Development and validation of a deep learning-based model to predict response and survival of T790M mutant non-small cell lung cancer patients in early clinical phase trials using electronic medical record and pharmacokinetic data.

Background: Epidermal growth factor receptor (EGFR) T790M mutation is the standard predictive biomarker for third-generation epidermal growth factor receptor tyrosine kinase inhibitor (EGFR-TKI) treatment. While not all T790M-positive patients respond to third-generation EGFR-TKIs and have a good prognosis, it necessitates novel tools to supplement EGFR genotype detection for predicting efficacy and stratifying EGFR-mutant patients with various prognoses. Mixture-of-experts (MoE) is designed to disassemble a large model into many small models. Meanwhile, it is also a model ensembling method that can better capture multiple patterns of intrinsic subgroups of enrolled patients. Therefore, the combination of MoE and Cox algorithm has the potential to predict efficacy and stratify survival in non-small cell lung cancer (NSCLC) patients with EGFR mutations. Methods: We utilized the electronic medical record (EMR) and pharmacokinetic parameters of 326 T790M-mutated NSCLC patients, including 283 patients treated with Abivertinib in phase I (n=177, for training) and II (n=106, for validation) clinical trials and an additional validation cohort 2 comprising 43 patients treated with BPI-7711. Furthermore, 18 patients underwent whole-exome sequencing for biological interpretation of CoxMoE. We evaluated the predictive performance for therapeutic response using the area under the curve (AUC) and the Concordance index (C-index) for progression-free survival (PFS). Results: CoxMoE exhibited AUCs of 0.73-0.83 for predicting efficacy defined by best overall response (BoR) and achieved C-index values of 0.64-0.65 for PFS prediction in training and validating cohorts. The PFS of 198 patients with a low risk [median, 6.0 (range, 1.0-23.3) months in the abivertinib treated cohort; median 16.5 (range, 1.4-27.4) months in BPI-7711 treated cohort] of being non-responder increased by 43% [hazard ratio (HR), 0.56; 95% confidence interval (CI), 0.40-0.78; P=0.0013] and 50% (HR, 0; 95% CI, 0-0; P=0.01) compared to those at high-risk [median, 4.2 (range, 1.0-35) months in the abivertinib treated cohort; median, 11.0 (range, 1.4-25.1) months in BPI-7711 treated cohort]. Additionally, activated partial thromboplastin time (APTT), creatinine clearance (Ccr), monocyte, and steady-state plasma trough concentration utilited to construct model were found significantly associated with drug resistance and aggressive tumor pathways. A robust correlation was observed between APTT and Ccr with PFS (log-rank test; P<0.01) and treatment response (Wilcoxon test; P<0.05), respectively. Conclusions: CoxMoE offers a valuable approach for patient selection by forecasting therapeutic response and PFS utilizing laboratory tests and pharmacokinetic parameters in the setting of early-phase clinical trials. Simultaneously, CoxMoE could predict the efficacy of third-generation EGFR-TKI non-invasively for T790M-positive NSCLC patients, thereby complementing existing EGFR genotype detection.

Olgotrelvir, a dual inhibitor of SARS-CoV-2 Mpro and cathepsin L, as a standalone antiviral oral intervention candidate for COVID-19.

