From 7d62cf6a9d5d12d846afe759cee5f2801aee7795 Mon Sep 17 00:00:00 2001 From: Tuomas Borman Date: Tue, 24 Mar 2026 08:46:06 +0200 Subject: [PATCH 1/6] up --- bibliography.bib | 25 +++++++++++ manuscript.qmd | 107 +++++++++++++++++++++++++++++++++++------------ 2 files changed, 105 insertions(+), 27 deletions(-) diff --git a/bibliography.bib b/bibliography.bib index 3db6ec4..e0dc47c 100644 --- a/bibliography.bib +++ b/bibliography.bib @@ -283,6 +283,21 @@ @article{clausen2024 year = {2024}, doi = {10.48550/arXiv.2402.05231} } +@article{cock2009, + author = {Cock, Peter J. A. and Antao, Tiago and Chang, Jeffrey T. and Chapman, Brad A. and Cox, Cymon J. and Dalke, Andrew and Friedberg, Iddo and Hamelryck, Thomas and Kauff, Frank and Wilczynski, Bartek and de Hoon, Michiel J. L.}, + title = {Biopython: freely available Python tools for computational molecular biology and bioinformatics}, + journal = {Bioinformatics}, + volume = {25}, + number = {11}, + pages = {1422-1423}, + year = {2009}, + month = {03}, + abstract = {Summary: The Biopython project is a mature open source international collaboration of volunteer developers, providing Python libraries for a wide range of bioinformatics problems. Biopython includes modules for reading and writing different sequence file formats and multiple sequence alignments, dealing with 3D macro molecular structures, interacting with common tools such as BLAST, ClustalW and EMBOSS, accessing key online databases, as well as providing numerical methods for statistical learning.Availability: Biopython is freely available, with documentation and source code at www.biopython.org under the Biopython license.Contact: All queries should be directed to the Biopython mailing lists, see www.biopython.org/wiki/\_Mailing\_listspeter.cock@scri.ac.uk.}, + issn = {1367-4803}, + doi = {10.1093/bioinformatics/btp163}, + url = {https://doi.org/10.1093/bioinformatics/btp163}, + eprint = {https://academic.oup.com/bioinformatics/article-pdf/25/11/1422/48989335/bioinformatics_25_11_1422.pdf}, +} @article{delia2023, author = {Domenica D'Elia and Jaak Truu and Leo Lahti and Magali Berland and Georgios Papoutsoglou and Michelangelo Ceci and Aldert Zomer and Marta B. Lopes and Eliana Ibrahimi and Aleksandra Gruca and Alina Nechyporenko and Marcus Frohme and Thomas Klammsteiner andEnrique Carrillo-de Santa Pau and Laura Judith Marcos-Zambrano and Karel Hron and Gianvito Pio and Andrea Simeon and Ramona Suharoschi and Isabel Moreno-Indias and Andriy Temko and Miroslava Nedyalkova and Elena-Simona Apostol and Ciprian-Octavian Truic\u{a} and Rajesh Shigdel and Jasminka Hasi\'{c}-Telalovi\'{c} and Erik Bongcam-Rudloff and Piotr Przymus and Naida Babi\'{c} Jordamovi\'{c} and Laurent Falquet and Sonia Tarazona and Alexia Sampri and Gaetano Isola and David P\'{e}rez-Serrano and Vladimir Trajkovik and Lubos Klucar and Tatjana Loncar-Turukalo and Aki Havulinna and Christian Jansen and Randi Bertelsen and Marcus Claesson}, title = {{Advancing microbiome research with machine learning: key findings from the ML4Microbiome {COST} action}}, @@ -1068,6 +1083,16 @@ @article{ramos2017 abstract = {Multiomics experiments are increasingly commonplace in biomedical research and add layers of complexity to experimental design, data integration, and analysis. R and Bioconductor provide a generic framework for statistical analysis and visualization, as well as specialized data classes for a variety of high-throughput data types, but methods are lacking for integrative analysis of multiomics experiments. The {MultiAssayExperiment} software package, implemented in R and leveraging Bioconductor software and design principles, provides for the coordinated representation of, storage of, and operation on multiple diverse genomics data. We provide the unrestricted multiple 'omics data for each cancer tissue in The Cancer Genome Atlas as ready-to-analyze {MultiAssayExperiment} objects and demonstrate in these and other datasets how the software simplifies data representation, statistical analysis, and visualization. The {MultiAssayExperiment} Bioconductor package reduces major obstacles to efficient, scalable, and reproducible statistical analysis of multiomics data and enhances data science applications of multiple omics datasets. Cancer Res; 77(21); e39-42. \textcopyright{}2017 {AACR}.