benchmarking

FastaGuard: FASTA preflight QC for modern bioinformatics pipelines

FastaGuard is a FASTA preflight QC tool that detects structural issues in assemblies and stops pipelines before expensive analysis, with high accuracy in identifying faults.

HYphlow: bringing end-to-end flow to HyPhy selection analyses, from taxon reconciliation to trait-based foreground assignment

HYphlow streamlines phylogenetic selection analyses by integrating data preparation, foreground assignment, HyPhy execution, and result extraction into a single workflow, improving precision and reproducibility.

BioResearchBench: 50 Long Horizon Biological Research Tasks

BioResearchBench evaluates AI models on 50 biology research tasks, revealing low success rates and highlighting challenges in data analysis, interpretation, and experimental design.

Synthetic MPRA perturbation supervision improves variant-effect prediction in sequence-to-function models

This paper improves variant-effect prediction in sequence-to-function models using synthetic MPRA data generated from distilled model predictions.

Unsupervised prioritization of gene-regulatory variants with isolation forests

The paper introduces eQIF, an unsupervised machine-learning method that integrates Enformer predictions to prioritize gene-regulatory variants, showing strong performance in predicting eQTLs and GWAS variants.

FedEpitope: Parameter-Efficient Federated Protein Language Models for Linear B-Cell Epitope Prediction

FedEpitope uses federated learning with LoRA to predict linear B-cell epitopes without centralizing data, achieving good performance across multiple clients.

The Reasoning Paradox in Scientific Sandboxes: Why Extended Reasoning Fails in Autonomous Bioinformatics and How to Fix It.

This paper identifies two failure modes in extended reasoning models within bioinformatics tasks and introduces DTDR to improve accuracy and reduce errors.

PhenoMe: An interactive AI framework for interpretable, microscopy-driven phenotyping

PhenoMe provides an open-source framework for analyzing microscopy images using foundation model-derived embeddings and experimental metadata to enable phenotyping and data exploration.

Phylogeny-Guided Global-Local Shrinkage for Microbiome Feature Selection

This paper introduces PGL, a Bayesian regression method for microbiome feature selection that uses phylogenetic trees to improve detection of exposure-associated ASVs.

Improving real-time search through deep learning-enhanced fragment ion indexing

The paper develops a deep learning-enhanced fragment ion indexing method to reduce memory usage in tandem mass spectrometry searches while maintaining search accuracy and speed.

DoAggregate: a pipeline for aggregation testing for rare-variant on a gene and pathway level

DoAggregate performs rare-variant aggregation tests across genes, pathways, and GO terms, providing detailed cohort-level results and visualizations.

MillionTrees: A global benchmark for tree detection across geography, sensor, and annotation geometry

The paper introduces MillionTrees, a global benchmark dataset for airborne tree detection, showing that current models struggle to generalize across diverse data and that training on MillionTrees improves performance.

A multidimensional benchmark of confounder-aware differential abundance strategies for single- and multi-cohort microbiome studies

This paper benchmarks confounder-aware differential abundance methods for microbiome studies, finding that covariate adjustment improves false discovery control but reduces sensitivity, with different strategies performing better under various conditions.

Guide-tree bias of whole genome alignment can mislead phylogenomic analyses

The paper shows guide-tree bias in whole-genome alignment can mislead phylogenomic analyses and proposes a consensus alignment strategy to reduce this bias.

SENgEAR: an interactive visualization platform for comparative analysis of senescence signatures and cellular communication

SEngEAR is a web platform for annotating senescent cells, visualizing communication networks, and comparing senescence signatures across datasets and contexts.

Inferring scaling laws of branching networks from their geometry by global optimization

This paper uses global optimization to infer scaling laws of branching networks from their geometry, revealing type-specific signatures and outperforming existing laws in vascular systems.

Diffusion-Based Synthetic Pretraining for Root Segmentation in Rhizotron Images

This paper generates synthetic rhizotron images using diffusion models and shows that pretraining on these images improves root segmentation performance, especially when real annotations are limited.

QC-espresso: Brewing quality in proteomics

QC-espresso provides an automated quality-control workflow for DIA proteomics data, generating structured reports to assess acquisition quality and quantitative reliability.

DECAPPING PROTEIN 5 regulates the circadian clock in Arabidopsis

This study identifies DCP5 as a key regulator of circadian RNA stability in Arabidopsis by modulating the decay of high-amplitude clock-controlled genes.

Assessing reinforcement learning and vigor with an online decision-making battery

The paper develops an online decision-making battery to assess reinforcement learning and vigor, finding two distinct factors with moderate reliability and associations with mania but not depression.

Quantifying microbial fitness in high-throughput experiments

This study examines how different fitness statistics in high-throughput microbial experiments affect interpretations of mutant fitness and evolutionary dynamics.

How Well Does Structural MRI Classify Autism? A Leakage-Free, Site-Aware and Externally Validated Machine-Learning Evaluation in Two ABIDE Cohorts

This paper evaluates the accuracy of structural MRI in classifying autism using leakage-free, site-aware, and externally validated machine learning methods across two ABIDE cohorts, finding modest performance.

SpaceBlocks: an expert-supervised workflow for cohort-level spatial transcriptomics analysis

SpaceBlocks is a workflow for reproducible, expert-supervised spatial transcriptomics analysis across platforms, identifying new cell types and differentially expressed genes in multiple datasets.

Top2All: Benchmarking sparse-to-transcriptome reconstruction from high-expression profiles across sex- and sex-steroid-defined conditions

The paper benchmarks sparse-to-transcriptome reconstruction models using high-expression profiles from mouse adrenal cells under sex and sex-steroid conditions, finding that gene-wise metrics and strong baselines are critical for evaluation.

Consensus methods for trees of blobs and level-1 phylogenetic networks

This paper introduces a consensus framework for phylogenetic networks, demonstrating its effectiveness on simulated and real datasets.

Leakage-Controlled Benchmarking of Variant Effect Predictors and Development of Gradient-Boosting Consensus Model

The paper benchmarks variant effect predictors using a leakage-controlled dataset and develops a gradient-boosting consensus model that outperforms existing tools.

Sea slugs unplugged: Review of subpopulation sampling in phylogeographic studies of nudibranchs and their allies

The paper reviews subpopulation sampling in phylogeographic studies of sea slugs, finding varied sampling designs and two significant associations between sampling and genetic differentiation.

Cell-in-drop genotyping detects megabase-scale loss of heterozygosity as a quantitative marker for CRISPR-Cas9 on-target toxicity

Optimal Conservation Prioritization for Waterfowl and Other Birds in Eastern Canada

The paper presents an optimized geospatial prioritization scheme for bird conservation in Eastern Canada using linear programming to maximize population coverage.

Individual-specific recovery of the healthy human gut microbiota after antibiotics

The paper shows that the human gut microbiota recovers to an individual-specific state after antibiotics, not to a generic healthy state.