Merge pull request #147 from csoneson/minor-edits

Minor edits reviewed and approved

Author: stephwon

joss/paper.bib

@@ -1,33 +1,3 @@
-@article{tian2025designed,
-  title={A designed synthetic microbiota provides insight to community function in Clostridioides difficile resistance},
-  author={Tian, Shuchang and Kim, Min Soo and Zhao, Jingcheng and Heber, Kerim and Hao, Fuhua and Koslicki, David and Tian, Sangshan and Singh, Vishal and Patterson, Andrew D and Bisanz, Jordan E},
-  journal={Cell Host \& Microbe},
-  year={2025},
-  doi={10.1016/j.chom.2025.02.007},
-  publisher={Elsevier}
-}
-@article{hera2023deriving,
-  title={Deriving confidence intervals for mutation rates across a wide range of evolutionary distances using FracMinHash},
-  author={Hera, Mahmudur Rahman and Pierce-Ward, N Tessa and Koslicki, David},
-  journal={Genome research},
-  volume={33},
-  number={7},
-  pages={1061--1068},
-  year={2023},
-  doi={10.1101/gr.277651.123},
-  publisher={Cold Spring Harbor Lab}
-}
-@article{blanca2022statistics,
-  title={The statistics of k-mers from a sequence undergoing a simple mutation process without spurious matches},
-  author={Blanca, Antonio and Harris, Robert S and Koslicki, David and Medvedev, Paul},
-  journal={Journal of Computational Biology},
-  volume={29},
-  number={2},
-  pages={155--168},
-  year={2022},
-  doi={10.1089/cmb.2021.0431},
-  publisher={Mary Ann Liebert, Inc., publishers 140 Huguenot Street, 3rd Floor New~…}
-}
 @article{irber2024sourmash,
   title={sourmash v4: A multitool to quickly search, compare, and analyze genomic and metagenomic data sets},
   author={Irber, Luiz and Pierce-Ward, N Tessa and Abuelanin, Mohamed and Alexander, Harriet and Anant, Abhishek and Barve, Keya and Baumler, Colton and Botvinnik, Olga and Brooks, Phillip and Dsouza, Daniel and others},
@@ -63,7 +33,6 @@ @article{ward2018metapoap
   publisher={Oxford University Press}
 }
 
-
 @article{marcelino2019metatranscriptomics,
   title={Metatranscriptomics as a tool to identify fungal species and subspecies in mixed communities--a proof of concept under laboratory conditions},
   author={Marcelino, Vanesa R and Irinyi, Laszlo and Eden, John-Sebastian and Meyer, Wieland and Holmes, Edward C and Sorrell, Tania C},
@@ -147,41 +116,6 @@ @article{meyer2022critical
 }
 
 %USE CASE EXAMPLE REFERENCES
-@article{hayden2022genome,
-  title={Genome capture sequencing selectively enriches bacterial DNA and enables genome-wide measurement of intrastrain genetic diversity in human infections},
-  author={Hayden, Hillary S and Joshi, Snehal and Radey, Matthew C and Vo, Anh T and Forsberg, Cara and Morgan, Sarah J and Waalkes, Adam and Holmes, Elizabeth A and Klee, Sara M and Emond, Mary J and others},
-  journal={Mbio},
-  volume={13},
-  number={5},
-  pages={e01424--22},
-  year={2022},
-  doi={10.1128/mbio.01424-22},
-  publisher={Am Soc Microbiol}
-}
-
-@article{rajeev2023metagenome,
-  title={Metagenome sequencing and recovery of 444 metagenome-assembled genomes from the biofloc aquaculture system},
-  author={Rajeev, Meora and Jung, Ilsuk and Lim, Yeonjung and Kim, Suhyun and Kang, Ilnam and Cho, Jang-Cheon},
-  journal={Scientific data},
-  volume={10},
-  number={1},
-  pages={707},
-  year={2023},
-  doi={10.1038/s41597-023-02622-0},
-  publisher={Nature Publishing Group UK London}
-}
-
-@article{zhang2022cultivation,
-  title={Cultivation and functional characterization of a deep-sea Lentisphaerae representative reveals its unique physiology and ecology},
-  author={Zhang, Tianhang and Zheng, Rikuan and Liu, Rui and Li, Ronggui and Sun, Chaomin},
-  journal={Frontiers in Marine Science},
-  volume={9},
-  pages={848136},
-  year={2022},
-  doi={10.3389/fmars.2022.848136},
-  publisher={Frontiers Media SA}
-}
-
 @article{schloss2020removal,
   title={Removal of rare amplicon sequence variants from 16S rRNA gene sequence surveys biases the interpretation of community structure data},
   author={Schloss, Patrick D},
@@ -191,18 +125,6 @@ @article{schloss2020removal
   publisher={Cold Spring Harbor Laboratory}
 }
 
