When there are few successful outcomes of experiments or positive user ratings for products, recommender systems may not provide meaningful recommendations for users or experts. Protein crystallization screening or early stages of recommender systems in scarcity of user ratings for products are examples of such instances. Protein crystallization screening helps determine factors (e.g., salts, pH of buffers, ionic strengths, temperature, type of precipitants) that are favorable for formation of a large protein crystal suitable for X- ray crystallography. While existing commercial screens may not generate crystalline outcomes for difficult proteins, their outcomes could be used for recommending novel screens. Current methods for protein crystallization screening such as Associative Experimental Design (AED) process only cocktails having one chemical per reagent while ignoring cocktails with multiple chemicals per reagent. To analyze cocktails having multiple chemicals per reagent, we propose our Associative Recommender System (ARS) that recommends novel crystallization conditions by analyzing the content of successful preliminary crystallization conditions. In wet lab experiments, the ARS yielded 10 new crystalline conditions for Tt189 (Nucleoside diphosphate kinase) in addition to 20 crystalline conditions generated by AED. Moreover, multiple range support by the ARS also yielded two novel crystalline conditions by pairing a crystalline outcome with a non-crystalline outcome for the same protein. In this thesis, we have also assessed the performance of ARS for movie recommendation to show its applicability to other domains beyond protein crystallization.
展开▼
