Zephyr Software (United States)

Abstract Background: Precision medicine (PM) has transformed cancer treatment but remains effective for only a subset of patients. Most tumors profiled with comprehensive genomic testing lack actionable biomarkers, and even when present, many patients fail to benefit from corresponding therapies. Some without recognized biomarkers respond in off-label contexts, highlighting the need for better biomarkers to capture drug response biology and deliver on the promise of PM. Osimertinib, a third-generation EGFR inhibitor, is used in conjunction with the single gene biomarker, EGFR. Response rates vary by EGFR variant and off-target activity has been reported. We hypothesized that integrating multi-modal data with machine learning could enhance osimertinib response predictions beyond the single-gene EGFR biomarker. Methods: We developed an AI/ML-enabled drug response prediction model that integrates clinical and molecular features with drug structure and functional data to generate drug response predictions. The model produces an AI-enabled composite biomarker (AI-CB) based on a small amount of clinical and molecular patient input data. Each prediction is paired with a proprietary Vulnerability Network™ (VN), providing insights into biological dependencies underlying response predictions. Osimertinib response predictions were evaluated retrospectively across multiple real-world (rw) NSCLC cohorts, including clinicogenomic data from liquid biopsy. The AI-CB was also validated in EGFR-negative NSCLC patient-derived xenografts (PDX). Results: Across multiple osimertinib-treated EGFR+ rw-NSCLC cohorts, the AI-CB accurately stratified patients by sensitivity to osimertinib, despite the presence of EGFR alterations in all patients. EGFR+ patients predicted to be insensitive showed a significant reduction in rw-overall survival compared to those predicted to be sensitive, indicating that osimertinib sensitivity may be impacted by more than just EGFR alterations. Compared to EGFR+ osimertinib insensitive patients, post-hoc and VN analysis across these two cohorts linked sensitivity to upregulation of pathways downstream of EGFR including NOTCH and TP63 and downregulation of RAS/RAF/MEK activity. The AI-CB was successfully validated in human PDX models without activating EGFR alterations. AI-CB application to AACR Project GENIE cohorts suggest that sensitivity to osimertinib could extend to a novel group of patients with NSCLC and beyond, e.g., colorectal cancer. Conclusion: ML enables the integration of diverse data types relevant to drug response, overcoming limitations of single-dimensional approaches. Incorporating AI-driven patient stratification models into drug development and clinical practice could greatly expand the utility of targeted therapies and create effective stratification strategies for drugs lacking adequate biomarkers. Citation Format: Maayan Baron, Felicia Kuperwaser, Colin Tang, Sunil Kumar, Dillon Tracy, Zong Miao, Olena Marchenko, Sepideh Foroutan, Amy Sheide, Nathaniel Tann, Samantha Pindak, Jacob Kaffey, Jordan Wolinsky, Sean Klei, Andrey Chursov, Brandon Funkhouser, Nick Lee, Patrick Bohan, Fahad Khan, Ripple Khera, Jean Michel Rouly, George Komatsoulis, Jeff Sherman, Emily Vucic, Rachael Brake. Identifying novel drivers of drug sensitivity using an AI-enabled composite biomarker - osimertinib sensitivity beyond EGFR [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 4640.

BackgroundImmune checkpoint inhibitors (ICIs) have transformed cancer therapy, yet their response rates remain modest, ranging from 20–40% across different cancer types.1 There exists a critical need for predictive tools to optimize treatments, avoid unnecessary side effects and identify patients most likely to respond to ICIs. Towards this goal, we developed a novel machine learning model for predicting overall survival (OS) in cancer patients undergoing treatment with ICIs, called ImmunoBERT, which takes as input clinical and molecular data currently available in real-world settings.MethodsWe curated a comprehensive clinicogenomics dataset of cancer patients treated with anti-PD1 and anti-CTLA4 checkpoint therapies (n=1700 patients), ICI drug structure embeddings and binding affinity profiles of ICI drug targets. Using this dataset, we trained ImmunoBERT (figure 1) which leverages large language models (LLMs)2 and ProteinBERT (a deep learning model built upon the classic Transformer/BERT architecture)3 to learn a generalization between ICI drugs, their protein targets, clinically available genomics data and patient outcome. Correlations and higher-order interactions between 220 genes commonly sequenced on commercial NGS panels were also leveraged using ImmunoBERT architecture, to reconstruct features that improved ICI survival response prediction accuracy, including n= 32 tumor microenvironment (TME) features, tumor mutational burden (TMB) and PDL1 expression.ResultsImmunoBERT performance was benchmarked against top performing machine learning models from the Anti-PD1 Response Prediction DREAM Challenge.4 The C-index (or concordance index) statistic was used to evaluate and compare the predictive accuracy of ImmunoBERT and the different survival models, where higher C-index indicates better predictive accuracy of the model. ImmunoBERT (C-index= 0.69) outperformed the top DREAM challenge models (C-index of 0.6348 for top submission) in predicting patient response to ICI therapies.ConclusionsOur study demonstrates the value of integrating biologically relevant factors, such as drug structure, target binding affinity and genomic information, into machine learning models to improve accuracy of ICI response predictions. Moreover, by effectively leveraging real-world clinicogenomics data, we were able to reconstruct additional biologically relevant features, including TME characteristics which further improved both the performance and interpretability of ImmunoBERT over current models. ImmunoBERT offers improved ICI prognostic capabilities, facilitating personalized treatment decisions to these promising drugs and enhancing patient care.AcknowledgementsThe authors would like to acknowledge members of the Zephyr AI science, engineering and data teamsReferencesSharma P, Hu-Lieskovan S, Wargo JA, Ribas A. Primary, Adaptive, and Acquired Resistance to Cancer Immunotherapy. Cell. 2017 Feb 9;168(4):707–23.Lee J, Yoon W, Kim S, Kim D, Kim S, So CH, Kang J. BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics. 2020 Feb 15;36(4):1234–40.Brandes N, Ofer D, Peleg Y, Rappoport N, Linial M. ProteinBERT: a universal deep-learning model of protein sequence and function. Bioinformatics. 2022 Apr 12;38(8):2102–10.Vincent BG, Szustakowski JD, Doshi P, Mason M, Guinney J, Carbone DP. Pursuing Better Biomarkers for Immunotherapy Response in Cancer Through a Crowdsourced Data Challenge. JCO Precis Oncol. 2021 Nov;5:51–4. 1295 Figure 1ImmunoBERT Design: ImmunoBERT uses tumor molecular data, drug structure and the corresponding target protein. The structure of the model is based on three deep neural networks, one for each of the described inputs, concatenated together to a final neural network that predicts overall survival to immune checkpoint inhibitor treatment

