Virtual Screening Strategies: A State of Art to Combat with Multiple Drug Resistance Strains

Khan, Asad

doi:10.15406/mojpb.2015.02.00042

Cited by 2 publications

(1 citation statement)

References 74 publications

(52 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Virtual Screening (VS) techniques) are often used as starting point for medical chemistry, for speedingup the drug discovery process by identifying compounds of high potential against specific targets. VS can be categorized in three main areas: (1) structure-based (requiring knowledge of the 3D structure of the target), (2) ligand-based (requiring knowledge of active ligands) and (3) hybrid approaches [5]. As the number of ligands in openly available databases is constantly increasing (e.g.…”

Section: Introductionmentioning

confidence: 99%

Multiple Instance Learning Based on Mol2vec Molecular Substructure Embeddings for Discovery of NDM-1 Inhibitors

Papastergiou

Azé²,

Bringay³

et al. 2022

Practical Applications of Computational Biology and Bioinformatics, 16th International Conference (PACBB 2022)

View full text Add to dashboard Cite

In this paper, we first present a new dataset of NDM-1 biological activities that is compiled by a cleaned version of the NMDI database. A literature review enriched the former database by 741 new compounds, comprising activities against NDM-1 classified in three classes (inactive, weakly and strongly active compounds) by specifying a unifying procedure for the labeling, which covers a range of different activity properties. Second, we restate the classification problem in the Multiple Instance Learning (MIL) setting by representing the compounds as a collection of Mol2vec vectors, each of them corresponding to a specific substructure (either atom or atom including their first neighbors). We observe an amelioration up to 45.7% and 38.47% in respect to balanced accuracy and F1-score, respectively, for the strongly active class in the MIL approach when compared to the classical Machine Learning paradigm. Finally, we present a classification and ranking framework based on classifiers learned by a k-fold CV procedure, which possess different hyperparameters per fold, learnt by a Bayes optimization procedure. We observe that the top-3 and top-5 ranked accuracies of the strongly active classified compounds yield 100% for the MIL setting.

show abstract

Section: Introductionmentioning

confidence: 99%

Multiple Instance Learning Based on Mol2vec Molecular Substructure Embeddings for Discovery of NDM-1 Inhibitors

Papastergiou

Azé²,

Bringay³

et al. 2022

Practical Applications of Computational Biology and Bioinformatics, 16th International Conference (PACBB 2022)

View full text Add to dashboard Cite

show abstract

Computational Drug Discovery Against COVID-19

Modanwal

Mulpuru

Mishra

2023

COVID-19: Origin, Impact and Management (Part 2)

View full text Add to dashboard Cite

The global spread of Severe Acute Respiratory Syndrome coronavirus 2 (SARS-CoV-2), which causes the disease COVID-19, has increased drastically since the first cases in Wuhan, People's Republic of China, at the end of 2019. There is no single drug that can be used specifically to treat COVID. The crucial stage in the drug development process is screening huge libraries of bioactive molecules against a biological target, usually a receptor or a protein. Virtual Screening (VS) has become a valuable tool in the drug development process as it allows for efficient in silico searches of millions of compounds, resulting in higher yields of possible therapeutic leads, and is cost-effective. The spread of the SARS-CoV-2 virus presents a major threat to world health and has resulted in a global crisis because of the high mortality rate and absence of clinically authorised treatments and vaccines for COVID-19. Finding effective drugs or repurposing available antiviral drugs is a critical need in the fight against COVID-19. VS can be classified as either Structural-Based Virtual Screening or Ligand-Based Virtual Screening. VS techniques have been widely applied in the field of antiviral drug design and have aided in the identification of new compounds as possible anti-viral drugs. Both LBVS and SBVS approaches have proved extremely helpful in identifying several prospective anti-viral drugs with nanomolar range. VS, in contrast to experimental approaches, is quick and cost-effective on the one side but has low prediction accuracy on the other.

show abstract

Virtual Screening Strategies: A State of Art to Combat with Multiple Drug Resistance Strains

Cited by 2 publications

References 74 publications

Multiple Instance Learning Based on Mol2vec Molecular Substructure Embeddings for Discovery of NDM-1 Inhibitors

Multiple Instance Learning Based on Mol2vec Molecular Substructure Embeddings for Discovery of NDM-1 Inhibitors

Computational Drug Discovery Against COVID-19

Contact Info

Product

Resources

About