scholarly journals Reorganization energies of flexible organic molecules as a challenging target for machine learning enhanced virtual screening

2021 ◽  
Author(s):  
Ke Chen ◽  
Christian Kunkel ◽  
Karsten Reuter ◽  
Johannes T. Margraf
Keyword(s):  
Machine Learning ◽  
Virtual Screening ◽  
Organic Semiconductors ◽  
Organic Molecules ◽  
Predictive Accuracy ◽  
Molecular Design ◽  
Reorganization Energy ◽  
Charge Carrier Mobility ◽  
Design Rule ◽  
Reorganization Energies

The molecular reorganization energy $\lambda$ strongly influences the charge carrier mobility of organic semiconductors and is therefore an important target for molecular design. Machine learning (ML) models generally have the potential to strongly accelerate this design process (e.g. in virtual screening studies) by providing fast and accurate estimates of molecular properties. While such models are well established for simple properties (e.g. the atomization energy), $\lambda$ poses a significant challenge in this context. In this paper, we address the questions of how ML models for $\lambda$ can be improved and what their benefit is in high-throughput virtual screening (HTVS) studies. We find that, while improved predictive accuracy can be obtained relative to a semiempirical baseline model, the improvement in molecular discovery is somewhat marginal. In particular, the ML enhanced screenings are more effective in identifying promising candidates but lead to a less diverse sample. We further use substructure analysis to derive a general design rule for organic molecules with low $\lambda$ from the HTVS results.

scholarly journals Selecting Machine-Learning Scoring Functions for Structure-Based Virtual Screening

2020 ◽  
Author(s):  
Pedro Ballester
Keyword(s):  
Machine Learning ◽  
Drug Discovery ◽  
Virtual Screening ◽  
Predictive Accuracy ◽  
Scoring Function ◽  
3D Models ◽  
Large Datasets ◽  
Scoring Functions ◽  
Discovery Process ◽  
Drug Discovery Process

Interest in docking technologies has grown parallel to the ever increasing number and diversity of 3D models for macromolecular therapeutic targets. Structure-Based Virtual Screening (SBVS) aims at leveraging these experimental structures to discover the necessary starting points for the drug discovery process. It is now established that Machine Learning (ML) can strongly enhance the predictive accuracy of scoring functions for SBVS by exploiting large datasets from targets, molecules and their associations. However, with greater choice, the question of which ML-based scoring function is the most suitable for prospective use on a given target has gained importance. Here we analyse two approaches to select an existing scoring function for the target along with a third approach consisting in generating a scoring function tailored to the target. These analyses required discussing the limitations of popular SBVS benchmarks, the alternatives to benchmark scoring functions for SBVS and how to generate them or use them using freely-available software.

Theoretical Investigation of Structural Effects on the Charge Transfer Properties in Modified Phthalocyanines

MRS Advances ◽  
2015 ◽  
Vol 1 (7) ◽  
pp. 453-458 ◽  
Author(s):  
Patrick J. Dwyer ◽  
Stephen P. Kelty
Keyword(s):  
Organic Semiconductors ◽  
Electron Affinity ◽  
Density Functional ◽  
Reorganization Energy ◽  
High Electron ◽  
Optoelectronic Materials ◽  
Research Attention ◽  
Efficient Charge ◽  
Reorganization Energies ◽  
P Type

ABSTRACTFor efficient charge separation and charge transport in optoelectronic materials, small internal reorganization energies are desired. While many p-type organic semiconductors have been reported with low internal reorganization energies, few n-type materials with low reorganization energy are known. Metal phthalocyanines have long received extensive research attention in the field of organic device electronics due to their highly tunable electronic properties through modification of the molecular periphery. In this study, density functional theory (DFT) calculations are performed on a series of zinc-phthalocyanines (ZnPc) with various degrees of peripheral per-fluoroalkyl (-C3F7) modification. Introduction of the highly electron withdrawing groups on the periphery leads to a lowering in the energy of the molecular frontier orbitals as well as an increase in the electron affinity. Additionally, all molecules studies are found to be most stable in their anionic form, demonstrating their potential as n-type materials. However, the calculated internal reorganization energy slightly increases as a function of peripheral modification. By varying the degree of modification we develop a strategy for obtaining an optimal balance between low reorganization energy and high electron affinity for the development of novel n-type optoelectronic materials.

