Add /api/stability endpoint with stability models and tighten sequence validation#5
Conversation
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 10809724ba
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
|
@codex review |
raiden9420
left a comment
There was a problem hiding this comment.
looking all good , need to use uniprot
|
Codex Review: Didn't find any major issues. Can't wait for the next one! ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
* started the work on backend * Add confidence metrics module and update requirements * added the docs and rearranged the files * Add /api/stability endpoint with stability models and tighten sequence validation (#5) * Remove issue markdown file and provide issue text inline * Modularize stability computation with isolated service logic * Add detailed backend feature and architecture docs * Fix stability request length validation after cleaning --------- Co-authored-by: jyotsana15 <jyotsanab15@gmail.com>
Motivation
Requestobject for consistency with other endpoints.Description
StabilityRequestandStabilityResponsePydantic models tobackend/main.pywith the same cleaning/validation as other sequence requests and enforced post-cleaning length checks.POST /api/stability(measure_stability) which computes aromaticity, an aliphatic index approximation, charge density, disorder fraction, aninstability_index, and astability_scoreand returns a classifiedstability_classwith details; the model is a deterministic heuristic for MVP screening.PredictRequest.validate_amino_acidsto check cleaned sequence length is between 10 and 2000 and raise aValueErrorif not.search_solubilitysignature toasync def search_solubility(request: Request, ...)to accept theRequestobject similarly to other endpoints.Testing
pytestand all tests passed.POST /api/stabilityendpoint verifying response schema and basic score ranges and they passed.closes #4
@codex