complexes demands precision and specificity in statistical ensemble modeling. One of the primary challenges in this domain lies in sampling from particular subsets of the state-space, driven either by existing structural knowledge or specific areas of interest within the state-space. We propose a method that enables sampling from distributions that rigorously adhere to arbitrary sets of geometric constraints in Euclidean spaces. This is achieved by integrating a constraint projection operator within the well-regarded architecture of Denoising Diffusion Probabilistic Models, a framework founded in generative modeling and probabilistic inference. The significance of this work becomes apparent, for instance, in the context of deep learning-based drug design, where it is imperative to maintain specific molecular profile interactions to realize the desired therapeutic outcomes and guarantee safety.
doi_str_mv 10.48550/arxiv.2307.04493
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2307_04493</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2307_04493</sourcerecordid><originalsourceid>FETCH-LOGICAL-a673-e4c24e5c0504836bf68eaee1cb419e95c89ef8ec4bc37721ba1fd35fa6900e593</originalsourceid><addsrcrecordid>eNotz7FOwzAUheEsDKjwAEz4BRKc2E5itpJCQWoFEt2ja-caXSmJke0g-vZA6XSGI_3Sl2U3JS9kqxS_g_BNX0UleFNwKbW4zNIW_YQpkGWdn2MKQHOKjGb2FrwBQyPF9HvuYSbnxyHeszV7CDR8IHPBT2zvR7TLCIFtjjNMZCNLnr2nsNi0BBzYhpxbIvlT0WKMGK-yCwdjxOvzrrLD0-Ohe853r9uXbr3LoW5EjtJWEpXlistW1MbVLQJiaY0sNWplW42uRSuNFU1TlQZKNwjloNaco9Jild3-Z0_s_jPQBOHY__H7E1_8AP0MV_k</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Geometric Constraints in Probabilistic Manifolds: A Bridge from Molecular Dynamics to Structured Diffusion Processes</title><source>arXiv.org</source><creator>Diamond, Justin ; Lill, Markus</creator><creatorcontrib>Diamond, Justin ; Lill, Markus</creatorcontrib><description>Understanding the macroscopic characteristics of biological complexes demands precision and specificity in statistical ensemble modeling. One of the primary challenges in this domain lies in sampling from particular subsets of the state-space, driven either by existing structural knowledge or specific areas of interest within the state-space. We propose a method that enables sampling from distributions that rigorously adhere to arbitrary sets of geometric constraints in Euclidean spaces. This is achieved by integrating a constraint projection operator within the well-regarded architecture of Denoising Diffusion Probabilistic Models, a framework founded in generative modeling and probabilistic inference. The significance of this work becomes apparent, for instance, in the context of deep learning-based drug design, where it is imperative to maintain specific molecular profile interactions to realize the desired therapeutic outcomes and guarantee safety.</description><identifier>DOI: 10.48550/arxiv.2307.04493</identifier><language>eng</language><subject>Computer Science - Learning ; Quantitative Biology - Quantitative Methods</subject><creationdate>2023-07</creationdate><rights>http://creativecommons.org/licenses/by/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/2307.04493$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2307.04493$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Diamond, Justin</creatorcontrib><creatorcontrib>Lill, Markus</creatorcontrib><title>Geometric Constraints in Probabilistic Manifolds: A Bridge from Molecular Dynamics to Structured Diffusion Processes</title><description>Understanding the macroscopic characteristics of biological complexes demands precision and specificity in statistical ensemble modeling. One of the primary challenges in this domain lies in sampling from particular subsets of the state-space, driven either by existing structural knowledge or specific areas of interest within the state-space. We propose a method that enables sampling from distributions that rigorously adhere to arbitrary sets of geometric constraints in Euclidean spaces. This is achieved by integrating a constraint projection operator within the well-regarded architecture of Denoising Diffusion Probabilistic Models, a framework founded in generative modeling and probabilistic inference. The significance of this work becomes apparent, for instance, in the context of deep learning-based drug design, where it is imperative to maintain specific molecular profile interactions to realize the desired therapeutic outcomes and guarantee safety.</description><subject>Computer Science - Learning</subject><subject>Quantitative Biology - Quantitative Methods</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz7FOwzAUheEsDKjwAEz4BRKc2E5itpJCQWoFEt2ja-caXSmJke0g-vZA6XSGI_3Sl2U3JS9kqxS_g_BNX0UleFNwKbW4zNIW_YQpkGWdn2MKQHOKjGb2FrwBQyPF9HvuYSbnxyHeszV7CDR8IHPBT2zvR7TLCIFtjjNMZCNLnr2nsNi0BBzYhpxbIvlT0WKMGK-yCwdjxOvzrrLD0-Ohe853r9uXbr3LoW5EjtJWEpXlistW1MbVLQJiaY0sNWplW42uRSuNFU1TlQZKNwjloNaco9Jild3-Z0_s_jPQBOHY__H7E1_8AP0MV_k</recordid><startdate>20230710</startdate><enddate>20230710</enddate><creator>Diamond, Justin</creator><creator>Lill, Markus</creator><scope>AKY</scope><scope>ALC</scope><scope>GOX</scope></search><sort><creationdate>20230710</creationdate><title>Geometric Constraints in Probabilistic Manifolds: A Bridge from Molecular Dynamics to Structured Diffusion Processes</title><author>Diamond, Justin ; Lill, Markus</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a673-e4c24e5c0504836bf68eaee1cb419e95c89ef8ec4bc37721ba1fd35fa6900e593</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Learning</topic><topic>Quantitative Biology - Quantitative Methods</topic><toplevel>online_resources</toplevel><creatorcontrib>Diamond, Justin</creatorcontrib><creatorcontrib>Lill, Markus</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Quantitative Biology</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Diamond, Justin</au><au>Lill, Markus</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Geometric Constraints in Probabilistic Manifolds: A Bridge from Molecular Dynamics to Structured Diffusion Processes</atitle><date>2023-07-10</date><risdate>2023</risdate><abstract>Understanding the macroscopic characteristics of biological complexes demands precision and specificity in statistical ensemble modeling. One of the primary challenges in this domain lies in sampling from particular subsets of the state-space, driven either by existing structural knowledge or specific areas of interest within the state-space. We propose a method that enables sampling from distributions that rigorously adhere to arbitrary sets of geometric constraints in Euclidean spaces. This is achieved by integrating a constraint projection operator within the well-regarded architecture of Denoising Diffusion Probabilistic Models, a framework founded in generative modeling and probabilistic inference. The significance of this work becomes apparent, for instance, in the context of deep learning-based drug design, where it is imperative to maintain specific molecular profile interactions to realize the desired therapeutic outcomes and guarantee safety.</abstract><doi>10.48550/arxiv.2307.04493</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2307.04493
ispartof
issn
language eng
recordid cdi_arxiv_primary_2307_04493
source arXiv.org
subjects Computer Science - Learning
Quantitative Biology - Quantitative Methods
title Geometric Constraints in Probabilistic Manifolds: A Bridge from Molecular Dynamics to Structured Diffusion Processes
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T06%3A54%3A36IST&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=Geometric%20Constraints%20in%20Probabilistic%20Manifolds:%20A%20Bridge%20from%20Molecular%20Dynamics%20to%20Structured%20Diffusion%20Processes&rft.au=Diamond,%20Justin&rft.date=2023-07-10&rft_id=info:doi/10.48550/arxiv.2307.04493&rft_dat=%3Carxiv_GOX%3E2307_04493%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