software / tool

This paper introduces NEBULA, a framework that models whole-brain neural activity and behavior in C. elegans, identifying shared dynamics for prediction and intervention.

The paper examines how different milk pretreatment methods affect microbiome dynamics during cheese production using metagenomic sequencing and identifies key microbial contributors to cheese quality.

Phasis identifies plant PHAS loci from small RNA sequencing data by combining statistical evidence and a register-resolved interpretation layer, outperforming existing tools in benchmark analyses.

The paper establishes consensus guidelines for constructing truthsets to validate functional assays in cancer variant interpretation, focusing on missense variants and clinical validation frameworks.

BraiNN is a framework for fast, personalized whole-brain network modeling using neural mass models, achieving rapid parameter fitting on consumer GPUs for clinical applications.

The paper designs structurally diverse antibody repertoires with drug-like properties using a computational method called CADAbRe, demonstrating their utility in binding to challenging targets.

TOPAS converts phosphoproteomic data into patient-specific reports for molecular tumor boards, focusing on clinically relevant signaling and therapeutic targets.

The paper designs a multimolecular proofreading circuit that overcomes the activity-fidelity trade-off in synthetic biological systems.

This study develops shelf-stable bioluminescence reagents and assay kits using capillary-assisted vitrification technology, demonstrating ambient storage and consistent performance in various assays.

The paper introduces cellmig, a Bayesian tool for quantifying cell migration velocity with uncertainty, improving reproducibility and biological insight in high-throughput assays.

The paper identifies a T-cell receptor structural signature that predicts acute GVHD risk by analyzing alloreactive clonotypes and introduces a metric to quantify clonal dominance.

Secure LSL adds encryption to the LSL protocol to protect biosignal data, enabling secure clinical and commercial use without changing existing applications.

A low-rank covariance probe on Evo 2 embeddings predicts ClinVar pathogenicity across SNVs and indels, while annotation probes plus an LLM produce mechanistic hypotheses; scores released for 4.2 million variants.

This paper develops a deep learning tool for automated segmentation and morphological analysis of lateral ventricles in rodent MRIs, achieving high accuracy and correlation with manual measurements.

MARiO predicts cancer missense variant pathogenicity by integrating variant-level features and patient-level clinical and genomic contexts, achieving high accuracy.

This study explores how biology instructors view video games as tools for teaching evolution, identifying design priorities based on student learning challenges.

The paper evaluates AlphaGenome's cross-species performance on mouse data, showing varying accuracy for different functional tasks and introduces a confidence scoring method for AI predictions.

The paper introduces MozClo, an expanded MoClo/PhytoBrick toolkit for large multigene assembly in plants, improving capacity and reducing cloning costs.

Rectangle provides a scalable deconvolution framework for bulk RNA-seq using single-cell data, achieving high accuracy and robustness across diverse benchmarks.

This paper introduces coding agents that generate interpretable single-cell embeddings from literature-based gene programs without training data or databases.

qg generates reproducible, configuration-driven acquisition queues for mass spectrometry with QC control and vendor-specific file output.

CICADA provides a unified framework for analyzing neurophysiological data in the NWB format, supporting both GUI-driven and programmatic workflows with modular analysis plugins.

This study surveys LGBTQ+ biologists to assess workplace climate and belonging, finding lower morale and exclusionary experiences among transgender and gender non-conforming scientists.

NinjaSeq replaces conventional end-repair/dA-tailing with restriction enzymes for nanopore sequencing, enabling random access and improved decoding accuracy.

Nemo 2.4 simulates eco-evolutionary dynamics and quantitative traits with flexible genetic models and efficient computation.

This paper introduces a normalized sequence patterning framework for intrinsically disordered proteins and a design algorithm to generate sequences with desired phase separation properties.

The paper develops ASO Atlas, a database of RNase H-mediated ASO sequences and their efficacy, and trains OligoAI, a deep learning model to predict ASO efficacy based on sequence and chemical features, reducing screening effort by 5.72-fold.

This paper introduces PGLD, an AI method that designs cost-effective DNA libraries for high-throughput experiments by optimizing synthesis-aware stochastic libraries.

Deep-Interact Studio allows users to build, train, and compare custom deep learning models for predicting biomolecular interactions, with interpretability and support for multiple interaction types.

DynaPIN extracts dynamic interface fingerprints from molecular simulations to better characterize protein interactions beyond static models.