}, keywords = {Software, Humans, Genomics, Computational Biology, Datasets as Topic, Genome, Human, Neoplasms} } +@software{rideout2023, + author = {Jai Ram Rideout and Greg Caporaso and Evan Bolyen and Daniel McDonald and Yoshiki Vázquez Baeza and Jorge Cañardo Alastuey and Anders Pitman and Jamie Morton and Jose Navas and Kestrel Gorlick and Justine Debelius and Zech Xu and llcooljohn and adamrp and Joshua Shorenstein and Laurent Luce and Will Van Treuren and charudatta-navare and Antonio Gonzalez and Colin J. Brislawn and Weronika Patena and Karen Schwarzberg and teravest and Jens Reeder and shiffer1 and Igor Sfiligoi and nbresnick and Qiyun Zhu and Dr. K. D. Murray and Karan Sharma}, + title = {biocore/scikit-bio: scikit-bio 0.5.9: Maintenance release}, + month = aug, + year = 2023, + publisher = {Zenodo}, + version = {0.5.9}, + doi = {10.5281/zenodo.8209901}, + url = {https://doi.org/10.5281/zenodo.8209901}, +} @article{righelli2022, author = {Righelli, Dario and Weber, Lukas M and Crowell, Helena L and Pardo, Brenda and Collado-Torres, Leonardo and Ghazanfar, Shila and Lun, Aaron T L and Hicks, Stephanie C and Risso, Davide}, title = {{SpatialExperiment}: infrastructure for spatially-resolved~transcriptomics data in {R} using {Bioconductor}}, diff --git a/manuscript.qmd b/manuscript.qmd index 7b8c601..440746f 100644 --- a/manuscript.qmd +++ b/manuscript.qmd @@ -332,13 +332,14 @@ extend the capacities far beyond the underlying technical framework [@katz2019]. However, frameworks focused solely on microbiome data science fall short on addressing the need to integrate data across diverse modalities, such as metagenomics, metabolomics, and host genomics. - The Bioconductor project embeds the methods of microbiome data science into a wider statistical programming framework alongside the concurrent development of interoperable methods and workflows for transcriptomics [@righelli2022], single-cell [@amezquita2020], metabolomics [@gatto2025], proteomics [@gatto2025; @anwar2025], and other -fields. Here, we introduce a mature data science ecosystem supporting the +fields. + +Here, we introduce a mature data science ecosystem supporting the integration and analysis of multi-modal datasets in microbiome research. It provides harmonized data import and presentation, and fast, robust methods for transforming abundance tables into biological insights. The @@ -350,6 +351,38 @@ evidence-based best practices, we present the online book [https://microbiome.github.io/OMA](https://microbiome.github.io/OMA/docs/devel) that introduces many dedicated topics in microbiome analysis. +# Computational environments {#sec-computational_environments} + +Several computational environments are available for microbiome data science, +each distinguished by its underlying paradigms, user communities, and scope of +functionality. For example, tools such as QIIME 2 [@bolyen2019], Anvi'o +[@eren2021], and Mothur [@schloss2009] emphasize standardized, workflow-oriented +approaches tailored to microbiome analysis. While these platforms provide robust +and well-validated solutions for microbiome data, they are typically designed +around specific data types and predefined pipelines, which can limit flexibility +when integrating heterogeneous data modalities within a unified analytical +framework. In addition, their workflow-centric design may not fully accommodate +the iterative nature of exploratory microbiome research. +Python-based ecosystems built around libraries such as Biopython [@cock2009] +and scikit-bio [@rideout2023] provide flexible, general-purpose toolkits, but +are less comprehensive than Bioconductor. As a result, users are often required +to implement more custom scripting and assemble their own analytical workflows. + +Bioconductor provides a comprehensive ecosystem of tools spanning multiple areas +of bioinformatics, extending beyond microbiome research. It facilitates +interoperability across domains by leveraging a shared data infrastructure, +enabling more seamless integration of multi-omics data. Rather than focusing on +predefined workflows, Bioconductor is oriented towards exploratory and +statistical data analysis, with components that can be flexibly combined into +custom workflows. While Python-based ecosystems benefit from rapidly evolving +machine learning and artificial intelligence tools, Bioconductor’s strengths lie +in robust statistical modeling and strong interoperability with other +computational environments. In addition, it is supported by a large, active +community and a mature, well-curated package ecosystem. Although this breadth +and complexity can introduce challenges, such as dependency management and +package compatibility, these are actively addressed through community standards, +coordinated release cycles, and continuous integration practices. + # Data infrastructure {#sec-infra} Data scientists routinely deal with interlinked assays, hierarchical data @@ -358,11 +391,13 @@ side information. This side information can include sample attributes like treatment group, collection site, or time point. The ability to integrate heterogeneous data elements is essential in biological research, where the individual components of a system can seldom be studied in -isolation. However, input data formats vary across different methods, leading -to technical complications and time lost on data wrangling. -Bioconductor addresses this through standardized data structures supported -by an ecosystem of interoperable methods, allowing the analyst to invest more -time in core analytical tasks. +isolation. However, this growing complexity introduces additional overhead, as +researchers must