4.7 Article

Application of artificial intelligence and machine learning for COVID-19 drug discovery and vaccine design

Related references

Note: Only part of the references are listed.
Review Biochemistry & Molecular Biology

Multi-substrate selectivity based on key loops and non-homologous domains: new insight into ALKBH family

Baofang Xu et al.

Summary: This study investigates the multi-substrate selectivity of the ALKBH demethylase family from the perspective of sequence and structural evolution. The construction of phylogenetic tree and comparison of key loops and non-homologous domains show that paralogs with close evolutionary relationships have similar domain compositions, indicating that variations in key loops lead to differences in substrate affinity.

CELLULAR AND MOLECULAR LIFE SCIENCES (2021)

Review Biochemical Research Methods

Modular arrangements of sequence motifs determine the functional diversity of KDM proteins

Zerong Wang et al.

Summary: KDM proteins exhibit diverse biological functions through modular activities given by different sequence motifs, including catalytic, targeting, regulatory, and potential motifs. These motifs interact with each other to form a complex functional network.

BRIEFINGS IN BIOINFORMATICS (2021)

Article Mathematical & Computational Biology

Screening of Prospective Plant Compounds as H1R and CL1R Inhibitors and Its Antiallergic Efficacy through Molecular Docking Approach

Hasan Zulfiqar et al.

Summary: This research utilized molecular docking to identify the best inhibitors against H1R and CL1R, and evaluate their anti-allergic efficacy. This in silico study will aid in the design of novel, safe, and cost-effective drugs in the future to enhance the quality of human life.

COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE (2021)

Article Biochemical Research Methods

eHSCPr discriminating the cell identity involved in endothelial to hematopoietic transition

Hao Wang et al.

Summary: The study introduced a predictor named eHSCPr for predicting the early stages of HSCs development. By comparing different gene selection methods, F-score captured critical surface markers and SVM analysis achieved an accuracy of over 94%, confirming important markers for HSCs development stages.

BIOINFORMATICS (2021)

Article Biochemical Research Methods

BERT4Bitter: a bidirectional encoder representations from transformers (BERT)-based model for improving the prediction of bitter peptides

Phasit Charoenkwan et al.

Summary: The BERT4Bitter model presented in this study utilizes a bidirectional encoder representation from transformers to predict bitter peptides directly from their amino acid sequence, achieving superior performance. Compared to traditional machine learning models, BERT4Bitter shows significant improvements in accuracy and correlation coefficient, offering a new approach for identifying bitter peptides.

BIOINFORMATICS (2021)

Article Biochemical Research Methods

Functional alterations caused by mutations reflect evolutionary trends of SARS-CoV-2

Liang Cheng et al.

Summary: Since the end of 2019, the COVID-19 pandemic has rapidly spread worldwide. Limited virus strains initially led to few mutations, but a steady mutation rate suggests an evolution towards increased infectivity and reduced virulence.

BRIEFINGS IN BIOINFORMATICS (2021)

Article Biochemistry & Molecular Biology

Circulating SARS-CoV-2 spike N439K variants maintain fitness while evading antibody-mediated immunity

Emma C. Thomson et al.

Summary: SARS-CoV-2 virus can mutate and evade immunity, with mutations like N439K conferring resistance against neutralizing monoclonal antibodies and enhancing binding affinity to hACE2 receptor. Despite similar in vitro replication fitness and clinical outcomes compared to wild type, N439K mutation highlights the importance of ongoing molecular surveillance for guiding vaccine and therapeutic development and usage.
Article Biochemistry & Molecular Biology

COVID-19 immune features revealed by a large-scale single-cell transcriptome atlas

Xianwen Ren et al.

Summary: The study revealed the presence of immune response dysfunction in COVID-19 patients, with different peripheral immune subtype changes associated with clinical features such as age, sex, severity, and disease stages. Additionally, dramatic transcriptomic changes were observed within virus-infected cells, and upregulation of S100A8/A9 in peripheral blood may contribute to the cytokine storms frequently observed in severe patients.
Article Chemistry, Medicinal

De novo design of new chemical entities for SARS-CoV-2 using artificial intelligence

Navneet Bung et al.

