Prediction of protein crystallization outcome using a hybrid method

The great power of protein crystallography to reveal biological structure is often limited by the tremen26 dous effort required to produce suitable crystals. A hybrid crystal growth predictive model is presented 27 that combines both experimental and sequence-derived data from target proteins, including novel vari28 ables derived from physico-chemical characterization such as R30, the ratio between a protein’s DSF 29 intensity at 30 C and at Tm. This hybrid model is shown to be more powerful than sequence-based pre30 diction alone – and more likely to be useful for prioritizing and directing the efforts of structural genom31 ics and individual structural biology laboratories. 32