track samples and features across multiple tables and manage an +increasing number of data elements. Moreover, input data formats vary across +different methods, leading to technical complications and time lost on data +wrangling. Bioconductor addresses these challenges through standardized data +structures supported by an ecosystem of interoperable methods, allowing the +analyst to invest more time in core analytical tasks. Bioconductor data structures support statistical analysis of complex data combinations [@huber2015] and are widely adopted by various @@ -517,7 +552,8 @@ sequences, and incorporates results from common analytical procedures such as dimensionality reduction, statistical transformations, and agglomeration by taxonomic, functional or other information. The interoperability with other Bioconductor classes facilitates scalable analysis and the design of modular -yet flexible workflows. In particular, the direct interoperability with the +yet flexible workflows, as TreeSE inherits full compatibility with methods +designed for SE. In particular, the direct interoperability with the widely adopted SE data science ecosystem distinguishes our TreeSE-based approach from phyloseq, which is another popular Bioconductor data container developed initially with a focus on 16S amplicon data analysis [@mcmurdie2012]. @@ -811,18 +847,26 @@ taxonomic, resistome, transcriptome, proteome, and metabolome profiling data, dedicated data containers have been developed for certain modalities by the Bioconductor community to address their specific characteristics; examples include single cell sequencing [@amezquita2020] and host genomics -[@lawrence2013]. Subsequent linking of the data from distinct modalities often -presents an additional challenge: multi-omics data is often sparse, so that -samples can be only partially matched between experiments. In other cases, -a single sample in one modality may link to two or more samples in another -modality [see @husso2023]. Integrating data across multiple modalities could -thus benefit from flexible sample mappings and the ability to accommodate -potentially different data containers corresponding to the different modalities. -The MultiAssayExperiment (MAE) data container [@ramos2017] provides a solution -to these two tasks and facilitates the integration of different omics -modalities (@fig-datacontainers b). Integration of multi-table data without such -a structured framework could lead to ambiguous mappings and inconsistent -results. For instance, diagonal integration methods +[@lawrence2013]. Linking data across modalities presents an additional technical +challenge, as multi-omics data are often sparse and only partially matched +across experiments. For example, one study may include 100 samples with +metagenomics sequencing data but only 40 with matched metabolomics. In other +cases, a single sample in one modality may link to two or more samples in +another modality (*e.g.*, due to technical or spatial replication) +[see @husso2023]. These scenarios require flexible sample mappings and the +ability to accommodate heterogeneous data containers across modalities. +The MultiAssayExperiment (MAE) data container [@ramos2017] addresses these +challenges by introducing a formal mapping layer (sampleMap) that links +biological samples to their corresponding measurements in each assay +(@fig-datacontainers b). This design supports one-to-one, one-to-many, and +partially overlapping sample relationships across experiments. Importantly, the +mapping is used during downstream operations: when subsetting an MAE object +(*e.g.*, selecting samples with both microbiome and metabolome data), the +framework automatically resolves the intersection of available samples and +ensures consistent alignment across all assays. Such structured handling of +sample relationships is particularly important for integrative methods, as it +reduces the risk of sample mismatches, a common source of irreproducibility in +ad hoc multi-table analyses. For instance, diagonal integration methods [@xu2022; @argelaguet2021computational]—where shared features across data types may not be explicitly defined—can benefit from such a systematic framework that enforces anchor alignment. This mirrors lessons @@ -1213,8 +1257,12 @@ modalities, such as resistomes [@salehi2025], metabolomes [@hintikka2021], host genomes [@qin2022], transcriptomes, or proteomes [@nyholm2020; @moreno-indias2021] (@fig-downstream_analyses). As we have demonstrated, the integrative data containers support complex combinations of -omics data sets [@huber2015; @ramos2017; @amezquita2020]. -Such integrative approaches in microbiome +omics data sets [@huber2015; @ramos2017; @amezquita2020]. By leveraging +standardized multi-assay data structures, users can apply a growing +number of integrative methods for multi-omics analysis. This eliminates the +need for manual data wrangling, reduces the risk of errors (*e.g.*, sample +mismatches), and enables the creation of modular, efficient, and reproducible +workflows. Such integrative approaches in microbiome research can be broadly categorized into three groups: Machine Learning (ML) prediction [@mallick2024], association-based approaches, and latent variable modeling [@jeganathan2021; @sherwani2025; @@ -1225,7 +1273,7 @@ analysis include cross-correlation, canonical correspondence analysis cross-correlation analysis can be used to quantify direct associations of samples or features between two data sets, anansi can supervise such analyses by incorporating known functional relations, and CCA and Joint-RPCA -provide further tools to discover and visualize shared latent variation. +provide further tools to discover and visualize shared latent variation. We hope that systematic integrative frameworks, such as the one proposed here, will accelerate the development, benchmarking, and standardization of multi-modal extensions for microbiome analysis. @@ -1469,8 +1517,12 @@ demands, the development and quality control of academic software critically relies on active and critical communities that can provide continuous benchmarking and support the identification and dissemination of evidence-based best practices [@berg2020; -@barker2022; @hocquet2024]. We actively support community formation -by online training resources and communication channels. Together with the +@barker2022; @hocquet2024]. Harmonized data structures and access to validated +methods help shape such best practices by enabling transparent benchmarking and +fostering community-driven consensus, while allowing users to flexibly select +and evaluate methods appropriate for their specific data and research questions. +Community formation is actively supported through +online training resources and communication channels. Together with the interactive applications, these resources provide accessible entry points for all developers and users. @@ -1487,7 +1539,8 @@ Bioconductor data structures [@huber2015; @ramos2017; @huang2021] have been adopted as a solution for multi-table data integration tasks in various domains such as single-cell sequencing ([OSCA book](https://bioconductor.org/books/release/OSCA/)) [@amezquita2020] -and transciptomics ([OSTA book](https://lmweber.org/OSTA/)). These resources +and transciptomics ([OSTA book](https://bioconductor.org/books/release/OSTA/)). +These resources demonstrate how standard data containers can support statistical programming on interlinked multi-table data sets. @@ -1600,7 +1653,7 @@ omics along varying spatial and temporal dimensions. In concert with parallel developments in other omics, our framework specifically addresses the need to integrate and jointly analyze interlinked abundance tables and supporting hierarchical and tabular side information across different omics. Whereas our -framework supports the basic data wrangling and microbiomedata science +framework supports the basic data wrangling and microbiome data science operations, it also provides the structured input necessary for probabilistic inference and scalable computation. This is essential as the recent developments in microbiome and multi-omics From d86efc169a3dcb7ddfca74e2b6f8739468acf8fa Mon Sep 17 00:00:00 2001 From: Tuomas Borman Date: Fri, 27 Mar 2026 13:42:16 +0200 Subject: [PATCH 2/6] up --- manuscript.qmd | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-) diff --git a/manuscript.qmd b/manuscript.qmd index 440746f..7b8d6b4 100644 --- a/manuscript.qmd +++ b/manuscript.qmd @@ -566,7 +566,9 @@ other profiles and alternative feature representations. It also offers substantial gains in memory efficiency and computing speed over phyloseq (@fig-benchmarking). While speedyseq is faster in certain operations, TreeSE tends to scale more efficiently in terms of execution time (t) and allocated -memory (m) as sample size (n) increases. Despite these advantages, optimizing +memory (m) as sample size (n) increases, especially as SE-based data containers +also offer built-in support for sparse and delayed matrices, which can improve +performance. Despite these advantages, optimizing time and memory consumption presents an obvious area for further development in the TreeSE-based framework. Conversion functions and detailed cheat sheets between the two formats are available to support interoperability between the @@ -1517,7 +1519,12 @@ demands, the development and quality control of academic software critically relies on active and critical communities that can provide continuous benchmarking and support the identification and dissemination of evidence-based best practices [@berg2020; -@barker2022; @hocquet2024]. Harmonized data structures and access to validated +@barker2022; @hocquet2024]. For example, starting with simple methods, early +computation of key measurements, and initial visual exploration improves +transparency, interpretability, and understanding of the data, while explicit +code and clear commenting further support traceability and verification. + +Harmonized data structures and access to validated methods help shape such best practices by enabling transparent benchmarking and fostering community-driven consensus, while allowing users to flexibly select and evaluate methods appropriate for their specific data and research questions. @@ -1547,10 +1554,11 @@ programming on interlinked multi-table data sets. **Interactive applications.