BACKGROUND: Oral antiviral drugs with improved antiviral potency and safety are needed to address current challenges in clinical practice for treatment of COVID-19, including the risks of rebound, drug-drug interactions, and emerging resistance. METHODS: Olgotrelvir (STI-1558) is designed as a next-generation antiviral targeting the SARS-CoV-2 main protease (Mpro), an essential enzyme for SARS-CoV-2 replication, and human cathepsin L (CTSL), a key enzyme for SARS-CoV-2 entry into host cells. FINDINGS: Olgotrelvir is a highly bioavailable oral prodrug that is converted in plasma to its active form, AC1115. The dual mechanism of action of olgotrelvir and AC1115 was confirmed by enzyme activity inhibition assays and co-crystal structures of AC1115 with SARS-CoV-2 Mpro and human CTSL. AC1115 displayed antiviral activity by inhibiting replication of all tested SARS-CoV-2 variants in cell culture systems. Olgotrelvir also inhibited viral entry into cells using SARS-CoV-2 Spike-mediated pseudotypes by inhibition of host CTSL. In the K18-hACE2 transgenic mouse model of SARS-CoV-2-mediated disease, olgotrelvir significantly reduced the virus load in the lungs, prevented body weight loss, and reduced cytokine release and lung pathologies. Olgotrelvir demonstrated potent activity against the nirmatrelvir-resistant Mpro E166 mutants. Olgotrelvir showed enhanced oral bioavailability in animal models and in humans with significant plasma exposure without ritonavir. In phase I studies (ClinicalTrials.gov: NCT05364840 and NCT05523739), olgotrelvir demonstrated a favorable safety profile and antiviral activity. CONCLUSIONS: Olgotrelvir is an oral inhibitor targeting Mpro and CTSL with high antiviral activity and plasma exposure and is a standalone treatment candidate for COVID-19. FUNDING: Funded by Sorrento Therapeutics.

Role of Drugs Used for Chronic Disease Management on Susceptibility and Severity of COVID-19: A Large Case-Control Study.

This study aimed to investigate whether specific medications used in the treatment chronic diseases affected either the development and/ or severity of coronavirus disease 2019 (COVID-19) in a cohort of 610 COVID-19 cases and 48,667 population-based controls from Zhejiang, China. Using a cohort of 578 COVID-19 cases and 48,667 population-based controls from Zhejiang, China, we tested the role of usage of cardiovascular, antidiabetic, and other medications on risk and severity of COVID-19. Analyses were adjusted for age, sex, and body mass index and for presence of relevant comorbidities. Individuals with hypertension taking calcium channel blockers had significantly increased risk (odds ratio (OR) = 1.73, 95% confidence interval (CI) 1.2-2.3) of manifesting symptoms of COVID-19, whereas those taking angiotensin receptor blockers and diuretics had significantly lower disease risk (OR = 0.22, 95% CI 0.15-0.30 and OR = 0.30, 95% CI 0.19-0.58, respectively). Among those with type 2 diabetes, dipeptidyl peptidase-4 inhibitors (OR = 6.02, 95% CI 2.3-15.5) and insulin (OR = 2.71, 95% CI 1.6-5.5) were more and glucosidase inhibitors were less prevalent (OR = 0.11, 95% CI 0.1-0.3) among with patients with COVID-19. Drugs used in the treatment of hypertension and diabetes influence the risk of development of COVID-19, but, not its severity.

Association of L-FABP T94A and MTP I128T polymorphisms with hyperlipidemia in Chinese subjects.

The purpose of this study was to evaluate the relation between the L-FABP T94A and MTP I128T polymorphisms and hyperlipidemia in Chinese subjects. We recruited 390 volunteers: 201 hyperlipidemic and 189 healthy volunteers. The L-FABP T94A and MTP I128T polymorphisms were genotyped using polymerase chain reaction-restriction fragment length polymorphism (PCR-RFLP). Anthropometry, lipid profile, and liver function of the subjects were determined. We observed that male carriers of the L-FABP A94 allele had significantly higher body weight (P = 0.012), higher body mass index (BMI) (P = 0.014), and higher plasma triacylglycerol levels (TAG) (P = 0.033) and lower ratios of high-density lipoprotein cholesterol (HDL-C) to total cholesterol (TC) (P = 0.008) than T94 homozygotes. The MTP T128 allele was associated with significantly lower serum TC (P < 0.001) and low-density lipoprotein cholesterol (LDL-C) (P < 0.001) levels in males. There was a direct correlation between the MTP T128 allele and a decreased risk of hyperlipidemia after adjusting for body mass index (OR = 0.327, 95 % CI: 0.178-0.600, P < 0.001). In conclusion, both the MTP I128T and the L-FABP T94A polymorphisms can affect serum lipid levels in the Chinese population. The MTP T128 allele offers protection against hyperlipidemia in the Chinese population.