A5082696725- Computational Drug Discovery Methods
- Protein Structure and Dynamics
- Machine Learning in Materials Science
- Neural Networks and Applications
- Hydrological Forecasting Using AI
- Smart Agriculture and AI
- Infrared Thermography in Medicine
- Algorithms and Data Compression
- Click Chemistry and Applications
- Spacecraft and Cryogenic Technologies
- Thermography and Photoacoustic Techniques
- Web Data Mining and Analysis
- Complex Network Analysis Techniques
- Photoacoustic and Ultrasonic Imaging
- Chemical Synthesis and Analysis
- Receptor Mechanisms and Signaling
- Scientific Computing and Data Management
- Metabolomics and Mass Spectrometry Studies
California State University Los Angeles
2022-2024
Amirkabir University of Technology
2020-2022
AmberTools is a free and open-source collection of programs used to set up, run, analyze molecular simulations. The newer features contained within AmberTools23 are briefly described in this Application note.
Calculation of protein–ligand binding affinity is a cornerstone drug discovery. Classic implicit solvent models, which have been widely used to accomplish this task, lack accuracy compared experimental references. Emerging data-driven on the other hand, are often accurate yet not fully interpretable and also likely be overfitted. In research, we explore application Theory-Guided Data Science in studying binding. A hybrid model introduced by integrating Graph Convolutional Network...
In this paper we develop a reliable system for smart irrigation of greenhouses using artificial neural networks, and an IoT architecture. Our solution uses four sensors in different layers soil to predict future moisture. Using dataset collected by running experiments on soils, show high performance networks compared existing alternative method support vector regression. To reduce the processing power network edge devices, propose transfer learning. Transfer learning also speeds up training...
Structure-based drug discovery aims to identify small molecules that can attach a specific target protein and change its functionality. Recently, deep learning has shown great promise in generating drug-like with biochemical features conditioned structural features. However, they usually fail incorporate an essential factor: the underlying physics which guides molecular formation binding real-world scenarios. In this work, we describe physics-guided generative model for new ligand discovery,...
Calculation of binding affinity biomolecules is an essential part drug discovery processes. Mainstream implicit solvent models that are widely used to accomplish this task lack accuracy compared experiments. Data-driven models, on the other hand, often accurate yet not fully interpretable and also likely be overfitted. In study, we explore application "Theory Guided Data Science" in protein-ligand prediction. A hybrid model constructed by combining Graph Convolutional Network (data-driven...
In this paper we develop a reliable system for smart irrigation of greenhouses using artificial neural networks, and an IoT architecture. Our solution uses four sensors in different layers soil to predict future moisture. Using dataset collected by running experiments on soils, show high performance networks compared existing alternative method support vector regression. To reduce the processing power network edge devices, propose transfer learning. Transfer learning also speeds up training...
Non-linear mapping is one of the most popular solutions for complex data structures and distinct patterns to cluster data. Auto encoder Networks (AENs) are widely used in clustering as they improve representation. In this paper, we collect Alexa.com by crawling websites profiles, where dataset has 84 columns with type number array words. Next, an AEN architecture presented identify specific exceptional encoded expresses new feature space our original (Our) Encoded clustered Affinity...
In-silico calculation of binding free energy between protein and ligands has vast applications in the early stages drug discovery. Most classical physics-based models, including implicit solvents, ignore entropy contributions from system. Instead, a simplified solvent is indirectly considered. This simplification often done because an under-sampled conformal space due to physics complexity. Machine learning (ML) methods offer practical venue incorporate accurate predictions experiment. While...