Silicosis is an irreversible chronic pulmonary disease caused by long-term inhalation and deposition of silica particles, which is currently incurable. The exhaustion of airway epithelial stem cells plays a pathogenetic role in silicosis. In present study, we investigated therapeutic effects and potential mechanism of human embryonic stem cell (hESC)-derived MSC-likes immune and matrix regulatory cells (IMRCs) (hESC-MSC-IMRCs), a type of manufacturable MSCs for clinical application in silicosis mice. Our results showed that the transplantation of hESC-MSC-IMRCs led the alleviation of silica-induced silicosis in mice, accompanied by inhibiting epithelia-mesenchymal transition (EMT), activating B-cell-specific Moloney murine leukemia virus integration site 1 (Bmi1) signaling and airway epithelial cell regeneration. In consistence, the secretome of hESC-MSC-IMRC exhibited abilities to restore the potency and plasticity of primary human bronchial epithelial cells (HBECs) proliferation and differentiation following the SiO2 -induced HBECs injury. Mechanistically, the secretome resolved the SiO2 -induced HBECs injury through the activation of BMI1 signaling and restoration of airway basal cell proliferation and differentiation. Moreover, the activation of BMI1 significantly enhanced the capacity of HBEC proliferation and differentiation to multiple airway epithelial cell types in organoids. Cytokine array revealed that DKK1, VEGF, uPAR, IL-8, Serpin E1, MCP-1 and Tsp-1 were the main factors in the hESC-MSC-IMRC secretome. These results demonstrated a potential therapeutic effect of hESC-MSC-IMRCs and their secretome for silicosis, in part through a mechanism by activating Bmi1 signaling to revert the exhaustion of airway epithelial stem cells, subsequentially enhance the potency and plasticity of lung epithelial stem cells.

Abstract The immune microenvironment plays a critical role in cancer development, progression and resistance to therapy. Specific tumor genotypes can profoundly influence the composition of the immune microenvironment. After oncogenic KRAS, TP53 is the most frequently mutated gene in pancreatic ductal adenocarcinoma (PDAC). KRASG12D mutations in tumor cells are known to modify the immune landscape of PDAC, however the immune effects of neomorphic TP53 mutations have not been defined. Focusing on the most common neomorphic TP53 mutation in human PDAC, we sought to evaluate the non-cell-autonomous role of gain-of-function mutant Trp53R172H in modulating the immune microenvironment of pancreatic tumors by using KrasG12D-mutated mouse pancreatic ductal epithelial cells (PDEC) genetically engineered to express the Trp53R172H gain-of-function. Orthotopically implanted tumors derived from CRISPR-generated KrasG12D/+;Trp53R172H/+ PDEC had a distinct immune profile in comparison to KrasG12D/+;Trp53+/+ tumors, characterized by an influx of intratumoral CD11b+Ly6G+ neutrophils and concomitant decreases in CD3+ T cells, CD8+ T cells, and CD4+ T helper 1 (Th1) cells. Analysis of publicly available human PDAC cohorts revealed enrichment of genes in neutrophil-related pathways in TP53-mutated tumors. Knockdown of CXCL2, a neutrophil chemoattractant, in the tumor epithelial compartment of CRISPR KrasG12D/+;Trp53R172H/+ PDEC tumors reversed the neutrophil phenotype. Depleting neutrophils in mice bearing CRISPR KrasG12D/+;Trp53R172H/+ PDEC tumors augmented sensitivity to combined CD40 immunotherapy and chemotherapy. Collectively, these data link gain-of-function mutant Trp53R172H to the presence of intratumoral neutrophils in pancreatic cancer and suggests that tumor genotypes could inform patient selection for immunotherapy. Citation Format: Despina Siolas, Emily Vucic, Emma Kurz, Cristina Hajdu, Dafna Bar-Sagi. Gain-of-function p53R172H mutation drives accumulation of neutrophils in the pancreatic tumor microenvironment promoting resistance to immunotherapy [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 6142.

This paper presents a novel means of controlling a dynamic power supply in continuous conduction mode via sliding-mode voltage control technique. Previous work has discussed the design and implementation of a high-efficiency dynamic power supply based on an asynchronous buck converter in open-loop operation. This work incorporates nonlinear control design for the dynamic buck converter that suits applications such as envelope tracking and amplitude modulation for Class E power amplifiers. The control system is shown, via MATLAB simulation, to accurately track time-varying reference signals, improve the power converter dynamics, and provide the desired output power while rejecting large load disturbances.

The DPLA ingestion system

The DPLA ingestion system

The DPLA ingestion system

The DPLA ingestion system

The DPLA ingestion code