Modeling, Machine Learning, Bioinformatics and Multi-omics Data in Soil Science

The integration of bioinformatics, machine learning and multi-omics has transformed soil science, providing powerful tools to unravel the complexity of soils as dynamic biological, chemical and physical systems. These approaches allow researchers to characterize soil communities and processes across scales, from genomes and transcriptomes of single populations to emergent properties such as soil health, nutrient cycling and suppressiveness to disease. By combining data from genomics, metagenomics, metatranscriptomics, proteomics, metabolomics, flux measurements, soil physicochemical properties and remote or proximal sensing, it is now possible to build models that link management practices, climate and soil biodiversity to ecosystem functions.

Despite this progress, important challenges remain for the broader implementation of these approaches in soil science. The field is moving from descriptive community profiling to predictive, mechanistic understanding of soil functions, but data harmonization, batch effects, computational bias and lack of transparent workflows still limit reproducibility. In many cases, machine learning models can correctly classify or predict outcomes such as yield, greenhouse gas emissions or disease incidence, but their biological interpretability and transferability across sites and years remain restricted. There is also a need to connect omics based indicators to established soil tests and agronomic or ecological benchmarks in order to gain acceptance among practitioners and regulators.

Recent advances show that multi-omics can identify soil health indicators, quantify functional guilds involved in nutrient cycling, reveal mechanisms of soil suppressiveness and support the design of microbial consortia and bioinputs. At the same time, process based and hybrid models are increasingly combining mechanistic understanding with data driven approaches to predict soil organic matter dynamics, greenhouse gas fluxes and nutrient availability. To fully realize this potential, the community needs robust bioinformatics pipelines, open and FAIR data practices and modeling frameworks that are transparent, validated and usable in decision support.

This Research Topic encourages contributions that connect bioinformatics and omics data to concrete challenges in soil science, including sustainable management, climate resilience, soil restoration and biological inputs. By bringing together expertise in soil microbiology, biogeochemistry, agronomy, ecology, data science and modeling, we aim to support the development of predictive and interpretable tools that improve soil assessment and management in both natural and managed ecosystems.

We welcome original research, reviews, perspectives and validated methodological contributions addressing, but not limited to, the following themes:

- Multi-omics approaches (metagenomics, metatranscriptomics, (meta)proteomics, metabolomics) for understanding soil health, disease suppressiveness and nutrient cycling.

- Machine learning for predictive modeling of soil functions, including carbon sequestration, greenhouse gas emissions, nutrient availability, disease incidence and crop performance.

- Integration of soil physicochemical data, management practices and omics based indicators into hybrid or process based models.

- Multi-omics integration frameworks to link soil microbial communities with plant traits, root exudation and rhizosphere processes.

- Explainable AI and interpretable models for soil diagnostics, management recommendations and policy support.

- Computational workflows, pipelines and tools for soil meta-omics and multi-omics data analysis, including reproducible and FAIR practices.

- Use of microbiome and metagenome data to design, monitor and model microbial inoculants, biofertilizers, biopesticides and synthetic communities in soil.

- New indices, biomarkers or indicators that combine chemical, physical and biological parameters into integrative measures of soil quality and soil health.

- Case studies that demonstrate translation of bioinformatics and modeling outputs into on farm or landscape scale decision making.

- Research gaps, standardization needs and conceptual frameworks for the next generation of data intensive soil science.

Article types and fees

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Case Report
• Classification
• Data Report
• Editorial
• FAIR² Data
• FAIR² DATA Direct Submission
• General Commentary
• Hypothesis and Theory
• ... View all formats

Articles that are accepted for publication by our external editors following rigorous peer review incur a publishing fee charged to Authors, institutions, or funders.

Article types

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Case Report
• Classification
• Data Report
• Editorial
• FAIR² Data
• FAIR² DATA Direct Submission
• General Commentary
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• Perspective
• Review
• Systematic Review
• Technology and Code

Keywords: Modeling, Machine Learning, Bioinformatics, Multi-omics Data

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.