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 can simultaneously learn underlying growth dynamics and noise structure from sparse biological data. Previous approaches assumed uniform Gaussian noise, but this framework discovers heteroscedastic (varying) noise patterns directly from data. The advance could improve mechanistic modeling across biology by better capturing the true variability in biological systems.
A new likelihood-based framework extends the existing BINNs approach to jointly learn both mechanistic dynamics and heteroscedastic noise models from sparse biological data. Traditional neural ordinary differential equation methods implicitly assume homoscedastic (uniform) Gaussian noise, which may not reflect the actual structure of biological variability. Using population growth as a test case, the authors demonstrate that their learnable noise model accurately recovers underlying noise structure while improving predictions of growth laws compared to existing methods. The framework is general and applicable beyond population dynamics to other mechanistic modeling problems in biology. This work addresses a significant limitation in current neural network approaches for discovering biological laws from data.
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
Topology-Aware Thermodynamics Improves DNA Probe Specificity Design
Researchers developed a new framework for designing DNA probes that accounts for the spatial organization of matched sequences, not just overall thermodynamic stability. Traditional methods rely on scalar measures like melting temperature and free energy, which miss how mismatches are distributed along the probe. The approach could improve diagnostic accuracy in applications like HPV detection and gene expression profiling.
Study Identifies Optimal Thermal Dose for Combining Focused Ultrasound with Immunotherapy in Tumors
Researchers used multimodal PET imaging to identify an optimal thermal dose range for focused ultrasound ablation that destroys tumor tissue while preserving conditions for immunotherapy delivery. The study found that excessive heating collapses blood vessels needed for antibody access, while insufficient heating fails to adequately reduce tumor burden. The findings could guide clinical design of combination treatments pairing thermal ablation with immunotherapies.
Plant MSH1 Protein Functions as Mismatch-Directed Nuclease for Organelle Genome Maintenance
Researchers have identified the precise mechanism by which the AtMSH1 protein in Arabidopsis plants recognizes and cleaves DNA mismatches and lesions, preventing mutations in organellar genomes. The protein combines a DNA mismatch recognition module with a nuclease domain that makes staggered cuts at specific positions relative to DNA damage. This discovery explains how plants maintain unusually low mutation rates in their mitochondrial and chloroplast DNA compared to other eukaryotes.