skip to main content


Title: A machine-learning-assisted study of the permeability of small drug-like molecules across lipid membranes
Study of the permeability of small organic molecules across lipid membranes plays a significant role in designing potential drugs in the field of drug discovery. Approaches to design promising drug molecules have gone through many stages, from experiment-based trail-and-error approaches, to the well-established avenue of the quantitative structure–activity relationship, and currently to the stage guided by machine learning (ML) and artificial intelligence techniques. In this work, we present a study of the permeability of small drug-like molecules across lipid membranes by two types of ML models, namely the least absolute shrinkage and selection operator (LASSO) and deep neural network (DNN) models. Molecular descriptors and fingerprints are used for featurization of organic molecules. Using molecular descriptors, the LASSO model uncovers that the electro-topological, electrostatic, polarizability, and hydrophobicity/hydrophilicity properties are the most important physical properties to determine the membrane permeability of small drug-like molecules. Additionally, with molecular fingerprints, the LASSO model suggests that certain chemical substructures can significantly affect the permeability of organic molecules, which closely connects to the identified main physical properties. Moreover, the DNN model using molecular fingerprints can help develop a more accurate mapping between molecular structures and their membrane permeability than LASSO models. Our results provide deep understanding of drug–membrane interactions and useful guidance for the inverse molecular design of drug-like molecules. Last but not least, while the current focus is on the permeability of drug-like molecules, the methodology of this work is general and can be applied for other complex physical chemistry problems to gain molecular insights.  more » « less
Award ID(s):
1755779
NSF-PAR ID:
10211812
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
Physical Chemistry Chemical Physics
Volume:
22
Issue:
35
ISSN:
1463-9076
Page Range / eLocation ID:
19687 to 19696
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    Antibiotic discovery has experienced a severe slowdown in terms of discovery of new candidates. In vitro screening methods using phospholipids to model the bacterial membrane provide a route to identify molecules that specifically disrupt bacterial membranes causing cell death. Thanks to the electrically insulating properties of the major component of the cell membrane, phospholipids, electronic devices are highly suitable transducers of membrane disruption. The organic electrochemical transistor (OECT) is a highly sensitive ion‐to‐electron converter. Here, the OECT is used as a transducer of the permeability of a lipid monolayer (ML) at a liquid:liquid interface, designed to read out changes in ion flux caused by compounds that interact with, and disrupt, lipid assembly. This concept is illustrated using the well‐documented antibiotic Polymixin B and the highly sensitive quantitation of permeability of the lipid ML induced by two novel recently described antibacterial amine‐based oligothioetheramides is shown, highlighting molecular scale differences in their disruption capabilities. It is anticipated that this platform has the potential to play a role in front‐line antimicrobial compound design and characterization thanks to the compatibility of semiconductor microfabrication technology with high‐throughput readouts.

     
    more » « less
  2. Abstract

    Interatomic potentials derived with Machine Learning algorithms such as Deep-Neural Networks (DNNs), achieve the accuracy of high-fidelity quantum mechanical (QM) methods in areas traditionally dominated by empirical force fields and allow performing massive simulations. Most DNN potentials were parametrized for neutral molecules or closed-shell ions due to architectural limitations. In this work, we propose an improved machine learning framework for simulating open-shell anions and cations. We introduce the AIMNet-NSE (Neural Spin Equilibration) architecture, which can predict molecular energies for an arbitrary combination of molecular charge and spin multiplicity with errors of about 2–3 kcal/mol and spin-charges with error errors ~0.01e for small and medium-sized organic molecules, compared to the reference QM simulations. The AIMNet-NSE model allows to fully bypass QM calculations and derive the ionization potential, electron affinity, and conceptual Density Functional Theory quantities like electronegativity, hardness, and condensed Fukui functions. We show that these descriptors, along with learned atomic representations, could be used to model chemical reactivity through an example of regioselectivity in electrophilic aromatic substitution reactions.