Summary: In this study, deep neural network-based generative and predictive models were used to design 33 potential compounds capable of inhibiting the 3CL protease of SARS-CoV-2. The generative model was optimized using transfer learning and reinforcement learning to focus around the chemical space corresponding to the protease inhibitors.

FUTURE MEDICINAL CHEMISTRY (2021)

Article Computer Science, Artificial Intelligence

Risk Prediction of Diabetes: Big data mining with fusion of multifarious physical examination indicators

Hui Yang et al.

Summary: The study designed a computational system to predict diabetes risk by combining various types of physical examination data. Statistical analysis was conducted on different physical examination indexes to develop a model that can distinguish diabetes patients from healthy individuals. A diabetes risk scorecard was established to improve the convenience and flexibility of the model. Lastly, an online diabetes risk assessment system was set up to enhance diabetes cascade screening and personal lifestyle management.

INFORMATION FUSION (2021)

Article Biochemistry & Molecular Biology

Predicting Potential SARS-COV-2 Drugs-In Depth Drug Database Screening Using Deep Neural Network Framework SSnet, Classical Virtual Screening and Docking

Nischal Karki et al.

Summary: Global cooperation is crucial in identifying potential pharmaceutical treatments and vaccines in the COVID-19 pandemic. The application of deep neural networks and screening of large compound libraries can effectively assist researchers in finding molecules that may treat COVID-19.

INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES (2021)

Article Multidisciplinary Sciences

Causal network models of SARS-CoV-2 expression and aging to identify candidates for drug repurposing

Anastasiya Belyaeva et al.

Summary: Given the severity of the SARS-CoV-2 pandemic, repurposing existing approved drugs quickly is a major challenge. This study identifies robust druggable protein targets within a principled causal framework that integrates aging signatures along with large-scale transcriptional drug screens and RNA-seq data.

NATURE COMMUNICATIONS (2021)

Article Computer Science, Artificial Intelligence

Deep Learning-Based Potential Ligand Prediction Framework for COVID-19 with Drug-Target Interaction Model

Shatadru Majumdar et al.

Summary: This paper presents a list of ligands with high binding affinity to the S-glycoprotein of 2019-nCoV, which can potentially be used for drug development against the novel coronavirus. Through the use of 1D convolutional networks, the authors predicted the binding affinity of these ligands, providing insights for potential drug targets.

COGNITIVE COMPUTATION (2021)

Article Multidisciplinary Sciences

An in silico deep learning approach to multi-epitope vaccine design: a SARS-CoV-2 case study

Zikun Yang et al.

Summary: The study introduces an in silico deep learning approach, DeepVacPred, for designing a multi-epitope vaccine against SARS-CoV-2, predicting and evaluating potential vaccine subunits, and ultimately constructing a 694aa multi-epitope vaccine that shows promise in combating the viral infection.

SCIENTIFIC REPORTS (2021)

Article Medicine, Research & Experimental

A computational framework for identifying the transcription factors involved in enhancer-promoter loop formation

Li Liu et al.

Summary: This study identified 361 significant TF pairs and constructed a TF interaction network by integrating data from different sources. Hub-TFs were found to potentially play important roles in the regulation of long-range interactions. The findings extended TF pairs identified in other experimental and computational approaches and will aid in further studying long-range interactions between enhancers and promoters.

MOLECULAR THERAPY-NUCLEIC ACIDS (2021)

Article Biochemical Research Methods

NeuroPred-FRL: an interpretable prediction model for identifying neuropeptide using feature representation learning

Md Mehedi Hasan et al.

Summary: Neuropeptides play a crucial role in regulating immune systems, and rapid and accurate identification of them is essential for basic research and drug development. Using machine learning and feature representation learning, the developed NeuroPred-FRL predictor demonstrates superior prediction performance, serving as a powerful tool for large-scale identification of neuropeptides.

BRIEFINGS IN BIOINFORMATICS (2021)

Article Biochemical Research Methods

StackIL6: a stacking ensemble model for improving the prediction of IL-6 inducing peptides

Phasit Charoenkwan et al.

