#
Lists (1)
Starred repositories
A Deep Learning Toolkit for DTI, Drug Property, PPI, DDI, Protein Function Prediction (Bioinformatics)
[CVPR 2025] BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature
MRAgent is an LLM-based tool that automates Mendelian randomization analysis, reducing manual effort by autonomously scanning literature, selecting GWAS data, and generating comprehensive reports, …
Build a system that can understand complex technical questions and provide accurate, contextual answers by connecting information across multiple knowledge sources
1
Updated Jun 27, 2025
GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
A super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG).
A memory-aware AI chatbot built on a knowledge graph to enable rich, contextual, and relational conversations.
Rare diseases knowledge graph
拼好RAG：手搓并融合了GraphRAG、LightRAG、Neo4j-llm-graph-builder进行知识图谱构建以及搜索；整合DeepSearch技术实现私域RAG的推理；自制针对GraphRAG的评估框架| Integrate GraphRAG, LightRAG, and Neo4j-llm-graph-builder for knowledge graph construct…
The Academic GPT pipeline automates the peer review of machine learning research papers by processing PDFs through text extraction and analysis with LLMs including GPT-3.5, GPT-4, and Mistral 7B, g…
Code for MedCPT, a model for zero-shot biomedical information retrieval.
MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs
BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model
litsearchr is an R package to partially automate search term selection for systematic reviews using keyword co-occurrence networks. In addition to identifying search terms, it can write Boolean sea…
Biomni: a general-purpose biomedical AI agent
Co-occurrence analysis in pubmed and faers of two lists of terms.
Biomedical foundation model: Continuous pretraining LLaMA with Pile/PubMed
SciFive: a text-text transformer model for biomedical literature
Using Pubmed data and tf.keras to predict if an ophthalmology paper will make it into a top 15 journal
S2ORC: The Semantic Scholar Open Research Corpus: https://www.aclweb.org/anthology/2020.acl-main.447/
Automatic generation of reviews of scientific papers
Pull high-quality, efficient embeddings for PubMed, arXiv and Wikipedia from Huggingface and use for local LLM inference/Retrieval Augmented Generation (RAG)
Building a pubmed graph, automatically.