☆ 4.7 Article

DNMG: Deep molecular generative model by fusion of 3D information for de novo drug design

METHODS (2023)

Related references

Note: Only part of the references are listed.

Article Biochemical Research Methods

AMDE: a novel attention-mechanism-based multidimensional feature encoder for drug-drug interaction prediction

Shanchen Pang et al.

Summary: The article introduces a novel attention-mechanism-based multidimensional feature encoder (AMDE) for DDI prediction, compares with various baseline methods, and experimental results show that AMDE performs better. AMDE achieves good results in the DDI prediction task.

BRIEFINGS IN BIOINFORMATICS (2022)

Add to Collection

Article Biochemistry & Molecular Biology

IMGG: Integrating Multiple Single-Cell Datasets through Connected Graphs and Generative Adversarial Networks

Xun Wang et al.

Summary: Eliminating batch-specific differences is crucial when integrating single-cell RNA-sequencing datasets generated under different experimental conditions. Existing methods cannot fully utilize information from multiple sources, so we propose a novel approach called IMGG, which integrates multiple single-cell datasets through connected graphs and generative adversarial networks (GAN), to eliminate nonbiological differences between batches.

INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES (2022)

Add to Collection

Article Biochemistry & Molecular Biology

TransPhos: A Deep-Learning Model for General Phosphorylation Site Prediction Based on Transformer-Encoder Architecture

Xun Wang et al.

Summary: Protein phosphorylation is a critical post-translational modification in eukaryotes, and predicting phosphorylation sites accurately is challenging. This article introduces a new deep learning-based predictor called TransPhos, which combines a transformer encoder and densely connected convolutional neural network blocks. Experimental results show that TransPhos outperforms other deep learning models and prediction tools, achieving good performance in predicting phosphorylation sites on training datasets.

INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES (2022)

Add to Collection

Article Biochemistry & Molecular Biology

Multi-TransDTI: Transformer for Drug-Target Interaction Prediction Based on Simple Universal Dictionaries with Multi-View Strategy

Gan Wang et al.

Summary: A novel end-to-end learning model was proposed to encode drugs and proteins and was evaluated on the BindingDB dataset, outperforming other models.

BIOMOLECULES (2022)

Add to Collection

Article Biochemical Research Methods

De novo molecular design with deep molecular generative models for PPI inhibitors

Jianmin Wang et al.

Summary: This study constructs a dataset for protein-protein interaction (PPI) targeted drug-likeness and proposes a deep molecular generative framework to generate novel drug-like molecules based on the features of seed compounds. The results show that the generated molecules have better PPI-targeted drug-likeness and drug-likeness, and the model performs comparably to other state-of-the-art molecule generation models.

BRIEFINGS IN BIOINFORMATICS (2022)

Add to Collection

Article Biochemical Research Methods

Molormer: a lightweight self-attention-based method focused on spatial structure of molecular graph for drug-drug interactions prediction

Xudong Zhang et al.

Summary: Multi-drug combinations for the treatment of complex diseases are important, but accurate identification of drug-drug interactions (DDIs) is crucial. Traditional methods ignore spatial structure information, so we propose Molormer, a lightweight attention-based method, to encode and process molecular graphs. Molormer outperforms state-of-the-art methods in multi-label DDIs dataset and shows good predictions in case studies.

BRIEFINGS IN BIOINFORMATICS (2022)

Add to Collection

Article Biochemical Research Methods

DeepFusion: A deep learning based multi-scale feature fusion method for predicting drug-target interactions

Tao Song et al.

Summary: In this study, DeepFusion, a deep learning based multi-scale feature fusion method, is proposed for predicting drug-target interactions. Experimental results show that DeepFusion achieves good prediction performance on different sub-datasets.

METHODS (2022)

Add to Collection

Article Mathematical & Computational Biology

Adaptive coding for DNA storage with high storage density and low coverage

Ben Cao et al.

Summary: This paper proposes an adaptive coding DNA storage system to address the low space utilization, high read coverage, and poor coding coupling in DNA storage. The system achieves high storage density and low read coverage, promoting the development of carbon-based storage.

NPJ SYSTEMS BIOLOGY AND APPLICATIONS (2022)

Add to Collection

Article Biology

FMG: An observable DNA storage coding method based on frequency matrix game graphs

Ben Cao et al.

Summary: A new DNA storage coding method based on the frequency matrix game graph (FMG) is proposed in this study, which solves the problems of low efficiency and high complexity in current coding methods. The proposed method optimizes the coding results by observing visible characteristics. It has a positive impact on the development of carbon-based storage coding.

COMPUTERS IN BIOLOGY AND MEDICINE (2022)

Add to Collection

Article Chemistry, Physical

TripDesign: A DNA Triplex Design Approach Based on Interaction Forces

Lijun Sun et al.

Summary: This study proposes a new DNA triplex design approach (TripDesign) based on interaction forces. The experimental results show that the sequences produced by TripDesign have high stability and reversibility, which can promote the application of DNA triplexes in nanotechnology.

JOURNAL OF PHYSICAL CHEMISTRY B (2022)

Add to Collection

Article Multidisciplinary Sciences

Transformer neural network for protein-specific de novo drug generation as a machine translation problem

Daria Grechishnikova

Summary: This study proposes a method that generates novel molecules with predicted ability to bind a target protein solely based on its amino acid sequence. By utilizing the Transformer neural network architecture, the model is able to produce realistic diverse compounds with structural novelty, showing promising results in drug discovery.

