Skip to content

Sg/backend improvements - #32

Open
saurabhinfocusp wants to merge 7 commits into
mainfrom
sg/backend-improvements
Open

Sg/backend improvements#32
saurabhinfocusp wants to merge 7 commits into
mainfrom
sg/backend-improvements

Conversation

@saurabhinfocusp

@saurabhinfocusp saurabhinfocusp commented Sep 21, 2026 •
edited
Loading

Copy link
Copy Markdown
Collaborator

Summary

  • Add a new "simple API" layer on top of the scaLR engine — scalr.train, scalr.annotate, scalr.load_model, scalr.validate, scalr.align_genes — for config-free, in-memory workflows (leakage-safe splitting, calibration, metrics, validation, gene alignment).
  • Layer in optional capabilities: hierarchical taxonomy annotation, cluster-refinement majority voting, doublet flagging, feature-selection stability scoring, and dataset benchmarking (quality + cost).
  • Add self-contained model artifacts (manifest.json, model.pt, configs, auto-generated model card) with a local model registry, and a scalr CLI (train, annotate, evaluate, validate, models list/info).
  • Add corresponding unit tests for all new modules.
  • Apply yapf/isort formatting fixes to satisfy CI style checks (no logic changes).
  • Update docs (README, CLAUDE.md), pyproject.toml, requirements.txt for the new modules/CLI entry point.

Test plan

  • pytest (new test_api.py, test_benchmark.py, test_cli.py, test_doublet.py, test_feature_stability.py, test_hierarchy.py, test_model_card.py, test_models.py, test_refinement.py, plus existing suites)
  • CLI-based training tested manually per latest commit message

saurabh and others added 5 commits September 21, 2026 17:28
saurabh
P0_implemantion_done
00454fa
saurabh @claude
fix: apply yapf/isort formatting to P0 implementation files
617dee8 
CI's yapf check failed because the new P0 files did not match the
project's .style.yapf (google style, 80 cols). Reformatted with
`yapf -ir --style .style.yapf` and `isort --settings-path .isort.cfg`;
no logic changes.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
saurabh
P1_implemantion_done
f3034fc
saurabh
Cli_based tranning_tested
966225d
saurabh @claude
fix: apply yapf formatting to scalr/cli.py
65e9eef 
CI's yapf check was failing because add_argument calls exceeded the
80-col limit. Reformatted with `yapf -ir --style .style.yapf`; no
logic changes.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
saurabh and others added 2 commits September 24, 2026 16:49
saurabh @claude
feat: add explainability API and streaming/chunked predict (P2)
a6d45c0 
Explainability: scalr/explain.py implements Grad x Input saliency
attribution, wired into AnnotationModel.explain()/explain_class() and
a new `scalr explain` CLI subcommand, to report which genes supported
or contradicted a prediction (per cell or per class).

Streaming predict: AnnotationModel.predict() gains streaming/chunk_size
params (implied by passing a file path); gene alignment and scoring now
happen chunk-by-chunk instead of materializing one aligned matrix for
the whole dataset, per the low-resource design goal. Forwarded through
scalr.annotate() and the `scalr annotate` CLI.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
saurabh @claude
docs: document explainability API and streaming predict in README
caa8ceb 
Add Python-API and CLI usage examples for model.explain()/explain_class()
and streaming/chunked model.predict(), added in a6d45c0.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@Saiyam26 Saiyam26 Awaiting requested review from Saiyam26
@falaktheoptimist falaktheoptimist Awaiting requested review from falaktheoptimist

At least 2 approving reviews are required to merge this pull request.

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@saurabhinfocusp