4.6 Article

Adaptive language model training for molecular design

Related references

Note: Only part of the references are listed.
Article Computer Science, Artificial Intelligence

Automating Genetic Algorithm Mutations for Molecules Using a Masked Language Model

Andrew E. Blanchard et al.

Summary: Inspired by biological systems, genetic algorithms have been widely used for optimization problems in various fields. However, the generalization of complex rearrangements and mutations remains a challenge. In this study, we propose the use of masked language models to automatically generate mutations, and the strategy is validated through an empirical study.

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION (2022)

Article Chemistry, Medicinal

MolGPT: Molecular Generation Using a Transformer-Decoder Model

Viraj Bagal et al.

Summary: The application of deep learning techniques in inverse molecular design for drug design has gained significant attention. In this study, we train a transformer-decoder model, MolGPT, on the next token prediction task using masked self-attention, and demonstrate that it performs on par with other modern machine learning frameworks for generating valid, unique, and novel druglike molecules. We also show that the model can be trained conditionally to control multiple properties of the generated molecules.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2022)

Article Computer Science, Hardware & Architecture

Language models for the prediction of SARS-CoV-2 inhibitors

Andrew E. Blanchard et al.

Summary: The article introduces the research results of using deep learning language models to generate and score drug candidates, reducing pre-training time and increasing dataset size. By fine-tuning the language model, inhibitors for important protein targets of the novel coronavirus were successfully identified. Genetic algorithm was used to find optimal candidates.

INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS (2022)

Article Chemistry, Medicinal

Generative Chemical Transformer: Neural Machine Learning of Molecular Geometric Structures from Chemical Language via Attention

Hyunseung Kim et al.

Summary: The paper introduces a neural network for generating chemicals that are better suited for specific purposes, which will improve the quality of human life. The model provides a deep understanding of molecular structures and generates highly realistic chemical strings that meet multiple target conditions.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2021)

Article Chemistry, Multidisciplinary

Using GANs with adaptive training data to search for new molecules

Andrew E. Blanchard et al.

Summary: This study introduces a new approach to training GANs using concepts from Genetic Algorithms to promote incremental exploration and limit the impacts of mode collapse, outperforming traditional methods by replacing training data samples with valid samples from the generator, leading to a significant increase in potential applications for GANs in drug discovery.

JOURNAL OF CHEMINFORMATICS (2021)

Article Computer Science, Hardware & Architecture

Enabling rapid COVID-19 small molecule drug design through scalable deep learning of generative models

Sam Ade Jacobs et al.

Summary: The researchers improved the production time and quality of machine learned models for small molecule antiviral design, achieving a training time reduction from a day to minutes and shifting the bottleneck from computer job turnaround time to human innovation time, resulting in greater efficiency.

INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS (2021)

Article Chemistry, Medicinal

Dynamic Profiling of β-Coronavirus 3CL Mpro Protease Ligand-Binding Sites

Eunice Cho et al.

Summary: This study compares the structural conservation of ligand-binding sites for M-pro enzymes from SARS-CoV2, SARS-CoV, and MERS-CoV, revealing that not all binding sites exhibit dynamic conservation despite high sequence and structural similarity. This complexity highlights the challenges of targeting all three M-pro enzymes with a single pan inhibitor.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2021)

Article Multidisciplinary Sciences

A merged molecular representation learning for molecular properties prediction with a web-based service

Hyunseob Kim et al.

Summary: This study introduces a new self-supervised method that can simultaneously learn SMILES and the chemical context of molecules for pre-training Transformer. By learning structural adjacency matrix embedding and inferring descriptor logic, the method enhances data generalization and achieves the best average performance.

SCIENTIFIC REPORTS (2021)

Proceedings Paper Computer Science, Artificial Intelligence

How Distinct Structural Flexibility within SARS-CoV-2 Spike Protein Reveals Potential Therapeutic Targets

Serena H. Chen et al.

Summary: The study uses artificial intelligence and molecular dynamics simulation to analyze the structure of the S protein of the novel coronavirus. The research reveals the flexibility of the S protein structure and identifies key regions that may be potential targets for therapeutic development. Additionally, similarities in immunodominant sites between different coronaviruses are highlighted, offering insight for effective treatment strategies for COVID-19.

