This project is dedicated to developing a set of automated tools and processes for extracting useful neuronal experimental data from datasets provided by the Allen Brain Institute, and converting these data into parameters that can be used for neuronal modeling on the NetPyNE platform, for comparison with cortical regions already validated by NetPyNE. The project flow is divided into the following steps: Data Collection: Automatically extracts data from the Allen Cell Type Database for specific cell types in the visual cortex, including electrophysiological properties, morphological characteristics, and gene expression patterns. The Allen Institute provides a powerful API that allows users to programmatically access and retrieve data. First through data cleaning, and then through data crawling to obtain data that is difficult to access in the API. In addition, domain-specific language models will be fine-tuned or trained using Google's Gemini model for subsequent data acquisition. Parameter Conversion: Develop tools(scripts) or design large language model prompts to automatically convert extracted data into a parameter format understood by the NetPyNE, such as .hoc or .swc format. Identify how to set reasonable default values for missing data. Model construction: Use the converted parameters to construct neural network models of relevant brain regions in NetPyNE. This includes defining neuron types, neuron connectivity, and synaptic interactions between neurons. Run Simulation: Run a simulation of the model in NetPyNE to simulate the brain's response to a specific input stimulus. Compare Results: Compare the simulation results with actual biological experimental data to verify the accuracy of the model. Intended set of deliverables: Automated Data Collection Tool. Parameter Conversion Script. Simulation Run Framework. Result Validation Report. Documentation and User Guide.