Optimizing peptide inhibitors of SARS-Cov-2 nsp10/nsp16 methyltransferase predicted through molecular simulation and machine learning

Hamre, John; Jafri, M. Saleet

doi:10.1016/j.imu.2022.100886

Cited by 5 publications

(8 citation statements)

References 74 publications

(88 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A short history of machine learning, its fundamentals, some applications of machine learning, and the maturation of machine learning methods have been discussed in a review by Lee et al (2017). Some studies have used machine learning methods to predict the function of peptides (Hamre & Jafri, 2022;Herrera-Bravo et al, 2022;Janairo, 2021;Lee et al, 2017;Nambiar et al, 2022;Shen et al, 2022). In a recent study, Shen et al (2022) utilized this technique to design an antioxidant peptide classification model with a precision above 0.95 according to the pseudo-amino acid compositions and motifs of peptides as input features.…”

Section: Computer-based Screening Of Antioxidant Peptidesmentioning

confidence: 99%

“…This method utilizes available datasets in relation to the amino acid sequences of all recorded peptides, frequency of their occurrence, and specific enzymes for releasing them with anticipated physicochemical and functional characteristics. Moreover, these datasets can also be employed to foresee the health properties, allergenicity, and organoleptic properties such as bitterness of the expected peptides (Hamre & Jafri, 2022; Herrera‐Bravo et al., 2022). Some of the principal bioinformatic analysis databases and tools used in this area are listed in Table 2.…”

Section: Computer‐based Screening Of Antioxidant Peptidesmentioning

confidence: 99%

“…Although numerous peptides have been uncovered in the last few decades, the function of countless peptides is not fully understood yet. Confronted with this numerous peptide data, manual assessment is considered extremely time and resource consuming (Hamre & Jafri, 2022; Herrera‐Bravo et al., 2022). In this context, a computer‐based approach to screening antioxidant peptides can decrease the trial and error of the procedures.…”

Section: Computer‐based Screening Of Antioxidant Peptidesmentioning

confidence: 99%

“…In this context, a computer‐based approach to screening antioxidant peptides can decrease the trial and error of the procedures. Machine learning combined with artificial intelligence can quickly recognize favorable leads to be synthesized, thus decreasing the overall compounds to be created and examined, making the entire development procedure more environmentally friendly and resource efficient (Hamre & Jafri, 2022; Herrera‐Bravo et al., 2022). Machine learning combines computer science, mathematics, and statistics to understand the data.…”

Section: Computer‐based Screening Of Antioxidant Peptidesmentioning

confidence: 99%

“…(2017). Some studies have used machine learning methods to predict the function of peptides (Hamre & Jafri, 2022; Herrera‐Bravo et al., 2022; Janairo, 2021; Lee et al., 2017; Nambiar et al., 2022; Shen et al., 2022). In a recent study, Shen et al.…”

Section: Computer‐based Screening Of Antioxidant Peptidesmentioning

confidence: 99%

See 4 more Smart Citations

Antioxidant peptides: Overview of production, properties, and applications in food systems

Mardani

Badakné

Farmani

et al. 2022

Comp Rev Food Sci Food Safe

View full text Add to dashboard Cite

In recent years, several studies have reported the beneficial effects of antioxidant peptides in delaying oxidation reactions. Thus, a growing number of food proteins have been investigated as suitable sources for obtaining these antioxidant peptides. In this study, some of the most critical developments in the discovery of peptidic antioxidants are discussed. Initially, the primary methods to release, purify, and identify these antioxidant peptides from various food‐derived sources are reviewed. Then, computer‐based screening methods of the available peptides are summarized, and methods to interpret their structure–activity relationship are illustrated. Finally, approaches to the large‐scale production of these bioactive peptides are described. In addition, the applications of these antioxidants in food systems are discussed, and gaps, future challenges, and opportunities in this field are highlighted. In conclusion, various food items can be considered promising sources to obtain these novel antioxidant peptides, which present various opportunities for food applications in addition to health promotion. The lack of in‐depth data on the link between the structure and activity of these antioxidants, which is critical for the prediction of possible bioactive amino acid sequences and their potency in food systems and in vivo conditions (rather than in vitro systems), requires further attention. Consequently, future collaborative research activities between the industry and academia are required to realize the commercialization objectives of these novel antioxidant peptides.