SCIENTIFIC REPORTS (2021)

Add to Collection

Review Biochemical Research Methods

Utilizing graph machine learning within drug discovery and development

Thomas Gaudelet et al.

Summary: Graph machine learning (GML) is gaining attention in the pharmaceutical and biotechnology industries for its ability to model biomolecular structures and integrate multi-omic datasets. While still emerging, milestones such as repurposed drugs entering in vivo studies indicate that GML will become a preferred modeling framework in biomedical machine learning.

BRIEFINGS IN BIOINFORMATICS (2021)

Add to Collection

Review Biochemical Research Methods

Molecular design in drug discovery: a comprehensive review of deep generative models

Yu Cheng et al.

Summary: Deep generative models have gained popularity in the field of deep learning, particularly in drug discovery, showing superior performance. Researchers categorize these models into two types, analyzing their advantages and disadvantages. Although de novo molecular design automation shows promise, there are challenges to be overcome.

BRIEFINGS IN BIOINFORMATICS (2021)

Add to Collection

Article Mathematical & Computational Biology

A Computationally Virtual Histological Staining Method to Ovarian Cancer Tissue by Deep Generative Adversarial Networks

Xiangyu Meng et al.

Summary: The study proposed a weakly supervised learning method using Generative Adversarial Network for virtual tissue staining. Experimental results showed that the method achieved a 93% accuracy in generating unstained fluorescence images of ovarian cancer, with high evaluations from doctors and deep learning on the image quality after virtual staining.

COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE (2021)

Add to Collection

Article Chemistry, Medicinal

AutoDock Vina 1.2.0: New Docking Methods, Expanded Force Field, and Python Bindings

Jerome Eberhardt et al.

Summary: AutoDock Vina is a widely used open-source program for molecular docking with new features such as support for macrocycles and explicit water molecules. The latest version also includes support for AutoDock4.2 scoring function, simultaneous docking of multiple ligands, and a batch mode for docking a large number of ligands. Python bindings have been implemented to facilitate scripting and workflow development.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2021)

Add to Collection

Review Computer Science, Artificial Intelligence

Geometric deep learning on molecular representations

Kenneth Atz et al.

Summary: Geometric deep learning, based on neural network architectures that process symmetry information, shows promise in molecular modeling applications. This review provides a detailed overview of molecular GDL, its applications, challenges, and future opportunities, highlighting the importance of geometric representations in molecular deep learning. Kenneth Atz and colleagues review the current progress and challenges of geometric deep learning in molecular sciences, emphasizing the significance of spatial structure information in molecules.

NATURE MACHINE INTELLIGENCE (2021)

Add to Collection

Article Chemistry, Medicinal

Bidirectional Molecule Generation with Recurrent Neural Networks

Francesca Grisoni et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2020)

Add to Collection

Article Pharmacology & Pharmacy

Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models

Daniil Polykovskiy et al.

FRONTIERS IN PHARMACOLOGY (2020)

Add to Collection

Article Chemistry, Medicinal

Shape-Based Generative Modeling for de Novo Drug Design

Miha Skalic et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2019)

Add to Collection

Article Chemistry, Multidisciplinary

A de novo molecular generation method using latent vector based generative adversarial network

Oleksii Prykhodko et al.

JOURNAL OF CHEMINFORMATICS (2019)

Add to Collection

Article Chemistry, Multidisciplinary

Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural Networks

Marwin H. S. Segler et al.

ACS CENTRAL SCIENCE (2018)

Add to Collection

Article Biochemical Research Methods

Development and evaluation of a deep learning model for protein-ligand binding affinity prediction

Marta M. Stepniewska-Dziubinska et al.

BIOINFORMATICS (2018)

Add to Collection

Article Chemistry, Medicinal

Frechet ChemNet Distance: A Metric for Generative Models for Molecules in Drug Discovery

Kristina Preuer et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2018)

Add to Collection

Article Chemistry, Multidisciplinary

Molecular de-novo design through deep reinforcement learning

Marcus Olivecrona et al.

JOURNAL OF CHEMINFORMATICS (2017)

Add to Collection

Article Chemistry, Medicinal

ZINC 15-Ligand Discovery for Everyone

Teague Sterling et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2015)

Add to Collection

Article Biochemistry & Molecular Biology

Estimation of the size of drug-like chemical space based on GDB-17 data

P. G. Polishchuk et al.

JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN (2013)

Add to Collection

Article Chemistry, Medicinal

ZINC: A Free Tool to Discover Chemistry for Biology

John J. Irwin et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2012)

Add to Collection

Article Chemistry, Medicinal

Directory of Useful Decoys, Enhanced (DUD-E): Better Ligands and Decoys for Better Benchmarking

Michael M. Mysinger et al.

JOURNAL OF MEDICINAL CHEMISTRY (2012)

Add to Collection

Article Chemistry, Multidisciplinary

Open Babel: An open chemical toolbox

Noel M. O'Boyle et al.

JOURNAL OF CHEMINFORMATICS (2011)

Add to Collection

Article Chemistry, Medicinal

New Substructure Filters for Removal of Pan Assay Interference Compounds (PAINS) from Screening Libraries and for Their Exclusion in Bioassays

Jonathan B. Baell et al.

JOURNAL OF MEDICINAL CHEMISTRY (2010)

Add to Collection

Article Chemistry, Medicinal

On the Art of Compiling and Using 'Drug-Like' Chemical Fragment Spaces

Joerg Degen et al.

CHEMMEDCHEM (2008)

Add to Collection

© Peeref 2019-2024. All rights reserved.