Dataset Information

Machine learning predicts new anti-CRISPR proteins.

ABSTRACT: The increasing use of CRISPR-Cas9 in medicine, agriculture, and synthetic biology has accelerated the drive to discover new CRISPR-Cas inhibitors as potential mechanisms of control for gene editing applications. Many anti-CRISPRs have been found that inhibit the CRISPR-Cas adaptive immune system. However, comparing all currently known anti-CRISPRs does not reveal a shared set of properties for facile bioinformatic identification of new anti-CRISPR families. Here, we describe AcRanker, a machine learning based method to aid direct identification of new potential anti-CRISPRs using only protein sequence information. Using a training set of known anti-CRISPRs, we built a model based on XGBoost ranking. We then applied AcRanker to predict candidate anti-CRISPRs from predicted prophage regions within self-targeting bacterial genomes and discovered two previously unknown anti-CRISPRs: AcrllA20 (ML1) and AcrIIA21 (ML8). We show that AcrIIA20 strongly inhibits Streptococcus iniae Cas9 (SinCas9) and weakly inhibits Streptococcus pyogenes Cas9 (SpyCas9). We also show that AcrIIA21 inhibits SpyCas9, Streptococcus aureus Cas9 (SauCas9) and SinCas9 with low potency. The addition of AcRanker to the anti-CRISPR discovery toolkit allows researchers to directly rank potential anti-CRISPR candidate genes for increased speed in testing and validation of new anti-CRISPRs. A web server implementation for AcRanker is available online at http://acranker.pythonanywhere.com/.

SUBMITTER: Eitzinger S

PROVIDER: S-EPMC7229843 | biostudies-literature | 2020 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning predicts new anti-CRISPR proteins.

Eitzinger Simon S Asif Amina A Watters Kyle E KE Iavarone Anthony T AT Knott Gavin J GJ Doudna Jennifer A JA Minhas Fayyaz Ul Amir Afsar FUAA

Nucleic acids research 20200501 9

The increasing use of CRISPR-Cas9 in medicine, agriculture, and synthetic biology has accelerated the drive to discover new CRISPR-Cas inhibitors as potential mechanisms of control for gene editing applications. Many anti-CRISPRs have been found that inhibit the CRISPR-Cas adaptive immune system. However, comparing all currently known anti-CRISPRs does not reveal a shared set of properties for facile bioinformatic identification of new anti-CRISPR families. Here, we describe AcRanker, a machine ...[more]

PMID: 32286628

Similar Datasets

Project description:Bcl-2 family anti-apoptotic proteins are overexpressed in several hematological and solid tumors, and contribute to tumor formation, progression, and resistance to therapy. They represent a promising therapeutic avenue to explore for cancer treatment. Venetoclax, a Bcl-2 inhibitor is currently used for hematological malignancies or is undergoing clinical trials for either hematological or solid tumors. Despite these progresses, ongoing efforts are focusing on the identification and development of new molecules targeting Bcl-2 protein and/or other family members. Methods: Machine learning guided virtual screening followed by surface plasmon resonance, molecular docking and pharmacokinetic analyses were performed to identify new inhibitors of anti-apoptotic members of Bcl-2 family and their pharmacokinetic profile. The sensitivity of cancer cells from different origin to the identified compounds was evaluated both in in vitro (cell survival, apoptosis, autophagy) and in vivo (tumor growth in nude mice) preclinical models. Results: IS20 and IS21 were identified as potential new lead compounds able to bind Bcl-2, Bcl-xL and Mcl-1 recombinant proteins. Molecular docking investigation indicated IS20 and IS21 could bind into the Beclin-1 BH3 binding site of wild type Bcl-2, Bcl-xL and Mcl-1 proteins. In particular, although the IS21 docked conformation did not show a unique binding mode, it clearly showed its ability in flexibly adapting to either BH3 binding sites. Moreover, both IS20 and IS21 reduced cell viability, clonogenic ability and tumor sphere formation, and induced apoptosis in leukemic, melanoma and lung cancer cells. Autophagosome formation and maturation assays demonstrated induction of autophagic flux after treatment with IS20 or IS21. Experiments with z-VAD-fmk, a pan-caspase inhibitor, and chloroquine, a late-stage autophagy inhibitor, demonstrated the ability of the two compounds to promote apoptosis by autophagy. IS21 also reduced in vivo tumor growth of both human leukemia and melanoma models. Conclusion: Virtual screening coupled with in vitro and in vivo experimental data led to the identification of two new promising inhibitors of anti-apoptotic proteins with good efficacy in the binding to recombinant Bcl-2, Bcl-xL and Mcl-1 proteins, and against different tumor histotypes.

Dataset Information

Machine learning predicts new anti-CRISPR proteins.

Publications

Machine learning predicts new anti-CRISPR proteins.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets