You are currently on a failover version of the Materials Cloud Archive hosted at CINECA, Italy.
Click here to access the main Materials Cloud Archive.
Note: If the link above redirects you to this page, it means that the Archive is currently offline due to maintenance. We will be back online as soon as possible.
This version is read-only: you can view published records and download files, but you cannot create new records or make changes to existing ones.
<?xml version='1.0' encoding='utf-8'?> <oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd"> <dc:creator>van Gerwen, Puck</dc:creator> <dc:creator>R. Briling, Ksenia</dc:creator> <dc:creator>Calvino Alonso, Yannick</dc:creator> <dc:creator>Franke, Malte</dc:creator> <dc:creator>Corminboeuf, Clemence</dc:creator> <dc:date>2024-10-16</dc:date> <dc:description>In recent years, there has been a surge of interest in predicting computed activation barriers, to enable the acceleration of the automated exploration of reaction networks. Consequently, various predictive approaches have emerged, ranging from graph-based models to methods based on the three-dimensional structure of reactants and products. In tandem, many representations have been developed to predict experimental targets, which may hold promise for barrier prediction as well. Here, we bring together all of these efforts and benchmark various methods (Morgan fingerprints, the DRFP, the CGR representation-based Chemprop, SLATMd, B²Rl², EquiReact and language model BERT + RXNFP) for the prediction of computed activation barriers on three diverse datasets. This record includes data to support the article "Benchmarking machine-readable vectors of chemical reactions on computed activation barriers". This supports the github repository https://github.com/lcmd-epfl/benchmark-barrier-learning which contains the codes and duplicates the data.</dc:description> <dc:identifier>https://materialscloud-archive-failover.cineca.it/record/2024.163</dc:identifier> <dc:identifier>doi:10.24435/materialscloud:xd-10</dc:identifier> <dc:identifier>mcid:2024.163</dc:identifier> <dc:identifier>oai:materialscloud.org:2401</dc:identifier> <dc:language>en</dc:language> <dc:publisher>Materials Cloud</dc:publisher> <dc:rights>info:eu-repo/semantics/openAccess</dc:rights> <dc:rights>Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode</dc:rights> <dc:subject>chemical reactions</dc:subject> <dc:subject>machine learning</dc:subject> <dc:subject>benchmark</dc:subject> <dc:subject>EPFL</dc:subject> <dc:subject>MARVEL/P2</dc:subject> <dc:subject>SNSF</dc:subject> <dc:subject>ERC</dc:subject> <dc:title>Benchmarking machine-readable vectors of chemical reactions on computed activation barriers</dc:title> <dc:type>Dataset</dc:type> </oai_dc:dc>