Jamie Milne
Papers
1
Total Citations
3
H-Index
1
About
Jamie Milne is a researcher at the forefront of applying artificial intelligence to structural biology, with a focus on automating and accelerating the analysis of macromolecular crystallisation experiments. Their most-cited work, "Not getting in too deep: a practical deep learning approach to routine crystallisation image classification" (2022), demonstrates a pragmatic yet powerful application of convolutional neural networks to classify crystallisation trial images. Using a relatively modest training set of approximately 16,000 images, Milne systematically compared four widely-used deep-learning architectures, offering a clear, implementable framework for labs seeking to automate image analysis without requiring extensive computational resources. This contribution is particularly valuable for high-throughput structural biology pipelines, where rapid and accurate classification of crystallisation outcomes can significantly reduce manual inspection time. With 3 citations to date, this work has already informed subsequent studies in automated crystallography. Milne’s research bridges the gap between cutting-edge AI and routine laboratory practice, making deep learning accessible for everyday crystallisation workflows—a key step toward fully autonomous structural biology.
Research Focus
Key Achievements
Top Papers
- 1