Xiang Wan

Bowman-Birk inhibitor is a protease inhibitor derived from soybeans that has demonstrated chemopreventive activity in a number of in vitro and animal systems. We conducted a 1-month phase IIa clinical trial of Bowman-Birk inhibitor concentrate in patients with oral leukoplakia. BBIC was administered to 32 subjects with oral leukoplakia for 1 month. We assessed toxicity and clinical and histological response of the lesions, and oral mucosal cell protease activity and serum micronutrient levels were measured. Clinical response was determined by measurement of pre- and posttreatment individual and total lesion areas and analysis of blinded clinical judgments of photographs. On the basis of prespecified response criteria, 31% of patients achieved a clinical response. BBIC was nontoxic in doses up to 1066 chymotrypsin inhibitory units. The mean pretreatment total lesion area decreased from 615 to 438 mm2after BBIC treatment. A linear fit of the dose-response relationship between dose of BBIC and decrease in total lesion area was suggested, and analysis of blinded clinical impression from lesion photographs confirmed this relationship. Overall, at all doses tested, a 24.2% decrease in total lesion area was observed following treatment. High pretreatment PA was associated with greater decreases in PA after BBIC administration. BBIC demonstrated clinical activity after oral administration to patients with oral leukoplakia. These results indicate that BBIC should be investigated for chemopreventive activity in a randomized clinical trial.

To deal with the lack of accuracy and generalization ability in some single models, grain output models were built with lots of relevant data, based on the powerful non-linear reflection of the back-propagation neural network. Three kinds of grain output models were built and took advantage of – particle swarm optimization algorithm, mind evolutionary algorithm, and genetic algorithm – to optimize the BP neural network. By the use of data fusion algorithm, the outcomes of different models can be modified and fused together, and the combination-predicted outcome can be obtained finally. Taking advantage of this combination model to predict the total grain output of China, the results showed that the total grain output in 2015 was a bit larger than the actual value of about 0.0115%. It was much more accurate than the three single models. The experimental results verify the feasibility and validity of the combination model.