New Framework Enables Neural Networks to Learn Both Growth Dynamics and Noise Patterns from Biological Data
Researchers have developed an extension to Biologically-Informed Neural Networks (BINNs) that simultaneously learns both the underlying growth dynamics and the noise model directly from data. Existing BINN approaches typically assume homoscedastic Gaussian noise, which can miss meaningful biological variability. The framework improves prediction accuracy for mechanistic laws and offers a more realistic treatment of heteroscedastic noise in biological systems.
A preprint posted to arXiv presents a likelihood-based extension to the Biologically-Informed Neural Networks (BINNs) framework that jointly learns both growth dynamics and noise structure from sparse biological data. Standard BINNs and similar neural ordinary differential equation approaches have generally assumed homoscedastic Gaussian noise—meaning constant variance—which may overlook biologically significant variability patterns. The new framework incorporates a learnable noise model, enabling the system to discover heteroscedastic noise (where variance changes with conditions) directly from observations. Using population growth as a test case, the authors demonstrate that their approach accurately recovers the true underlying noise structure and yields better predictions of growth laws compared to existing methods. The work is presented as a general framework applicable beyond population growth to other mechanistic neural network modeling contexts in biology. The paper spans 28 pages with six figures and was submitted by Rebecca Crossley on June 11, 2026.
What's missing
As a preprint, this work has not yet undergone formal peer review. The study demonstrates the framework primarily on population growth examples; generalizability to other biological systems with different noise structures remains to be validated. The authors do not appear to benchmark computational cost or scalability against existing BINN approaches, and the conditions under which heteroscedastic noise modeling provides meaningful gains over simpler assumptions are not fully characterized.
What different sources said
- arXiv q-bioCenter
A likelihood-based framework for simultaneously learning both noise and growth dynamics using biologically-informed neural networks
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.