benchmarking

Near-complete genome assembly of the African turquoise killifish enables locus-level profiling of transposable element expression

The paper presents a near-complete genome assembly of the African turquoise killifish and evaluates how TR detection programs and TE workflows affect TE expression profiling.

Distributed AI agents enable comprehensive discovery of biological insights at scale

The paper introduces distributed AI agents to analyze large-scale biological datasets, demonstrating their ability to rapidly extract insights and predict outcomes across a Perturb-seq atlas.

SpectroBird: Event-Level Vocalization Detection and Curation for Avian Ecology

SpectroBird detects and curates individual avian vocalization events from field recordings, enabling detailed ecological analysis of vocalization patterns.

BioMINTREL expands biological problem solving through cross-disciplinary representations

BioMINTREL enhances biological analysis by integrating cross-disciplinary methods, improving agreement with experts and uncovering new insights from existing data.

The modular nature of long-association pathways in the human brain

Diffusion MRI tractography below 750 µm resolves the dorsal superior longitudinal fasciculus into layered fiber systems of varying length, matching macaque tracing; 1.5 mm tractography misses this.

Facilitating Valid Statistical Inference in Biomedical Image Synthesis

This paper evaluates the statistical validity of synthetic biomedical images and introduces PAMS to improve biological inference.

Real-time noise cancellation for EEG monitoring and brain-computer interfaces

This paper introduces rtSOUND, a real-time EEG noise cancellation algorithm that improves signal-to-noise ratio for brain-computer interfaces and monitoring applications.

Clonucopya: An end-to-end workflow bridging tumor clonal architecture and drug prioritization

Clonucopya links tumor clonal architecture to drug prioritization by integrating subclonal inference and drug ranking tools in an end-to-end workflow.

CAZyme Annotation of Five Parasitic Trichomonads Reveals a Conserved Repertoire of Host Glycan Targeting Proteins

The paper annotates CAZymes in five parasitic trichomonads, identifying 1,406 genes and revealing conserved mucin O-glycan-targeting and antibacterial CAZyme toolkits.

Representational geometry as a fidelity metric for connectome-constrained networks: evidence from the Drosophila visual system

The paper introduces representational geometry as a metric to assess biological fidelity in neural networks, showing it distinguishes real from random wiring before training but not after both are trained to task adequacy.

Decoding Clade-Specific bNAb-HIV-1 Env Interactions Using Machine Learning

This study uses machine learning to predict bNAb-HIV-1 Env binding energies across clades, revealing clade-specific binding patterns and affinity trends.

Systematic comparison of color representations between humans and deep neural networks: towards predicting human color perception in a vast color space

This study compares how different learning paradigms enable deep neural networks to predict human color perception across a vast color space.

Effectiveness and efficiency of temporary fences as mitigation measures for preventing amphibians roadkill

This study compares the effectiveness and efficiency of temporary amphibian fences made from different materials and with overhangs, finding that polyethylene tarp and overhanged fences are most effective, while polyethylene netting is most efficient for long-term use.

SHAPPEing agent-based models to spatial data: Sequential Hooke's law Algorithm for Point Pattern reconstruction with Environmental constraints

SHAPPE reconstructs spatial point patterns from environmental constraints, improving ABM initialization and reducing cell interaction errors in glioblastoma samples.

A reinforcement learning framework for goal-directed stimulation of engineered neuronal networks

This paper introduces a reinforcement learning framework for controlling engineered neuronal networks to identify stimulation patterns that drive specific activity motifs.

Experimental trophic flexibility guides a compartmentalized genome-scale model of red microalgae Galdieria sulphuraria

The paper develops an organelle-resolved genome-scale metabolic model for Galdieria sulphuraria that links trophic state and substrate identity with carbon use and product capacity.

Phenomic selection enables nursery screening for field performance in maize and pea

This paper demonstrates that UAV-based phenomic selection can predict field performance of nursery-grown maize and pea genotypes without genotyping.

Implications for Faster Healing with Fewer Applications: Sustained Graft Persistence and Favorable Wound-Healing Biology of a Proprietary Processed Placental Tissue Allograft

This study shows that XWRAP, a proprietary processed placental tissue allograft, maintains greater graft integrity and reduces the need for reapplication compared to conventional and commercial comparators.

Towards predictive ecological biogeography: Predicting vegetation type using fine-scale measurements of the abiotic environment

The paper uses machine learning to predict vegetation types from abiotic environmental variables with high accuracy, identifying key soil factors that influence predictions.

Mechanism-guided Discovery of Fluoroacetate Dehalogenase (FAcD) Variants for Enzymatic PFAS Defluorination

The paper presents DeFluorX, a pipeline using Boltz-2 to identify FAcD variants for PFAS defluorination by analyzing geometric and energetic factors in enzyme-PFAS complexes.

A Dataset of Human Sperm Microscopy Videos for Detection, Tracking, and Motility Parameter Analysis

The paper introduces HSMV, a dataset of human sperm microscopy videos for detection, tracking, and motility analysis, with annotated and unannotated clips for algorithm benchmarking.

Leveraging synthetic environmental covariates to explore crop genotype by environment interactions

The paper introduces a method to analyze genotype by environment interactions by examining environmental effects across growth stages, finding that early grain fill stages have the greatest impact on yield variance.

Evaluation and primer for using DeepLabCut to track small animals in large spaces

This paper evaluates DeepLabCut's performance in tracking small animals in large spaces and provides a primer on its use.

Capturing domain-level detail of molecular interactions in the IMEx Consortium binding domain data set

The paper presents a manually curated dataset of protein binding domains, linking them to molecular interactions and genomic variations for benchmarking and disease mechanism studies.

Assessing a natural gene drive for population control in house mice

The paper models the use of the t haplotype for suppressing house mouse populations and finds that combined releases with trapping or competitive males can reduce eradication times compared to tCRISPR.

CucurbitAgent: An AI agent for exploring cucurbit multi-omics resources

CucurbitAgent is an AI agent that integrates multi-omics data and literature for cucurbit crops, achieving high accuracy in answering gene-specific queries.

Coupled Effects of Airway Deformation and Carrier Gas on Pulmonary Gas-Particle Flow Dynamics Using an Euler-Lagrange Method with Dynamic Mesh

This study develops a deformable lung airway model to assess how airway deformation and carrier gas affect aerosol transport and deposition in the respiratory system.

Anomaly detection uncovers emerging novelty in coral assemblages of the Great Barrier Reef

The paper uses anomaly detection to quantify ecological novelty in coral assemblages of the Great Barrier Reef over 29 years, finding increasing novelty linked to declining coral cover and diversity.

Navigating the rapidly evolving landscape of sequencing-based spatial transcriptomics technologies: a comprehensive multi-platform benchmark

This study benchmarks multiple sequencing-based spatial transcriptomics platforms across tissue types and preservation methods to evaluate their performance and establish standardized metrics for future research.

Competition among viral elements for VIPR RNA-directed genome silencing

The paper shows that VIPR systems in E. coli mediate competition between phages and their satellite counterparts, with satellites using decoy RNAs to counteract repression.