Matching by OS Prognostic Score to Construct External Controls in Lung Cancer Clinical Trials.

External controls (eControls) leverage historical data to create non-randomized control arms. The lack of randomization can result in confounding between the experimental and eControl cohorts. To balance potentially confounding variables between the cohorts, one of the proposed methods is to match on prognostic scores.

Correlation Between Early Trends of a Prognostic Biomarker and Overall Survival in Non-Small-Cell Lung Cancer Clinical Trials.

Purpose: Overall survival (OS) is the primary end point in phase III oncology trials. Given low success rates, surrogate end points, such as progression-free survival or objective response rate, are used in early go/no-go decision making. Here, we investigate whether early trends of OS prognostic biomarkers, such as the ROPRO and DeepROPRO, can also be used for this purpose.

Generative artificial intelligence empowers digital twins in drug discovery and clinical trials.

Introduction: The concept of Digital Twins (DTs) translated to drug development and clinical trials describes virtual representations of systems of various complexities, ranging from individual cells to entire humans, and enables in silico simulations and experiments. DTs increase the efficiency of drug discovery and development by digitalizing processes associated with high economic, ethical, or social burden. The impact is multifaceted: DT models sharpen disease understanding, support biomarker discovery and accelerate drug development, thus advancing precision medicine.

Label-free imaging of 3D pluripotent stem cell differentiation dynamics on chip.

Massive, parallelized 3D stem cell cultures for engineering human cell types require imaging methods with high time and spatial resolution to fully exploit technological advances in cell culture technologies. Here, we introduce a large-scale integrated microfluidic chip platform for automated 3D stem cell differentiation. To fully enable dynamic high-content imaging on the chip platform, we developed a label-free deep learning method called Bright2Nuc to predict nuclear staining in 3D from confocal microscopy bright-field images.

CD25 targeting with the afucosylated human IgG1 antibody RG6292 eliminates regulatory T cells and CD25+ blasts in acute myeloid leukemia.

Background: Acute Myeloid leukemia is a heterogeneous disease that requires novel targeted treatment options tailored to the patients' specific microenvironment and blast phenotype.

Methods: We characterized bone marrow and/or blood samples of 37 AML patients and healthy donors by high dimensional flow cytometry and RNA sequencing using computational analysis. In addition, we performed ex vivo ADCC assays using allogeneic NK cells isolated from healthy donors and AML patient material to test the cytotoxic potential of CD25 Mab (also referred to as RG6292 and RO7296682) or isotype control antibody on regulatory T cells and CD25+ AML cells.

A Novel EGFRvIII T-Cell Bispecific Antibody for the Treatment of Glioblastoma.

T-cell bispecific antibodies (TCB) are engineered molecules that bind both the T-cell receptor and tumor-specific antigens. Epidermal growth factor receptor variant III (EGFRvIII) mutation is a common event in glioblastoma (GBM) and is characterized by the deletion of exons 2-7, resulting in a constitutively active receptor that promotes cell proliferation, angiogenesis, and invasion. EGFRvIII is expressed on the surface of tumor cells and is not expressed in normal tissues, making EGFRvIII an ideal neoantigen target for TCBs.

A novel DPH5-related diphthamide-deficiency syndrome causing embryonic lethality or profound neurodevelopmental disorder.

Purpose: Diphthamide is a post-translationally modified histidine essential for messenger RNA translation and ribosomal protein synthesis. We present evidence for DPH5 as a novel cause of embryonic lethality and profound neurodevelopmental delays (NDDs).

Methods: Molecular testing was performed using exome or genome sequencing.

Artificial Intelligence for Prognostic Scores in Oncology: a Benchmarking Study.

Prognostic scores are important tools in oncology to facilitate clinical decision-making based on patient characteristics. To date, classic survival analysis using Cox proportional hazards regression has been employed in the development of these prognostic scores. With the advance of analytical models, this study aimed to determine if more complex machine-learning algorithms could outperform classical survival analysis methods.

CD40 Agonist Targeted to Fibroblast Activation Protein α Synergizes with Radiotherapy in Murine HPV-Positive Head and Neck Tumors.

Purpose: The incidence of human papillomavirus-associated head and neck squamous cell carcinoma (HPV-HNSCC) is rising worldwide and although current therapeutic modalities are efficient in the majority of patients, there is a high rate of treatment failures. Thus, novel combination approaches are urgently needed to achieve better disease control in patients with HPV-HNSCC. We investigated the safety and therapeutic efficacy of a novel fibroblast activation protein (FAP)-targeted CD40 agonist (FAP-CD40) in combination with local hypofractionated radiation in a syngeneic HPV-HNSCC model.

Fibroblast Activation Protein α-Targeted CD40 Agonism Abrogates Systemic Toxicity and Enables Administration of High Doses to Induce Effective Antitumor Immunity.

Purpose: CD40 agonists hold great promise for cancer immunotherapy (CIT) as they enhance dendritic cell (DC) activation and concomitant tumor-specific T-cell priming. However, the broad expression of CD40 accounts for sink and side effects, hampering the efficacy of anti-CD40 antibodies. We hypothesized that these limitations can be overcome by selectively targeting CD40 agonism to the tumor.

Deep Learning-based Propensity Scores for Confounding Control in Comparative Effectiveness Research: A Large-scale, Real-world Data Study.

Background: Due to the non-randomized nature of real-world data, prognostic factors need to be balanced, which is often done by propensity scores (PSs). This study aimed to investigate whether autoencoders, which are unsupervised deep learning architectures, might be leveraged to compute PS.

Methods: We selected patient-level data of 128,368 first-line treated cancer patients from the Flatiron Health EHR-derived de-identified database.