scholarly journals Selecting Machine-Learning Scoring Functions for Structure-Based Virtual Screening

2020 ◽  
Author(s):  
Pedro Ballester
Keyword(s):  
Machine Learning ◽  
Drug Discovery ◽  
Virtual Screening ◽  
Predictive Accuracy ◽  
Scoring Function ◽  
3D Models ◽  
Large Datasets ◽  
Scoring Functions ◽  
Discovery Process ◽  
Drug Discovery Process

Interest in docking technologies has grown parallel to the ever increasing number and diversity of 3D models for macromolecular therapeutic targets. Structure-Based Virtual Screening (SBVS) aims at leveraging these experimental structures to discover the necessary starting points for the drug discovery process. It is now established that Machine Learning (ML) can strongly enhance the predictive accuracy of scoring functions for SBVS by exploiting large datasets from targets, molecules and their associations. However, with greater choice, the question of which ML-based scoring function is the most suitable for prospective use on a given target has gained importance. Here we analyse two approaches to select an existing scoring function for the target along with a third approach consisting in generating a scoring function tailored to the target. These analyses required discussing the limitations of popular SBVS benchmarks, the alternatives to benchmark scoring functions for SBVS and how to generate them or use them using freely-available software.

scholarly journals Robust, high-performance n-type organic semiconductors

2020 ◽  
Vol 6 (18) ◽  
pp. eaaz0632 ◽  
Author(s):  
Toshihiro Okamoto ◽  
Shohei Kumagai ◽  
Eiji Fukuzaki ◽  
Hiroyuki Ishii ◽  
Go Watanabe ◽  
...  
Keyword(s):  
Organic Semiconductors ◽  
High Performance ◽  
Molecular Design ◽  
High Reliability ◽  
Atmospheric Stability ◽  
Charge Carrier Mobility ◽  
Electron System ◽  
Environmental Stability ◽  
High Electron ◽  
Molecular Features

Organic semiconductors (OSCs) are important active materials for the fabrication of next-generation organic-based electronics. However, the development of n-type OSCs lags behind that of p-type OSCs in terms of charge-carrier mobility and environmental stability. This is due to the absence of molecular designs that satisfy the requirements. The present study describes the design and synthesis of n-type OSCs based on challenging molecular features involving a π-electron core containing electronegative N atoms and substituents. The unique π-electron system simultaneously reinforces both electronic and structural interactions. The current n-type OSCs exhibit high electron mobilities with high reliability, atmospheric stability, and robustness against environmental and heat stresses and are superior to other existing n-type OSCs. This molecular design represents a rational strategy for the development of high-end organic-based electronics.

The influence of external electric fields on charge reorganization energy in organic semiconductors

2019 ◽  
Vol 55 (16) ◽  
pp. 2384-2387 ◽  
Author(s):  
Weicong Huang ◽  
Hu Shi ◽  
Hongguang Liu ◽  
Clémence Corminboeuf
Keyword(s):  
Electric Field ◽  
Organic Semiconductors ◽  
Electric Fields ◽  
Reorganization Energy ◽  
Ring Carbon ◽  
External Electric Fields ◽  
Anisotropic Character ◽  
Reorganization Energies

Charge reorganization energies (λ) of inter-ring carbon–carbon (IRCC) bond connected conjugated polycyclics are shown to exhibit an electric-field-driven anisotropic character.

scholarly journals Virtual Screening of Antitumor Inhibitors Targeting BRD4 Based on Machine Learning Methods

