Search for: All records

Abstract MotivationLarge language models (LLMs) are being adopted at an unprecedented rate, yet still face challenges in knowledge-intensive domains such as biomedicine. Solutions such as pretraining and domain-specific fine-tuning add substantial computational overhead, requiring further domain-expertise. Here, we introduce a token-optimized and robust Knowledge Graph-based Retrieval Augmented Generation (KG-RAG) framework by leveraging a massive biomedical KG (SPOKE) with LLMs such as Llama-2-13b, GPT-3.5-Turbo, and GPT-4, to generate meaningful biomedical text rooted in established knowledge. ResultsCompared to the existing RAG technique for Knowledge Graphs, the proposed method utilizes minimal graph schema for context extraction and uses embedding methods for context pruning. This optimization in context extraction results in more than 50% reduction in token consumption without compromising the accuracy, making a cost-effective and robust RAG implementation on proprietary LLMs. KG-RAG consistently enhanced the performance of LLMs across diverse biomedical prompts by generating responses rooted in established knowledge, accompanied by accurate provenance and statistical evidence (if available) to substantiate the claims. Further benchmarking on human curated datasets, such as biomedical true/false and multiple-choice questions (MCQ), showed a remarkable 71% boost in the performance of the Llama-2 model on the challenging MCQ dataset, demonstrating the framework’s capacity to empower open-source models with fewer parameters for domain-specific questions. Furthermore, KG-RAG enhanced the performance of proprietary GPT models, such as GPT-3.5 and GPT-4. In summary, the proposed framework combines explicit and implicit knowledge of KG and LLM in a token optimized fashion, thus enhancing the adaptability of general-purpose LLMs to tackle domain-specific questions in a cost-effective fashion. Availability and implementationSPOKE KG can be accessed at https://spoke.rbvi.ucsf.edu/neighborhood.html. It can also be accessed using REST-API (https://spoke.rbvi.ucsf.edu/swagger/). KG-RAG code is made available at https://github.com/BaranziniLab/KG_RAG. Biomedical benchmark datasets used in this study are made available to the research community in the same GitHub repository. 

Out of the several hundred copies ofrRNAgenes arranged in the nucleolar organizing regions (NOR) of the five human acrocentric chromosomes, ~50% remain transcriptionally inactive. NOR-associated sequences and epigenetic modifications contribute to the differential expression of rRNAs. However, the mechanism(s) controlling the dosage of active versus inactiverRNAgenes within each NOR in mammals is yet to be determined. We have discovered a family of ncRNAs, SNULs (Single NUcleolus Localized RNA), which form constrained sub-nucleolar territories on individual NORs and influence rRNA expression. Individual members of the SNULs monoallelically associate with specific NOR-containing chromosomes. SNULs share sequence similarity to pre-rRNA and localize in the sub-nucleolar compartment with pre-rRNA. Finally, SNULs control rRNA expression by influencing pre-rRNA sorting to the DFC compartment and pre-rRNA processing. Our study discovered a novel class of ncRNAs influencing rRNA expression by forming constrained nucleolar territories on individual NORs. 

Abstract Clinical, biomedical, and translational science has reached an inflection point in the breadth and diversity of available data and the potential impact of such data to improve human health and well‐being. However, the data are often siloed, disorganized, and not broadly accessible due to discipline‐specific differences in terminology and representation. To address these challenges, the Biomedical Data Translator Consortium has developed and tested a pilot knowledge graph‐based “Translator” system capable of integrating existing biomedical data sets and “translating” those data into insights intended to augment human reasoning and accelerate translational science. Having demonstrated feasibility of the Translator system, the Translator program has since moved into development, and the Translator Consortium has made significant progress in the research, design, and implementation of an operational system. Herein, we describe the current system’s architecture, performance, and quality of results. We apply Translator to several real‐world use cases developed in collaboration with subject‐matter experts. Finally, we discuss the scientific and technical features of Translator and compare those features to other state‐of‐the‐art, biomedical graph‐based question‐answering systems. 

Abstract The role of plasticity and epigenetics in shaping cancer evolution and response to therapy has taken center stage with recent technological advances including single cell sequencing. This roadmap article is focused on state-of-the-art mathematical and experimental approaches to interrogate plasticity in cancer, and addresses the following themes and questions: is there a formal overarching framework that encompasses both non-genetic plasticity and mutation-driven somatic evolution? How do we measure and model the role of the microenvironment in influencing/controlling non-genetic plasticity? How can we experimentally study non-genetic plasticity? Which mathematical techniques are required or best suited? What are the clinical and practical applications and implications of these concepts? 

Neuronal networks are the standard heuristic model today for describing brain activity associated with animal behavior. Recent studies have revealed an extensive role for a completely distinct layer of networked activities in the brain—the gene regulatory network (GRN)—that orchestrates expression levels of hundreds to thousands of genes in a behavior-related manner. We examine emerging insights into the relationships between these two types of networks and discuss their interplay in spatial as well as temporal dimensions, across multiple scales of organization. We discuss properties expected of behavior-related GRNs by drawing inspiration from the rich literature on GRNs related to animal development, comparing and contrasting these two broad classes of GRNs as they relate to their respective phenotypic manifestations. Developmental GRNs also represent a third layer of network biology, playing out over a third timescale, which is believed to play a crucial mediatory role between neuronal networks and behavioral GRNs. We end with a special emphasis on social behavior, discuss whether unique GRN organization andcis-regulatory architecture underlies this special class of behavior, and review literature that suggests an affirmative answer. 

Abstract Knowledge representation and reasoning (KR&R) has been successfully implemented in many fields to enable computers to solve complex problems with AI methods. However, its application to biomedicine has been lagging in part due to the daunting complexity of molecular and cellular pathways that govern human physiology and pathology. In this article, we describe concrete uses of Scalable PrecisiOn Medicine Knowledge Engine (SPOKE), an open knowledge network that connects curated information from thirty‐seven specialized and human‐curated databases into a single property graph, with 3 million nodes and 15 million edges to date. Applications discussed in this article include drug discovery, COVID‐19 research and chronic disease diagnosis, and management.