3D Deep Learning for Biological Function Prediction from Physical Fields

Abstract

Predicting the biological function of molecules, be it proteins or drug-like compounds, from their atomic structure is an important and long-standing problem. Function is dictated by structure, since it is by spatial interactions that molecules interact with each other, both in terms of steric complementarity, as well as intermolecular forces. Thus, the electron density field and electrostatic potential field of a molecule contain the "raw fingerprint" of how this molecule can fit to binding partners. In this paper, we show that deep learning can predict biological function of molecules directly from their raw 3D approximated electron density and electrostatic potential fields. Protein function based on EC numbers is predicted from the approximated electron density field. In another experiment, the activity of small molecules is predicted with quality comparable to state-of-the-art descriptor-based methods. We propose several alternative computational models for the GPU with different memory and runtime requirements for different sizes of molecules and of databases. We also propose application-specific multi-channel data representations. With future improvements of training datasets and neural network settings in combination with complementary information sources (sequence, genomic context, expression level), deep learning can be expected to show its generalization power and revolutionize the field of molecular function prediction.

graphDelta: MPNN Scoring Function for the Affinity Prediction of Protein–Ligand Complexes

“…For example, one can calculate interactions with a probe atom to construct 3D molecular field or use some physicochemical or DFT (3D electron density) calculations as 3D filed representations. 31,35 Both of these approaches have limitations: atom-to-channel representation leads to dramatic increase in the number of input channels, which are crucial for memory consumption. It is also inefficient because many channels are empty or sparse.…”

TF3P: Three-dimensional Force Fields Fingerprint Learned by Deep Capsular Network

“…Besides fingerprints, Gaussian-based representation used by commercial software ROCS 17 is another vivid example that strengthen this argument. When it further comes to voxelized representation 18,19 , it is a common practice to integrate this representation with supervised convolutional DNN and has demonstrated promising results on the prediction of the biological target or binding affinity for small molecule [20][21][22][23][24][25] . Despite this, there is no 3D fingerprint learned by DNN reported thus far.…”