Publications by authors named "M Kutsal"
Strength, ductility, and failure properties of metals are tailored by plastic deformation routes. Predicting these properties requires modeling of the structural dynamics and stress evolution taking place on several length scales. Progress has been hampered by a lack of representative 3D experimental data at industrially relevant degrees of deformation.
View Article and Find Full Text PDFComputational drug discovery on human immunodeficiency virus with a customized long short-term memory variational autoencoder deep-learning architecture.
CPT Pharmacometrics Syst Pharmacol
February 2024
Article Synopsis
- The ongoing fight against HIV is hindered by the lack of an effective vaccine and the virus's ability to develop drug resistance, highlighting the need for new therapies.
- This study utilized a deep-learning method called a long short-term memory (LSTM) variational autoencoder to explore potential new drugs for HIV, training on a dataset of 1,377 SMILES-encoded compounds with a high accuracy of 91%.
- The research generated new drug candidates, evaluated their interactions with HIV using AI models, and confirmed their drug likeliness based on Lipinski's rule of five, showcasing a promising direction for drug discovery against HIV.
Three-dimensional X-ray diffraction microscopy, 3DXRD, has become an established tool for orientation and strain mapping of bulk polycrystals. However, it is limited to a finite spatial resolution of ∼1.5-3 µm.
View Article and Find Full Text PDFA geometric deep learning model for display and prediction of potential drug-virus interactions against SARS-CoV-2.
Chemometr Intell Lab Syst
October 2022
Article Synopsis
- The Omicron variant of coronavirus spread quickly but became less lethal due to vaccines and immunity, reducing hospitalizations and demand.
- There is uncertainty about the future dangers of new variants and ongoing risks from animal reservoirs, highlighting the need for research on drug-virus interactions to prepare for potential threats.
- A study proposes using geometric deep learning to predict drug-virus interactions, utilizing advanced data representation techniques, resulting in a model that achieves 97% accuracy, outperforming existing prediction methods.
Connecting a bulk material's microscopic defects to its macroscopic properties is an age-old problem in materials science. Long-range interactions between dislocations (line defects) are known to play a key role in how materials deform or melt, but we lack the tools to connect these dynamics to the macroscopic properties. We introduce time-resolved dark-field x-ray microscopy to directly visualize how dislocations move and interact over hundreds of micrometers deep inside bulk aluminum.
View Article and Find Full Text PDF