4.7 Article

Deep Learning-Based Bioactive Therapeutic Peptide Generation and Screening

Related references

Note: Only part of the references are listed.
Review Biochemical Research Methods

Artificial intelligence in the prediction of protein-ligand interactions: recent advances and future directions

Ashwin Dhakal et al.

Summary: New drug production can take over 12 years and cost around $2.6 billion, with the COVID-19 pandemic emphasizing the need for more powerful computational methods in drug discovery. This review focuses on computational approaches using artificial intelligence (AI) to predict protein-ligand interactions, particularly in deep learning methods. The correlation between protein-ligand interaction aspects and the proposal to study them together could lead to more accurate machine learning-based prediction strategies.

BRIEFINGS IN BIOINFORMATICS (2022)

Article Chemistry, Medicinal

DeLA-Drug: A Deep Learning Algorithm for Automated Design of Druglike Analogues

Teresa Maria Creanza et al.

Summary: In this paper, a deep learning algorithm called DeLA-Drug is introduced for the automated design of druglike analogues. By capturing the syntax of SMILES strings and employing a new sampling strategy, DeLA-Drug can generate molecules similar to known bioactive compounds, while preserving their druglike properties and synthetic accessibility. This algorithm is fast and suitable for generating focused libraries for high-throughput screening in low-data regimes.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2022)

Article Biotechnology & Applied Microbiology

Trends in peptide drug discovery

Markus Muttenthaler et al.

Summary: This Perspective summarizes key trends in peptide drug discovery and development, including human hormones, elegant medicinal chemistry and rational design strategies, peptide drugs derived from nature, and major breakthroughs in molecular biology and peptide chemistry. It also emphasizes lessons from earlier approaches that are still relevant today and discusses emerging strategies impact on peptide drug discovery.

NATURE REVIEWS DRUG DISCOVERY (2021)

Article Biochemical Research Methods

Combining genetic algorithm with machine learning strategies for designing potent antimicrobial peptides

Kyle Boone et al.

Summary: This study combines an evolutionary method with rough set theory, a transparent machine learning approach, to design antimicrobial peptides (AMPs). The approach uses supervised learning boundaries to customize AMP design, and employs in vitro bacterial assays, codon-representation of peptides, genetic algorithm, and machine learning to accelerate the process. The results demonstrate that AMP design can be customized to maintain activity and simplify production, with the use of codon-based genetic algorithms combined with rough set theory for computational search on peptide sequences.

BMC BIOINFORMATICS (2021)

Article Microbiology

PepVAE: Variational Autoencoder Framework for Antimicrobial Peptide Generation and Activity Prediction

Scott N. Dean et al.

Summary: The study introduces the PepVAE framework for designing novel AMPs using VAE and antimicrobial activity prediction models. By sampling from different regions of the learned latent space, new AMP sequences can be generated with minimal input parameters for controlled production of AMPs with predicted antimicrobial activity. This modular design framework shows promise for development of novel AMPs with experimental validation.

FRONTIERS IN MICROBIOLOGY (2021)

Article Biochemical Research Methods

DeepImmuno: deep learning-empowered prediction and generation of immunogenic peptides for T-cell immunity

Guangyuan Li et al.

Summary: Cytolytic T-cells are crucial in adaptive immunity, and understanding T-cell immunity is important for cancer immunotherapies and vaccine development. Computational methods were used to predict immunogenic peptides, with a beta-binomial distribution method proposed to derive peptide immunogenic potential from sequence. Multiple machine learning and deep learning models were compared, with convolutional neural network (CNN) identified as the best prediction model, outperforming existing methods and accurately predicting T-cell antigen recognition and SARS-CoV-2 variants. An independent generative adversarial network approach also accurately simulated immunogenic peptides.

BRIEFINGS IN BIOINFORMATICS (2021)

Article Pharmacology & Pharmacy

An Integrated Deep Learning and Molecular Dynamics Simulation-Based Screening Pipeline Identifies Inhibitors of a New Cancer Drug Target TIPE2

Haiping Zhang et al.

Summary: The TIPE2 protein plays a significant role in cancer and inflammatory diseases, and utilizing deep learning and molecular dynamics simulation methods can help identify potential inhibitors against TIPE2. Among the screened compounds, UM-164 demonstrated the strongest binding affinity to TIPE2, showing promising potential as an inhibitor.

FRONTIERS IN PHARMACOLOGY (2021)

Review Medicine, General & Internal

Breast cancer

Sibylle Loibl et al.

Summary: Breast cancer diagnosis and treatment have become increasingly complex, incorporating various biomarkers and neoadjuvant therapies, with de-escalation schemes for radiotherapy now becoming standard practice.

LANCET (2021)

Article Chemistry, Multidisciplinary

Beam Search for Automated Design and Scoring of Novel ROR Ligands with Machine Intelligence

Michael Moret et al.