Summary: IL-6 release is stimulated by antigenic peptides and immune cells, making IL-6 inducing peptides useful not only as diagnostic biomarkers, but also as inhibitors for aggressive immune responses. A novel stacking ensemble model, StackIL6, was developed using twelve feature descriptors and five machine learning algorithms, showing better performance than existing methods in identifying IL-6 inducing peptides. Accessible through a web server, StackIL6 has the potential to aid in the rapid screening of promising peptides for diagnostic and immunotherapeutic applications.

BRIEFINGS IN BIOINFORMATICS (2021)

Article Multidisciplinary Sciences

Network medicine framework for identifying drug-repurposing opportunities for COVID-19

Deisy Morselli Gysi et al.

Summary: The study utilized multiple algorithms to rank a large number of drugs, finding that combining the consensus of various predictive methods significantly improves the success rate of drug screening and proposes new medications for treating COVID-19. Furthermore, it was discovered that the majority of drugs successfully reducing viral infection do not bind to the target proteins of SARS-CoV-2, suggesting a network-based mechanism rather than docking strategies.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2021)

Letter Multidisciplinary Sciences

COVID-19 induces lower levels of IL-8, IL-10, and MCP-1 than other acute CRS-inducing diseasesYY

Liang Cheng et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2021)

Article Chemistry, Multidisciplinary

Artificial Intelligence-Guided De Novo Molecular Design Targeting COVID-19

Srilok Srinivasan et al.

Summary: An AI-driven de novo molecular design strategy has been developed to discover new therapeutic agents against SARS-CoV-2, outperforming existing FDA and non-FDA molecules. This approach enables accelerated design and discovery of chemical molecules with desired functionality.

ACS OMEGA (2021)

Article Biochemistry & Molecular Biology

An integrative drug repositioning framework discovered a potential therapeutic agent targeting COVID-19

Yiyue Ge et al.

Summary: A drug repositioning framework was developed to identify CVL218 as a potential treatment for COVID-19, with in vitro assays showing its inhibitory effect on SARS-CoV-2 replication and interaction with viral proteins, as well as suppression of inflammatory cytokines relevant to immunopathology induced by the virus.

SIGNAL TRANSDUCTION AND TARGETED THERAPY (2021)

Article Computer Science, Information Systems

Knowledge-Graph-Based Drug Repositioning against COVID-19 by Graph Convolutional Network with Attention Mechanism

Mingxuan Che et al.

Summary: The current global crisis caused by COVID-19 has led to a need for identifying suitable drugs for the virus. Researchers successfully utilized a knowledge-graph-based drug repositioning method to predict effective drugs for treating COVID-19, confirming the method's efficacy in predicting drug-disease interactions for both normal diseases and COVID-19.

FUTURE INTERNET (2021)

Article Computer Science, Artificial Intelligence

A deep learning framework for high-throughput mechanism-driven phenotype compound screening and its application to COVID-19 drug repurposing

Thai-Hoang Pham et al.

Summary: In drug discovery and repurposing, the Deep Chemical Expression graph neural network is developed to predict chemical-induced gene expression profiles and applied to drug repurposing for COVID-19 treatments. Experimental results show superior performance and support for downstream classification tasks.

NATURE MACHINE INTELLIGENCE (2021)

Article Biochemical Research Methods

Predicting Drug-target Interactions via FM-DNN Learning

Jihong Wang et al.

CURRENT BIOINFORMATICS (2020)

Article Biochemical Research Methods

Research on Gastric Cancer's Drug-resistant Gene Regulatory Network Model

Zhi Li et al.

CURRENT BIOINFORMATICS (2020)

Article Biochemical Research Methods

A Machine Learning-based Diagnosis of Thyroid Cancer Using Thyroid Nodules Ultrasound Images

Xuesi Ma et al.

CURRENT BIOINFORMATICS (2020)

Article Biochemical Research Methods

Identification of Novel Key Targets and Candidate Drugs in Oral Squamous Cell Carcinoma

Juan Liu et al.

CURRENT BIOINFORMATICS (2020)

Article Biochemical Research Methods

A Drug Target Interaction Prediction Based on LINE-RF Learning

Jihong Wang et al.

CURRENT BIOINFORMATICS (2020)

Review Biochemical Research Methods

Cancer Diagnosis and Disease Gene Identification via Statistical Machine Learning

Liuyuan Chen et al.

CURRENT BIOINFORMATICS (2020)

Editorial Material Medicine, General & Internal

Coronavirus Infections-More Than Just the Common Cold

Catharine I. Paules et al.

JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION (2020)

Review Chemistry, Medicinal

Machine intelligence in peptide therapeutics: A next-generation tool for rapid disease screening

Shaherin Basith et al.

MEDICINAL RESEARCH REVIEWS (2020)

Article Biochemical Research Methods

DeepLGP: a novel deep learning method for prioritizing lncRNA target genes

Tianyi Zhao et al.

BIOINFORMATICS (2020)

Article Medicine, Research & Experimental

Machine Learning of Single-Cell Transcriptome Highly Identifies mRNA Signature by Comparing F-Score Selection with DGE Analysis

Pengfei Liang et al.

MOLECULAR THERAPY-NUCLEIC ACIDS (2020)

Article Mathematical & Computational Biology

Deep Learning Based Drug Screening for Novel Coronavirus 2019-nCov

Haiping Zhang et al.

INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES (2020)

Article Multidisciplinary Sciences

A SARS-CoV-2 protein interaction map reveals targets for drug repurposing

David E. Gordon et al.

NATURE (2020)

Review Biochemical Research Methods

A Mini-review of Computational Approaches to Predict Functions and Findings of Novel Micro Peptides

Mohsin Ali Nasir et al.

CURRENT BIOINFORMATICS (2020)

Article Immunology

COVID-19 Coronavirus Vaccine Design Using Reverse Vaccinology and Machine Learning

Edison Ong et al.

FRONTIERS IN IMMUNOLOGY (2020)

Article Biochemical Research Methods

Repurpose Open Data to Discover Therapeutics for COVID-19 Using Deep Learning

Xiangxiang Zeng et al.

JOURNAL OF PROTEOME RESEARCH (2020)

Review Genetics & Heredity

Feasibility of Mesenchymal Stem Cell Therapy for COVID-19: A Mini Review

Jingwen Li et al.

CURRENT GENE THERAPY (2020)

Review Cell Biology

COVID-19 and multiorgan failure: A narrative review on potential mechanisms

Tahmineh Mokhtari et al.

JOURNAL OF MOLECULAR HISTOLOGY (2020)

Editorial Material Biochemical Research Methods

Artificial Intelligence for Bioinformatics and Biomedicine

Yongqing Zhang

CURRENT BIOINFORMATICS (2020)

Article Virology

Transcription-based drug repurposing for COVID-19

Richard Killick et al.

VIRUS RESEARCH (2020)

Correction Biochemistry & Molecular Biology

Emerging Pandemic Diseases: How We Got to COVID-19 (vol 182, pg 1077, 2020)

David M. Morens et al.

Article Chemistry, Multidisciplinary

Target identification among known drugs by deep learning from heterogeneous networks

Xiangxiang Zeng et al.

CHEMICAL SCIENCE (2020)

Article Biochemistry & Molecular Biology

Predicting commercially available antiviral drugs that may act on the novel coronavirus (SARS-CoV-2) through a drug-target interaction deep learning model

Bo Ram Beck et al.

COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL (2020)

Article Biochemical Research Methods

deepDR: a network-based deep learning approach to in silico drug repositioning

Xiangxiang Zeng et al.

BIOINFORMATICS (2019)

Review Microbiology

Origin and evolution of pathogenic coronaviruses

Jie Cui et al.

NATURE REVIEWS MICROBIOLOGY (2019)

Article Biochemistry & Molecular Biology

Revealing Gene Function and Transcription Relationship by Reconstructing Gene-Level Chromatin Interaction

Li Liu et al.

COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL (2019)

Article Medicine, Research & Experimental

M6APred-EL: A Sequence-Based Predictor for Identifying N6-methyladenosine Sites Using Ensemble Learning

Leyi Wei et al.

MOLECULAR THERAPY-NUCLEIC ACIDS (2018)

Article Biochemical Research Methods

RGDtrip: A Database for the Investigation of Proteins Containing the RGD Tripeptide

Yiannis Hatzis et al.

CURRENT BIOINFORMATICS (2018)

Article Biochemical Research Methods

Improved and Promising Identification of Human MicroRNAs by Incorporating a High-Quality Negative Set

Leyi Wei et al.

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS (2014)