The identification of candidate effective combination regimens for pancreatic cancer using the histoculture drug response assay

Noninvasive Computed Tomography-Based Deep Learning Model Predicts In Vitro Chemosensitivity Assay Results in Pancreatic Cancer

OBJECTIVES

We aimed to predict in vitro chemosensitivity assay results from computed tomography (CT) images by applying deep learning (DL) to optimize chemotherapy for pancreatic ductal adenocarcinoma (PDAC).

MATERIALS AND METHODS

Preoperative enhanced abdominal CT images and the histoculture drug response assay (HDRA) results were collected from 33 PDAC patients undergoing surgery. Deep learning was performed using CT images of both the HDRA-positive and HDRA-negative groups. We trimmed small patches from the entire tumor area. We established various prediction labels for HDRA results with 5-fluorouracil (FU), gemcitabine (GEM), and paclitaxel (PTX). We built a predictive model using a residual convolutional neural network and used 3-fold cross-validation.

RESULTS

Of the 33 patients, effective response to FU, GEM, and PTX by HDRA was observed in 19 (57.6%), 11 (33.3%), and 23 (88.5%) patients, respectively. The average accuracy and the area under the receiver operating characteristic curve (AUC) of the model for predicting the effective response to FU were 93.4% and 0.979, respectively. In the prediction of GEM, the models demonstrated high accuracy (92.8%) and AUC (0.969). Likewise, the model for predicting response to PTX had a high performance (accuracy, 95.9%; AUC, 0.979).

CONCLUSIONS

Our CT patch-based DL model exhibited high predictive performance in projecting HDRA results. Our study suggests that the DL approach could possibly provide a noninvasive means for the optimization of chemotherapy.

Identifying CDC7 as a synergistic target of chemotherapy in resistant small-cell lung cancer via CRISPR/Cas9 screening

There is currently a lack of efficacious treatments for patients with chemo-resistant small-cell lung cancer (SCLC), leading to poor prognoses. We examined a chemo-resistant SCLC cell line using genome-wide CRISPR/Cas9 screening and identified serine/threonine kinase cell division cycle 7 (CDC7) as a potential synergistic target. Silencing CDC7 in chemo-resistant SCLC cells decreased the IC₅₀ and improved the efficacy of chemotherapy. Based on the highest single agent model, the CDC7 inhibitor XL413 had a synergistic effect with both cisplatin and etoposide in chemo-resistant SCLC cells, but had no such effect in chemo-sensitive SCLC cells; the combination of XL413 and chemotherapy significantly inhibited cell growth. Western blot and flow cytometry showed that the combined treatments increased apoptosis, whereas XL413 alone had little effect on apoptosis. An analysis of cell cycle and cyclin protein levels indicated that the combination of XL413 and chemotherapy-induced G1/S phase arrest and DNA damage in chemo-resistant SCLC cells. Xenografted tumor and histoculture drug response assays using patient-derived xenografts showed that XL413 improved the efficacy of chemotherapy in vivo and with SCLC tissues. These results suggest that XL413 exerts a synergistic effect with chemotherapy on chemo-resistant SCLC.

Co-implantation of Tumor and Extensive Surrounding Tissue Improved the Establishment Rate of Surgical Specimens of Human-Patient Cancer in Nude Mice: Toward the Goal of Universal Individualized Cancer Therapy

BACKGROUND/AIM

The discovery of the nude mouse model enabled the experimental growth of human-patient tumors. However, the low establishment rate of tumors in nude and other immunodeficient strains of mice has limited wide-spread clinical use.

MATERIALS AND METHODS

In order to increase the establishment rate of surgical specimens of patient tumors, we transplanted tumors to nude mice subcutaneously along with large amounts of surrounding tissue of the tumor.

RESULTS

The new transplantation method increased the establishment rate in nude mice to 66% compared to the old method of implanting the surgical tumor specimen with surrounding tissue removed (14%). High stage and presence of metastasis in the patient donor are positively correlated to tumor engraftment in nude mice.

CONCLUSION

The new method can potentially allow most cancer patients who undergo surgery or biopsy to have their own mouse model for drug-sensitivity testing.