Dataset Information

Prediction of Premature Termination Codon Suppressing Compounds for Treatment of Duchenne Muscular Dystrophy Using Machine Learning.

ABSTRACT: A significant percentage of Duchenne muscular dystrophy (DMD) cases are caused by premature termination codon (PTC) mutations in the dystrophin gene, leading to the production of a truncated, non-functional dystrophin polypeptide. PTC-suppressing compounds (PTCSC) have been developed in order to restore protein translation by allowing the incorporation of an amino acid in place of a stop codon. However, limitations exist in terms of efficacy and toxicity. To identify new compounds that have PTC-suppressing ability, we selected and clustered existing PTCSC, allowing for the construction of a common pharmacophore model. Machine learning (ML) and deep learning (DL) models were developed for prediction of new PTCSC based on known compounds. We conducted a search of the NCI compounds database using the pharmacophore-based model and a search of the DrugBank database using pharmacophore-based, ML and DL models. Sixteen drug compounds were selected as a consensus of pharmacophore-based, ML, and DL searches. Our results suggest notable correspondence of the pharmacophore-based, ML, and DL models in prediction of new PTC-suppressing compounds.

SUBMITTER: Wang K

PROVIDER: S-EPMC7503396 | biostudies-literature | 2020 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction of Premature Termination Codon Suppressing Compounds for Treatment of Duchenne Muscular Dystrophy Using Machine Learning.

Wang Kate K Romm Eden L EL Kouznetsova Valentina L VL Tsigelny Igor F IF

Molecules (Basel, Switzerland) 20200826 17

A significant percentage of Duchenne muscular dystrophy (DMD) cases are caused by premature termination codon (PTC) mutations in the dystrophin gene, leading to the production of a truncated, non-functional dystrophin polypeptide. PTC-suppressing compounds (PTCSC) have been developed in order to restore protein translation by allowing the incorporation of an amino acid in place of a stop codon. However, limitations exist in terms of efficacy and toxicity. To identify new compounds that have PTC- ...[more]

PMID: 32858918

Similar Datasets

Project description:Dystrophinopathies cover a spectrum of rare progressive X-linked muscle diseases, arising from DMD mutations. They are among the most common pediatric muscular dystrophies, being Duchenne muscular dystrophy (DMD) the most severe form. Despite the fact that there is still no cure for these serious diseases, unprecedented advances are being made for the development of therapies for DMD. Some of which are already conditionally approved: exon skipping and premature stop codon read-through. The present work aimed to characterize the mutational spectrum of DMD in an Argentinian cohort, to identify candidates for available pharmacogenetic treatments and finally, to conduct a comparative analysis of the Latin American (LA) frequencies of mutations amenable for available DMD therapies. We studied 400 patients with clinical diagnosis of dystrophinopathy, implementing a diagnostic molecular algorithm including: MLPA/PCR/Sanger/Exome and bioinformatics. We also performed a meta-analysis of LA's metrics for DMD available therapies. The employed algorithm resulted effective for the achievement of differential diagnosis, reaching a detection rate of 97%. Because of this, corticosteroid treatment was correctly indicated and validated in 371 patients with genetic confirmation of dystrophinopathy. Also, 20 were eligible for exon skipping of exon 51, 21 for exon 53, 12 for exon 45 and another 70 for premature stop codon read-through therapy. We determined that 87.5% of DMD patients will restore the reading frame with the skipping of only one exon. Regarding nonsense variants, UGA turned out to be the most frequent premature stop codon observed (47%). According to the meta-analysis, only four LA countries (Argentina, Brazil, Colombia and Mexico) provide the complete molecular algorithm for dystrophinopathies. We observed different relations among the available targets for exon skipping in the analyzed populations, but a more even proportion of nonsense variants (∼40%). In conclusion, this manuscript describes the theragnosis carried out in Argentinian dystrophinopathy patients. The implemented molecular algorithm proved to be efficient for the achievement of differential diagnosis, which plays a crucial role in patient management, determination of the standard of care and genetic counseling. Finally, this work contributes with the international efforts to characterize the frequencies and variants in LA, pillars of drug development and theragnosis.

Dataset Information

Prediction of Premature Termination Codon Suppressing Compounds for Treatment of Duchenne Muscular Dystrophy Using Machine Learning.

Publications

Prediction of Premature Termination Codon Suppressing Compounds for Treatment of Duchenne Muscular Dystrophy Using Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets