benchmark study

MetaOmixTools: an interactive web suite for meta-analysis of ranked features and functional enrichment

MetaOmixTools provides a web-based platform for meta-analysis of ranked features and functional enrichment, enabling integration of multi-study omics data to identify conserved biological insights.

Critical Assessment of ML models for ADMET Prediction in TDC leaderboards

The paper evaluates ADMET prediction models on TDC leaderboards, finding most top models lack reproducibility and exhibit data leakage, with only three methods passing rigorous checks.

Benchmarking computational tools for locus-specific analysis of transposable elements in single-cell RNA-seq datasets

The paper benchmarks tools for locus-specific TE analysis in scRNA-seq, finding older TEs are more accurately quantified, while young TEs face challenges due to multi-mapping reads.

Heterozygote Advantage of a Single-Copy SNAP18 Truncation Allele Enables Dominant SCN Resistance and Yield Preservation in Soybean

This paper identifies a SNAP18 truncation allele that provides dominant resistance to soybean cyst nematode and preserves yield through heterozygous expression.

Domain-adaptation deep learning models do not outperform simple baseline models in single-cell anti-cancer drug sensitivity prediction

This study shows that complex domain adaptation models do not outperform simple gradient boosting models in predicting single-cell anti-cancer drug sensitivity.

Impact of tissue staining and scanner variation on the performance of pathology foundation models: a study of sarcomas and their mimics

Across 14 sarcoma and mimic subtypes, six pathology foundation models beat ResNet50 but lost accuracy under multi-institutional staining; adding 121 externally stained slides narrowed the gap.

How parents judge newborn screening expansion in the genomic era: a theory-informed survey in France from the SeDeN-p3 study

This study surveys French parents' views on expanding newborn screening to include genomic testing, finding high support but nuanced concerns about uncertainty and equity.

Systematic benchmarking demonstrates large language models have not reached the diagnostic accuracy of traditional rare-disease decision support tools

This study benchmarks large language models against a traditional diagnostic tool for genetic disease diagnosis using 5,213 case reports, finding LLMs lag behind in accuracy.

Benchmarking Geometric Morphometric Methods: A Performance Evaluation for Gastropod Shell Shape Analyses

This study benchmarks three geometric morphometric methods for analyzing gastropod shell shape, finding that each method has distinct strengths in clustering, interpretability, and efficiency for different research goals.

CIRCE: a scalable Python package to predict cis-regulatory DNA interactions from single-cell chromatin accessibility data

CIRCE predicts cis-regulatory DNA interactions from single-cell chromatin accessibility data, improving speed and memory use compared to Cicero.

A lateral temporal network for transmodal combinatorial semantics: Convergent evidence from a multi-study investigation

This study identifies a shared neural network for semantic and social cognition through convergent evidence from neuroimaging analyses and language models.

Donor-specific assemblies enhance somatic structural variant detection in complex genomic regions

This study benchmarks donor-specific assemblies for improved detection of somatic structural variants in a melanoma cell line, finding they identify more variants, especially in repeat-rich regions.

Bridging the gaps between field-based ecology and remote sensing to estimate plant functional diversity: a systematic review

This paper reviews the integration of field-based ecology and remote sensing to estimate plant functional diversity, identifying conceptual and methodological gaps and opportunities for convergence.

MultiGS: A comprehensive and user-friendly genomic prediction platform Integrating statistical, machine learning, and deep learning models for breeders

MultiGS is a genomic prediction platform that integrates various models for breeders, showing improved accuracy and efficiency in different prediction scenarios.

pmultiqc: An open-source, lightweight, and metadata-oriented QC reporting library for MS proteomics

pmultiqc generates metadata-aware QC reports for proteomics data using standardized metrics and integrates with existing workflows and cloud services.

Genetic regulation of fasting-induced longevity effects

This study shows that genetic background and sex influence responses to intermittent fasting in mice, with effects on lifespan and health outcomes varying across strains.

SMECT: a framework for benchmarking post-GWAS methods for spatial mapping of cells associated with human complex traits

SMECT benchmarks post-GWAS methods for spatial mapping of cells associated with human complex traits, revealing trade-offs between sensitivity and specificity across methods.

Conserved RNA-protein modules link early anthracycline responses to atrial fibrillation risk

The paper identifies RNA-protein modules linked to anthracycline-induced cardiotoxicity and atrial fibrillation risk through multi-omics integration.

Coexistent PTEN and PIK3CA alterations hyperactivate mTORC1 signaling in endometrial cancers and cause their selective sensitivity to mTORC1 inhibition

This study shows that coexisting PTEN and PIK3CA mutations in endometrial cancers hyperactivate mTORC1, making them sensitive to mTORC1 inhibitors but not PI3K or AKT inhibitors.

Standardized transcriptome analysis improves rare disease diagnosis in the pan-European Solve-RD consortium

The paper presents a standardized RNA-seq analysis framework for rare disease diagnosis, identifying molecular diagnoses in 7.7% of previously undiagnosed cases.

Reproducible Tools and Enhanced Computational Workflows for Batch Effect Evaluation of High-Throughput Data Using BatchQC

The paper introduces BatchQC, an R package for assessing and correcting batch effects in high-throughput data with reproducible tools and workflows.

PRECISE TBI Model Catalog: Increasing Accessibility and Reproducibility in TBI research

The paper introduces a centralized catalog of preclinical TBI models to improve reproducibility and accessibility by consolidating metadata from published studies.

Taxonomy-aware, disorder-matched benchmarking of phase-separating protein predictors

The paper benchmarks phase-separating protein predictors using a taxonomy-aware, disorder-matched benchmark to reduce biases and improve evaluation.

Enhanced multi-omic viral profiling from microbial community sequencing with BAQLaVa

BAQLaVa improves viral profiling from metagenomes and metatranscriptomes, revealing reduced virome diversity in inflammatory bowel diseases and novel phage-host relationships.

Genomic insights into substance use and disinhibitory disorders

This study identifies 1,294 genomic regions and 961 effector genes associated with externalizing disorders, revealing neural mechanisms and polygenic predictors of variance in these conditions.

Virtual Cells Need Context, Not Just Scale

The paper argues that scaling model capacity alone is insufficient for Virtual Cells, emphasizing the need for contextual diversity and causal representation learning over data volume.

MetaKnogic-Alpha: A Hyper-Relational Knowledge Base for Grounded Metabolic Reasoning

MetaKnogic-Alpha transforms biomedical literature into a hyper-relational knowledge base for metabolic reasoning, achieving high mechanistic accuracy through automated synthesis and biochemical grounding.

A Comprehensive Benchmarking Study on Computational Tools for Cross-omics Label Transfer from Single-cell RNA to ATAC Data

This study benchmarks 27 computational tools for transferring cell type labels from scRNA-seq to scATAC-seq data across human and mouse tissues, finding Bridge and GLUE as top performers.

AbNovoBench: a resource and benchmarking platform for monoclonal antibody de novo sequencing

AbNovoBench benchmarks de novo sequencing algorithms for monoclonal antibodies using a large dataset and provides an online platform for antibody sequencing workflows.

A Systematic Benchmark of Antibiotic Resistance Gene Detection Tools for Shotgun Metagenomic Datasets

This study benchmarks five ARG detection tools on simulated metagenomic datasets, showing coverage and community complexity impact accuracy, with ARGprofiler leading in F1-score and computational efficiency.