** Graphical user interfaces provide accessible entry points to the framework. The iSEEtree and miaDash packages provide interactive analysis and visualization tools for -microbiome data [@benedetti2025]. Their -interface supports automatic generation of source code and replicable -workflows as well as analysis templates for users without a strong -programming expertise. Moreover, the tidy R paradigm, available +microbiome data [@benedetti2025]. The former extends iSEE to provide support for +TreeSE objects, while the latter builds on iSEEtree to enable analyses without +requiring any programming. Their interface supports automatic generation of +source code and replicable workflows as well as analysis templates for users +without a strong programming expertise. Moreover, the tidy R paradigm, available through tidyomics, simplifies the syntax and can streamline the workflows [@hutchison2024]. These tools allow users to analyze and visualize complex data combinations with ease. @@ -1624,7 +1632,12 @@ In order to enjoy the benefits of automation while maintaining flexibility, data scientists routinely remix open-source software components into custom workflows. However, the lack of commonly adopted data representation standards often hinders the development, sharing, -and application of modular, interoperable statistical workflows. +and application of modular, interoperable statistical workflows. Here we present +a R/Bioconductor ecosystem for microbiome data science. While TreeSE and MAE are +prior contributions, we have built an ecosystem around them through further +method and community development. We also provide a comprehensive online book +supporting learning and reproducible analysis, resulting in an ecosystem ready +for microbiome research. **The Bioconductor community** is widely recognized for developing open research software for life sciences. Its @@ -1678,7 +1691,9 @@ documented the open data science ecosystem for multi-modal microbiome research built on widely adopted Bioconductor data containers, software libraries, data resources, tutorials, and a growing community of developers. Further extensions could include methods for temporal, spatial, and multi-omic -analyses. Finally, supporting interoperability between R and other +analyses along with an end-to-end case study demonstrating how an example +analysis can be conducted in practice from raw data to results. +Finally, supporting interoperability between R and other programming languages could facilitate the application of other machine learning frameworks. As the field evolves, the developer communities will continue to integrate new tools and approaches to improve integrative analyses of From d4660cd328ac4a2cd29203d0bfcdfb1c2b392918 Mon Sep 17 00:00:00 2001 From: Tuomas Borman Date: Tue, 7 Apr 2026 09:33:16 +0300 Subject: [PATCH 3/6] up --- manuscript.qmd | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/manuscript.qmd b/manuscript.qmd index 7b8d6b4..ce8d98f 100644 --- a/manuscript.qmd +++ b/manuscript.qmd @@ -351,15 +351,15 @@ evidence-based best practices, we present the online book [https://microbiome.github.io/OMA](https://microbiome.github.io/OMA/docs/devel) that introduces many dedicated topics in microbiome analysis. -# Computational environments {#sec-computational_environments} +# Data analytical frameworks {#sec-data_frameworks} -Several computational environments are available for microbiome data science, -each distinguished by its underlying paradigms, user communities, and scope of -functionality. For example, tools such as QIIME 2 [@bolyen2019], Anvi'o +Several data analytical frameworks are available for microbiome data science, +each distinguished by its underlying paradigms, user communities, and scope. +For example, tools such as QIIME 2 [@bolyen2019], Anvi'o [@eren2021], and Mothur [@schloss2009] emphasize standardized, workflow-oriented -approaches tailored to microbiome analysis. While these platforms provide robust -and well-validated solutions for microbiome data, they are typically designed -around specific data types and predefined pipelines, which can limit flexibility +approaches tailored to microbiome analysis. While these platforms provide +validated solutions for microbiome data, they are typically designed +around specific data types and predefined pipelines. This can limit flexibility when integrating heterogeneous data modalities within a unified analytical framework. In addition, their workflow-centric design may not fully accommodate the iterative nature of exploratory microbiome research. @@ -568,7 +568,7 @@ substantial