benchmark study

How Bias Shapes the Leaderboard: Scoring Function Performance Under Scrutiny

This study evaluates how systemic biases affect scoring function performance in virtual screening, finding that biases can inflate results and that classical methods outperform machine learning models on out-of-distribution targets.

BioPathfinder: Evidence-guided multi-agent platform enables hypothesis discovery for CAR-T engineering

A provenance-tracked multi-agent system curated 57 CAR-T patient scRNA-seq studies, generated reviewable hypotheses, and prioritized KLRC1/NKG2A, whose blockade improved CD8+ CAR-T antitumour activity in a Raji xenograft model.

Comparison of multiple video tracking-based behavioral summary approaches for compound discrimination

Scalar keypoint aggregates matched Keypoint-MoSeq, VAME, SimBA and A-SOiD at discriminating eight drug-dose treatments across 314 mouse open-field recordings; social context did not improve recall.

OmniAge: a compendium of aging omic biomarkers links mitotic clocks to clonal hematopoiesis and causality

OmniAge compiles 413 aging biomarkers across 12 categories and reveals associations between mitotic clocks, clonal hematopoiesis, and cancer risk using blood datasets.

Spike inference from calcium imaging data acquired with GCaMP8 indicators

This study evaluates and optimizes spike inference methods for GCaMP8 calcium imaging data, showing improved detection of high-frequency spikes and real-time activity.

Towards Principled Evaluation of Single-Cell Perturbation Prediction Models

The paper evaluates single-cell perturbation prediction models by developing a taxonomy and tool to standardize benchmarking protocols across datasets.

Benchmarking Neural Decoders for Brain-Computer Interfaces and Neural Population Analysis

BEND-BCI benchmarks 23 neural decoding methods across multiple tasks and recordings, showing that accuracy alone does not determine the best decoder for practical use.

FERRET: Framework to Evaluate Robustness in Regulatory Networks Using Heterogeneous Cell Types

FERRET evaluates the robustness of single-cell gene regulatory network inference methods using biological validation and two metrics: RAUC and Monotonicity.

DOME Copilot: A resource to automate transparent reporting of artificial intelligence methods

DOME Copilot automates the generation of transparent AI methodology reports for life science publications, matching or exceeding manual quality while reducing creation time.

Advanced Open-Source Experimental-Design Tools for Microplate-Based Assays with Acoustic Liquid Handling

The paper introduces PickliPy, an open-source framework for converting assay designs into ADE picklists, enabling reproducible and scalable microplate-based experiments.

Scanning for Representation: A Scoping Review of Racial and Ethnic Diversity in MRI Studies of the Maternal Brain

This paper reviews MRI studies of the maternal brain to assess racial and ethnic diversity, finding underreporting, overrepresentation of white participants, and geographic bias.

Feasibility of Precision Functional Mapping in Youth Multi-Echo fMRI Data

This study evaluates Precision Functional Mapping (PFM) in youth multi-echo fMRI data, showing improved functional connectivity reliability and network stability with increased data quantity.

Robust evidence for modest neoselachian diversity loss across the K/Pg: Response to Guinot et al.

The paper reanalyzes neoselachian diversity through the K/Pg boundary using new data and methods, finding no diversity collapse during the K/Pg and robust results across different data treatments.

A prioritization strategy for protecting Conservation Imperatives Sites

This paper prioritizes 1,667 Conservation Imperatives Sites to protect threatened species, focusing on areas with high irreplaceability and conversion pressure.

Statistical tests for bivariate spatial association across multi-omics data with disjoint coordinates

Autocorrelation-aware bivariate Moran's I, bivariate Gaussian process tests and generalized additive models (R package sbivar) test cross-modality colocalisation on disjoint coordinates; many existing permutation tests inflate false positives.

scSAID: A Comprehensive Cross-Species Single-Cell Skin Atlas Reveals Species-Specific Responses to Psoriasis

scSAID provides a cross-species single-cell skin atlas to study psoriasis, revealing species-specific molecular signatures and identifying a novel drug target.

An openly licensed benchmark and per-gene calibration map for missense pathogenicity predictors on activating cancer drivers

The paper benchmarks missense pathogenicity predictors on cancer drivers and provides a per-gene calibration map to improve their performance in somatic variant interpretation.

A hierarchical framework for cortical and subcortical gray-matter parcellation across rodents, primates, and humans

The paper develops a hierarchical atlas for gray-matter parcellation across multiple species, validated through cross-species comparisons and connectivity analysis.

MechAInistic: An LLM-guided Multi-Agent System for Reasoning over Genome-Scale Constraint-Based Metabolic Models

MechAInistic uses a multi-agent system guided by LLMs to generate auditable hypotheses from genome-scale metabolic models, identifying potential drug targets and metabolic rewiring in disease states.

Phenotyping replication is a major determinant of genomic predictive ability in sweet sorghum (Sorghum bicolor Moench)

The paper evaluates how phenotyping replication, training population size, and genomic relatedness affect genomic predictive ability in sweet sorghum breeding programs.

General cognitive function and the brain's structural connectome

The paper shows that general cognitive function is supported by a widespread white matter network across multiple brain regions and connectivity measures.

GeneBench-Pro: Evaluating Multistage Statistical Reasoning in Genomics, Quantitative Biology, and Translational Biomedicine

GeneBench-Pro evaluates AI agents' ability to perform multi-stage scientific analyses in genomics and biomedicine, showing improved benchmarking over previous versions with mixed model performance.

Benchmarking Artificial Intelligence Models for Predicting Nuclear Receptor Activity from Tox21 Assays

This study benchmarks AI models for predicting nuclear receptor activity using Tox21 assays, finding that tree-based models perform better on imbalanced data while deep learning shows robustness on moderate imbalances.

LocusBlend: Flexible multi-index regional visualization of genomic association signals

LocusBlend blends linkage disequilibrium colors for up to three index variants in LocusZoom and LocusCompare plots, helping separate independent signals at complex Alzheimer's disease loci.

Evo 2's Perception of Single Nucleotide Substitutions in the Genes of Two Plant Model Organisms

Evo 2 7B assigns higher perplexity to plant gene alleles carrying randomly simulated single-nucleotide substitutions than to those observed in vivo, in Arabidopsis and rice; significant but small effect.

Neuromuscular, Cardiovascular, and Cognitive Fatigue in Motor Learning: A Systematic Review

This study reviews how cognitive, cardiovascular, and neuromuscular fatigue affect motor learning, finding mixed effects on acquisition and retention with limited neurophysiological evidence.

scRepresenter: a workflow for computing, integrating and benchmarking cellular representations in single-cell transcriptomics

scRepresenter provides a workflow to compute, integrate, and benchmark cellular representations from scRNA-seq data using different methods for complex disease analysis.

Measurement Equivalence of On-Scalp OPM-MEG and Cryogenic MEG for Auditory and Somatosensory Cortical Mapping Across Development

In 18 participants aged 10-45, OPM-MEG and SQUID-MEG placed auditory and somatosensory dipoles in the same cortical areas with matched latencies, differing by small systematic offsets and amplitude scaling.

Knowledge and misconceptions of the French population regarding medical genetics: a survey of 3,000 respondents

This study surveys 3,000 French individuals to assess their knowledge and misconceptions about medical genetics, revealing limited understanding and significant gaps in awareness of genetic testing limitations and legal frameworks.

Survey and Evaluation of Applied Containerization Practices in Bioinformatics

The paper evaluates containerization practices in bioinformatics, finding that most containers fail to build or pull, with version control activity predicting success.