benchmarking

StoichRNA: A Scalable Framework to Map and Optimize Combinatorial RNA Systems at Single-Cell Resolution

StoichRNA maps and optimizes combinatorial RNA systems at single-cell resolution by analyzing RNA stoichiometry and identifying optimal combinations for desired cellular functions.

What does domain-specific pretraining buy? A 170,000-parameter plant peptide language model against the ESM-2 scaling curve

The paper trains a domain-specific plant peptide language model and compares its performance to generalist models, finding domain pretraining provides significant efficiency gains.

WispLab: open-source browser workbenches for laboratory image and qPCR analysis with reference-based verification

WispLab provides open-source browser tools for image and qPCR analysis with reference-based verification, showing numerical agreement with Python references.

CALISTO: A Standardized and Open-Source Software for Magnetic Tweezer Force Calibration

CALISTO calibrates magnetic tweezers forces using three thermal-motion-based methods, improving accuracy by filtering problematic data.

Optimal MR-ARFI encoding parameters for a range of contemporary magnetic field gradient systems

The paper optimizes MR-ARFI gradient parameters and provides a simulation tool to enhance sensitivity under various hardware conditions.

Strain resolution and wide relative abundance quantification of bacterial microbiomes with nanopore sequencing of the ribosomal RNA operon

This paper demonstrates strain-level resolution and quantification of bacterial microbiomes using nanopore sequencing of the ribosomal RNA operon, showing accurate relative abundance quantification over multiple orders of magnitude.

Unsupervised source separation and clustering of soundscape recordings predicts avian richness in hyperdiverse systems

This paper introduces an unsupervised method for estimating avian species richness from soundscape recordings, showing it outperforms traditional acoustic indices and automated identification models in hyperdiverse systems.

MedMCP: An Open Agentic Ecosystem for Medical Imaging Workflows

MedMCP provides an agentic framework for medical imaging workflows, enabling non-technical users to apply state-of-the-art image analysis through natural language and shareable workflows.

A Translational Reference for Green Autofluorescence Imaging in the Rhesus Macaque Eye using the OcuMet Beacon

This study establishes normative green autofluorescence (GAF) values in rhesus macaques across different retinal regions and links GAF to age, intraocular pressure, and retinal structure.

U-Chrom: a unified framework for single-cell and spatial 3D genome data

U-Chrom provides a unified framework for analyzing single-cell and spatial 3D genome data, showing consistent cell-type differences across assays.

Accounting for gene action improves the accuracy of polygenic scores for some complex traits

This study introduces PGSa,d, a polygenic scoring framework that incorporates both additive and dominance effects, showing improved accuracy for traits with significant dominance contributions.

On Deriving Synteny Blocks by Compacting Elements

This paper introduces a formal framework for deriving synteny blocks directly from sequence data to better capture genomic rearrangements without obscuring structural variation.

StainAI-Web: An Interactive Platform for Whole-Slide Microglial Morphology Analysis

StainAI-Web provides an interactive platform for automated microglial morphology analysis of whole-slide histology images, enabling efficient and reproducible quantification and visualization.

Trust, but Verify: Epistemic Uncertainty-Gated Pseudo-Labeling for Safer Semi-Supervised Malaria Screening

This paper introduces an uncertainty-gated pseudo-labeling method for semi-supervised malaria screening, reducing silent failures without sacrificing accuracy.

Survival-associated cellular communication networks in human solid cancers

The paper develops SKyNet to identify survival-associated cell-cell communication networks in solid cancers using single-cell and bulk RNA-seq data, finding specific interactions linked to patient outcomes.

RegDesign-Bench: Benchmarking computational methods for cell-type-specific regulatory DNA design

RegDesign-Bench evaluates computational methods for designing cell-type-specific regulatory DNA, showing that performance on individual metrics does not guarantee overall effectiveness.

Benchmarking and integration of viral prediction tools to uncover viral dark matter across divergent low abundance metagenomes

The paper benchmarks viral prediction tools in low-abundance metagenomes and finds that combining tools improves viral detection while reducing false positives.

Benchmarking Microbiome Methods for Improved Metagenomic Sequencing of Lower Respiratory Tract Samples

The paper benchmarks microbiome methods to improve metagenomic sequencing of lower respiratory tract samples by optimizing DNA purification strategies.

Beyond Segmentation Accuracy: Evaluating Biological Fidelity in Spatial Pathology

The paper evaluates how segmentation accuracy affects biological fidelity in spatial pathology, finding that segmentation errors significantly impact tumor-immune interactions despite similar segmentation performance.

muDM: A Queryable Multi-Resolution Data Model for Vector Geometry in Spatial Bioimaging

muDM is a multi-resolution data model for spatial bioimaging that enables querying of vector geometries with associated molecular data across resolutions, improving classifier performance for neuron meshes.

Advances in 16S Taxonomic Classification: Impacts on Species-Level Resolution of Female Bladder Microbiota

The paper evaluates updated 16S rRNA sequencing methods and databases for improved species-level classification of the urinary microbiome.

Physics-informed neural network for predicting myocardial mechanics from in vivo physiological measurements

This paper introduces a physics-informed neural network to predict myocardial mechanics from physiological measurements, showing improved stress prediction and disease stratification in pulmonary hypertension.

scOmnom: scalable end-to-end single-cell RNA-seq analysis with auditable resolution selection

scOmnom provides a scalable, semi-automated workflow for single-cell RNA-seq analysis, enabling auditable clustering-resolution selection and annotation refinement across large datasets.

Genetic Perturbation Prediction Models Fail Out-of-Distribution: A Rigorous Benchmark and Systematic Evaluation

This paper evaluates perturbation prediction models under out-of-distribution conditions and finds they perform poorly, highlighting the need for better generalization.

PeakLocus: A transcript-aware toolkit for RNA-Centric Genomic Annotation

PeakLocus assigns RNA features to transcript intervals with high accuracy, outperforming existing tools in benchmark tests across multiple species.

MIEN: a deep-learning model for pocket-conditioned glycan pose and conformation discrimination

MIEN improves glycan pose ranking by distinguishing experimentally observed conformations from non-native ones in protein-carbohydrate interactions.

Determinants of cysteine coverage by chemoproteomics

This study identifies factors governing cysteine detection in chemoproteomics using machine learning and statistical filtering, showing that peptide properties and abundance are key determinants.

Identifying and ranking species that need urgent management action to achieve Target 4 of the Global Biodiversity Framework

This paper presents a protocol to identify and rank species needing urgent management action for Target 4 of the Global Biodiversity Framework using IUCN Red List data.

Structural order emerges without mechanical order inside living cells

The paper investigates intracellular mechanical properties and structural organization in RPE1 cells, finding no significant spatial mechanical patterns or correlations between structures and mechanical properties.

Auditing Confidence-Calibrated Benchmarking of Single-Cell Perturbation Models

The paper audits a benchmarking framework for single-cell perturbation models, revealing flaws in metric interpretation and calibration, and identifies a specific calibration failure in split-conformal prediction.