Summary: Chemical language models coupled with the beam search algorithm were used to automate molecule design and scoring, resulting in the discovery of novel inverse agonists for retinoic acid receptor-related orphan receptors (RORs). These designs were synthesizable in three reaction steps and exhibited low-micromolar to nanomolar potency towards RORg, showcasing the potential of generative artificial intelligence in data-driven drug discovery.

ANGEWANDTE CHEMIE-INTERNATIONAL EDITION (2021)

Article Chemistry, Medicinal

xDeep-AcPEP: Deep Learning Method for Anticancer Peptide Activity Prediction Based on Convolutional Neural Network and Multitask Learning

Jiarui Chen et al.

Summary: This study used deep learning to predict the biological activity of anticancer peptides against six tumor cells, showing that multitask learning models performed better than single-task models. The best models achieved low mean squared error and high correlation coefficients in cross validation. By inferring the contribution of residues to activity, the interpretability of the model's predictions was enhanced.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2021)

Article Multidisciplinary Sciences

Structure, mechanism and crystallographic fragment screening of the SARS-CoV-2 NSP13 helicase

Joseph A. Newman et al.

Summary: The SARS-CoV-2 NSP13 helicase is crucial for viral replication and is considered a promising drug target. Crystal structures of NSP13 in different forms provide insights into its mechanism and potential inhibition methods. A crystallographic fragment screen identified 65 fragments bound to NSP13, offering opportunities for developing novel antiviral drugs.

NATURE COMMUNICATIONS (2021)

Article Multidisciplinary Sciences

A deep-learning framework for multi-level peptide-protein interaction prediction

Yipin Lei et al.

Summary: The authors proposed a deep learning framework CAMP for predicting peptide-protein interactions and identifying important binding residues. Comprehensive evaluation showed that CAMP outperformed other methods in predicting peptide-protein interactions. CAMP serves as a significant tool in facilitating peptide drug discovery.

NATURE COMMUNICATIONS (2021)

Article Multidisciplinary Sciences

Computational design of SARS-CoV-2 peptide binders with better predicted binding affinities than human ACE2 receptor

Thassanai Sitthiyotha et al.

Summary: In order to design SARS-CoV-2 peptide binders with higher affinity than ACE2, computational protein design was utilized to improve the ACE2-PD residues 21-45 (SPB25), resulting in three predicted peptides (SPB25(Q22R), SPB25(F8R/K11W/L25R), and SPB25(F8R/K11F/Q22R/L25R)) with better binding affinities and slightly higher stabilities than ACE2. This study presents a promising approach to develop SARS-CoV-2 inhibitors through peptide design.

SCIENTIFIC REPORTS (2021)

Review Nanoscience & Nanotechnology

Self-Assembled Peptide Drug Delivery Systems

Jia Yang et al.

Summary: Peptides can be used as modules to construct self-assembled peptide nanomaterials, which have the potential to reduce drug toxicity, improve drug targeting, and enhance drug delivery efficiency. Different strategies for designing peptide nanomaterials, including ex situ construction, in situ morphological transformation, and in situ construction of peptide drug delivery systems, can be used for drug delivery.

ACS APPLIED BIO MATERIALS (2021)

Article Computer Science, Artificial Intelligence

Expanding functional protein sequence spaces using generative adversarial networks

Donatas Repecka et al.

Summary: De novo protein design for catalysis of any desired chemical reaction has long been a goal in protein engineering. ProteinGAN, a self-attention-based variant of generative adversarial networks, has been developed to learn natural protein sequence diversity and generate functional protein sequences. This AI approach shows potential in rapidly generating diverse functional proteins within biological constraints.

NATURE MACHINE INTELLIGENCE (2021)

Article Chemistry, Multidisciplinary

Beam Search for Automated Design and Scoring of Novel ROR Ligands with Machine Intelligence

Michael Moret et al.

Summary: Chemical language models combined with the beam search algorithm as an automated molecule design and scoring technique can generate novel compounds with potential bioactivity. The newly discovered inverse agonists can be synthesized in a few simple reaction steps and exhibit low micromolar to nanomolar potency towards RORg. This model-intrinsic sampling technique eliminates the strict need for external compound scoring functions, further expanding the applicability of generative artificial intelligence to data-driven drug discovery.

ANGEWANDTE CHEMIE-INTERNATIONAL EDITION (2021)

Article Biochemistry & Molecular Biology

A Deep Learning Approach to Antibiotic Discovery

Jonathan M. Stokes et al.

Article Biotechnology & Applied Microbiology

Advances in oral peptide therapeutics

Daniel J. Drucker

NATURE REVIEWS DRUG DISCOVERY (2020)

Article Multidisciplinary Sciences

Improved protein structure prediction using predicted interresidue orientations

Jianyi Yang et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2020)

Review Biochemical Research Methods

RNA-Dependent RNA Polymerase as a Target for COVID-19 Drug Discovery

Wei Zhu et al.

SLAS DISCOVERY (2020)

Article Chemistry, Multidisciplinary

Variational Autoencoder for Generation of Antimicrobial Peptides

Scott N. Dean et al.

ACS OMEGA (2020)

Article Chemistry, Medicinal

The SARS-CoV-2 main protease as drug target

Sven Ullrich et al.

