Scientific Computing and Data Management

The Findings Workflow: An agentic, collaborative, provenance-tracked framework for scientific data analysis with Claude Code

The paper introduces the Findings Workflow, a framework that enhances reproducibility and trust in LLM-assisted scientific analysis by structuring the process with provenance tracking and collaborative features.

Microbiology Galaxy Lab: The first community-driven gateway for reproducible and FAIR analysis of microbial data

The paper introduces the Microbiology Galaxy Lab, a community-driven platform for reproducible and FAIR microbial data analysis, offering tools for various omics data types and use cases.

Verifiable Agentic Science on Public Infrastructure

This paper demonstrates agentic science on public infrastructure to ensure reproducibility by making all agent actions and workflows publicly accessible.

Benchmarking Large Language Models for Transcriptomic Data Analysis and Visualization: Multi-Model Workflow Evaluation

This study benchmarks large language models for automated transcriptomic data analysis and visualization workflows, finding that prompt specificity improves code quality but performance varies with preprocessing and environment.

The GA4GH Workflow Execution Service: A Standard API for Workflow Execution and Management in Genomics

The paper introduces the GA4GH Workflow Execution Service API, which standardizes workflow execution across different compute environments and demonstrates its cross-site functionality.

LLM-assisted analytical review catches statistical errors that human researchers miss: documented evidence from two computational biology case studies

PigGPA: A Domain-Constrained Agent for Porcine Genomic Breeding with Verifiable Tool Execution

PigGPA improves genomic breeding analysis by combining domain knowledge with verifiable tool execution, achieving consistent results across tasks.