Search for: All records

ABSTRACT Platform trials are multi‐arm designs that simultaneously evaluate multiple treatments for a single disease within the same overall trial structure. Unlike traditional randomized controlled trials, they allow treatment arms to enter and exit the trial at distinct times while maintaining a control arm throughout. This control arm comprises both concurrent controls, where participants are randomized concurrently to either the treatment or control arm, and non‐concurrent controls, who enter the trial when the treatment arm under study is unavailable. While flexible, platform trials introduce the challenge of using non‐concurrent controls, raising questions about estimating treatment effects. Specifically, which estimands should be targeted? Under what assumptions can these estimands be identified and estimated? Are there any efficiency gains? In this article, we discuss issues related to the identification and estimation assumptions of common choices of estimand. We conclude that the most robust strategy to increase efficiency without imposing unwarranted assumptions is to target the concurrent average treatment effect (cATE), the ATE among only concurrent units, using a covariate‐adjusted doubly robust estimator. Our studies suggest that, for the purpose of obtaining efficiency gains, collecting important prognostic variables is more important than relying on non‐concurrent controls. We also discuss the perils of targeting ATE due to an untestable extrapolation assumption that will often be invalid. We provide simulations illustrating our points and an application to the ACTT platform trial, resulting in a 20% improvement in precision compared to the naive estimator that ignores non‐concurrent controls and prognostic variables. 

Cybergrooming emerges as a growing threat to adolescent safety and mental health. One way to combat cybergrooming is to leverage predictive artificial intelligence (AI) to detect predatory behaviors in social media. However, these methods can encounter challenges like false positives and negative implications such as privacy concerns. Another complementary strategy involves using generative artificial intelligence to empower adolescents by educating them about predatory behaviors. To this end, we envision developing state-of-the-art conversational agents to simulate the conversations between adolescents and predators for educational purposes. Yet, one key challenge is the lack of a dataset to train such conversational agents. In this position paper, we present our motivation for empowering adolescents to cope with cybergrooming. We propose to develop large-scale, authentic datasets through an online survey targeting adolescents and parents. We discuss some initial background behind our motivation and proposed design of the survey, such as situating the participants in artificial cybergrooming scenarios, then allowing participants to respond to the survey to obtain their authentic responses. We also present several open questions related to our proposed approach and hope to discuss them with the workshop attendees. 

Abstract Nonlinear optical imaging modalities, such as stimulated Raman scattering (SRS) microscopy, use pulsed-laser excitation with high peak intensity that can perturb the native state of cells. In this study, we used bulk RNA sequencing, quantitative measurement of cell proliferation, and fluorescent measurement of the generation of reactive oxygen species to assess phototoxic effects of near-IR pulsed laser radiation, at different time scales, for laser excitation settings relevant to SRS imaging. We define a range of laser excitation settings for which there was no significant change in mouse Neuro2A cells after laser exposure. This study provides guidance for imaging parameters that minimize photo-induced perturbations in SRS microscopy to ensure accurate interpretation of experiments with time-lapse imaging or with paired measurements of imaging and sequencing on the same cells. 

Conventionally, DNN models are trained once in the cloud and deployed in edge devices such as cars, robots, or unmanned aerial vehicles (UAVs) for real-time inference. However, there are many cases that require the models to adapt to new environments, domains, or users. In order to realize such domain adaption or personalization, the models on devices need to be continuously trained on the device. In this work, we design EF-Train, an efficient DNN training accelerator with a unified channel-level parallelism-based convolution kernel that can achieve end-to-end training on resource-limited low-power edge-level FPGAs. It is challenging to implement on-device training on resource-limited FPGAs due to the low efficiency caused by different memory access patterns among forward and backward propagation and weight update. Therefore, we developed a data reshaping approach with intra-tile continuous memory allocation and weight reuse. An analytical model is established to automatically schedule computation and memory resources to achieve high energy efficiency on edge FPGAs. The experimental results show that our design achieves 46.99 GFLOPS and 6.09 GFLOPS/W in terms of throughput and energy efficiency, respectively. 

Abstract Tissue development and disease lead to changes in cellular organization, nuclear morphology, and gene expression, which can be jointly measured by spatial transcriptomic technologies. However, methods for jointly analyzing the different spatial data modalities in 3D are still lacking. We present a computational framework to integrate Spatial Transcriptomic data using over-parameterized graph-based Autoencoders with Chromatin Imaging data (STACI) to identify molecular and functional alterations in tissues. STACI incorporates multiple modalities in a single representation for downstream tasks, enables the prediction of spatial transcriptomic data from nuclear images in unseen tissue sections, and provides built-in batch correction of gene expression and tissue morphology through over-parameterization. We apply STACI to analyze the spatio-temporal progression of Alzheimer’s disease and identify the associated nuclear morphometric and coupled gene expression features. Collectively, we demonstrate the importance of characterizing disease progression by integrating multiple data modalities and its potential for the discovery of disease biomarkers. 

Aquaporins are water channel proteins in cell membrane, highly specific for water molecules while restricting the passage of contaminants and small molecules, such as urea and boric acid. Cysteine functional groups were installed on aquaporin Z for covalent attachment to the polymer membrane matrix so that the proteins could be immobilized to the membranes and aligned in the direction of the flow. Depth profiling using x-ray photoelectron spectrometer (XPS) analysis showed the presence of functional groups corresponding to aquaporin Z modified with cysteine (Aqp-SH). Aqp-SH modified membranes showed a higher salt rejection as compared to unmodified membranes. For 2 M NaCl and CaCl2 solutions, the rejection obtained from Aqp-SH membranes was 49.3 ± 7.5% and 59.1 ± 5.1%. On the other hand, the rejections obtained for 2 M NaCl and CaCl2 solutions from unmodified membranes were 0.8 ± 0.4% and 1.3 ± 0.2% respectively. Furthermore, Aqp-SH membranes did not show a significant decrease in salt rejection with increasing feed concentrations, as was observed with other membranes. Through simulation studies, it was determined that there was approximately 24% capping of membrane pores by dispersed aquaporins.