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
-
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…
-
New READ framework uses retrieval-alignment diffusion for drug design
Researchers have introduced READ, a novel framework for structure-based drug design that utilizes retrieval-alignment diffusion models. This approach conditions molecular generation on small molecules targeting homologo…
-
Ant body size predicts lifespan but not aging or heat death
A new study published on arXiv investigates the mortality risks of ant workers, examining lifespan duration, senescence trajectory, and thermal vulnerability across 18 Australian ant species. The research found that bod…
-
New path integral model frames cognition as cost optimization
Researchers have developed a mathematical and physical formulation for cognitive cost optimization, modeling goal-directed cognitive processes as imaginary-time evolution under a projector Hamiltonian. This approach ali…
-
New EEGNet Architecture Improves Error Signal Decoding with Multisensory Feedback
Researchers have developed a novel multi-branch EEGNet architecture to improve the decoding of error-related potentials (ErrPs) under complex multisensory feedback conditions. This approach utilizes auxiliary supervisio…
-
Masked autoencoders learn perception-relevant neural representations from unlabeled data
Researchers have demonstrated that masked autoencoders can learn meaningful representations from unlabeled neural data, specifically resting-state neural activity. By pretraining a masked autoencoder on hours of spontan…
-
New AI model learns compact brain graph representations for cognitive state decoding
Researchers have developed a novel method for creating compact representations of functional brain graphs using a graph transformer autoencoder. This approach incorporates domain-specific geometric information as an ind…
-
AI framework prioritizes biomedical annotations using knowledge graphs
Researchers have developed a new framework to improve the efficiency of biomedical curation by prioritizing candidate annotations using knowledge graphs. This approach leverages machine learning and knowledge graph embe…
-
Neuroscience paper proposes novel geometric framework for interbrain network analysis
Researchers have introduced a novel geometric framework for analyzing interbrain network dynamics in neuroscience. This approach moves beyond traditional correlation-based synchrony metrics by interpreting changes in ne…
-
New differentiable metric aids codon harmonization for gene expression
Researchers have developed a new method called Smooth %MinMax (%MinMax(s)) to improve the process of codon harmonization in genetic engineering. This technique offers a differentiable relaxation of the existing %MinMax …
-
New Gaussian process framework enhances omics data classification
Researchers have developed a new structured Gaussian process classification framework designed to improve the analysis of complex biological data. This method integrates biological pathway information directly into the …
-
REST-GAN model synthesizes EEG signals and learns transferable representations
Researchers have developed REST-GAN, a novel generative adversarial network designed to synthesize resting-state electroencephalogram (EEG) signals and extract transferable representations. This framework combines adver…