-@article{jia2022sequencing,
-  title={Sequencing introduced false positive rare taxa lead to biased microbial community diversity, assembly, and interaction interpretation in amplicon studies},
-  author={Jia, Yangyang and Zhao, Shengguo and Guo, Wenjie and Peng, Ling and Zhao, Fang and Wang, Lushan and Fan, Guangyi and Zhu, Yuanfang and Xu, Dayou and Liu, Guilin and others},
-  journal={Environmental Microbiome},
-  volume={17},
-  number={1},
-  pages={1--18},
-  year={2022},
-  doi={10.1186/s40793-022-00436-y},
-  publisher={Springer}
-}
-
 @article{kunin2008bioinformatician,
   title={A bioinformatician's guide to metagenomics},
   author={Kunin, Victor and Copeland, Alex and Lapidus, Alla and Mavromatis, Konstantinos and Hugenholtz, Philip},
@@ -217,7 +139,7 @@ @article{kunin2008bioinformatician
 
 @article{schlaberg2017validation,
   title={Validation of metagenomic next-generation sequencing tests for universal pathogen detection},
-  author={Schlaberg, Robert and Chiu, Charles Y and Miller, Steve and Procop, Gary W and Weinstock, George and Professional Practice Committee and Committee on Laboratory Practices of the American Society for Microbiology and Microbiology Resource Committee of the College of American Pathologists},
+  author={Schlaberg, Robert and Chiu, Charles Y and Miller, Steve and Procop, Gary W and Weinstock, George and {Professional Practice Committee and Committee on Laboratory Practices of the American Society for Microbiology} and {Microbiology Resource Committee of the College of American Pathologists}},
   journal={Archives of Pathology and Laboratory Medicine},
   volume={141},
   number={6},
@@ -249,16 +171,6 @@ @article{marcelino2020ccmetagen
   publisher={Springer}
 }
 
-%Schloss PD. Removal of rare amplicon sequence variants from 16s rrna gene sequence surveys biases the interpretation of community structure data. bioRxiv, 2020, preprint: not peer reviewed. https://doi.org/10.1101/2020.12.11.422279.
-
-@article{Schloss,
-  title={Removal of rare amplicon sequence variants from 16s rrna gene sequence surveys biases the interpretation of community structure data},
-  author={Patrick D. Schloss},
-  journal={bioRxiv},
-  doi={10.1101/2020.12.11.422279},
-  year={2020}
-}
-
 @article{jia2022sequencing,
   title={Sequencing introduced false positive rare taxa lead to biased microbial community diversity, assembly, and interaction interpretation in amplicon studies},
   author={Jia, Yangyang and Zhao, Shengguo and Guo, Wenjie and Peng, Ling and Zhao, Fang and Wang, Lushan and Fan, Guangyi and Zhu, Yuanfang and Xu, Dayou and Liu, Guilin and others},
@@ -283,73 +195,27 @@ @article{jousset2017less
   publisher={Oxford University Press}
 }
 
-@article{hu2022tenebrionibacter,
-  title={Tenebrionibacter intestinalis gen. nov., sp. nov., a member of a novel genus of the family Enterobacteriaceae, isolated from the gut of the plastic-eating mealworm Tenebrio molitor L.},
-  author={Hu, Lin and Yang, Yu},
-  journal={International Journal of Systematic and Evolutionary Microbiology},
-  volume={72},
-  number={2},
-  pages={005246},
-  year={2022},
-  doi={10.1099/ijsem.0.005246},
-  publisher={Microbiology Society}
-}
-
-@article{hardwick2018synthetic,
-  title={Synthetic microbe communities provide internal reference standards for metagenome sequencing and analysis},
-  author={Hardwick, Simon A and Chen, Wendy Y and Wong, Ted and Kanakamedala, Bindu S and Deveson, Ira W and Ongley, Sarah E and Santini, Nadia S and Marcellin, Esteban and Smith, Martin A and Nielsen, Lars K and others},
-  journal={Nature communications},
-  volume={9},
-  number={1},
-  pages={3096},
-  year={2018},
-  doi={10.1038/s41467-018-05555-0},
-  publisher={Nature Publishing Group UK London}
-}
-
-@article{singer2016next,
+@article{Singer2016MockCommunity,
   title={Next generation sequencing data of a defined microbial mock community},
   author={Singer, Esther and Andreopoulos, Bill and Bowers, Robert M and Lee, Janey and Deshpande, Shweta and Chiniquy, Jennifer and Ciobanu, Doina and Klenk, Hans-Peter and Zane, Matthew and Daum, Christopher and others},
   journal={Scientific data},
   volume={3},
   number={1},
-  pages={1--8},
+  pages={160081},
   year={2016},
   doi={10.1038/sdata.2016.81},
   publisher={Nature Publishing Group}
 }
 
