{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T10:49:54Z","timestamp":1792147794833,"version":"4.4.0"},"reference-count":0,"publisher":"Bentham Science Publishers Ltd.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CTMC"],"published-print":{"date-parts":[[2026,10,13]]},"abstract":"<jats:sec>\n                    <jats:title>Introduction:<\/jats:title>\n                    <jats:p>The type III Phosphatidylinositol 4-kinase (PI4KIII\u03b2) serves as a key\nhost factor that mediates the replication of RNA viruses and is involved in essential membrane\ntrafficking events. The development of PI4KIII\u03b2-specific inhibitors could give insights into the\nenzyme's function and contribute to the treatment of viral diseases. However, the molecular features\nthat determine inhibitor activity and selectivity remain unclear.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>PI4KIII\u03b2 inhibitors with reported biological activities (pIC50) were systematically analyzed\nusing machine-learning methods. Molecular characterization was performed using RDKit,\nChemopy descriptors, and PubChem fingerprints. Multiple classification and regression models\nwere developed and evaluated using 10-fold cross-validation to establish robust structureactivity\nrelationships.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>results:<\/jats:title>\n                    <jats:p>It was suggested that the PubChem fingerprints-based linear regression, SMOreg, and GaussianProcesses models were more appropriate for the studied dataset to deliver the best predictive ability, which showed a correlation coefficient value &amp;gt; 0.7 in the 10-fold cross-validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>It was suggested that the PubChem fingerprint-based linear regression, SMOreg, and\nGaussianProcesses models were more appropriate for the studied dataset to deliver the best predictive\nability, which showed a correlation coefficient value &gt; 0.7 in the 10-fold crossvalidation.\nPubChemFP389 and PubChemFP572, representing amidine-like fragments or guanidine-\nrelated motifs, and the aromatic amine fragment showed a negative correlation with respect\nto biological activity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion:<\/jats:title>\n                    <jats:p>The study describes predictive models and provides insights into essential structural\nfeatures in chemical compounds relevant for inhibitory activity, which could assist in the design\nand optimization of novel PI4KIII\u03b2 inhibitors for antiviral and anticancer applications. A similar\napproach may be extended to a larger dataset of molecules or to other related drug targets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions:<\/jats:title>\n                    <jats:p>The findings suggest that excessive basicity and certain polar functionalities may\nbe detrimental to PI4KIII\u03b2 inhibition, providing important insights into the structural features\ninfluencing ligand binding and activity.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2174\/0115680266517367261009103151","type":"journal-article","created":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T10:25:31Z","timestamp":1792146331000},"source":"Crossref","is-referenced-by-count":0,"title":["Reliability of Machine Learning Approaches Towards the Identification of Novel PI4KIII\u03b2 Inhibitors"],"prefix":"10.2174","volume":"26","author":[{"given":"Priyanka","family":"Andola","sequence":"first","affiliation":[{"name":"School of Chemistry, University of Hyderabad, Hyderabad 500046, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prasanna","family":"Sagane","sequence":"additional","affiliation":[{"name":"School of Chemistry, University of Hyderabad, Hyderabad 500046, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lalitha","family":"Guruprasad","sequence":"additional","affiliation":[{"name":"School of Chemistry, University of Hyderabad, Hyderabad 500046, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"965","container-title":["Current Topics in Medicinal Chemistry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.eurekaselect.com\/article\/download?doi=10.2174\/0115680266517367261009103151","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.eurekaselect.com\/259492\/article","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.eurekaselect.com\/article\/download?doi=10.2174\/0115680266517367261009103151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T10:25:37Z","timestamp":1792146337000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.eurekaselect.com\/259492\/article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,13]]},"references-count":0,"alternative-id":["LiveAll1"],"URL":"https:\/\/doi.org\/10.2174\/0115680266517367261009103151","relation":{},"ISSN":["1568-0266"],"issn-type":[{"value":"1568-0266","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10,13]]}}}