Abstract: A system and method of using machine learning to predict the pharmacokinetics of a therapeutic radiopharmaceutical on a subject patient using the biodistribution data of the patient in order to dynamically treat the patient using the radiopharmaceutical.

Abstract: Methods and compositions for inhibiting PDX-1 are provided according to the present invention. An anti-PDX-1 agent included in inventive methods and compositions includes an antibody, an aptamer, an antisense oligonucleotide, a ribozyme and/or an inhibitory compound. Methods of inhibiting PDX-1 expression in a tumor cell are provided by the present invention which include contacting a tumor cell with an effective amount of an anti-PDX-1 agent highly or completely complementary to a specified region of an RNA molecule encoding PDX-1. Such an agent specifically hybridizes with the RNA molecule encoding PDX-1 and inhibits the expression of a PDX-1 gene in the tumor cell. Compositions including anti-PDX-1 siRNA and/or shRNA are described. Recombinant expression constructs encoding anti-PDX-1 siRNA or shRNA according to the present invention are described.