A comprehensive evaluation of regression-based drug responsiveness prediction models, using cell viability inhibitory concentrations (IC50 values).

MOTIVATION: Predicting drug response is critical for precision medicine. Diverse methods have predicted drug responsiveness, as measured by the half-maximal drug inhibitory concentration (IC50), in cultured cells. Although IC50s are continuous, traditional prediction models have dealt mainly with binary classification of responsiveness. However, since there are few regression-based IC50 predictions, comprehensive evaluations of regression-based IC50 prediction models, including machine learning (ML) and deep learning (DL), for diverse data types and dataset sizes, have not been addressed. RESULTS: Here, we constructed 11 input data settings, including multi-omics settings, with varying dataset sizes, then evaluated the performance of regression-based ML and DL models to predict IC50s. DL models considered two convolutional neural network architectures: CDRScan and residual neural network (ResNet). ResNet was introduced in regression-based DL models for predicting drug response for the first time. As a result, DL models performed better than ML models in all the settings. Also, ResNet performed better than or comparable to CDRScan and ML models in all settings. AVAILABILITY AND IMPLEMENTATION: The data underlying this article are available in GitHub at https://github.com/labnams/IC50evaluation. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Plasma Aldo-Keto Reductase Family 1 Member B10 as a Biomarker Performs Well in the Diagnosis of Nonalcoholic Steatohepatitis and Fibrosis.

We found several blood biomarkers through computational secretome analyses, including aldo-keto reductase family 1 member B10 (AKR1B10), which reflected the progression of nonalcoholic fatty liver disease (NAFLD). After confirming that hepatic AKR1B10 reflected the progression of NAFLD in a subgroup with NAFLD, we evaluated the diagnostic accuracy of plasma AKR1B10 and other biomarkers for the diagnosis of nonalcoholic steatohepatitis (NASH) and fibrosis in replication cohort. We enrolled healthy control subjects and patients with biopsy-proven NAFLD (n = 102) and evaluated the performance of various diagnostic markers. Plasma AKR1B10 performed well in the diagnosis of NASH with an area under the receiver operating characteristic (AUROC) curve of 0.834 and a cutoff value of 1078.2 pg/mL, as well as advanced fibrosis (AUROC curve value of 0.914 and cutoff level 1078.2 pg/mL), with further improvement in combination with C3. When we monitored a subgroup of obese patients who underwent bariatric surgery (n = 35), plasma AKR1B10 decreased dramatically, and 40.0% of patients with NASH at baseline showed a decrease in plasma AKR1B10 levels to below the cutoff level after the surgery. In an independent validation study, we proved that plasma AKR1B10 was a specific biomarker of NAFLD progression across varying degrees of renal dysfunction. Despite perfect correlation between plasma and serum levels of AKR1B10 in paired sample analysis, its serum level was 1.4-fold higher than that in plasma. Plasma AKR1B10 alone and in combination with C3 could be a useful noninvasive biomarker for the diagnosis of NASH and hepatic fibrosis.

A Deep Learning Model for Cell Growth Inhibition IC50 Prediction and Its Application for Gastric Cancer Patients.

Heterogeneity in intratumoral cancers leads to discrepancies in drug responsiveness, due to diverse genomics profiles. Thus, prediction of drug responsiveness is critical in precision medicine. So far, in drug responsiveness prediction, drugs' molecular "fingerprints", along with mutation statuses, have not been considered. Here, we constructed a 1-dimensional convolution neural network model, DeepIC50, to predict three drug responsiveness classes, based on 27,756 features including mutation statuses and various drug molecular fingerprints. As a result, DeepIC50 showed better cell viability IC50 prediction accuracy in pan-cancer cell lines over two independent cancer cell line datasets. Gastric cancer (GC) is not only one of the lethal cancer types in East Asia, but also a heterogeneous cancer type. Currently approved targeted therapies in GC are only trastuzumab and ramucirumab. Responsive GC patients for the drugs are limited, and more drugs should be developed in GC. Due to the importance of GC, we applied DeepIC50 to a real GC patient dataset. Drug responsiveness prediction in the patient dataset by DeepIC50, when compared to the other models, were comparable to responsiveness observed in GC cell lines. DeepIC50 could possibly accurately predict drug responsiveness, to new compounds, in diverse cancer cell lines, in the drug discovery process.

Anti-inflammatory Effects of Flavonoids on TNBS-induced Colitis of Rats.

It has been shown that the extracts including eupatilin and quercetin-3-ß-D-glucuronopyranoside had mucoprotective effects on the esophagus and stomach through their antioxidant activities. This study was designed to investigate the anti-inflammatory effect of these flavonoid compounds in an animal model of inflammatory bowel disease induced by 2,4,6-trinitrobenzene sulfonic acid. Experimental colitis was induced by intracolonic administration of 2,4,6-trinitrobenzene sulfonic acid. Extracts including eupatilin or quercetin-3-ß-D-glucuronopyranoside were orally administered to animals 48, 24, and 1 h prior to the induction of colitis and then again 24 h later. The animals were sacrificed 48 h after by 2,4,6-trinitrobenzene sulfonic acid treatment and the macroscopic appearance of the colonic lesions was scored in a blinded manner on a scale of 1 to 10. The inflammatory response to colitis induction was assessed by measuring myeloperoxidase activity, nitric oxide production, tumor necrosis factor-α expression, total glutathione levels, and malondialdehyde concentrations in the colon. The results indicated that extracts including eupatilin and extracts including quercetin-3-ß-D-glucuronopyranoside dose-dependently improved the morphology of the lesions induced by 2,4,6-trinitrobenzene sulfonic acid and reduced the ulcer index accordingly. In addition, rats receiving extracts including eupatilin and extracts including quercetin-3-ß-D-glucuronopyranoside showed significantly decreased levels of mucosal myeloperoxidase activity, nitric oxide production, tumor necrosis factor-α expression, and malondialdehyde levels, and increased total glutathione levels. Extracts including eupatilin and extracts including quercetin-3-ß-D-glucuronopyranoside ameliorated the inflammatory response and colonic injury in acute colitis by decreasing oxidative stress and neutrophil activation. Extracts including eupatilin and extracts including quercetin-3-ß-D-glucuronopyranoside may inhibit acute colitis.

Acid-induced COX-2 expression and prostaglandin E2 production via activation of ERK1/2 and p38 MAPK in cultured feline esophageal smooth muscle cells.

Cyclooxygenase (COX)-2 is known to play an important role in inflammatory conditions such as reflux esophagitis resulting from acid reflux. In this study, we tested whether an acidic medium (pH 4.0) induces an increase in COX-2 expression or PGE(2) production, and explored the implication of mitogen-activated protein kinases (MAPKs) activation in these responses in cultured cat esophageal smooth muscle cells. Acidic cytotoxicity was assessed and expression changes in COXs or phosphorylated MAPKs were analyzed by Western blotting. PGE(2) production was measured by immunoassay. No significant decrease in cell viability was observed for 6 h exposure to acidic medium. COX-2 expression and PGE(2) production significantly increased to maximal levels at 6 h exposure to acidic medium. The cells also exhibited significant activation of ERK1/2 and p38 MAPK, but not JNK within 10 min under acidic medium. The increments of COX-2 expression and PGE(2) production by acidic medium were decreased by pretreatment with PD98059 or SB202190, respectively. These results suggest that acidic environments may enhance the COX-2 expression and PGE(2) production through activation of ERK1/2 and p38 MAPK in the cultured cat esophageal smooth muscle cells.