<HashMap><database>biostudies-literature</database><scores/><additional><omics_type>Unknown</omics_type><submitter>Wei S</submitter><pubmed_abstract>Precise design of excited-state intramolecular proton transfer (ESIPT) molecules targeting advanced optoelectronic or biological sensing applications presents a fundamental challenge. Controlling the energy difference (Δ&lt;i>E&lt;/i>*) between normal (N*) and tautomeric (T*) excited-state forms is crucial, yet the complex interplay of hydrogen bond (H-bond) strength, proton donor acidity, and proton acceptor basicity with Δ&lt;i>E&lt;/i>* remains insufficiently explored. Conventional trial-and-error approaches for designing tailored ESIPT compounds suffer from inefficient synthesis. To address this, we constructed a high-quality ESIPT dataset by introducing ten substituents with progressively increasing electron-donating capacity into six representative ESIPT parent scaffolds. Integrating qualitative</pubmed_abstract><journal>Chemical science</journal><full_dataset_link>https://www.ebi.ac.uk/biostudies/studies/S-EPMC12910287</full_dataset_link><repository>biostudies-literature</repository><pubmed_title>Unveiling key descriptors &amp;lt;i&amp;gt;via&amp;lt;/i&amp;gt; machine learning: toward rational molecular design of chromophores with excited-state intramolecular proton transfer.</pubmed_title><pmcid>PMC12910287</pmcid><pubmed_authors>Yang Z</pubmed_authors><pubmed_authors>Li Y</pubmed_authors><pubmed_authors>Guo Y</pubmed_authors><pubmed_authors>Wei S</pubmed_authors><pubmed_authors>Xia A</pubmed_authors><pubmed_authors>Yang C</pubmed_authors><pubmed_authors>Kuang Z</pubmed_authors><pubmed_authors>Zhao H</pubmed_authors></additional><is_claimable>false</is_claimable><name>Unveiling key descriptors &amp;lt;i&amp;gt;via&amp;lt;/i&amp;gt; machine learning: toward rational molecular design of chromophores with excited-state intramolecular proton transfer.</name><description>Precise design of excited-state intramolecular proton transfer (ESIPT) molecules targeting advanced optoelectronic or biological sensing applications presents a fundamental challenge. Controlling the energy difference (Δ&lt;i>E&lt;/i>*) between normal (N*) and tautomeric (T*) excited-state forms is crucial, yet the complex interplay of hydrogen bond (H-bond) strength, proton donor acidity, and proton acceptor basicity with Δ&lt;i>E&lt;/i>* remains insufficiently explored. Conventional trial-and-error approaches for designing tailored ESIPT compounds suffer from inefficient synthesis. To address this, we constructed a high-quality ESIPT dataset by introducing ten substituents with progressively increasing electron-donating capacity into six representative ESIPT parent scaffolds. Integrating qualitative</description><dates><release>2026-01-01T00:00:00Z</release><publication>2026 Feb</publication><modification>2026-07-16T11:56:54.242Z</modification><creation>2026-07-09T10:53:01.139Z</creation></dates><accession>S-EPMC12910287</accession><cross_references><pubmed>41710208</pubmed><doi>10.1039/d5sc07051a</doi></cross_references></HashMap>