D
Dimitris K. Agrafiotis
Researcher at Princeton University
Publications - 119
Citations - 4947
Dimitris K. Agrafiotis is an academic researcher from Princeton University. The author has contributed to research in topics: Set (abstract data type) & Artificial neural network. The author has an hindex of 39, co-authored 118 publications receiving 4584 citations. Previous affiliations of Dimitris K. Agrafiotis include Johnson & Johnson & Johnson & Johnson Pharmaceutical Research and Development.
Papers
More filters
Journal ArticleDOI
QSAR without borders
Eugene N. Muratov,Eugene N. Muratov,Jürgen Bajorath,Robert P. Sheridan,Igor V. Tetko,Dmitry Filimonov,Vladimir Poroikov,Tudor I. Oprea,Tudor I. Oprea,Tudor I. Oprea,Igor I. Baskin,Igor I. Baskin,Alexandre Varnek,Adrian E. Roitberg,Olexandr Isayev,Stefano Curtalolo,Denis Fourches,Yoram Cohen,Alán Aspuru-Guzik,David A. Winkler,Dimitris K. Agrafiotis,Artem Cherkasov,Alexander Tropsha +22 more
TL;DR: This Perspective summarizes recent technological advances in QSAR modeling but it also highlights the applicability of algorithms, modeling methods, and validation practices developed inQSAR to a wide range of research areas outside of traditional QSar boundaries including synthesis planning, nanotechnology, materials science, biomaterials, and clinical informatics.
Journal ArticleDOI
Recognizing Pitfalls in Virtual Screening: A Critical Review
Thomas Scior,Andreas Bender,Gary Tresadern,José L. Medina-Franco,Karina Martinez-Mayorga,Thierry Langer,Karina Cuanalo-Contreras,Dimitris K. Agrafiotis +7 more
TL;DR: This review attempts to catalogue published and unpublished problems, shortcomings, failures, and technical traps of VS methods with the aim to avoid pitfalls by making the user aware of them in the first place.
Patent
System and method of automatically generating chemical compounds with desired properties
TL;DR: A computer-based, iterative process for generating chemical entities with defined physical, chemical and/or bioactive properties is described in this paper, where robotic synthesis instructions are automatically generated to control the synthesis of the directed diversity chemical library.
Journal ArticleDOI
Feature selection for structure-activity correlation using binary particle swarms.
TL;DR: The algorithm is applied in the construction of parsimonious quantitative structure-activity relationship (QSAR) models based on feed-forward neural networks and is tested on three classical data sets from the QSAR literature.
Journal ArticleDOI
On the use of neural network ensembles in QSAR and QSPR.
TL;DR: It is demonstrated that bagging may not be the best possible choice and that simpler techniques such as retraining with the full sample can often produce superior results, which are rationalized using Krogh and Vedelsby's decomposition of the generalization error.