improved DOCKing

the main thrust of this release adds new support for DOCK6 receptor and DOCKing parameters. The remainder of the changes is mostly logical improvements in the codebase that will (unfortunately) break some client code. The CalculationData has been renamed to a Simulation and the CalculationRunner.prepare_and_run() methods now return the Result object rather than the full Simulation (as was done previously. This will speed up task distribution for virtual screening purposes but now loses the added information of the prepared_ligand and prepared_receptor filenames (which will be lost forever if utilizing the VirtualScreen interface.) We'll look back into adding this information back, but we don't think any users were actually taking advantage of this information.

Additionally, a full VirtualScreen used to crash when handed an invalid molecule. Theoretically, users could always prevent this via pre-filtering what molecules are passed, but now the returned score array just handles them silently and indicates nan values in their place. Note that nan could also indicate that the molecule failed during simulation itself, which means it could be attempted again and possibly succeed (about 1% of molecules randomly fail.) Now, however a nan could mean one of those two things. If this distinction is important, you can do the following:

import numpy as np
from rdkit import Chem
import pyscreener as ps

# smis: Iterable[str]
vs = ps.virtual_screen(...)
s = vs(smis)
failed_idxs = np.arange(len(s))[np.isnan(s)]
invalid_mol_idxs = set(i for i in failed_idxs if Chem.MolFromSmiles(smis[i]) is None)
failed_sim_idxs = set(failed_idxs) -inavlid_mol_idxs

happy screening!

joss-release

What's Changed

• Iss/entry points hotfix by @davidegraff in #14
• Update CI Badge by @mikemhenry in #27
• Fix codecov badge by @mikemhenry in #28
• Feat/versioning by @davidegraff in #30
• Iss/linting by @davidegraff in #31
• Feat/gh templates by @davidegraff in #32
• add examples by @davidegraff in #33
• fix coverage by @davidegraff in #34

New Contributors

• @mikemhenry made their first contribution in #27

Full Changelog: v1.1.0...v1.1.1

pyscreener-v1.1.0

A few minor improvements from the initial release:

• *DockingRunner.prepare_from_smi() now use RDKit geometry optimization instead of OpenBabel (#12)
• SMILES can now be supplied to a LigandSupply to encapsulate all of your molecules in one object. Previously, SMILES strings would have to be passed to a VirtualScreen separate from LigandSupply.ligands, but now you can pass in your SMILES strings to LigandSupply.__init__() via the smis keyword argument. NOTE: this change breaks backwards compatibility for positional args (#12)
• the addition of entry point scripts. Pyscreener can now be invoked directly on the command line via pyscreener, rather than having to clone this repo and run python run.py. There is also an additional pyscreener-check script to see if your environment is configured properly for your desired screen type and input metadata (#13). You can still use the --smoke-test arg, but pyscreener-check uses positional arguments on the command line rather than flags.

What's Changed

• Feature/smiles input lig supply by @davidegraff in #12
• Feature/entry point scripts by @davidegraff in #13

Full Changelog: v1.0.0...v1.1.0

pyscreener v1 !

We're happy to release the first official version of pyscreener!

Pyscreener was initially developed as a small research tool for active learning, but a lot of development has taken place over the last few months to completely revamp the package into a more fully featured and maintainable python package for pythonic docking/simulation calls! The high-level usage of pyscreener remains the same (in that the core functionality defines an object which maps a SMILES string to a scalar result from a simulation,) but the entire object model underlying the package has now changed to fundamentally separate the data (i.e., simulation parameters/results) from objects that actually conduct simulations (e.g., Runners). While some features of v1.0 are not fully completed, these are more for bookkeeping, like testing and a robust CI.

No major feature updates are planned for the foreseeable future, so we hope you find this useful as-is!

pyscreener alpha

We never formally "released" the alpha version of pyscreener that was open-sourced at the same time as MolPAL. While we believe the completely refactored version 1 is far superior to this original alpha version, we are adding a release tag for this version for the sake of posterity so that those who have developed using the old version of the codebase can still access it.