Search for: All records

Narrative data spans all disciplines and provides a coherent model of the world to the reader or viewer. Recent advancement in machine learning and Large Language Models (LLMs) have enable great strides in analyzing natural language. However, Large language models (LLMs) still struggle with complex narrative arcs as well as narratives containing conflicting information. Recent work indicates LLMs augmented with external knowledge bases can improve the accuracy and interpretability of the resulting models. In this work, we analyze the effectiveness of applying knowledge graphs (KGs) in understanding true-crime podcast data from both classical Natural Language Processing (NLP) and LLM approaches. We directly compare KG-augmented LLMs (KGLLMs) with classical methods for KG construction, topic modeling, and sentiment analysis. Additionally, the KGLLM allows us to query the knowledge base in natural language and test its ability to factually answer questions. We examine the robustness of the model to adversarial prompting in order to test the model's ability to deal with conflicting information. Finally, we apply classical methods to understand more subtle aspects of the text such as the use of hearsay and sentiment in narrative construction and propose future directions. Our results indicate that KGLLMs outperform LLMs on a variety of metrics, are more robust to adversarial prompts, and are more capable of summarizing the text into topics. 

During development, cell signaling instructs tissue patterning, the process by which initially identical cells give rise to spatially organized structures consisting of different cell types. How multiple signals combinatorially instruct fate in space and time remains poorly understood. Simultaneous measurement of signaling activity through multiple signaling pathways and of the cell fates they control is critical to addressing this problem. Here we describe an iterative immunofluorescence protocol and computational pipeline to interrogate pattern formation in a 2D model of human gastrulation with far greater multiplexing than is possible with standard immunofluorescence techniques. This protocol and computational pipeline together enable imaging followed by spatial and co‐localization analysis of over 27 proteins in the same gastruloids. We demonstrate this by clustering single cell protein expression, using techniques familiar from scRNA‐seq, and linking this to spatial position to calculate spatial distributions and cell signaling activity of different cell types. These methods are not limited to patterning in 2D gastruloids and can be easily extended to other contexts. In addition to the iterative immunofluorescence protocol and analysis pipeline, Support Protocols for 2D gastruloid differentiation and producing micropatterned multi‐well slides are included. 

Abstract Deforestation is a major threat to global environmental wellness, with illegal logging as one of the major causes. Recently, there has been increased effort to model environmental crime, with the goal of assisting law enforcement agencies in deterring these activities. We present a continuous model for illegal logging applicable to arbitrary domains. We model the practice of criminals under influence of law enforcement agencies using tools from multiobjective optimal control theory and consider non-instantaneous logging events and load-dependent travel velocity. We calibrate our model using real deforestation data from the Brazilian rainforest and demonstrate the importance of geographically targeted patrol strategies.