Biology subjects

Joachimiak, M. P.

Publications and source records attributed to Joachimiak, M. P..

6 recordsLinked to original sources

bioRxiv2026

Data coherence over data volume drives generalisable genome-based prediction of microbial carbon utilisation

Microbial carbon utilisation is a foundational ecological phenotype that remains difficult to predict from genomes despite well-characterised pathways. Machine-learning models generalise poorly across datasets, a failure usually attributed to training-set size and taxonomic bias. To test this, we integrated binary growth phenotypes for 819 strains across 240 carbon sources from four datasets. Balanced accuracy fell from 0.86 within datasets to 0.62 across them, and testing on close relatives recovered only 0.03 of that drop, so mechanistically inconsistent genotype-phenotype relationships drove models to dataset-correlated shortcuts. Restricting training to concordant samples (measured growth matched their annotated pathway) doubled the carbon sources recovering known pathway genes across datasets (6 to 12 of 15), whereas matched random subsets did not. Adding over 8000 literature-curated BacDive genomes to the training set did not improve cross-dataset performance more than the smaller concordant set, suggesting coherence matters more than volume. Because such filtering requires a mechanistic predictor, we tested a mechanism-free alternative combining phylogenetic agreement and experimental labels, which recovered part of the gain but not the recall advantage. Concordance-trained models were bounded specialists, rescuing mechanistic false negatives twice as often as false positives (44\% versus 19\%), mostly metabolic generalists. To locate those bounds, model confidence defined an applicability domain, and prioritising low-confidence genomes for training improved cross-dataset accuracy more than random or diversity-based sampling, especially for the weaker phenotypes. This recasts generalisation in biological machine learning as a problem of label-mechanism agreement and applicability-domain definition, alongside data volume and algorithm choice.

bioinformatics↗

bioRxiv2026

MicroGrowAgents: An Agentic AI System for Microbial Cultivation Engineering

Microbial cultivation optimization remains labor-intensive and inefficient, requiring extensive experimental screening to identify suitable growth conditions. Traditional one-factor-at-a-time approaches are particularly ineffective for exploring complex, multidimensional nutrient parameter spaces. We present MicroGrowAgents, an agent-assisted system for auditable design of candidate growth media through integration of knowledge graphs, metabolic modeling, and optimal experimental design. The system comprises 29 documented agents implementing 58 skills across seven functional categories that query structured biological knowledge (KG-Microbe: 864,363 validated species), Bakta-annotated genomes (667,000+ annotated features), curated organism-specific FACTS sheets, and a DOI-linked publication corpus, and apply this evidence to three ends: recommending candidate ingredients and concentration ranges, specifying the factors of a statistically optimal MaxPro experimental design, and interpreting cultivation outcomes against known biochemistry. We applied the approach to Methylorubrum extorquens AM1 (formerly Methylobacterium extorquens; reclassified per LPSN) by cultivating 69 designed media plus a default media baseline (70 total tested conditions) in quadruplicate and assessing two concurrent objectives: biomass turbidity (740 nm) and apparent residual-Nd depletion (residual Nd by arsenazo III). Monte-Carlo resampling of the replicate-level uncertainty (1000 iterations) identified MPOB_058 as the single MC-stable Pareto-optimal condition (membership frequency 0.922); paired-control biology analysis flags MPOB_058 as chemistry-confounded and nominates MPOB_008 as the cleaner biological-signal anchor (its lower abiotic-drift contribution to the residual-Nd measurement makes it the better candidate for confirming biological lanthanide handling in a follow-up round), with MPOB_019 borderline-stable, providing a prioritized anchor set for confirmation in subsequent rounds rather than a single declared optimum. The integration of chemical similarity search (208,000+ embeddings), metabolic gap analysis, and multi-modal reasoning enables evidence-based hypothesis generation that reduces experimental burden while accelerating discovery of growth-promoting conditions. On the Biolog Odin platform, the MC-stable composite candidate MPOB_058 grew 79% more integrated biomass (area under the 740 nm growth curve) and 46% faster (maximum specific growth rate _max; Gompertz fits, R{superscript 2} > 0.99) than the standard MP base medium for this organism (the unsupplemented starting-point recipe carried as the on-plate control). This biomass and growth-rate advantage is a direct kinetic measurement; the conditions apparent residual-Nd depletion ranking, by contrast, awaits confirmation in a subsequent round, because MPOB_058s apparent Nd depletion is partly abiotic. Unlike general-purpose AI co-scientists, MicroGrowAgents grounds every recommendation in inspectable evidence -- structured provenance manifests with per-session input checksums, schema- and ontology-validated outputs, and 90.5% literature citation coverage (143 of 158 curated DOIs with evidence-supports-claim verification) -- separating deterministic design and analysis from agentic interpretation so that recommendations are transparent, explainable, and auditable, while passing 7 of 9 bbop-skills agentic-system criteria in a Claude-Code self-audit (the two unmet criteria are MCP-standardized tool exposure and full input-data cryptographic hashing, both tracked roadmap items). The Bigger PictureIdentifying growth conditions for poorly characterized microbes is one specific instance of a recurring problem in the natural sciences: how to integrate heterogeneous prior knowledge -- structured databases, published literature, mechanistic models -- with statistically efficient experimental design so that limited wet-lab time is spent where it most reduces the search. We show that a multi-agent AI system can perform that integration from organism input to wet-lab design, with every recommendation traceable from its source evidence through to the experimental design that tested it. The same architecture (specialized agents over structured knowledge bases, mechanistic models, and statistical design, with checksummed provenance recorded as the unit of evidence) is in principle transferable to other DBTL loops against under-explored search spaces such as catalyst discovery, materials formulation, cell-line engineering, drug-combination screens, or environmental remediation. We demonstrate it here only for microbial cultivation and flag cross-domain transfer as future work rather than a demonstrated capability. Our cultivation results on Methylorubrum extorquens AM1 are a concrete demonstration that this pattern works on real laboratory data: an uncertainty-aware shortlist of candidate media emerged from Monte-Carlo stability analysis of two competing objectives, with the leading composite candidate growing 79% more integrated biomass and 46% faster than the standard MP base medium for this organism; this biomass and growth-rate advantage is directly measured, while its apparent residual-Nd depletion advantage awaits confirmation in a subsequent round, since the apparent Nd depletion is partly abiotic. But the lesson we want to port across research domains is the architecture and its provenance discipline, not the specific organism. MicroGrowAgents is released under BSD-3 with checksummed YAML provenance manifests so that any group adopting these agents inherits a workflow designed to be re-runnable from its recorded inputs.