show abstract

Section: Computer-based Screening Of Antioxidant Peptidesmentioning

confidence: 99%

Section: Computer‐based Screening Of Antioxidant Peptidesmentioning

confidence: 99%

Section: Computer‐based Screening Of Antioxidant Peptidesmentioning

confidence: 99%

Section: Computer‐based Screening Of Antioxidant Peptidesmentioning

confidence: 99%

Section: Computer‐based Screening Of Antioxidant Peptidesmentioning

confidence: 99%

See 3 more Smart Citations

Antioxidant peptides: Overview of production, properties, and applications in food systems

Mardani

Badakné

Farmani

et al. 2022

Comp Rev Food Sci Food Safe

View full text Add to dashboard Cite

show abstract

Identification of motif-based interactions between SARS-CoV-2 protein domains and human peptide ligands pinpoint antiviral targets

Mihalič,

Benz,

Kassa

et al. 2023

Nat Commun

View full text Add to dashboard Cite

The virus life cycle depends on host-virus protein-protein interactions, which often involve a disordered protein region binding to a folded protein domain. Here, we used proteomic peptide phage display (ProP-PD) to identify peptides from the intrinsically disordered regions of the human proteome that bind to folded protein domains encoded by the SARS-CoV-2 genome. Eleven folded domains of SARS-CoV-2 proteins were found to bind 281 peptides from human proteins, and affinities of 31 interactions involving eight SARS-CoV-2 protein domains were determined (KD ∼ 7-300 μM). Key specificity residues of the peptides were established for six of the interactions. Two of the peptides, binding Nsp9 and Nsp16, respectively, inhibited viral replication. Our findings demonstrate how high-throughput peptide binding screens simultaneously identify potential host-virus interactions and peptides with antiviral properties. Furthermore, the high number of low-affinity interactions suggest that overexpression of viral proteins during infection may perturb multiple cellular pathways.

show abstract

AI-guided pipeline for protein–protein interaction drug discovery identifies a SARS-CoV-2 inhibitor

Trepte,

Secker,

Olivet

et al. 2024

Mol Syst Biol

View full text Add to dashboard Cite

Protein–protein interactions (PPIs) offer great opportunities to expand the druggable proteome and therapeutically tackle various diseases, but remain challenging targets for drug discovery. Here, we provide a comprehensive pipeline that combines experimental and computational tools to identify and validate PPI targets and perform early-stage drug discovery. We have developed a machine learning approach that prioritizes interactions by analyzing quantitative data from binary PPI assays or AlphaFold-Multimer predictions. Using the quantitative assay LuTHy together with our machine learning algorithm, we identified high-confidence interactions among SARS-CoV-2 proteins for which we predicted three-dimensional structures using AlphaFold-Multimer. We employed VirtualFlow to target the contact interface of the NSP10-NSP16 SARS-CoV-2 methyltransferase complex by ultra-large virtual drug screening. Thereby, we identified a compound that binds to NSP10 and inhibits its interaction with NSP16, while also disrupting the methyltransferase activity of the complex, and SARS-CoV-2 replication. Overall, this pipeline will help to prioritize PPI targets to accelerate the discovery of early-stage drug candidates targeting protein complexes and pathways.

show abstract

Optimizing peptide inhibitors of SARS-Cov-2 nsp10/nsp16 methyltransferase predicted through molecular simulation and machine learning

Cited by 5 publications

References 74 publications

Antioxidant peptides: Overview of production, properties, and applications in food systems

Antioxidant peptides: Overview of production, properties, and applications in food systems

Identification of motif-based interactions between SARS-CoV-2 protein domains and human peptide ligands pinpoint antiviral targets

AI-guided pipeline for protein–protein interaction drug discovery identifies a SARS-CoV-2 inhibitor

Contact Info

Product

Resources

About