add boltz

.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Jeremy Wohlwend, Gabriele Corso, Saro Passaro
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1,13 +1,65 @@
----
-title: Boltz
-emoji: 🏢
-colorFrom: purple
-colorTo: purple
-sdk: gradio
-sdk_version: 5.6.0
-app_file: app.py
-pinned: false
-short_description: AlphaFold3 Like Model
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+<h1 align="center">Boltz-1:
+
+Democratizing Biomolecular Interaction Modeling
+</h1>
+
+![](docs/boltz1_pred_figure.png)
+
+Boltz-1 is an open-source model which predicts the 3D structure of proteins, rna, dna and small molecules; it handles modified residues, covalent ligands and glycans, as well as condition the generation on pocket residues. 
+
+For more information about the model, see our [technical report](https://gcorso.github.io/assets/boltz1.pdf).
+
+## Installation
+Install boltz with PyPI (recommended):
+
+```
+pip install boltz
+```
+
+or directly from GitHub for daily updates:
+
+```
+git clone https://github.com/jwohlwend/boltz.git
+cd boltz; pip install -e .
+```
+> Note: we recommend installing boltz in a fresh python environment
+
+## Inference
+
+You can run inference using Boltz-1 with:
+
+```
+boltz predict input_path
+```
+
+Boltz currently accepts three input formats:
+
+1. Fasta file, for most use cases
+
+2. A comprehensive YAML schema, for more complex use cases
+
+3. A directory containing files of the above formats, for batched processing
+
+To see all available options: `boltz predict --help` and for more informaton on these input formats, see our [prediction instructions](docs/prediction.md).
+
+## Training
+
+If you're interested in retraining the model, see our [training instructions](docs/training.md).
+
+## Contributing
+
+We welcome external contributions and are eager to engage with the community. Connect with us on our [Slack channel](https://boltz-community.slack.com/archives/C0818M6DWH2) to discuss advancements, share insights, and foster collaboration around Boltz-1.
+
+## Coming very soon
+
+- [ ] Pocket conditioning support
+- [ ] More examples
+- [ ] Full data processing pipeline
+- [ ] Colab notebook for inference
+- [ ] Confidence model checkpoint
+- [ ] Support for custom paired MSA
+- [ ] Kernel integration
+
+## License
+
+Our model and code are released under MIT License, and can be freely used for both academic and commercial purposes.

app.py

@@ -1,8 +1,14 @@
 import gradio as gr
 import os
 from gradio_molecule3d import Molecule3D
+import sys
+import os
+# from boltz.main_test import predict  # Import your predict function
+current_dir = os.path.dirname(os.path.abspath(__file__))
+src_path = os.path.join(current_dir, "boltz", "src")
+sys.path.append(src_path)
 from boltz.main_test import predict  # Import your predict function
-
+# from boltz.src.boltz.main_test import predict
 # Example Molecule3D representation settings
 reps = [
     {
@@ -22,10 +28,10 @@ reps = [
 def run_prediction(input_file):
     # Assuming `input_file` is a Gradio `File` object
     data = input_file.name  # Get the path to the uploaded .fasta file
-    out_dir = "/predict"  # Set your output directory
+    out_dir = "./predict"  # Set your output directory
     cache = "~/.boltz"
     accelerator = "cpu"
-    sampling_steps = 200
+    sampling_steps = 1
     diffusion_samples = 1
     output_format = "pdb"
 
@@ -33,16 +39,9 @@ def run_prediction(input_file):
     predict(
         data=data,
         out_dir=out_dir,
-        cache=cache,
-        checkpoint=checkpoint,
-        devices=devices,
         accelerator=accelerator,
-        recycling_steps=recycling_steps,
         sampling_steps=sampling_steps,
-        diffusion_samples=diffusion_samples,
-        output_format=output_format,
-        num_workers=num_workers,
-        override=override,
+        output_format=output_format
     )
 
     # Fetch the generated PDB file

pyproject.toml

@@ -0,0 +1,78 @@
+[build-system]
+requires = ["setuptools >= 61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "boltz"
+version = "0.1.0"
+requires-python = ">=3.9"
+description = "Boltz-1"
+readme = "README.md"
+dependencies = [
+    "torch>=2.2",
+    "numpy==1.26.3",
+    "hydra-core==1.3.2",
+    "pytorch-lightning==2.4.0",
+    "rdkit==2024.3.6",
+    "dm-tree==0.1.8",
+    "requests==2.32.3",
+    "pandas==2.2.3",
+    "types-requests",
+    "einops==0.8.0",
+    "einx==0.3.0",
+    "fairscale==0.4.13",
+    "mashumaro==3.14",
+    "modelcif==1.2",
+    "wandb==0.18.7",
+    "click==8.1.7",
+    "pyyaml==6.0.2",
+    "biopython==1.84",
+    "scipy==1.13.1",
+]
+
+[project.scripts]
+boltz = "boltz.main:cli"
+
+[project.optional-dependencies]
+lint = ["ruff"]
+
+[tool.ruff]
+src = ["src"]
+extend-exclude = ["conf.py"]
+target-version = "py39"
+lint.select = ["ALL"]
+lint.ignore = [
+    "COM812",  # Conflicts with the formatter
+    "ISC001",  # Conflicts with the formatter
+    "ANN101",  # "missing-type-self"
+    "RET504",  # Unnecessary assignment to `x` before `return` statementRuff
+    "S101",    # Use of `assert` detected
+    "D100",    # Missing docstring in public module
+    "D104",    # Missing docstring in public package
+    "PT001",   # https://github.com/astral-sh/ruff/issues/8796#issuecomment-1825907715
+    "PT004",   # https://github.com/astral-sh/ruff/issues/8796#issuecomment-1825907715
+    "PT005",   # https://github.com/astral-sh/ruff/issues/8796#issuecomment-1825907715
+    "PT023",   # https://github.com/astral-sh/ruff/issues/8796#issuecomment-1825907715
+    "FBT001",
+    "FBT002",
+    "PLR0913", # Too many arguments to init (> 5)
+]
+
+[tool.ruff.lint.per-file-ignores]
+"**/__init__.py" = [
+    "F401", # Imported but unused
+    "F403", # Wildcard imports
+]
+"docs/**" = [
+    "INP001", # Requires __init__.py but folder is not a package.
+]
+"scripts/**" = [
+    "INP001", # Requires __init__.py but folder is not a package.
+]
+
+[tool.ruff.lint.pyupgrade]
+# Preserve types, even if a file imports `from __future__ import annotations`(https://github.com/astral-sh/ruff/issues/5434)
+keep-runtime-typing = true
+
+[tool.ruff.lint.pydocstyle]
+convention = "numpy"