Blog

Engineering notes, deep dives, and build logs from the people making LynxKite.

Building an Explainable Toxicity Knowledge Graph

Evaluating toxicity is a multi-faceted, highly context-dependent problem. In collaboration with Hummingbird Bioscience, and with support from NVIDIA Inception, we built a context-first toxicity knowledge graph — extracting schema-constrained claims from regulatory documents, literature and trial data, then using structural modeling and graph-based ranking to turn...

Read post

Run the Latest Hugging Face Models on Your GPU Cluster Instantly

NVIDIA NIMs are a good option when the container already exists, but new biology models show up on Hugging Face all the time and we got tired of waiting for a vendor image. A LynxKite Inference Microservice (LIM) is a Python row function with @lim on...

Read post

Fine-Tune Any LLM Without Writing a Single Line of Code

Fine-tuning an LLM used to mean writing 400 lines of Python just to get started. We got tired of watching domain experts give up before the first training run. So we built a LynxKite LLM Training plugin: a visual, drag-and-drop workflow for the entire fine-tuning process....

Read post

Explaining GNN predictions with Gemma 4

LynxKite has a flexible graph neural network designer where you can choose from a variety of GNN layers. Graph attention networks are a great choice in many applications. In addition to providing good predictions, GATs are unique in that the attention mechanism gives us insights into...

Read post