Michiel Stock

Plant models are essential for understanding the mechanisms underlying complex plant processes and for predicting growth under varying environmental conditions. They play a central role in plant science and have direct applications in plant breeding, crop management, and related fields. Functional–structural plant models form a widely used class of models that explicitly represent plant structure. Because functional–structural plant models are difficult to implement from scratch, several frameworks have been developed to make them more accessible. However, none of the existing frameworks adopts an acausal modelling approach. Acausal modelling allows users to define systems as differential equation systems without prescribing causal relationships in advance, thereby improving model composability, reusability, and user-friendliness. We introduce PlantModules.jl, an acausal, differential-equation-based functional plant modelling framework designed to integrate with existing structural modelling frameworks for the creation of functional–structural plant models. The framework emphasizes modular model construction, extensibility and customizability, and provides core functionality centred on plant-water relations, offering a broadly applicable foundation for describing plant growth. We illustrate the framework’s capabilities through three case studies, including validation against pine tree growth data. As an open-source Julia library, PlantModules.jl provides a flexible platform for future plant modelling efforts.

As biology becomes increasingly data-driven, so does the field of phage lysins, enzymes that degrade bacterial cell walls and offer promising alternatives to traditional antibiotics. Five years ago, we introduced PhaLP, a centralized resource for Phage Lytic Protein sequences and associated metadata to support global research efforts. Here, we present PhaLP 2.0, an enhanced database designed to address key challenges in computational lysin research by integrating newly identified lysins from thousands of metagenomes. To expand the known diversity of lysins beyond that of cultured phages, we developed SUBLYME, a protein-embedding-based machine-learning Software designed to Uncover and classify Bacteriophage Lysins from Metagenomic datasets. Using embeddings derived from the well-curated sequences of the original PhaLP database, we trained support vector machines to distinguish lysins from non-lysins in viromes and classify them as endolysins or virion-associated lysins. The models achieved an average F1 score of 98% on held-out clusters. SUBLYME enabled the discovery of 743 000 new lysin sequences from EnVhogDB, a virome-derived protein database, increasing the number of known lysin clusters 40-fold, from 1000 to 40 000. SUBLYME and PhaLP 2.0 are accessible online at https://github.com/Rousseau-Team/sublyme and https://phalp.ugent.be, respectively. Together, these advances establish PhaLP 2.0 as a comprehensive and scalable portal for lysin discovery, classification, and sequence analysis, paving the way for future antibacterial applications and evolutionary insights.

As biology grows increasingly data-driven, so too does the field of phage lysins, enzymes that degrade bacterial cell walls and hold promise as alternatives to traditional antibiotics. Five years ago, we introduced PhaLP, a centralized resource for Pha ge L ytic P rotein sequences and associated metadata to support global research efforts. Here, we present PhaLP 2.0, a significantly enhanced database designed to overcome key challenges in the computational study of lysins by integrating the newly identified lysins obtained from thousands of metagenomes. To expand the known diversity of lysins beyond those from cultured phages, we developed SUBLYME, a protein embedding-based machine learning S oftware designed to U ncover and classify B acteriophage Ly sins in Me tagenomic datasets. Using embeddings derived from the prior well-curated protein sequences of the original PhaLP database, we trained support vector machines to distinguish lysins from non-lysins in viromes and classify them as either endolysins or virion-associated lysins. The models achieved an average F1-score of 98% on held-out lysin clusters. SUBLYME enabled the discovery of 743,000 new lysin sequences from EnVhogDB, a virome-derived protein database, increasing the number of known lysin clusters by a factor of 40, from 1,000 to 40,000. PhaLP 2.0 entries were annotated by integrating Pfam functional predictions to the refined delineations obtained with SPAED, an algorithm that leverages the predicted aligned error matrix from AlphaFold predictions to identify domain boundaries. Both SUBLYME and the PhaLP 2.0 database are accessible online at https://github.com/Rousseau-Team/sublyme and http://phalp.ugent.be, respectively. Together, these advances establish PhaLP 2.0 as a comprehensive and scalable portal for the discovery, classification, and sequence analysis of phage lysins, paving the way for future antibacterial applications and evolutionary insights.

