No project description provided
Project description
PrexSyn Engine
PrexSyn Engine is the C++ backend library for PrexSyn. It provides a high-throughput data pipeline that generates synthetic pathways annotated with molecular properties to train PrexSyn models. It also includes a fast detokenizer for reconstructing synthetic pathways and product molecules from model outputs.
Installation & Usage (v0)
PrexSyn Engine v0 is automatically installed from conda-forge as a dependency when you install PrexSyn. Please refer to the documentation and PrexSyn repository for usage instructions.
🚧 PrexSyn Engine v1 Work in Progress
The previous version (v0) of PrexSyn Engine is dynamically linked to RDKit and Boost to enable interoperability with RDKit's Mol objects on the Python side. However, we have found that the restrictions and risks associated with this design choice outweigh the benefits. For example, dynamic linking limits installation to Conda only and prevents distribution via PyPI. Moreover, future changes in RDKit API/ABI (which are very likely) could break the compatibility and cause runtime errors that are hard to debug.
Therefore, we are working on a new version of PrexSyn Engine that is statically linked to RDKit. This new version will be distributed as a PyPI wheel package. It will be free from the risk of breaking changes in upstream libraries.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distributions
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file prexsyn_engine-1.0.0.dev1.tar.gz.
File metadata
- Download URL: prexsyn_engine-1.0.0.dev1.tar.gz
- Upload date:
- Size: 203.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ee4121ba4de4f1e72476fb585e8cbcb519acd26556eb9a24ad1f2708fd05493b
|
|
| MD5 |
3853d07578a87f9c01509f6d3398f12b
|
|
| BLAKE2b-256 |
7763affc9baeca75937123d9ae204230aaf52dc0638ed3b3e44b551bfd97f01b
|
File details
Details for the file prexsyn_engine-1.0.0.dev1-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.
File metadata
- Download URL: prexsyn_engine-1.0.0.dev1-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
- Upload date:
- Size: 3.4 MB
- Tags: CPython 3.14t, manylinux: glibc 2.27+ x86-64, manylinux: glibc 2.28+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
33f65d1c4bcc94ba767ba9020a336d9350b86c4912840df295f75cf099d6f939
|
|
| MD5 |
9920f509dd26b3fd8a0c4dffaf793e56
|
|
| BLAKE2b-256 |
342a19ac25b01bc4d26903eede82a1258a28743304ddbc513a3a8a0797c4f125
|
File details
Details for the file prexsyn_engine-1.0.0.dev1-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.
File metadata
- Download URL: prexsyn_engine-1.0.0.dev1-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
- Upload date:
- Size: 3.4 MB
- Tags: CPython 3.14, manylinux: glibc 2.27+ x86-64, manylinux: glibc 2.28+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f7cfc4abdf20057b8598599605e5784124ea099b86935271b21b26c06ac96074
|
|
| MD5 |
b2feb187216f449356260a394b8e4a78
|
|
| BLAKE2b-256 |
03f7b8524ba91c6808eb83d61057214cbdc1b9df1ad6805cf33aa2699e9f0b82
|
File details
Details for the file prexsyn_engine-1.0.0.dev1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.
File metadata
- Download URL: prexsyn_engine-1.0.0.dev1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
- Upload date:
- Size: 3.4 MB
- Tags: CPython 3.13, manylinux: glibc 2.27+ x86-64, manylinux: glibc 2.28+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4308442f26bffb6b7d6cca5af7e390786108ec16c77e258e7fd2c94d490ff446
|
|
| MD5 |
82768b1d42030ff34a5c007fe6233092
|
|
| BLAKE2b-256 |
37bbc963b9310cfe03bf02f3c4d3d60968f8ee9aaac71d68c4fd333efa45a89c
|
File details
Details for the file prexsyn_engine-1.0.0.dev1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.
File metadata
- Download URL: prexsyn_engine-1.0.0.dev1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
- Upload date:
- Size: 3.4 MB
- Tags: CPython 3.12, manylinux: glibc 2.27+ x86-64, manylinux: glibc 2.28+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
8bf2645f52883ce297aa8fd8b939308a1348e56aeb57dcf708194142cddcbda1
|
|
| MD5 |
4d1371ab25e60874e337b0ac3a5de42c
|
|
| BLAKE2b-256 |
bbda7c50ba11ca471b3674352be1cbaf3835e80bb9a05dcff2d25de7332707aa
|
File details
Details for the file prexsyn_engine-1.0.0.dev1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.
File metadata
- Download URL: prexsyn_engine-1.0.0.dev1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
- Upload date:
- Size: 3.4 MB
- Tags: CPython 3.11, manylinux: glibc 2.27+ x86-64, manylinux: glibc 2.28+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6c73abe1d87ff1eca92c6543b20ee9212fd0e4f204e3b10e910a324de76775dd
|
|
| MD5 |
d058977967f50a8de1a840ce8549f7f1
|
|
| BLAKE2b-256 |
ae27c0cd7e8ca988eb2e514da5c7cd127c5b622fd5cff39dc85e14eb4920823b
|
File details
Details for the file prexsyn_engine-1.0.0.dev1-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.
File metadata
- Download URL: prexsyn_engine-1.0.0.dev1-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
- Upload date:
- Size: 3.4 MB
- Tags: CPython 3.10, manylinux: glibc 2.27+ x86-64, manylinux: glibc 2.28+ x86-64
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0b128320e23e8177286407cad8feb43be4a4702313e7efdf369fc52dff869919
|
|
| MD5 |
c6b2a82ddf76da5d2e76562db6c32d0f
|
|
| BLAKE2b-256 |
b092f7519367f7406fc95d95a20579e0654e5848a80e10a615a2ab2ab6782693
|
