Matrix Factorization-based Technique for Drug Repurposing Predictions.

Classical drug design methodologies are hugely costly and time-consuming, with approximately 85% of the new proposed molecules failing in the first three phases of the FDA drug approval process. Thus, strategies to find alternative indications for already approved drugs that leverage computational methods are of crucial relevance. We previously demonstrated the efficacy of the Non-negative Matrix Tri-Factorization, a method that allows exploiting both data integration and machine learning, to infer novel indications for approved drugs. In this work, we present an innovative enhancement of the NMTF method that consists of a shortest-path evaluation of drug-protein pairs using the protein-to-protein interaction network. This approach allows inferring novel protein targets that were never considered as drug targets before, increasing the information fed to the NMTF method. Indeed, this novel advance enables the investigation of drug-centric predictions, simultaneously identifying therapeutic classes, protein targets and diseases associated with a particular drug. To test our methodology, we applied the NMTF and shortest-path enhancement methods to an outdated collection of data and compared the predictions against the most updated version, obtaining very good performance, with an Average Precision Score of 0.82. The data enhancement strategy allowed increasing the number of putative protein targets from 3,691 to 15,295, while the predictive performance of the method is slightly increased. Finally, we also validated our top-scored predictions according to the literature, finding relevant confirmation of predicted interactions between drugs and protein targets, as well as of predicted annotations between drugs and both therapeutic classes and diseases.

Evaluating the application of Pareto navigation guided automated radiotherapy treatment planning to prostate cancer.

BACKGROUND AND PURPOSE: Current automated planning methods do not allow for the intuitive exploration of clinical trade-offs during calibration. Recently a novel automated planning solution, which is calibrated using Pareto navigation principles, has been developed to address this issue. The purpose of this work was to clinically validate the solution for prostate cancer patients with and without elective nodal irradiation. MATERIALS AND METHODS: For 40 randomly selected patients (20 prostate and seminal vesicles (PSV) and 20 prostate and pelvic nodes (PPN)) automatically generated volumetric modulated arc therapy plans (VMATAuto) were compared against plans created by expert dosimetrists under clinical conditions (VMATClinical) and no time pressures (VMATIdeal). Plans were compared through quantitative comparison of dosimetric parameters and blind review by an oncologist. RESULTS: Upon blind review 39/40 and 33/40 VMATAuto plans were considered preferable or equal to VMATClinical and VMATIdeal respectively, with all deemed clinically acceptable. Dosimetrically, VMATAuto, VMATClinical and VMATIdeal were similar, with observed differences generally of low clinical significance. Compared to VMATClinical, VMATAuto reduced hands-on planning time by 94% and 79% for PSV and PPN respectively. Total planning time was significantly reduced from 22.2 mins to 14.0 mins for PSV, with no significant reduction observed for PPN. CONCLUSIONS: A novel automated planning solution has been evaluated, whose Pareto navigation based calibration enabled clinical decision-making on trade-off balancing to be intuitively incorporated into automated protocols. It was successfully applied to two sites of differing complexity and robustly generated high quality plans in an efficient manner.

HyperCare: a prototype of an active database for compliance with essential hypertension therapy guidelines.

HyperCare is a prototype of a decision support system for essential hypertension care management. The medical knowledge implemented in HyperCare derives from the guidelines for the management of mild hypertension of the World Health Organization/International Society of Hypertension, and from the recommendations of the United States Joint National Committee on Detection, Evaluation and Treatment of High Blood Pressure. HyperCare has been implemented using Chimera, an active database language developed at the Politecnico di Milano. HyperCare proves the possibility to use active database systems in developing a medical data-intensive application where inferential elaboration of moderate complexity is required.