The cover image is based on the article Quality‐Diversity Methods for the Modern Data Scientist by Michiel Stock et al., https://doi.org/10.1002/wics.70047 . image

Unlike gradient‐based methods, evolutionary algorithms use populations and exploit randomness to find novel and performant solutions. Quality‐Diversity algorithms have recently emerged as a distinct paradigm designed to cultivate populations of simultaneously high‐performing yet behaviorally diverse solutions. These algorithms show considerable success in challenging fields such as robotics and reinforcement learning. Despite their proven effectiveness and growing popularity, Quality‐Diversity algorithms remain relatively underrecognized and underutilized in the broader data science landscape. This review aims to bridge this gap by providing a comprehensive introduction to the Quality‐Diversity paradigm, elucidating its underlying philosophy, and synthesizing illustrative case studies for a general machine learning audience. This article is categorized under: Algorithms and Computational Methods > Genetic Algorithms and Evolutionary Computing

Most species experience microclimate temperatures, that is, variable and fine‐grained thermal conditions determined by atmospheric conditions interacting with biotic and abiotic components of the earth's surface. Unfortunately, measuring microclimates at biologically meaningful grain sizes is challenging. We showcase the potential of fibre‐optic distributed temperature sensing (DTS) to quantify diurnal variation in microclimatic air temperatures during the growing season along a 135‐m forest edge‐to‐interior transect at 25‐cm horizontal resolution. We benchmark DTS measurements against the microclimate quantified with ultrafine wire thermocouples and more conventional sensors at 15‐m intervals along the transect. Diurnal measurements from DTS indicate maximal cooling of forest floor temperatures (up to −6°C) in the morning (around 8:00 AM) and well away from the forest edge. Negative offset values gradually increased during the day reaching zero (0°C) in the evening (around 21:00 PM). Synthesis . While both DTS and discrete point sampling with microclimate loggers allow to quantify diurnal cycles of microclimate gradients with unified spatial and temporal patterns, DTS provides accurate temperature measurements at a spatial detail nearly impossible to achieve with discrete point sampling. When applied over transects of several hundreds of meters—up to kilometres—fibre‐optic DTS is a cost‐efficient alternative offering substantial potential to advancing microclimate research.

Balanced energy-protein (BEP) supplementation during pregnancy and lactation can improve birth outcomes and infant growth, with the gut microbiome as a potential mediator. The MISAME-III randomized controlled trial (ClinicalTrial.gov: NCT03533712) assessed the effect of BEP supplementation, provided during pregnancy and the first six months of lactation, on small-for-gestational age prevalence and length-for-age Z-scores at six months in rural Burkina Faso. Nested within MISAME-III, this sub-study examines the impact of BEP supplementation on maternal and infant gut microbiomes and their mediating role in birth outcomes and infant growth. A total of 152 mother-infant dyads (n = 71 intervention, n = 81 control) were included for metagenomic sequencing, with stool samples collected at the second and third trimesters, and at 1–2 and 5–6 months postpartum. BEP supplementation significantly altered maternal gut microbiome diversity, composition, and function, particularly those with immune-modulatory properties. Pathways linked to lipopolysaccharide biosynthesis were depleted and the species Bacteroides fragilis was enriched in BEP-supplemented mothers. Maternal BEP supplementation also accelerated infant microbiome changes and enhanced carbohydrate metabolism. Causal mediation analyses identified specific taxa mediating the effect of BEP on birth outcomes and infant growth. These findings suggest that maternal supplementation modulates gut microbiome composition and influences early-life development in resource-limited settings.

Advances in bioinformatics are primarily due to new algorithms for processing diverse biological data sources. While sophisticated alignment algorithms have been pivotal in analyzing biological sequences, deep learning has substantially transformed bioinformatics, addressing sequence, structure, and functional analyses. However, these methods are incredibly data-hungry, compute-intensive, and hard to interpret. Hyperdimensional computing (HDC) has recently emerged as an exciting alternative. The key idea is that random vectors of high dimensionality can represent concepts such as sequence identity or phylogeny. These vectors can then be combined using simple operators for learning, reasoning, or querying by exploiting the peculiar properties of high-dimensional spaces. Our work reviews and explores HDC’s potential for bioinformatics, emphasizing its efficiency, interpretability, and adeptness in handling multimodal and structured data. HDC holds great potential for various omics data searching, biosignal analysis, and health applications.