Software Engineering Research

Scientific computing in the age of agentic AI: an exploratory field report

This paper explores the use of LLM-based coding agents in scientific computing, presenting case studies in the life sciences and discussing their potential and challenges.

Benchmarking Large Language Models for Bio-Image Analysis Code Generation

This work benchmarks large language models for generating Python code in bio-image analysis, evaluating 18 models on 57 tasks with reference solutions and unit-tests.

Empirical study on software and process quality in bioinformatics tools

This study evaluates software quality and process issues in HTS alignment tools, finding high maintainability but increasing technical debt and recommending improvements in tooling and documentation.

A large-scale analysis of bioinformatics code on GitHub

This paper analyzes 1,720 bioinformatics GitHub repositories to explore relationships between code properties, development activity, and software impact.