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

Release of v1.0 of BioNeMo Modular Co-Design (MoCo) #575

Merged
merged 12 commits into from
Jan 15, 2025

Conversation

nvdreidenbach
Copy link
Collaborator

Release of v1.0 of BioNeMo Modular Co-Design (MoCo)

Introduces modular interpolants for various popular generative model frameworks including continuous and discrete diffusion and flow matching.

Summary

Introduces MoCo.

Details

See documentation.md for details.

Usage

pip install bionemo-moco

from bionemo.moco.interpolants import ContinuousFlowMatcher
from bionemo.moco.distributions.time import UniformTimeDistribution
from bionemo.moco.distributions.prior import GaussianPrior

uniform_time = UniformTimeDistribution()
moon_prior = GaussianPrior()
sigma = 0.1
cfm = ContinuousFlowMatcher(time_distribution=uniform_time, 
                            prior_distribution=moon_prior, 
                            sigma=sigma, 
                            prediction_type="velocity")

see examples directory for notebook tutorials

Testing

Unit tests for all key functions.

Tests for these changes can be run via:

pytest -v tests

@jstjohn
Copy link
Collaborator

jstjohn commented Jan 11, 2025

/build-ci

@codecov-commenter
Copy link

codecov-commenter commented Jan 11, 2025

Codecov Report

Attention: Patch coverage is 78.73232% with 406 lines in your changes missing coverage. Please review.

Project coverage is 86.01%. Comparing base (7960ada) to head (cd6b7a3).
Report is 1 commits behind head on main.

Files with missing lines Patch % Lines
...oco/interpolants/continuous_time/continuous/vdm.py 47.51% 95 Missing ⚠️
...inuous_time/continuous/continuous_flow_matching.py 64.86% 65 Missing ⚠️
...moco/interpolants/discrete_time/continuous/ddpm.py 70.40% 58 Missing ⚠️
...bionemo/moco/schedules/inference_time_schedules.py 76.72% 37 Missing ⚠️
.../moco/schedules/noise/continuous_snr_transforms.py 63.29% 29 Missing ⚠️
...us_time/continuous/optimal_transport/ot_sampler.py 82.05% 14 Missing ⚠️
...o/moco/schedules/noise/discrete_noise_schedules.py 73.07% 14 Missing ⚠️
...inuous/optimal_transport/equivariant_ot_sampler.py 85.55% 13 Missing ⚠️
.../src/bionemo/moco/interpolants/base_interpolant.py 84.41% 12 Missing ⚠️
...rc/bionemo/moco/interpolants/batch_augmentation.py 41.17% 10 Missing ⚠️
... and 16 more
Additional details and impacted files
@@            Coverage Diff             @@
##             main     #575      +/-   ##
==========================================
- Coverage   88.78%   86.01%   -2.77%     
==========================================
  Files          81      116      +35     
  Lines        5027     6936    +1909     
==========================================
+ Hits         4463     5966    +1503     
- Misses        564      970     +406     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

@nvdreidenbach
Copy link
Collaborator Author

/build-ci

@nvdreidenbach nvdreidenbach enabled auto-merge (squash) January 15, 2025 03:23
Copy link
Collaborator

@jstjohn jstjohn left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ship

@nvdreidenbach nvdreidenbach added this pull request to the merge queue Jan 15, 2025
Merged via the queue into NVIDIA:main with commit c868563 Jan 15, 2025
7 checks passed
@nvdreidenbach nvdreidenbach deleted the moco-release branch January 15, 2025 22:00
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 this pull request may close these issues.

5 participants