Using Cartesian Doubt To Build a Sequencing-Based View of Microbiology

Tierney, Braden T.; Szymanski, Erika; Henriksen, James R.; Kostic, Aleksandar D.; Patel, Chirag

doi:10.1128/msystems.00574-21

Cited by 3 publications

(2 citation statements)

References 35 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because of their application to non-curated data, reconstructed networks can be used for the elucidation of new biology, such as the discovery of new species and metabolic pathways in gut microbiome samples [60]. Reconstructed networks can also be created from individually sequenced faecal samples to catch incidents of horizontal gene transfer and random mutation that lead to novel metabolic function [51].…”

Section: Discussionmentioning

confidence: 99%

Selection of an Ideal Machine Learning Framework for Predicting Perturbation Effects on Network Topology of Bacterial KEGG Pathways

Robben

Nasr

Das

et al. 2022

Preprint

View full text Add to dashboard Cite

Biological networks for bacterial species are used to assign functional information to newly sequenced organisms but network quality can be largely affected by poor gene annotations. Current methods of gene annotation use homologous alignment to determine orthology, and have been shown to degrade network accuracy in non-model bacterial species. To address these issues in the KEGG pathway database, we investigated the ability for machine learning (ML) algorithms to re-annotate bacterial genes based on motif or homology information. The majority of the ensemble, clustering, and deep learning algorithms that we explored showed higher prediction accuracy than CD-hit in predicting EC ID, Map ID, and partial Map ID. Motif-based, machine-learning methods of annotation in new species were more accurate, faster, and had higher precisionrecall than methods of homologous alignment or orthologous gen clustering. Gradient boosted ensemble methods and neural networks also predicted higher connectivity of networks, finding twice as many new pathway interactions than blast alignment. The use of motif-based, machine-learning algorithms in annotation software will allow researchers to develop powerful network tools to interact with bacterial microbiomes in ways previously unachievable through homologous sequence alignment.

show abstract

Section: Discussionmentioning

confidence: 99%

Selection of an Ideal Machine Learning Framework for Predicting Perturbation Effects on Network Topology of Bacterial KEGG Pathways

Robben

Nasr

Das

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Several Perspective pieces in this series present new approaches for making sense of microbiome sequence data or new tools to fill major gaps in our knowledge of the diversity and functions of microbiomes. Tierney et al rethink how we should analyze and categorize the deluge of microbiome sequence data ( 7 ). Much of our historical understanding of microbiology is based on microbes that can be cultured.…”

Section: Technologies and Tools Neededmentioning

confidence: 99%

Deciphering the Microbiome: Integrating Theory, New Technologies, and Inclusive Science

et al. 2022

View full text Add to dashboard Cite

show abstract

Comparison of the Strengths and Weaknesses of Machine Learning Algorithms and Feature Selection on KEGG Database Microbial Gene Pathway Annotation and Its Effects on Reconstructed Network Topology

Robben,

Nasr,

Das

et al. 2023

Journal of Computational Biology

View full text Add to dashboard Cite

Using Cartesian Doubt To Build a Sequencing-Based View of Microbiology

Abstract: The technological leap of DNA sequencing generated a tension between modern metagenomics and historical microbiology. We are forcibly harmonizing the output of a modern tool with centuries of experimental knowledge derived from culture-based microbiology.

Cited by 3 publications

References 35 publications

Selection of an Ideal Machine Learning Framework for Predicting Perturbation Effects on Network Topology of Bacterial KEGG Pathways

Selection of an Ideal Machine Learning Framework for Predicting Perturbation Effects on Network Topology of Bacterial KEGG Pathways

Deciphering the Microbiome: Integrating Theory, New Technologies, and Inclusive Science

Comparison of the Strengths and Weaknesses of Machine Learning Algorithms and Feature Selection on KEGG Database Microbial Gene Pathway Annotation and Its Effects on Reconstructed Network Topology

Contact Info

Product

Resources

About