2021 ◽  
Author(s):  
Keliang Wu ◽  
Chenghua Zhang ◽  
Bing He ◽  
Huanxin Li ◽  
Shan Tang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Virtual Screening ◽  
Molecular Design ◽  
Random Forest Model ◽  
Learning Methods ◽  
Forest Model ◽  
Design And Synthesis ◽  
Machine Learning Methods ◽  
Dynamics Simulations

Abstract BRD4 is a hot antitumor target. In this study, three kinds of machine learning methods were used to establish classification models of BRD4 inhibitors, achieving satisfactory prediction performance. Through comparison, random forest model worked best, the parameters of which were also optimized. Then, the best random forest model was applied to perform virtual screening against ZINC database and a total of 89 potential compounds with BRD4 inhibitory activity were eventually identified. Further, seven molecules were chosen from the hits, and a docking calculation was carried out for each molecule, showing a strong interaction between ligand and BRD4. Subsequently, these molecules were evaluated by molecular dynamics simulations, all having certain binding stability. The results have proved the effectiveness of the developed models based on machine learning methods and the molecules filtered by virtual screening not only have a significant guiding in practice for the molecular design and synthesis, but also can provide great possibility for the discoveries and final approvals of anti-cancer drugs targeting BRD4.

Theoretical investigations of charge carrier transport in organic semiconductors of naphthalene bisimides N-substituted with alkoxyphenyl groups

2015 ◽  
Vol 93 (7) ◽  
pp. 740-748 ◽  
Author(s):  
Jun Yin ◽  
Kadali Chaitanya ◽  
Xue-Hai Ju
Keyword(s):  
Density Functional Theory ◽  
Charge Carrier ◽  
Organic Semiconductors ◽  
Carrier Mobility ◽  
Density Functional ◽  
Reorganization Energy ◽  
Charge Carrier Mobility ◽  
Transport Processes ◽  
Functional Theory ◽  
Transfer Integral

Three novel alkoxyphenyl N-substituted naphthalene bisimide derivatives, N,N′-bis(4-n-butoxyphenyl)-1,8:4,5-naphthalenetetracarboxylic (NBI1), N,N′-bis(4-n-hexyloxyphenyl)-1,8:4,5-naphthalenetetracarboxylic (NBI2), and N,N′-bis(4-n-octyloxyphenyl)-1,8:4,5-naphthalenetetracarboxylic (NBI3) as potential organic semiconductors, have been investigated using density functional theory calculations coupled with the incoherent charge-hopping model at the molecular and crystal levels. The calculated results demonstrate that the low-lying and delocalized LUMOs and larger adiabatic electron affinities of these compounds are beneficial to their stability when acting as n-type organic semiconductors. The reorganization energy and transfer integral can significantly influence the charge carrier mobility. The compounds featured with the small reorganization energy and large transfer integral have relatively high charge mobilities. The electron coupling among the dominant hopping pathways indicates that the charge-transport processes happen in the parallel dimer of neighboring molecules with π–π interaction. The investigation of the angle dependence of charge carrier mobility showed that both NBI1 and NBI3 crystals exhibit remarkable anisotropic charge transporting behaviors. The calculated absorption spectra by the time-dependent density functional theory revealed that the strongest absorption peaks in the visible region are assigned to the π → π* transition and these peaks are regulated by the transitions of HOMO → LUMO. The calculated electron mobilities of NBI1, NBI2, and NBI3 are 0.0365, 0.0312, and 0.0801 cm2 V–1 s–1, respectively, indicating that these compounds are suitable for n-type organic semiconductors.

scholarly journals Machine Learning to Accelerate Screening for Marcus Reorganization Energies

2021 ◽  
Author(s):  
Omri Abaarbanel ◽  
Geoffrey Hutchison
Keyword(s):  
Machine Learning ◽  
Charge Transport ◽  
Density Functional ◽  
Activation Barrier ◽  
Reorganization Energy ◽  
Transport Parameters ◽  
Light Emitting Devices ◽  
Wide Range ◽  
Important Challenge ◽  
Reorganization Energies

