Moving beyond MARCO

The use of imaging systems in protein crystallisation means that the experimental setups no longer require manual inspection to determine the outcome of the trials. However, it leads to the problem of how best to find images which contain useful information about the crystallisation experiments. The adoption of a deeplearning approach in 2018 enabled a four-class machine classification system of the images to exceed human accuracy for the first time. Underpinning this was the creation of a labelled training set which came from a consortium of several different laboratories. The MARCO classification model does not have the same accuracy on local data as it does on images from the original test set; this can be somewhat mitigated by retraining the ML model and including local images. We have characterized the image data used in the original MARCO model, and performed extensive experiments to identify training settings most likely to enhance the local performance of a MARCO-dataset based ML classification model.

Automated summary

The use of imaging systems in protein crystallisation eliminates the need for manual inspection of experimental setups. However, finding images with useful information about the experiments becomes a challenge. In 2018, a deep learning approach achieved higher accuracy than humans in classifying images, aided by a labelled training set from multiple laboratories. While the MARCO classification model does not perform as well on local data, retraining the model with local images can partially improve its performance.