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. 

Abstract MotivationComputer inference of biological mechanisms is increasingly approachable due to dynamically rich data sources such as single-cell genomics. Inferred molecular interactions can prioritize hypotheses for wet-lab experiments to expedite biological discovery. However, complex data often come with unwanted biological or technical variations, exposing biases over marginal distribution and sample size in current methods to favor spurious causal relationships. ResultsConsidering function direction and strength as evidence for causality, we present an adapted functional chi-squared test (AdpFunChisq) that rewards functional patterns over non-functional or independent patterns. On synthetic and three biology datasets, we demonstrate the advantages of AdpFunChisq over 10 methods on overcoming biases that give rise to wide fluctuations in the performance of alternative approaches. On single-cell multiomics data of multiple phenotype acute leukemia, we found that the T-cell surface glycoprotein CD3 delta chain may causally mediate specific genes in the viral carcinogenesis pathway. Using the causality-by-functionality principle, AdpFunChisq offers a viable option for robust causal inference in dynamical systems. Availability and implementationThe AdpFunChisq test is implemented in the R package ‘FunChisq’ (2.5.2 or above) at https://cran.r-project.org/package=FunChisq. All other source code along with pre-processed data is available at Code Ocean https://doi.org/10.24433/CO.2907738.v1 Supplementary informationSupplementary materials are available at Bioinformatics online. 

Abstract MotivationEnvironmental DNA (eDNA), as a rapidly expanding research field, stands to benefit from shared resources including sampling protocols, study designs, discovered sequences, and taxonomic assignments to sequences. High-quality community shareable eDNA resources rely heavily on comprehensive metadata documentation that captures the complex workflows covering field sampling, molecular biology lab work, and bioinformatic analyses. There are limited sources that provide documentation of database development on comprehensive metadata for eDNA and these workflows and no open-source software. ResultsWe present medna-metadata, an open-source, modular system that aligns with Findable, Accessible, Interoperable, and Reusable guiding principles that support scholarly data reuse and the database and application development of a standardized metadata collection structure that encapsulates critical aspects of field data collection, wet lab processing, and bioinformatic analysis. Medna-metadata is showcased with metabarcoding data from the Gulf of Maine (Polinski et al., 2019). Availability and implementationThe source code of the medna-metadata web application is hosted on GitHub (https://github.com/Maine-eDNA/medna-metadata). Medna-metadata is a docker-compose installable package. Documentation can be found at https://medna-metadata.readthedocs.io/en/latest/?badge=latest. The application is implemented in Python, PostgreSQL and PostGIS, RabbitMQ, and NGINX, with all major browsers supported. A demo can be found at https://demo.metadata.maine-edna.org/. Supplementary informationSupplementary data are available at Bioinformatics online.