2021 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA) (2021)

Letter Infectious Diseases

An interactive web-based dashboard to track COVID-19 in real time

Ensheng Dong et al.

LANCET INFECTIOUS DISEASES (2020)

Article Multidisciplinary Sciences

De novo generation of hit-like molecules from gene expression signatures using artificial intelligence

Oscar Mendez-Lucio et al.

NATURE COMMUNICATIONS (2020)

Article Chemistry, Medicinal

AMPL: A Data-Driven Modeling Pipeline for Drug Discovery

Amanda J. Minnich et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2020)

Article Chemistry, Medicinal

Supercomputer-Based Ensemble Docking Drug Discovery Pipeline with Application to Covid-19

A. Acharya et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2020)

Article Pharmacology & Pharmacy

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

Daniil Polykovskiy et al.

FRONTIERS IN PHARMACOLOGY (2020)

Article Chemistry, Medicinal

Drug Analogs from Fragment-Based Long Short-Term Memory Generative Neural Networks

Mahendra Awale et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2019)

Article Chemistry, Medicinal

GuacaMol: Benchmarking Models for de Novo Molecular Design

Nathan Brown et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2019)

Review Chemistry, Multidisciplinary

Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery

Xin Yang et al.

CHEMICAL REVIEWS (2019)

Article Chemistry, Multidisciplinary

QBMG: quasi-biogenic molecule generator with deep recurrent neural network

Shuangjia Zheng et al.

JOURNAL OF CHEMINFORMATICS (2019)

Article Chemistry, Multidisciplinary

A retrosynthetic analysis algorithm implementation

Ian A. Watson et al.

JOURNAL OF CHEMINFORMATICS (2019)

Article Chemistry, Multidisciplinary

Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural Networks

Marwin H. S. Segler et al.

ACS CENTRAL SCIENCE (2018)

Review Pharmacology & Pharmacy

The rise of deep learning in drug discovery

Hongming Chen et al.

DRUG DISCOVERY TODAY (2018)

Article Chemistry, Multidisciplinary

Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules

Rafael Gomez-Bombarelli et al.

ACS CENTRAL SCIENCE (2018)

Article Biochemical Research Methods

Deep clustering of protein folding simulations

Debsindhu Bhowmik et al.

BMC BIOINFORMATICS (2018)

Article Chemistry, Medicinal

Computational Modeling of β-Secretase 1 (BACE-1) Inhibitors Using Ligand Based Approaches

Govindan Subramanian et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2016)

Article Multidisciplinary Sciences

Quantum chemistry structures and properties of 134 kilo molecules

Raghunathan Ramakrishnan et al.

SCIENTIFIC DATA (2014)

Article Chemistry, Multidisciplinary

Stochastic Voyages into Uncharted Chemical Space Produce a Representative Library of All Possible Drug-Like Compounds

Aaron M. Virshup et al.

JOURNAL OF THE AMERICAN CHEMICAL SOCIETY (2013)

Article Chemistry, Medicinal

A Bayesian Approach to in Silico Blood-Brain Barrier Penetration Modeling

Ines Filipa Martins et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2012)

Article Chemistry, Multidisciplinary

Quantifying the chemical beauty of drugs

G. Richard Bickerton et al.

NATURE CHEMISTRY (2012)

Article Chemistry, Medicinal

De Novo Drug Design Using Multiobjective Evolutionary Graphs

Christos A. Nicolaou et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2009)

Article Chemistry, Medicinal

The molecule evoluator.: An interactive evolutionary algorithm for the design of drug-like molecules

EW Lameijer et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2006)

Article Chemistry, Medicinal

Mining a chemical database for fragment co-occurrence:: Discovery of chemical cliches

EW Lameijer et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2006)

Article Chemistry, Multidisciplinary

A graph-based genetic algorithm and its application to the multiobjective evolution of median molecules

N Brown et al.

JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES (2004)

Article Biochemistry & Molecular Biology

De novo design of molecular architectures by evolutionary assembly of drug-derived building blocks

G Schneider et al.

JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN (2000)