Malignant Neoplasm of Breast

Example 1

The MCA-miner method disclosed herein in FIGS. 2A-2C, when used together with BRL, offers the power of rule list interpretability while maintaining the predictive capabilities of already established machine learning methods.

The performance and computational efficiency of the new MCA-miner is benchmarked against the “Titanic” dataset, as well as the following five (5) datasets available in the UCI Machine Learning Repository: “Adult,” “Autism Screening Adult,” “Breast Cancer Wisconsin (Diagnostic),” “Heart Disease,” and “HIV-1 protease cleavage,” which are designated as Adult, ASD, Cancer, Heart, and HIV, respectively. These datasets represent a wide variety of real-world experiments and observations, thus enabling the improvements described herein to be compared against the original BRL implementation using the FP-Growth miner.

All six benchmark datasets correspond to binary classification tasks. The experiments were conducted using the same set up in each of the benchmarks. First, the dataset is transformed into a format that is compatible with the disclosed BRL implementation. Second, all continuous attributes are quantized into either two (2) or three (3) categories, while keeping the original categories of all other variables. It is worth noting that depending on the dataset and how its data was originally collected, the existing taxonomy and expert domain knowledge are prioritized in some instances to generate the continuous variable quantization. A balanced quantization is generated when no other information was available. Third, a model is trained and tested using 5-fold cross-validations, reporting the average accuracy and Area Under the ROC Curve (AUC) as model performance measurements.

Table 1 presents the empirical result of comparing both implementations. The notation in the table follows the definitions above. To strive for a fair comparison between both implementations, the parameters rmax=2 and smin=0:3 are fixed for both methods, and in particular for MCA-miner μmin=0:5 and M=70 are also set. The multi-core implementations for both the new MCA-miner and BRL were executed on six parallel processes, and stopped when the Gelman & Rubin parameter satisfied {circumflex over (R)}≤1.05. All the experiments were run using a single AWS EC2 c5.18×large instance with 72 cores.

It is clear from the experiments in Table 1 that the new MCA-miner matches the performance of FP-Growth in each case, while significantly reducing the computation time required to mine rules and train a BRL model.

Example 8

The efficacy of CHP20-25 against PARG activity was examined by dot blot assays. PARG was incubated with PAR for 20 min at room temperature with or without inhibitors. PAR-digestion results were analyzed using dot blotting with anti-PAR antibody. IC₅₀ values of CHP20-25 were measured by dot blotting with anti-PAR antibody in a dose course of CHP20-25. Colony formation assays were performed using HCC1937 (BRCA1-mutant breast cancer cells) and PARPi-resistant UWB1.289 (BRCA1-mutant ovarian cancer cells) with 2.5-20 μM PARG inhibitors (CHP20-25, FIG. 6A). The IC₅₀ and EC₅₀ values of CHP20-25 were summarized in the table (FIG. 6B).

Example 23

We have demonstrated that LXR agonists inhibit in vitro cancer progression phenotypes in breast cancer, pancreatic cancer, and renal cancer. To investigate if LXR agonist treatment inhibits breast cancer primary tumor growth in vivo, mice injected with MDA-468 human breast cancer cells were treated with either a control diet or a diet supplemented with LXR agonist GW3965 2 (FIG. 36).

To determine the effect of orally delivered GW3965 2 on breast cancer tumor growth, 2×106 MDA-468 human breast cancer cells were resuspended in 50 μL PBS and 50 μL matrigel and the cell suspension was injected into both lower memory fat pads of 7-week-old Nod Scid gamma female mice. The mice were assigned to a control diet treatment or a GW3965-supplemented diet treatment (75 mg/kg/day) two days prior to injection of the cancer cells. The GW3965 2 drug compound was formulated in the mouse chow by Research Diets, Inc. Tumor dimensions were measured using digital calipers, and tumor volume was calculated as (small diameter)²×(large diameter)/2.

Treatment with GW3965 resulted in significant reduction in breast cancer tumor size in vivo (FIG. 36).