BIOORGANIC & MEDICINAL CHEMISTRY LETTERS (2020)

Article Medicine, Research & Experimental

DeepACP: A Novel Computational Approach for Accurate Identification of Anticancer Peptides by Deep Learning Algorithm

Lezheng Yu et al.

MOLECULAR THERAPY-NUCLEIC ACIDS (2020)

Article Computer Science, Artificial Intelligence

Predicting drug-protein interaction using quasi-visual question answering system

Shuangjia Zheng et al.

NATURE MACHINE INTELLIGENCE (2020)

Review Physics, Applied

Using metadynamics to explore complex free-energy landscapes

Giovanni Bussi et al.

NATURE REVIEWS PHYSICS (2020)

Review Biochemistry & Molecular Biology

Development and Application of Computational Methods in Phage Display Technology

Bifang He et al.

CURRENT MEDICINAL CHEMISTRY (2019)

Review Biochemistry & Molecular Biology

A Comprehensive Review on Current Advances in Peptide Drug Development and Design

Andy Chi-Lung Lee et al.

INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES (2019)

Article Medicine, General & Internal

Lung Cancer

Faria Nasim et al.

MEDICAL CLINICS OF NORTH AMERICA (2019)

Review Computer Science, Artificial Intelligence

A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures

Yong Yu et al.

NEURAL COMPUTATION (2019)

Article Biochemistry & Molecular Biology

Computational antimicrobial peptide design and evaluation against multidrug-resistant clinical isolates of bacteria

Deepesh Nagarajan et al.

JOURNAL OF BIOLOGICAL CHEMISTRY (2018)

Article Chemistry, Medicinal

Generative Recurrent Networks for De Novo Drug Design

Anvita Gupta et al.

MOLECULAR INFORMATICS (2018)

Article Biochemistry & Molecular Biology

Therapeutic peptides: Historical perspectives, current development trends, and future directions

Jolene L. Lau et al.

BIOORGANIC & MEDICINAL CHEMISTRY (2018)

Review Biochemistry & Molecular Biology

Targeting BCL-2 regulated apoptosis in cancer

Kirsteen J. Campbell et al.

OPEN BIOLOGY (2018)

Review Cell Biology

Genetics and biology of prostate cancer

Guocan Wang et al.

GENES & DEVELOPMENT (2018)

Review Cell Biology

CDK4/6 Inhibition in Cancer: Beyond Cell Cycle Arrest

Shom Goel et al.

TRENDS IN CELL BIOLOGY (2018)

Editorial Material Biotechnology & Applied Microbiology

New antibiotic hits Gram-negative bacteria

Katie Kingwell

NATURE REVIEWS DRUG DISCOVERY (2018)

Article Biochemistry & Molecular Biology

Affinity Maturation of a Cyclic Peptide Handle for Therapeutic Antibodies Using Deep Mutational Scanning

Martijn van Rosmalen et al.

JOURNAL OF BIOLOGICAL CHEMISTRY (2017)

Article Chemistry, Medicinal

Hybrid Network Model for Deep Learning of Chemical Data: Application to Antimicrobial Peptides

Petra Schneider et al.

MOLECULAR INFORMATICS (2017)

Article Biochemistry & Molecular Biology

APD3: the antimicrobial peptide database as a tool for research and education

Guangshun Wang et al.

NUCLEIC ACIDS RESEARCH (2016)

Review Cell Biology

Advancement and applications of peptide phage display technology in biomedical science

Chien-Hsun Wu et al.

JOURNAL OF BIOMEDICAL SCIENCE (2016)

Review Microbiology

Nuclear entry of DNA viruses

Nikta Fay et al.

FRONTIERS IN MICROBIOLOGY (2015)

Article Biochemistry & Molecular Biology

Search for identical octapeptides in unrelated proteins: Structural plasticity revisited

K. M. Saravanan et al.

BIOPOLYMERS (2012)

Article Biochemistry & Molecular Biology

Rosetta FlexPepDock web server-high resolution modeling of peptide-protein interactions

Nir London et al.

NUCLEIC ACIDS RESEARCH (2011)

Article Multidisciplinary Sciences

Accelerating Protein Docking in ZDOCK Using an Advanced 3D Convolution Library

Brian G. Pierce et al.

PLOS ONE (2011)

Review Infectious Diseases

Infections caused by Gram-positive bacteria: a review of the global challenge

Neil Woodford et al.

JOURNAL OF INFECTION (2009)

Article Biochemistry & Molecular Biology

Structure-based design of a T-cell receptor leads to nearly 100-fold improvement in binding affinity for pepMHC

Jaafar N. Haidar et al.

PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS (2009)

Review Oncology

Topoisomerase I inhibitors: camptothecins and beyond

Yves Pommier

NATURE REVIEWS CANCER (2006)

Article Biochemistry & Molecular Biology

The PeptideAtlas project

Frank Desiere et al.

NUCLEIC ACIDS RESEARCH (2006)