-@article{van2023synthetic,
-  title={Synthetic microbial communities (SynComs) of the human gut: design, assembly, and applications},
-  author={van Leeuwen, Pim T and Brul, Stanley and Zhang, Jianbo and Wortel, Meike T},
-  journal={FEMS Microbiology Reviews},
-  volume={47},
-  number={2},
-  pages={fuad012},
-  year={2023},
-  doi={10.1093/femsre/fuad012},
-  publisher={Oxford University Press}
-}
-
 @article{Irber2022FracMinHash,
-  author    = {Irber, Luiz C. and Brooks, Patrick T. and Reiter, Travis E. and Pierce-Ward, Nathan T. and Hera, M. R. and Koslicki, David and Brown, C. Titus},
+  author    = {Irber, Luiz and Brooks, Patrick T. and Reiter, Travis E. and Pierce-Ward, Nathan T. and Hera, M. R. and Koslicki, David and Brown, C. Titus},
   title     = {Lightweight compositional analysis of metagenomes with FracMinHash and minimum metagenome covers},
   journal   = {bioRxiv},
   year      = {2022},
   doi       = {10.1101/2022.01.11.475838},
   url       = {https://doi.org/10.1101/2022.01.11.475838}
 }
 
-@article{Singer2016MockCommunity,
-  author    = {Singer, Esther and Bushnell, Brian and Coleman-Derr, Devin and Douglas, Gina M. and Bowman, Benjamin and Bowers, Robert M. and Levy, Adi and Gies, Esther and Cheng, Jan-Fang and Copeland, Alex and others},
-  title     = {Next generation sequencing data of a defined microbial mock community},
-  journal   = {Scientific Data},
-  volume    = {3},
-  number    = {1},
-  pages     = {1--8},
-  year      = {2016},
-  publisher = {Nature Publishing Group}
-}
 @book{irber2020decentralizing,
   title={Decentralizing indices for genomic data},
   author={Irber Jr, Luiz Carlos},

joss/paper.md

@@ -64,7 +64,7 @@ Identifying genomes in metagenomics samples can be complicated by taxonomic prof
 
 Accurately identifying low-abundance microbial communities remains a significant challenge in metagenomics. Current methods rely on arbitrary filter thresholds that, even when applied, produce results skewed by sequencing errors and evolutionary processes, compromising profiling accuracy and leading to misinterpretations [@schloss2020removal; @jia2022sequencing]. The lack of a systematic credibility framework can undermine researcher confidence, a problem compounded by incomplete reference databases and variable sequencing coverage depth.
 
-Metagenomic methods depend on reference databases that are often incomplete and misaligned with taxonomic frameworks, leaving evolutionarily diverged microbes undetected and causing profiling inaccuracies [@kunin2008bioinformatician; @schlaberg2017validation; @loeffler2020improving; @marcelino2020ccmetagen]. Addressing this equires  analytical frameworks that incorporate genome similarity metrics, though sequencing coverage depth presents an additional challenge to reliable microbial detection.
+Metagenomic methods depend on reference databases that are often incomplete and misaligned with taxonomic frameworks, leaving evolutionarily diverged microbes undetected and causing profiling inaccuracies [@kunin2008bioinformatician; @schlaberg2017validation; @loeffler2020improving; @marcelino2020ccmetagen]. Addressing this requires analytical frameworks that incorporate genome similarity metrics, though sequencing coverage depth presents an additional challenge to reliable microbial detection.
 
 Sequence coverage depth—the portion of a microbe’s genome detected in a sample—is crucial for detecting low-abundance microbes, which are often misinterpreted as noise due to limited sequencing depth [@mande2012classification; @shakya2013comparative; @sczyrba2017critical; @meyer2022critical]. The lack of guidelines for biologically meaningful coverage depth thresholds introduces subjectivity, making dynamic coverage depth thresholds essential. Yet even with adequate coverage and reliable genome references, controlling statistical errors remains a major challenge.
 
@@ -111,7 +111,7 @@ We present the three use case examples to demonstrate the application of YACHT f
 
 **Low abundance samples:** YACHT can analyze metagenomic samples with low microbial DNA concentrations common in clinical and environmental studies. Using a human skin metagenomics samples, we show that ANI threshold and k-size markedly influence species specificity. See [Low abundance samples](https://github.com/KoslickiLab/YACHT/tree/main/use_case_examples/low_abundance_samples).
 
-**Metagenomic-assembled genome (MAG) fishing:** Using a single MAG as a training reference database, YACHT searches for specific MAGs within a sample. Applied to two skin metagenomic samples, results shows detection is sensitive to sequencing depth, coverage, and parameter choice. See [MAG fishing](https://github.com/KoslickiLab/YACHT/tree/main/use_case_examples/MAG_fishing).
+**Metagenomic-assembled genome (MAG) fishing:** Using a single MAG as a training reference database, YACHT searches for specific MAGs within a sample. Applied to two skin metagenomic samples, results shows that detection is sensitive to sequencing depth, coverage, and parameter choice. See [MAG fishing](https://github.com/KoslickiLab/YACHT/tree/main/use_case_examples/MAG_fishing).
 
 **Synthetic metagenomes:** YACHT verifies the presence of designed microbes in mock microbial communities. Higher ANI thresholds recover expected genomes while lower thresholds introduce false positives, demonstrating how ANI and minimum coverage parameters affect sensitivy and specificity. See [Synthetic metagenomes](https://github.com/KoslickiLab/YACHT/tree/main/use_case_examples/synthetic_metagenome)