Understanding and predicting the charge transport properties of π-conjugated materials is an important challenge for designing new organic electronic applications, including solar cells, plastic transistors, light-emitting devices, and chemical sensors. A key component of the hopping mechanism of charge transfer in these materials is the Marcus reorganization energy, which serves as an activation barrier to hole or electron transfer. While modern density functional methods have proven to accurately predict trends in intramolecular reorganization energy, such calculations are computationally expensive. In this work, we outline active machine learning methods to predict computed intramolecular reorganization energies of a wide range of polythiophenes and their use towards screening new compounds with low internal reorganization energies. Our models have an overall root mean square error of ±0.113 eV, but a much smaller RMSE of only ±0.036 eV on the new screening set. Since the larger error derives from high-reorganization energy compounds, the new method is highly effective to screen for compounds with potentially efficient charge transport parameters.

scholarly journals Machine Learning to Accelerate Screening for Marcus Reorganization Energies

2021 ◽  
Author(s):  
Omri Abaarbanel ◽  
Geoffrey Hutchison
Keyword(s):  
Machine Learning ◽  
Charge Transport ◽  
Density Functional ◽  
Activation Barrier ◽  
Reorganization Energy ◽  
Transport Parameters ◽  
Light Emitting Devices ◽  
Wide Range ◽  
Important Challenge ◽  
Reorganization Energies

Understanding and predicting the charge transport properties of π-conjugated materials is an important challenge for designing new organic electronic applications, including solar cells, plastic transistors, light-emitting devices, and chemical sensors. A key component of the hopping mechanism of charge transfer in these materials is the Marcus reorganization energy, which serves as an activation barrier to hole or electron transfer. While modern density functional methods have proven to accurately predict trends in intramolecular reorganization energy, such calculations are computationally expensive. In this work, we outline active machine learning methods to predict computed intramolecular reorganization energies of a wide range of polythiophenes and their use towards screening new compounds with low internal reorganization energies. Our models have an overall root mean square error of ±0.113 eV, but a much smaller RMSE of only ±0.036 eV on the new screening set. Since the larger error derives from high-reorganization energy compounds, the new method is highly effective to screen for compounds with potentially efficient charge transport parameters.

scholarly journals Handling Imbalance Classification Virtual Screening Big Data Using Machine Learning Algorithms

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Sahar K. Hussin ◽  
Salah M. Abdelmageid ◽  
Adel Alkhalil ◽  
Yasser M. Omar ◽  
Mahmoud I. Marie ◽  
...  
Keyword(s):  
Machine Learning ◽  
Virtual Screening ◽  
Predictive Accuracy ◽  
Specific Protein ◽  
Machine Learning Algorithms ◽  
Large Set ◽  
High Dimensions ◽  
Screening Process ◽  
Screening Accuracy ◽  
Critical Process

Virtual screening is the most critical process in drug discovery, and it relies on machine learning to facilitate the screening process. It enables the discovery of molecules that bind to a specific protein to form a drug. Despite its benefits, virtual screening generates enormous data and suffers from drawbacks such as high dimensions and imbalance. This paper tackles data imbalance and aims to improve virtual screening accuracy, especially for a minority dataset. For a dataset identified without considering the data’s imbalanced nature, most classification methods tend to have high predictive accuracy for the majority category. However, the accuracy was significantly poor for the minority category. The paper proposes a K-mean algorithm coupled with Synthetic Minority Oversampling Technique (SMOTE) to overcome the problem of imbalanced datasets. The proposed algorithm is named as KSMOTE. Using KSMOTE, minority data can be identified at high accuracy and can be detected at high precision. A large set of experiments were implemented on Apache Spark using numeric PaDEL and fingerprint descriptors. The proposed solution was compared to both no-sampling method and SMOTE on the same datasets. Experimental results showed that the proposed solution outperformed other methods.

Sign in / Sign up

Export Citation Format

Share Document