     
    more » « less
  3. Organic molecules and polymers have a broad range of applications in biomedical, chemical, and materials science fields. Traditional design approaches for organic molecules and polymers are mainly experimentally-driven, guided by experience, intuition, and conceptual insights. Though they have been successfully applied to discover many important materials, these methods are facing significant challenges due to the tremendous demand of new materials and vast design space of organic molecules and polymers. Accelerated and inverse materials design is an ideal solution to these challenges. With advancements in high-throughput computation, artificial intelligence (especially machining learning, ML), and the growth of materials databases, ML-assisted materials design is emerging as a promising tool to flourish breakthroughs in many areas of materials science and engineering. To date, using ML-assisted approaches, the quantitative structure property/activity relation for material property prediction can be established more accurately and efficiently. In addition, materials design can be revolutionized and accelerated much faster than ever, through ML-enabled molecular generation and inverse molecular design. In this perspective, we review the recent progresses in ML-guided design of organic molecules and polymers, highlight several successful examples, and examine future opportunities in biomedical, chemical, and materials science fields. We further discuss the relevant challenges to solve in order to fully realize the potential of ML-assisted materials design for organic molecules and polymers. In particular, this study summarizes publicly available materials databases, feature representations for organic molecules, open-source tools for feature generation, methods for molecular generation, and ML models for prediction of material properties, which serve as a tutorial for researchers who have little experience with ML before and want to apply ML for various applications. Last but not least, it draws insights into the current limitations of ML-guided design of organic molecules and polymers. We anticipate that ML-assisted materials design for organic molecules and polymers will be the driving force in the near future, to meet the tremendous demand of new materials with tailored properties in different fields. 
    more » « less
  4. Abstract

    Cell membranes are fundamental for cellular function as they protect the cell and control passage in and out of the cell. Despite their clear significance, cell membranes are often difficult to study, due to their complexity and the lack of available technologies to interface with them and transduce their functions. Overcoming this complexity by developing simple, reductionist models can facilitate their study. Indeed, lipid layers represent a simplified yet representative model for a cell membrane. Lipid layers are highly insulating, a property that is directly affected by changes in lipid packing or membrane fluidity. Such physical changes in the membrane models can be characterized by coupling them with an electronic transducer. Herein, a lipid monolayer that is stabilized between two immiscible solvents is integrated with an organic electrochemical transistor, which is capable of operating in a biphasic solvent mixture. The platform is used to evaluate how lidocaine, a widely used anesthetic the working mechanism of which is still a matter of debate, interacts with the cell membrane. The present study provides evidence that the anesthetic directly interacts with the lipids in the membrane, affecting their packing and therefore the monolayer permeability. The proposed platform provides an elegant solution for studying compound–membrane interactions.

     
    more » « less
  5. The majority of bioactive molecules act on membrane proteins or intracellular targets and therefore needs to partition into or cross biological membranes. Natural products often exhibit lipid modifications to facilitate critical molecule–membrane interactions, and in many cases their bioactivity is markedly reduced upon removal of a lipid group. However, despite its importance in nature, lipid-conjugation of small molecules is not commonly used in chemical biology and medicinal chemistry, and the effect of such conjugation has not been systematically studied. To understand the composition of lipids found in natural products, we carried out a chemoinformatic characterization of the “natural product lipidome”. According to this analysis, lipidated natural products predominantly contain saturated medium-chain lipids (MCLs), which are significantly shorter than the long-chain lipids (LCLs) found in membranes and lipidated proteins. To study the usefulness of such modifications in probe design, we systematically explored the effect of lipid conjugation on five different small molecule chemotypes and find that permeability, cellular retention, subcellular localization, and bioactivity can be significantly modulated depending on the type of lipid tail used. We demonstrate that MCL conjugation can render molecules cell-permeable and modulate their bioactivity. With all explored chemotypes, MCL-conjugates consistently exhibited superior uptake or bioactivity compared to LCL-conjugates and either comparable or superior uptake or bioactivity to short-chain lipid (SCL)-conjugates. Together, our findings suggest that conjugation of small molecules with MCLs could be a powerful strategy for the design of probes and drugs. 
    more » « less