gains in memory efficiency and computing speed over phyloseq tends to scale more efficiently in terms of execution time (t) and allocated memory (m) as sample size (n) increases, especially as SE-based data containers also offer built-in support for sparse and delayed matrices, which can improve -performance. Despite these advantages, optimizing +performance [@huber2015]. Despite these advantages, optimizing time and memory consumption presents an obvious area for further development in the TreeSE-based framework. Conversion functions and detailed cheat sheets between the two formats are available to support interoperability between the @@ -1633,8 +1633,9 @@ maintaining flexibility, data scientists routinely remix open-source software components into custom workflows. However, the lack of commonly adopted data representation standards often hinders the development, sharing, and application of modular, interoperable statistical workflows. Here we present -a R/Bioconductor ecosystem for microbiome data science. While TreeSE and MAE are -prior contributions, we have built an ecosystem around them through further +a R/Bioconductor ecosystem for multimodal microbiome data science. While +TreeSE and MAE are prior contributions [@huang2021; @ramos2017], we have built +an ecosystem around them through further method and community development. We also provide a comprehensive online book supporting learning and reproducible analysis, resulting in an ecosystem ready for microbiome research. From aa6e4a5598eff6f9e4b82f1b0d1fa163a0711bf7 Mon Sep 17 00:00:00 2001 From: Tuomas Borman Date: Tue, 7 Apr 2026 15:45:23 +0300 Subject: [PATCH 4/6] up --- manuscript.qmd | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/manuscript.qmd b/manuscript.qmd index ce8d98f..df9f0a8 100644 --- a/manuscript.qmd +++ b/manuscript.qmd @@ -357,7 +357,7 @@ Several data analytical frameworks are available for microbiome data science, each distinguished by its underlying paradigms, user communities, and scope. For example, tools such as QIIME 2 [@bolyen2019], Anvi'o [@eren2021], and Mothur [@schloss2009] emphasize standardized, workflow-oriented -approaches tailored to microbiome analysis. While these platforms provide +approaches tailored to microbiome analysis. While these frameworks provide validated solutions for microbiome data, they are typically designed around specific data types and predefined pipelines. This can limit flexibility when integrating heterogeneous data modalities within a unified analytical @@ -852,7 +852,8 @@ include single cell sequencing [@amezquita2020] and host genomics [@lawrence2013]. Linking data across modalities presents an additional technical challenge, as multi-omics data are often sparse and only partially matched across experiments. For example, one study may include 100 samples with -metagenomics sequencing data but only 40 with matched metabolomics. In other +metagenomics sequencing data but only 40 with matched metabolomics +[@sherwani2025]. In other cases, a single sample in one modality may link to two or more samples in another modality (*e.g.*, due to technical or spatial replication) [see @husso2023]. These scenarios require flexible sample mappings and the From bc6493400cb3b02d4202c44814e6584b60da4bad Mon Sep 17 00:00:00 2001 From: Tuomas Borman Date: Wed, 8 Apr 2026 07:30:39 +0300 Subject: [PATCH 5/6] Update scikit-bio citation --- bibliography.bib | 24 ++++++++++++++---------- manuscript.qmd | 2 +- 2 files changed, 15 insertions(+), 11 deletions(-) diff --git a/bibliography.bib b/bibliography.bib index e0dc47c..4369f26 100644 --- a/bibliography.bib +++ b/bibliography.bib @@ -67,6 +67,20 @@ @article{armstrong2021 month = sep, pages = {2131–2137} } +@article{aton2025, + title = {Scikit-bio: a fundamental Python library for biological omic data analysis}, + volume = {23}, + ISSN = {1548-7105}, + url = {http://dx.doi.org/10.1038/s41592-025-02981-z}, + DOI = {10.1038/s41592-025-02981-z}, + number = {2}, + journal = {Nature Methods}, + publisher = {Springer Science and Business Media LLC}, + author = {Aton, Matthew and McDonald, Daniel and Cañardo Alastuey, Jorge and Azom, Raeed and Batra, Paarth and Bezshapkin, Valentyn and Bolyen, Evan and Cagle, Alexander and Caporaso, J. Gregory and Debelius, Justine W. and Gorlick, Kestrel and Hamsanipally, Nirmitha and Hunger, Lars and Keluskar, Aryan and Liao, Disen and Lu, Yang Young and Navas-Molina, Jose A. and Pitman, Anders and Rideout, Jai Ram and Sazonov, Anton and Sathappan, Bharath and Schwarzberg Lipson, Karen and Sfiligoi, Igor and Tapo, Chris and Vázquez-Baeza, Yoshiki and Wu, Zijun and Xu, Zhenjiang Zech and Ye, Mingsong Sam and Zhao, Jianshu and Knight, Rob and Morton, James T. and Zhu, Qiyun}, + year = {2025}, + month = dec, + pages = {274–276} +} @article{awais2025, title = {Foundation models defining a new era in vision: a survey and outlook}, author = {Awais, Muhammad and Naseer, Muzammal and Khan, Salman and Anwer, Rao Muhammad and Cholakkal, Hisham and