PMID- 33446856
OWN - NLM
STAT- MEDLINE
DCOM- 20210916
LR  - 20240330
IS  - 2045-2322 (Electronic)
IS  - 2045-2322 (Linking)
VI  - 11
IP  - 1
DP  - 2021 Jan 14
TI  - Predicting bacteriophage hosts based on sequences of annotated receptor-binding 
      proteins.
PG  - 1467
LID - 10.1038/s41598-021-81063-4 [doi]
LID - 1467
AB  - Nowadays, bacteriophages are increasingly considered as an alternative treatment 
      for a variety of bacterial infections in cases where classical antibiotics have 
      become ineffective. However, characterizing the host specificity of phages 
      remains a labor- and time-intensive process. In order to alleviate this burden, 
      we have developed a new machine-learning-based pipeline to predict bacteriophage 
      hosts based on annotated receptor-binding protein (RBP) sequence data. We focus 
      on predicting bacterial hosts from the ESKAPE group, Escherichia coli, Salmonella 
      enterica and Clostridium difficile. We compare the performance of our predictive 
      model with that of the widely used Basic Local Alignment Search Tool (BLAST). Our 
      best-performing predictive model reaches Precision-Recall Area Under the Curve 
      (PR-AUC) scores between 73.6 and 93.8% for different levels of sequence 
      similarity in the collected data. Our model reaches a performance comparable to 
      that of BLASTp when sequence similarity in the data is high and starts 
      outperforming BLASTp when sequence similarity drops below 75%. Therefore, our 
      machine learning methods can be especially useful in settings in which sequence 
      similarity to other known sequences is low. Predicting the hosts of novel 
      metagenomic RBP sequences could extend our toolbox to tune the host spectrum of 
      phages or phage tail-like bacteriocins by swapping RBPs.
FAU - Boeckaerts, Dimitri
AU  - Boeckaerts D
AD  - KERMIT, Department of Data Analysis and Mathematical Modelling, Ghent University, 
      Ghent, Belgium.
AD  - Laboratory of Applied Biotechnology, Department of Biotechnology, Ghent 
      University, Ghent, Belgium.
FAU - Stock, Michiel
AU  - Stock M
AD  - KERMIT, Department of Data Analysis and Mathematical Modelling, Ghent University, 
      Ghent, Belgium.
FAU - Criel, Bjorn
AU  - Criel B
AD  - Laboratory of Applied Biotechnology, Department of Biotechnology, Ghent 
      University, Ghent, Belgium.
FAU - Gerstmans, Hans
AU  - Gerstmans H
AD  - Laboratory of Applied Biotechnology, Department of Biotechnology, Ghent 
      University, Ghent, Belgium.
AD  - Laboratory of Gene Technology, Department of Biosystems, KU Leuven, Leuven, 
      Belgium.
AD  - MeBioS-Biosensors group, Department of BioSystems, KU Leuven, Leuven, Belgium.
FAU - De Baets, Bernard
AU  - De Baets B
AD  - KERMIT, Department of Data Analysis and Mathematical Modelling, Ghent University, 
      Ghent, Belgium.
FAU - Briers, Yves
AU  - Briers Y
AD  - Laboratory of Applied Biotechnology, Department of Biotechnology, Ghent 
      University, Ghent, Belgium. Yves.Briers@UGent.be.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20210114
PL  - England
TA  - Sci Rep
JT  - Scientific reports
JID - 101563288
RN  - 0 (Viral Tail Proteins)
SB  - IM
MH  - Animals
MH  - Bacteria/genetics
MH  - Bacteriophages/*genetics
MH  - Clostridioides difficile/genetics
MH  - Escherichia coli/genetics
MH  - Host Specificity/*genetics
MH  - Humans
MH  - Machine Learning
MH  - Metagenomics/methods
MH  - Protein Binding/genetics
MH  - Salmonella enterica/genetics
MH  - Sequence Analysis, DNA/*methods
MH  - Viral Tail Proteins/genetics
MH  - Virion/genetics
PMC - PMC7809048
COIS- The authors declare no competing interests.
EDAT- 2021/01/16 06:00
MHDA- 2021/09/18 06:00
PMCR- 2021/01/14
CRDT- 2021/01/15 05:56
PHST- 2020/05/04 00:00 [received]
PHST- 2020/12/30 00:00 [accepted]
PHST- 2021/01/15 05:56 [entrez]
PHST- 2021/01/16 06:00 [pubmed]
PHST- 2021/09/18 06:00 [medline]
PHST- 2021/01/14 00:00 [pmc-release]
AID - 10.1038/s41598-021-81063-4 [pii]
AID - 81063 [pii]
AID - 10.1038/s41598-021-81063-4 [doi]
PST - epublish
SO  - Sci Rep. 2021 Jan 14;11(1):1467. doi: 10.1038/s41598-021-81063-4.