Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Parsing JSON with newlines #292

Closed
whitead opened this issue Jun 25, 2024 · 0 comments · Fixed by #293
Closed

Parsing JSON with newlines #292

whitead opened this issue Jun 25, 2024 · 0 comments · Fixed by #293

Comments

@whitead
Copy link
Owner

whitead commented Jun 25, 2024

If the model response looks like:

{
  "summary": "The excerpt discusses different approaches to representing protein structures for machine learning, including equivariant methods. It mentions that scalar quantities of proteins like interaction interfaces are intrinsically rotation and translation invariant. The text describes several equivariant approaches:

1. Tensor Field Networks (TFN) using rotation equivariant convolutions based on spherical harmonics
2. Cormorant networks improving on TFN with Clebsch-Gordan non-linearity 
3. Geometric vector perceptron (GVP) using linear operations on vectors respecting rotation equivariance
4. Equivariant graph neural networks

The excerpt notes that TFN architectures have been successful in predicting protein-protein complex quality. However, it does not explicitly state that equivariant layers are definitively better at modeling protein structure compared to other approaches.",
  "relevance_score": 7
}

we do not parse it correctly. We should be able to handle that.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging a pull request may close this issue.

1 participant