Protein Model Fine-Tuning
Fine-tune protein language models for custom property prediction.
Overview
Teach a pretrained protein model to predict properties you have measured, such as enzyme activity, melting temperature, or solubility. Upload labeled amino-acid sequences and optionally matching structures, then learn numerical properties or class labels for one or several targets together. The results include the best saved model, training progress, and predictions on proteins kept separate for evaluation. Use the saved training job in Protein Model Inference to score new proteins. You need at least 300 available compute credits to submit a fine-tuning job. Training time and credit use vary with the model, dataset size, and settings.
Run Protein Model Fine-Tuning on Neurosnap
The Protein Model Fine-Tuning online webserver allows anybody with a Neurosnap account to run and access Protein Model Fine-Tuning, no downloads required. Information submitted through this webserver is kept confidential and never sold to third parties as detailed by our strong Terms of Use and Privacy Policy.
Features
- Learns numerical properties, binary categories, and multiclass categories for whole proteins, including multiple targets with missing measurements.
- Supports ESM2, ESM C, AMPLIFY, ProTrek, DPLM, SaProt, ProtT5, ProstT5, and ProtBERT with configurable learning components.
- Offers adapter, LoRA, QLoRA, and full-backbone tuning, with optional matching structures for SaProt and ProstT5.
- Keeps related proteins together across training, validation, and test splits and supports user-defined split assignments.
- Returns the best validation-selected model, training progress, per-target metrics, and held-out predictions for review and reuse.
Statistics
Neurosnap periodically calculates runtime statistics based on job execution data. These estimates provide a general guideline for how long your job may take, but actual runtimes can vary significantly depending on factors like input size or settings used.
| Statistic | Value |
|---|---|
| Credit Usage Rate | loading... |
| Estimated Total Cost | loading... |
| Runtime Mean | loading... |
| Runtime Median | loading... |
| Runtime Standard Deviation | loading... |
| Runtime 90th Percentile | loading... |
| Runtime Longest | loading... |
API Request
Access Protein Model Fine-Tuning using the Neurosnap API by sending a request using any programming language with HTTP support. To safely generate an API key, visit the API tab of your overview page.
Similar Tools
Explore tools with similar features, categories, and use cases.
Citations
Please cite the original work when using Protein Model Fine-Tuning in publications or research outputs.
|
Amani, Keaun, and Danial Gharaie Amirabadi. 2024. Neurosnap SDK Package. Software. https://github.com/NeurosnapInc/neurosnap. |
|
Neurosnap Inc. (2022). Neurosnap: An online platform for computational biology and chemistry. Available at: https://neurosnap.ai/ |