A
Alexander Tropsha
Researcher at University of North Carolina at Chapel Hill
Publications - 306
Citations - 26956
Alexander Tropsha is an academic researcher from University of North Carolina at Chapel Hill. The author has contributed to research in topics: Quantitative structure–activity relationship & Virtual screening. The author has an hindex of 71, co-authored 288 publications receiving 22898 citations. Previous affiliations of Alexander Tropsha include Kazan Federal University.
Papers
More filters
Posted Content
AFLOW-ML: A RESTful API for machine-learning predictions of materials properties
Eric Gossett,Cormac Toher,Corey Oses,Olexandr Isayev,Fleur Legrain,Frisco Rose,Eva Zurek,Jesús Carrete,Natalio Mingo,Alexander Tropsha,Stefano Curtarolo,Stefano Curtarolo +11 more
TL;DR: AFLow-ML (AFLOW $\underline{\mathrm{M}}$achine $\ underline{L}}$earning) overcomes the problem by streamlining the use of the machine learning methods developed within the AFLOW consortium by providing an open RESTful API to directly access the continuously updated algorithms.
Journal ArticleDOI
Pseudotorsional OCCO backbone angle as a single descriptor of protein secondary structure
TL;DR: It is suggested that the secondary structure can be adequately characterized by a single descriptor, the Oi‐1 Ci‐1CiOi pseudotorsional backbone angle, and preliminary results indicate that this new approach has a significant potential for rapid identification of fold families in the Protein Data Bank.
Book ChapterDOI
Cross-Validated R2 Guided Region Selection for CoMFA Studies
Alexander Tropsha,Sung Jin Cho +1 more
TL;DR: In this article, the results of the field evaluation in every grid-point for every molecule in the dataset are placed in the CoMFA QSAR table which, therefore, contains thousands of columns.
Book ChapterDOI
A topological characterization of protein structure
TL;DR: An objective characterization of protein structure based entirely on the geometry of its parts is developed, and preliminary results from the discrimination of protein families using this representation are provided.
Journal ArticleDOI
Target-specific native/decoy pose classifier improves the accuracy of ligand ranking in the CSAR 2013 benchmark.
TL;DR: This study reconfirms that target-specific pose scoring models are capable of enhancing the reliability of structure-based molecular docking by discarding decoy poses.