Shah, Mubarak and Yang, Ming-Hsuan and Khan, Fahad Shahbaz}, @@ -1083,16 +1097,6 @@ @article{ramos2017 abstract = {Multiomics experiments are increasingly commonplace in biomedical research and add layers of complexity to experimental design, data integration, and analysis. R and Bioconductor provide a generic framework for statistical analysis and visualization, as well as specialized data classes for a variety of high-throughput data types, but methods are lacking for integrative analysis of multiomics experiments. The {MultiAssayExperiment} software package, implemented in R and leveraging Bioconductor software and design principles, provides for the coordinated representation of, storage of, and operation on multiple diverse genomics data. We provide the unrestricted multiple 'omics data for each cancer tissue in The Cancer Genome Atlas as ready-to-analyze {MultiAssayExperiment} objects and demonstrate in these and other datasets how the software simplifies data representation, statistical analysis, and visualization. The {MultiAssayExperiment} Bioconductor package reduces major obstacles to efficient, scalable, and reproducible statistical analysis of multiomics data and enhances data science applications of multiple omics datasets. Cancer Res; 77(21); e39-42. \textcopyright{}2017 {AACR}.}, keywords = {Software, Humans, Genomics, Computational Biology, Datasets as Topic, Genome, Human, Neoplasms} } -@software{rideout2023, - author = {Jai Ram Rideout and Greg Caporaso and Evan Bolyen and Daniel McDonald and Yoshiki Vázquez Baeza and Jorge Cañardo Alastuey and Anders Pitman and Jamie Morton and Jose Navas and Kestrel Gorlick and Justine Debelius and Zech Xu and llcooljohn and adamrp and Joshua Shorenstein and Laurent Luce and Will Van Treuren and charudatta-navare and Antonio Gonzalez and Colin J. Brislawn and Weronika Patena and Karen Schwarzberg and teravest and Jens Reeder and shiffer1 and Igor Sfiligoi and nbresnick and Qiyun Zhu and Dr. K. D. Murray and Karan Sharma}, - title = {biocore/scikit-bio: scikit-bio 0.5.9: Maintenance release}, - month = aug, - year = 2023, - publisher = {Zenodo}, - version = {0.5.9}, - doi = {10.5281/zenodo.8209901}, - url = {https://doi.org/10.5281/zenodo.8209901}, -} @article{righelli2022, author = {Righelli, Dario and Weber, Lukas M and Crowell, Helena L and Pardo, Brenda and Collado-Torres, Leonardo and Ghazanfar, Shila and Lun, Aaron T L and Hicks, Stephanie C and Risso, Davide}, title = {{SpatialExperiment}: infrastructure for spatially-resolved~transcriptomics data in {R} using {Bioconductor}}, diff --git a/manuscript.qmd b/manuscript.qmd index df9f0a8..0bfb14f 100644 --- a/manuscript.qmd +++ b/manuscript.qmd @@ -364,7 +364,7 @@ when integrating heterogeneous data modalities within a unified analytical framework. In addition, their workflow-centric design may not fully accommodate the iterative nature of exploratory microbiome research. Python-based ecosystems built around libraries such as Biopython [@cock2009] -and scikit-bio [@rideout2023] provide flexible, general-purpose toolkits, but +and scikit-bio [@aton2025] provide flexible, general-purpose toolkits, but are less comprehensive than Bioconductor. As a result, users are often required to implement more custom scripting and assemble their own analytical workflows. From cb83adb64a4248aadd290ad5447047d4e948c371 Mon Sep 17 00:00:00 2001 From: Tuomas Borman Date: Wed, 8 Apr 2026 08:52:27 +0300 Subject: [PATCH 6/6] Updated comparison to other analytical frameworks --- bibliography.bib | 15 --------------- manuscript.qmd | 43 +++++++++++++++++++------------------------ 2 files changed, 19 insertions(+), 39 deletions(-) diff --git a/bibliography.bib b/bibliography.bib index 4369f26..4149c7b 100644 --- a/bibliography.bib +++ b/bibliography.bib @@ -297,21 +297,6 @@ @article{clausen2024 year = {2024}, doi = {10.48550/arXiv.2402.05231} } -@article{cock2009, - author = {Cock, Peter J. A. and Antao, Tiago and Chang, Jeffrey T. and Chapman, Brad A. and Cox, Cymon J. and Dalke, Andrew and Friedberg, Iddo and Hamelryck, Thomas and Kauff, Frank and Wilczynski, Bartek and de Hoon, Michiel J. L.}, - title = {Biopython: freely available Python tools for computational molecular biology and bioinformatics}, - journal = {Bioinformatics}, - volume = {25}, - number = {11}, - pages = {1422-1423}, - year = {2009}, - month = {03}, - abstract = {Summary: The Biopython project is a mature open source international collaboration of volunteer developers, providing Python libraries for a wide range of bioinformatics problems. Biopython includes modules for reading and writing different sequence file formats and multiple sequence alignments, dealing with 3D macro molecular structures, interacting with common tools such as BLAST, ClustalW and EMBOSS, accessing key online databases, as well as providing numerical methods for statistical learning.Availability: Biopython is freely available, with documentation and source code at www.biopython.org under the Biopython license.Contact: All queries should be directed to the Biopython mailing lists, see www.biopython.org/wiki/\_Mailing\_listspeter.cock@scri.ac.uk.}, - issn = {1367-4803}, - doi = {10.1093/bioinformatics/btp163}, - url = {https://doi.org/10.1093/bioinformatics/btp163}, - eprint = {https://academic.oup.com/bioinformatics/article-pdf/25/11/1422/48989335/bioinformatics_25_11_1422.pdf}, -} @article{delia2023, author = {Domenica D'Elia and Jaak Truu and Leo Lahti and Magali Berland and Georgios Papoutsoglou and Michelangelo Ceci and Aldert Zomer and Marta B. Lopes and Eliana Ibrahimi and Aleksandra Gruca and Alina Nechyporenko and Marcus Frohme and Thomas Klammsteiner andEnrique Carrillo-de Santa Pau and Laura Judith Marcos-Zambrano and Karel Hron and Gianvito Pio and Andrea Simeon and Ramona Suharoschi and Isabel Moreno-Indias and Andriy Temko and Miroslava Nedyalkova and Elena-Simona Apostol and Ciprian-Octavian Truic\u{a} and Rajesh Shigdel and Jasminka Hasi\'{c}-Telalovi\'{c} and Erik Bongcam-Rudloff and Piotr Przymus and Naida Babi\'{c} Jordamovi\'{c} and Laurent Falquet and Sonia Tarazona and Alexia Sampri and Gaetano Isola and David P\'{e}rez-Serrano and Vladimir Trajkovik and Lubos Klucar and Tatjana Loncar-Turukalo and Aki Havulinna and Christian Jansen and Randi Bertelsen and Marcus Claesson}, title = {{Advancing microbiome research with machine learning: key findings from the ML4Microbiome {COST} action}}, diff --git a/manuscript.qmd b/manuscript.qmd index 0bfb14f..bd9422d 100644 --- a/manuscript.qmd +++ b/manuscript.qmd @@ -357,31 +357,26 @@ Several data analytical frameworks are available for microbiome data science, each distinguished by its underlying paradigms, user communities, and scope. For example, tools such as QIIME 2 [@bolyen2019], Anvi'o [@eren2021], and Mothur [@schloss2009] emphasize standardized, workflow-oriented -approaches tailored to microbiome analysis. While these frameworks provide -validated solutions for microbiome data, they are typically designed -around specific data types and predefined pipelines. This can limit flexibility +approaches tailored to microbiome analysis. These frameworks provide +validated and user-friendly solutions, enabling development of efficient +end-to-end workflows for microbiome research. However, they are typically +designed around specific data types, which can limit flexibility when integrating heterogeneous data modalities within a unified analytical -framework. In addition, their workflow-centric design may not fully accommodate -the iterative nature of exploratory microbiome research. -Python-based ecosystems built around libraries such as Biopython [@cock2009] -and scikit-bio [@aton2025] provide flexible, general-purpose toolkits, but -are less comprehensive than Bioconductor. As a result, users are often required -to implement more custom scripting and assemble their own analytical workflows. - -Bioconductor provides a comprehensive ecosystem of tools spanning multiple areas -of bioinformatics, extending beyond microbiome research. It facilitates -interoperability across domains by leveraging a shared data infrastructure, -enabling more seamless integration of multi-omics data. Rather than focusing on -predefined workflows, Bioconductor is oriented towards exploratory and -statistical data analysis, with components that can be flexibly combined into -custom workflows. While Python-based ecosystems benefit from rapidly evolving -machine learning and artificial intelligence tools, Bioconductor’s strengths lie -in robust statistical modeling and strong interoperability with other -computational environments. In addition, it is supported by a large, active -community and a mature, well-curated package ecosystem. Although this breadth -and complexity can introduce challenges, such as dependency management and -package compatibility, these are actively addressed through community standards, -coordinated release cycles, and continuous integration practices. +framework. In contrast, Bioconductor supports a more exploratory, statistical +analysis oriented paradigm spanning multiple areas of bioinformatics beyond +microbiome research. + +This data analytical paradigm of Bioconductor is similar to scikit-bio's +[@aton2025]. While scikit-bio as a Python-based ecosystem benefits from rapidly +evolving machine learning and artificial intelligence tools, Bioconductor’s +strengths lie in robust statistical modeling and strong interoperability with +other computational environments. Another key distinction is community +structure: scikit-bio is relatively centralized, whereas Bioconductor packages +are developed and maintained by a distributed community, resulting in a broad +toolset. Although this can introduce challenges, such as dependency management +and package compatibility, these are actively addressed through community +standards, coordinated release cycles, and continuous integration practices, +including shared data structures. # Data infrastructure {#sec-infra}