Abstract: A method and a software tool is achieved that measures the distance between a parameter vector that describes an industrial process and vectors that characterize different enzymatic activities. A distance matrix is built and used to construct a hierarchical binary cluster tree of parameter vectors. A novel scoring system is used to rank the hierarchically grouped enzymes. To select the best enzymes for the chimeric fusion enzyme for a particular industrial process, the novel scoring system takes into account biochemical and biophysical variables by creating a belief system. The scoring is generated by summing the products of a biochemical/biophysical variable and its belief parameters/weights for those enzymes found by the distance matrix to have enzymatic activities closest to the enzymatic activities of the industrial process. These scores are then used to select the best enzymes for the particular industrial process.

Abstract: A crystallization parameter optimization process includes self-learning programs based on neural networks or smart algorithms that divine optimal crystallization conditions. The operation of these programs is ideally coupled with a high throughput automated crystallization experiment system. Through the use of successful as well as unsuccessful crystallization experimental samples, the programs are efficiently able to predict optimal crystallization variables after sampling only a modest fraction of all possible variable permutations.