synthetic biology↗

bioRxiv2025

KG-Microbe - Building Modular and Scalable Knowledge Graphs for Microbiome and Microbial Sciences

The integration of many disparate forms of data is essential for understanding the microbial world and its interaction with the environment and human health. Doing so is particularly challenging in the context of microbe-host and microbe-microbe interactions that contribute to health or environmental outcomes. There are often thousands of relevant microbial species, and millions of interactions among those microbes and with their environment or host. Some experimental observations only distinguish coarser taxonomic resolutions such as family or phylum-level. Integrated information (e.g., about host and microbial physiology, genetics, and metabolism) facilitates deeper understanding of complex interactions and helps interpret correlative results. The KG-Microbe construction framework is a novel approach to harmonizing bacterial and archaeal data in the form of a knowledge graph (KG). Starting from a core KG with organismal traits, environments and growth preferences, the framework generates a hierarchy of related KGs targeting specific conceptual use cases, including the human host-associated microbiome in the context of disease. KG-Microbe is a standardized and interoperable framework that integrates microbial organismal and genomic traits, represented ontologically, for biomedical, environmental, and other applications. The framework supports customizable taxa subsets representing microbial lineages or communities of interest. Evaluations of the KG-Microbe knowledge graphs through a series of competency questions demonstrate the accuracy and effectiveness of the data harmonization, and the utility of the resulting KGs in inflammatory bowel and Parkinsons diseases. Finally, the predictive and environmental capabilities of the KGs are demonstrated by explaining growth preferences through training a model using graph features. KG-Microbe is a flexible, modular enabling technology for humans and machine learning methods to uncover mechanistic explanations of microbial associations.

bioinformatics↗

bioRxiv2022

Deep surveys of transcriptional modules with Massive Associative Kbiclustering (MAK)

