Quantitative Biology
PulseAugur coverage of Quantitative Biology — every cluster mentioning Quantitative Biology across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
Evolutionary hypothesis proposed for context-dependent brightness perception
Researchers have proposed an evolutionary hypothesis to explain White's illusion, a phenomenon related to context-dependent brightness perception. Their work suggests that a constant-percentage correction function could…
-
ApproxBrain framework redefines neural system computational sufficiency
Researchers have developed a new framework called ApproxBrain to better understand computational sufficiency in neural systems. This approach moves beyond single-point estimates to define sufficiency as a cost-indexed f…
-
VenusGenome model advances microbial genome representation learning
Researchers have developed VenusGenome, a novel gene-resolution masked autoencoder designed for microbial genome representation learning. This model incorporates genome-aware attention mechanisms to distinguish biologic…
-
AI research papers tackle learning stability and RL complexity, while discourse heats up
Two recent arXiv papers explore the theoretical underpinnings of machine learning. One paper investigates the stability of learning algorithms when gradient information is sparse and intermittently available, suggesting…
-
New framework Tessera enhances spatial transcriptomics analysis
Researchers have developed Tessera, a new framework for representation learning in spatial transcriptomics. This method aims to capture both molecular signals and the spatial organization of cells within a tissue microe…
-
Cross-species neural learning aligns mouse and human brain dynamics
Researchers have developed a novel dual-rule contrastive learning framework to align neural activity representations across species, aiming to improve the prediction of drug efficacy in neurological disorders. This meth…
-
New Interpretable Memory Model SBD Improves Spaced Repetition Accuracy
Researchers have developed SBD, a novel memory model for spaced repetition software that aims to improve accuracy and interpretability. Unlike existing models that rely solely on test set accuracy, SBD is designed to ex…
-
Paper reveals how input symmetries can distort AI representational similarity analyses
A new paper published on arXiv details how symmetries in network inputs can confound representational similarity analyses (RSMs). The research demonstrates that these stimulus symmetries can lead to functionally equival…
-
New framework predicts cellular responses to perturbations using energy-guided flow matching
Researchers have developed scEGFlow, a novel framework utilizing energy-guided flow matching to predict cellular responses to perturbations. This method models continuous transitions between cellular states and uses ene…
-
New methods scTrilemma and CellMSA advance single-cell representation learning · 2 sources tracked
Researchers have developed two new methods, scTrilemma and CellMSA, aimed at improving single-cell representation learning. scTrilemma utilizes a latent-bottleneck VAE to balance biological identity, invariance to conte…
-
AI language models learn to control biological systems offline
Researchers have developed a method to control biological systems, such as xenobots, using natural language prompts. This approach leverages vision-language models to learn mappings between linguistic instructions and b…
-
Trillion-parameter LLM enables 18-hour clinical tumor genome analysis on consumer hardware
Researchers have developed a framework that enables the analysis of whole genome sequencing (WGS) data for clinical tumor diagnosis using a trillion-parameter large language model (LLM). This system can run on consumer-…
-
AI model identifies and predicts ocean eco-provinces with uncertainty quantification
Researchers have developed a method using unsupervised machine learning to identify and predict global ocean eco-provinces, which are ecologically significant regions. The study, led by Makayla McDevitt, utilizes explai…
-
AbFlow framework enables end-to-end antibody design with enhanced binding affinity
Researchers have developed AbFlow, a novel framework for designing full-atom antibodies end-to-end. This method utilizes an equivariant Surface Multi-channel Encoder that leverages antigen interaction data to refine ant…
-
New framework ReGeoDTA enhances drug-target affinity prediction by preserving molecular data
Researchers have developed ReGeoDTA, a novel framework designed to improve drug-target affinity (DTA) prediction by preserving crucial chemical and geometric information in molecular representations. This approach aims …
-
AI model predicts oligonucleotide melting behavior with high accuracy
Researchers have developed a condition-aware nucleotide language model capable of accurately predicting oligonucleotide melting behavior. This model integrates contextual sequence representations with explicit informati…
-
New PopPert framework predicts cellular responses from unpaired single-cell data
Researchers have developed PopPert, a novel framework for predicting cellular responses to genetic and chemical perturbations. Unlike previous methods that require cell-to-cell correspondence, PopPert models population-…
-
Bee-like agents evolve complex communication codes in simulation
Researchers have modeled the evolution of communication codes in bee-like agents, focusing on the honeybee waggle dance. The study simulated how direct pointing evolves in horizontal-comb scenarios and how this transiti…
-
Bee-like agents evolve communication codes in simulated populations
Researchers have modeled the emergence and evolution of communication codes in populations of bee-like agents, focusing on the honeybee waggle dance. The study found that direct pointing to food sources evolves when foo…
-
New cognitive model analyzes visuospatial complexity in embodied active vision
Researchers have introduced a new framework to analyze multimodal data, focusing on how complexity influences embodied perception and interaction in dynamic environments. This model categorizes complexity into quantitat…