Deeplasmid: Deep learning accurately separates plasmids from bacterial chromosomes

Wb, Andreopoulos; Am, Geller; Lucke, Miriam; Balewski, J.; Clum, Alicia; Ivanova, Natalia; Levy, Asaf

doi:10.1101/2021.03.11.434936

Cited by 7 publications

(1 citation statement)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also postulated that the models could have learned more sophisticated features of the mitochondrial DNA, such as a different encoding codond,or the density of the genetic information 52 . Furthermore, deep learning models have been shown to successfully detect circular plasmids, based on their sequencing data, by examining larger chunks of the plasmid sequences achieved by longer reads as well as additional genomic features 53 , information that could contribute to a successful classi cation. We think a thorough analysis of a trained deep learning model from this work, as was done for the visual analysis models 48 , could provide useful insights for further research in this eld and perhaps new biological features that were not considered important before would be discovered.…”

Section: Deep Learning Model Selectionmentioning

confidence: 99%

Adaptive sequencing using nanopores and deep learning of mitochondrial DNA

Danilevsky

Polsky

Shomron

2022

Briefings in Bioinformatics

View full text Add to dashboard Cite

Nanopore sequencing is an emerging technology that reads DNA by utilizing a unique method of detecting nucleic acid sequences and identifies the various chemical modifications they carry. Deep learning has increased in popularity as a useful technique to solve many complex computational tasks. ‘Adaptive sequencing’ is an implementation of selective sequencing, intended for use on the nanopore sequencing platform. In this study, we demonstrated an alternative method of software-based selective sequencing that is performed in real time by combining nanopore sequencing and deep learning. Our results showed the feasibility of using deep learning for classifying signals from only the first 200 nucleotides in a raw nanopore sequencing signal format. This was further demonstrated by comparing the accuracy of our deep learning classification model across data from several human cell lines and other eukaryotic organisms. We used custom deep learning models and a script that utilizes a ‘Read Until’ framework to target mitochondrial molecules in real time from a human cell line sample. This achieved a significant separation and enrichment ability of 2.3-fold. In a series of very short sequencing experiments (10, 30 and 120 min), we identified genomic and mitochondrial reads with accuracy above 90%, although mitochondrial DNA comprised only 0.1% of the total input material. The uniqueness of our method is the ability to distinguish two groups of DNA even without a labeled reference. This contrasts with studies that required a well-defined reference, whether of a DNA sequence or of another type of representation. Additionally, our method showed higher correlation to the theoretically possible enrichment factor, compared with other published methods. We believe that our results will lay the foundation for rapid and selective sequencing using nanopore technology and will pave the approach for clinical applications that use nanopore sequencing data.

show abstract

Section: Deep Learning Model Selectionmentioning

confidence: 99%

Adaptive sequencing using nanopores and deep learning of mitochondrial DNA

Danilevsky

Polsky

Shomron

2022

Briefings in Bioinformatics

View full text Add to dashboard Cite

show abstract

The extracellular contractile injection system is enriched in environmental microbes and associates with numerous toxins

et al. 2021

Self Cite

View full text Add to dashboard Cite

The extracellular Contractile Injection System (eCIS) is a toxin-delivery particle that evolved from a bacteriophage tail. Four eCISs have previously been shown to mediate interactions between bacteria and their invertebrate hosts. Here, we identify eCIS loci in 1,249 bacterial and archaeal genomes and reveal an enrichment of these loci in environmental microbes and their apparent absence from mammalian pathogens. We show that 13 eCIS-associated toxin genes from diverse microbes can inhibit the growth of bacteria and/or yeast. We identify immunity genes that protect bacteria from self-intoxication, further supporting an antibacterial role for some eCISs. We also identify previously undescribed eCIS core genes, including a conserved eCIS transcriptional regulator. Finally, we present our data through an extensive eCIS repository, termed eCIStem. Our findings support eCIS as a toxin-delivery system that is widespread among environmental prokaryotes and likely mediates antagonistic interactions with eukaryotes and other prokaryotes.

show abstract

Plasmids encode and can mobilize onion pathogenicity inPantoea agglomerans

Shin,

Asselin,

Smith

et al. 2024

Preprint

View full text Add to dashboard Cite

Pantoea agglomeransis one of fourPantoeaspecies for which strains have been reported in the United States to cause bacterial rot of onion bulbs. However, not allP. agglomeransstrains are pathogenic to onion. We characterized onion-associated strains ofP. agglomeransto elucidate the genetic and genomic signatures of onion-pathogenicP. agglomerans. We collected >300P. agglomeransstrains associated with symptomatic onion plants and bulbs from public culture collections, research laboratories, and a multi-year survey in 11 states in the USA. Genome assemblies were generated for 87P. agglomeransstrains that showed a range in onion virulence phenotypes. Combining the 87 genome assemblies with 100 high-quality, publicP. agglomeransgenome assemblies identified two well-represented and well-supportedP. agglomeransphylogroups. Strains causing severe symptoms on onion leaves and bulbs were only identified in Phylogroup II and encoded the HiVir biosynthetic cluster for the phytotoxin pantaphos, supporting the role of HiVir as a crucial pathogenicity factor. Using a MASH-based plasmid classification system, theP. agglomeransHiVir cluster was determined to be encoded in two distinct plasmid contexts: 1) as an accessory gene cluster on a conservedP. agglomeransplasmid (pAggl), or 2) on a mosaic cluster of plasmids common among onion strains (pOnion). Analysis of closed genomes ofP. agglomeransrevealed that the pOnion plasmids harboredaltgenes responsible for encoding tolerance to the thiosulfinate defensive chemistry inAlliumspp. Additionally, many of these pOnion plasmids harboredcopgene clusters, which confer resistance to copper. However, the pOnion plasmids encoded the HiVir cluster less frequently. We demonstrated that the pOnion plasmid pCB1C, encoding HiVir andaltclusters as well as an intact conjugative type IV secretion system (T4SS), can act as a natively mobilizable pathogenicity plasmid that transformsP. agglomeransPhylogroup I strains, including environmental strains, into virulent pathogens of onion. This work indicates a central role for plasmids and plasmid ecology in mediatingP. agglomeransinteractions with onion plants, with potential implications for onion bacterial disease management.

show abstract

Deeplasmid: Deep learning accurately separates plasmids from bacterial chromosomes

Cited by 7 publications

References 57 publications

Adaptive sequencing using nanopores and deep learning of mitochondrial DNA

Adaptive sequencing using nanopores and deep learning of mitochondrial DNA

The extracellular contractile injection system is enriched in environmental microbes and associates with numerous toxins

Plasmids encode and can mobilize onion pathogenicity inPantoea agglomerans

Contact Info

Product

Resources

About