Biclustering can reveal functional patterns in common biological data such as gene expression. Biclusters are ordered submatrices of a larger matrix that represent coherent data patterns. A critical requirement for biclusters is high coherence across a subset of columns, where coherence is defined as a fit to a mathematical model of similarity or correlation. Biclustering, though powerful, is NP-hard, and existing biclustering methods implement a wide variety of approximations to achieve tractable solutions for real world datasets. High bicluster coherence becomes more computationally expensive to achieve with high dimensional data, due to the search space size and because the number, size, and overlap of biclusters tends to increase. This complicates an already difficult problem and leads existing methods to find smaller, less coherent biclusters. Our unsupervised Massive Associative K-biclustering (MAK) approach corrects this size bias while preserving high bicluster coherence both on simulated datasets with known ground truth and on real world data without, where we apply a new measure to evaluate biclustering. Moreover, MAK jointly maximizes bicluster coherence with biological enrichment and finds the most enriched biological functions. Another long-standing problem with these methods is the overwhelming data signal related to ribosomal functions and protein production, which can drown out signals for less common but therefore more interesting functions. MAK reports the second-most enriched non-protein production functions, with higher bicluster coherence and arrayed across a large number of biclusters, demonstrating its ability to alleviate this biological bias and thus reflect the mediation of multiple biological processes rather than recruitment of processes to a small number of major cell activities. Finally, compared to the union of results from 11 top biclustering methods, MAK finds 21 novel S. cerevisiae biclusters. MAK can generate high quality biclusters in large biological datasets, including simultaneous integration of up to four distinct biological data types. Author summaryBiclustering can reveal functional patterns in common biological data such as gene expression. A critical requirement for biclusters is high coherence across a subset of columns, where coherence is defined as a fit to a mathematical model of similarity or correlation. Biclustering, though powerful, is NP-hard, and existing biclustering methods implement a wide variety of approximations to achieve tractable solutions for real world datasets. This complicates an already difficult problem and leads existing biclustering methods to find smaller and less coherent biclusters. Using the MAK methodology we can correct the bicluster size bias while preserving high bicluster coherence on simulated datasets with known ground truth as well as real world datasets, where we apply a new data driven bicluster set score. MAK jointly maximizes bicluster coherence with biological enrichment and finds more enriched biological functions, including other than protein production. These functions are arrayed across a large number of MAK biclusters, demonstrating ability to alleviate this biological bias and reflect the mediation of multiple biological processes rather than recruitment of processes to a small number of major cell activities. MAK can generate high quality biclusters in large biological datasets, including simultaneous integration of up to four distinct biological data types.

bioinformatics↗

bioRxiv2020

KG-COVID-19: a framework to produce customized knowledge graphs for COVID-19 response

Integrated, up-to-date data about SARS-CoV-2 and coronavirus disease 2019 (COVID-19) is crucial for the ongoing response to the COVID-19 pandemic by the biomedical research community. While rich biological knowledge exists for SARS-CoV-2 and related viruses (SARS-CoV, MERS-CoV), integrating this knowledge is difficult and time consuming, since much of it is in siloed databases or in textual format. Furthermore, the data required by the research community varies drastically for different tasks - the optimal data for a machine learning task, for example, is much different from the data used to populate a browsable user interface for clinicians. To address these challenges, we created KG-COVID-19, a flexible framework that ingests and integrates biomedical data to produce knowledge graphs (KGs) for COVID-19 response. This KG framework can also be applied to other problems in which siloed biomedical data must be quickly integrated for different research applications, including future pandemics. BIGGER PICTUREAn effective response to the COVID-19 pandemic relies on integration of many different types of data available about SARS-CoV-2 and related viruses. KG-COVID-19 is a framework for producing knowledge graphs that can be customized for downstream applications including machine learning tasks, hypothesis-based querying, and browsable user interface to enable researchers to explore COVID-19 data and discover relationships.

bioinformatics↗

bioRxiv2019

Semantic Integration of Clinical Laboratory Tests from Electronic Health Records for Deep Phenotyping and Biomarker Discovery

Electronic Health Record (EHR) systems typically define laboratory test results using the Laboratory Observation Identifier Names and Codes (LOINC) and can transmit them using Fast Healthcare Interoperability Resource (FHIR) standards. LOINC has not yet been semantically integrated with computational resources for phenotype analysis. Here, we provide a method for mapping LOINC-encoded laboratory test results transmitted in FHIR standards to the Human Phenotype Ontology (HPO) terms. We annotated the medical implications of 2421 commonly used laboratory tests with HPO terms. Using these annotations, a software assesses laboratory test results and converts each into an HPO term. We validated our approach with EHR data from 15,681 patients with respiratory complaints and identified known biomarkers for asthma. Finally, we provide a freely available SMART on FHIR application that can be used within EHR systems. Our approach allows reusing readily available laboratory tests in EHR for deep phenotyping and using the hierarchical structure of HPO for association studies with medical outcomes and genomics.\n\nOne Sentence SummaryWe present an approach to semantically integrating LOINC-encoded laboratory data with the Human Phenotype Ontology and show that the integrated LOINC data can be used to identify biomarkers for asthma from electronic health record data.

bioinformatics↗