A5079583126- Computational Drug Discovery Methods
- Machine Learning in Materials Science
- Protein Structure and Dynamics
- Analytical Chemistry and Chromatography
- Metabolomics and Mass Spectrometry Studies
- Neural Networks and Applications
- Advanced Graph Neural Networks
- Advanced Neural Network Applications
- CCD and CMOS Imaging Sensors
- Machine Learning in Bioinformatics
- Various Chemistry Research Topics
- Advanced Memory and Neural Computing
- Chemical Synthesis and Analysis
University of Connecticut
2020-2023
Abstract Graph generative models have recently emerged as an interesting approach to construct molecular structures atom‐by‐atom or fragment‐by‐fragment. In this study, we adopt the fragment‐based strategy and decompose each input molecule into a set of small chemical fragments. drug discovery, few molecules are designed by replacing certain substituents with their bioisosteres alternative moieties. This inspires us group decomposed fragments different fragment clusters according local...
Molecular similarity search is a simple but powerful chemoinformatics tool to rapidly find molecules that are structurally similar known reference compound from large molecular database. A variety of indexing structures had been developed improve the performance over However, those algorithms often require computational cost build indices and process queries, especially for large-scale dataset. We study problem accelerating using high computing (HPC) design general speed up existing...
Being able to learn from complex data with phase information is imperative for many signal processing applications. Today's real-valued deep neural networks (DNNs) have shown efficiency in latent analysis but fall short when applied the domain. Deep (DCN), contrast, can data, high computational costs; therefore, they cannot satisfy instant decision-making requirements of deployable systems dealing observations or bursts. Recent, Binarized Complex Neural Network (BCNN), which integrates DCNs...
Molecular similarity search has been widely used in drug discovery to identify structurally similar compounds from large molecular databases rapidly. With the increasing size of chemical libraries, there is growing interest efficient acceleration large-scale search. Existing works mainly focus on CPU and GPU accelerate computation Tanimoto coefficient measuring pairwise between different fingerprints. In this paper, we propose optimize an FPGA-based accelerator design exhaustive approximate...
Structurally similar analogues of given query compounds can be rapidly retrieved from chemical databases by the molecular similarity search approaches. However, computational cost associated with exhaustive a large compound database will quite high. Although latest indexing algorithms greatly speed up process, they cannot readily applicable to problems due lack Tanimoto metric implementation. In this paper, we first implement Python or C++ codes enable via several recent algorithms, such as...
Being able to learn from complex data with phase information is imperative for many signal processing applications. Today' s real-valued deep neural networks (DNNs) have shown efficiency in latent analysis but fall short when applied the domain. Deep (DCN), contrast, can data, high computational costs; therefore, they cannot satisfy instant decision-making requirements of deployable systems dealing observations or bursts. Recent, Binarized Complex Neural Network (BCNN), which integrates DCNs...
Deep generative models have recently emerged as encouraging tools for the de novo molecular structure generation. Even though considerable advances been achieved in recent years, field of design is still its infancy. One potential solution may be to integrate domain knowledge structural or medicinal chemistry into data-driven machine learning process address specific deep molecule generation goals. This manuscript proposes a new graph-based hierarchical variational autoencoder (VAE) model...
Deep generative models have recently emerged as encouraging tools for the de novo molecular structure generation. Even though considerable advances been achieved in recent years, field of design is still its infancy. One potential solution may be to integrate domain knowledge structural or medicinal chemistry into data-driven machine learning process address specific deep molecule generation goals. This manuscript proposes a new graph-based hierarchical variational autoencoder (VAE) model...
Molecular similarity search has been widely used in drug discovery to identify structurally similar compounds from large molecular databases rapidly. With the increasing size of chemical libraries, there is growing interest efficient acceleration large-scale search. Existing works mainly focus on CPU and GPU accelerate computation Tanimoto coefficient measuring pairwise between different fingerprints. In this paper, we propose optimize an FPGA-based accelerator design exhaustive approximate...
Knowledge graphs have become a popular method for representing large, relational data. Similar to citation networks and social networks, relationships in chemical reaction data can also be uniquely captured using knowledge graph. However, relatively few studies exist concerning the application of graph mining techniques numerical representation reactions. In this study, we develop pipeline transforming large-scale databases reactions into heterogeneous graphs, which their reactants products...