MACHINE LEARNING PIPELINE USING DNA-ENCODED LIBRARY SELECTIONS

Embodiments of the disclosure involve training machine learned models using DNA-encoded library experimental data outputs and for deploying the trained machine learned models for conducting a virtual compound screen, for performing a hit selection and analysis, or for predicting binding affinities b...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Ma, Ralph, Sultan, Mohammad Muneeb, Riesselman, Adam, Dreiman, Gabriel, Liu, Bowen, Ruggiu, Fiorella
Format:	Patent
Sprache:	eng
Schlagworte:	CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS PHYSICS
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	Ma, Ralph Sultan, Mohammad Muneeb Riesselman, Adam Dreiman, Gabriel Liu, Bowen Ruggiu, Fiorella
description	Embodiments of the disclosure involve training machine learned models using DNA-encoded library experimental data outputs and for deploying the trained machine learned models for conducting a virtual compound screen, for performing a hit selection and analysis, or for predicting binding affinities between compounds and targets. Machine learned models are trained using one or more augmentations that selectively expand molecular representations of a training dataset. Furthermore, machine learned models are trained to account for confounding covariates, thereby improving the machine learned models' abilities to conduct a virtual screen, perform a hit selection, and to predict binding affinities.
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2023130619A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2023130619A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2023130619A13</originalsourceid><addsrcrecordid>eNrjZLDzdXT28PRzVfBxdQzy8_RzVwjwDHD1AYmEBoO4Ln6Ouq5-zv4uri4KPp5OQY5BkQrBrj6uziGe_n7BPAysaYk5xam8UJqbQdnNNcTZQze1ID8-tbggMTk1L7UkPjTYyMDI2NDYwMzQ0tHQmDhVAPJvKvA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>MACHINE LEARNING PIPELINE USING DNA-ENCODED LIBRARY SELECTIONS</title><source>esp@cenet</source><creator>Ma, Ralph ; Sultan, Mohammad Muneeb ; Riesselman, Adam ; Dreiman, Gabriel ; Liu, Bowen ; Ruggiu, Fiorella</creator><creatorcontrib>Ma, Ralph ; Sultan, Mohammad Muneeb ; Riesselman, Adam ; Dreiman, Gabriel ; Liu, Bowen ; Ruggiu, Fiorella</creatorcontrib><description>Embodiments of the disclosure involve training machine learned models using DNA-encoded library experimental data outputs and for deploying the trained machine learned models for conducting a virtual compound screen, for performing a hit selection and analysis, or for predicting binding affinities between compounds and targets. Machine learned models are trained using one or more augmentations that selectively expand molecular representations of a training dataset. Furthermore, machine learned models are trained to account for confounding covariates, thereby improving the machine learned models' abilities to conduct a virtual screen, perform a hit selection, and to predict binding affinities.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS ; PHYSICS</subject><creationdate>2023</creationdate><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://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230427&DB=EPODOC&CC=US&NR=2023130619A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230427&DB=EPODOC&CC=US&NR=2023130619A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Ma, Ralph</creatorcontrib><creatorcontrib>Sultan, Mohammad Muneeb</creatorcontrib><creatorcontrib>Riesselman, Adam</creatorcontrib><creatorcontrib>Dreiman, Gabriel</creatorcontrib><creatorcontrib>Liu, Bowen</creatorcontrib><creatorcontrib>Ruggiu, Fiorella</creatorcontrib><title>MACHINE LEARNING PIPELINE USING DNA-ENCODED LIBRARY SELECTIONS</title><description>Embodiments of the disclosure involve training machine learned models using DNA-encoded library experimental data outputs and for deploying the trained machine learned models for conducting a virtual compound screen, for performing a hit selection and analysis, or for predicting binding affinities between compounds and targets. Machine learned models are trained using one or more augmentations that selectively expand molecular representations of a training dataset. Furthermore, machine learned models are trained to account for confounding covariates, thereby improving the machine learned models' abilities to conduct a virtual screen, perform a hit selection, and to predict binding affinities.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLDzdXT28PRzVfBxdQzy8_RzVwjwDHD1AYmEBoO4Ln6Ouq5-zv4uri4KPp5OQY5BkQrBrj6uziGe_n7BPAysaYk5xam8UJqbQdnNNcTZQze1ID8-tbggMTk1L7UkPjTYyMDI2NDYwMzQ0tHQmDhVAPJvKvA</recordid><startdate>20230427</startdate><enddate>20230427</enddate><creator>Ma, Ralph</creator><creator>Sultan, Mohammad Muneeb</creator><creator>Riesselman, Adam</creator><creator>Dreiman, Gabriel</creator><creator>Liu, Bowen</creator><creator>Ruggiu, Fiorella</creator><scope>EVB</scope></search><sort><creationdate>20230427</creationdate><title>MACHINE LEARNING PIPELINE USING DNA-ENCODED LIBRARY SELECTIONS</title><author>Ma, Ralph ; Sultan, Mohammad Muneeb ; Riesselman, Adam ; Dreiman, Gabriel ; Liu, Bowen ; Ruggiu, Fiorella</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2023130619A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Ma, Ralph</creatorcontrib><creatorcontrib>Sultan, Mohammad Muneeb</creatorcontrib><creatorcontrib>Riesselman, Adam</creatorcontrib><creatorcontrib>Dreiman, Gabriel</creatorcontrib><creatorcontrib>Liu, Bowen</creatorcontrib><creatorcontrib>Ruggiu, Fiorella</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ma, Ralph</au><au>Sultan, Mohammad Muneeb</au><au>Riesselman, Adam</au><au>Dreiman, Gabriel</au><au>Liu, Bowen</au><au>Ruggiu, Fiorella</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>MACHINE LEARNING PIPELINE USING DNA-ENCODED LIBRARY SELECTIONS</title><date>2023-04-27</date><risdate>2023</risdate><abstract>Embodiments of the disclosure involve training machine learned models using DNA-encoded library experimental data outputs and for deploying the trained machine learned models for conducting a virtual compound screen, for performing a hit selection and analysis, or for predicting binding affinities between compounds and targets. Machine learned models are trained using one or more augmentations that selectively expand molecular representations of a training dataset. Furthermore, machine learned models are trained to account for confounding covariates, thereby improving the machine learned models' abilities to conduct a virtual screen, perform a hit selection, and to predict binding affinities.</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	eng
recordid	cdi_epo_espacenet_US2023130619A1
source	esp@cenet
subjects	CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS PHYSICS
title	MACHINE LEARNING PIPELINE USING DNA-ENCODED LIBRARY SELECTIONS
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-20T09%3A58%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=Ma,%20Ralph&rft.date=2023-04-27&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2023130619A1%3C/epo_EVB%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