pkai 0.0.4

A fast and interpretable deep learning approach to accurate electrostatics-driven pKa prediction

pKAI

A fast and interpretable deep learning approach to accurate electrostatics-driven pKa prediction

@article{pkai,
author = {Reis, Pedro B. P. S. and Vila-Viçosa, Diogo and Bertolini, Marco and Montanari, Floriane and Machuqueiro, Miguel and Clevert, Djork-Arné},
title = {pKAI: A fast and interpretable deep learning approach to accurate electrostatics-driven pKa prediction},
note = {in preparation}
}

Installation & Basic Usage

We recommend installing pKAI on a conda enviroment.

conda env create -f environment.yml
conda activate pKAI

python3 -m pip install git+https://github.com/bayer-science-for-a-better-life/pKAI.git

pKAI <pdbfile>

It can also be used as python function,

from pKAI import pKAI

pks = pKAI(pdb)

where each element of the returned list is a tuple of size 4. (chain, resnumb, resname, pk)

pKAI+ vs pKAI models

pKAI+ (default model) aims to predict experimental pK_a values from a single conformation. To do such, the interactions characterized in the input structure are given less weight and, as a consequence, the predictions are closer to the pK_a values of the residues in water. This effect is comparable to an increase in the dielectric constant of the protein in Poisson-Boltzmann models. In these models, the dielectric constant tries to capture, among others, electronic polarization and side-chain reorganization. When including conformational sampling explicitly, one should use a lower value for the dielectric constant of the protein. Likewise, one should use pKAI -- instead of pKAI+ -- as in this model there is no penalization of the interactions' impact on the predicted pK_a values.

tl;dr version

• use pKAI+ for pK_a predictions arising from a single structure
• use pKAI for pK_a predictions arising from multiple conformations

Change the model to be used in the calculation by evoking the model argument:

pKAI <pdbfile> --model pKAI

Benchmark

Performed on 927 experimental values taken from the PKAD database.

Method	RMSE	MAE
Thurlkill1	1.02	0.70
PROPKA2	1.04	0.69
PypKa3	0.98	0.66
pKAI+	0.91	0.59

[1] Thurlkill, Richard L et al. “pK values of the ionizable groups of proteins.” doi:10.1110/ps.051840806

[2] Olsson, Mats H M et al. “PROPKA3: Consistent Treatment of Internal and Surface Residues in Empirical pKa Predictions.” doi:10.1021/ct100578z

[3] Reis, Pedro B P S et al. “PypKa: A Flexible Python Module for Poisson-Boltzmann-Based pKa Calculations.” doi:10.1021/acs.jcim.0c00718

License

This source code is licensed under the MIT license found in the LICENSE file in the root directory of this source tree.

Contacts

Please submit a github issue to report bugs and to request new features. Alternatively, you may email the developer directly.