Updated project metadata. we developed a web-based application (QCMAP) for interactive diagnosis and prediction of the per-formance of LC-MS systems across different biological sample types. Leveraging on a standardized HeLa sample run in Sydney MS core facility, we trained predictive models on a panel of commonly used performance factors to pinpoint the precise conditions to a (un)satisfactory performance in three LC-MS systems. Next, we demonstrated that the learned model can be applied to predict LC-MS system performance for brain samples generated from an independent study. By compiling these predictive models into our web-application, QCMAP allows users to supply their own samples to benchmark the performance of their LC-MS systems and identify key factors for instrument opti-misation.. To demonstrate this, we obtained 10 datasets generated on a QECl instrument from mouse brain samples with different levels of quality.