Towards Efficient Generation, Correction and Properties Control of Unique Drug-like Structures

2019 ◽  
Author(s):  
Maksym Druchok ◽  
Dzvenymyra Yarish ◽  
Oleksandr Gurbych ◽  
Mykola Maksymenko
Keyword(s):  
Deep Neural Network ◽  
Molecular Descriptors ◽  
Material Design ◽  
Molecular Structures ◽  
The Novel ◽  
Efficient Design ◽  
Continuous Space ◽  
Multi Stage ◽  
Synthetic Accessibility ◽  
Novel Structures

<div> <div> <div> <p>Efficient design and screening of the novel molecules is a major challenge in drug and material design. This report focuses on a multi-stage pipeline in which several deep neural network (DNN) models are combined to map discrete molecular representations into continuous vector space to later generate from it new molecular structures with desired properties. Here the Attention-based Sequence-to-Sequence model is added to “spellcheck” and correct generated structures while the oversampling in the continuous space allows generating candidate structures with desired distribution for properties and molecular descriptors even for small reference datasets. We further use computer simulation to validate the desired properties in the numerical experiment. With the focus on the drug design, such pipeline allows generating novel structures with control of SAS (Synthetic Accessibility Score) and a series of ADME metrics that assess the drug-likeliness. </p> </div> </div> </div>

Towards Efficient Generation, Correction and Properties Control of Unique Drug-like Structures

2019 ◽  
Author(s):  
Maksym Druchok ◽  
Dzvenymyra Yarish ◽  
Oleksandr Gurbych ◽  
Mykola Maksymenko
Keyword(s):  
Deep Neural Network ◽  
Molecular Descriptors ◽  
Material Design ◽  
Molecular Structures ◽  
The Novel ◽  
Efficient Design ◽  
Continuous Space ◽  
Multi Stage ◽  
Synthetic Accessibility ◽  
Novel Structures

<div> <div> <div> <p>Efficient design and screening of the novel molecules is a major challenge in drug and material design. This report focuses on a multi-stage pipeline in which several deep neural network (DNN) models are combined to map discrete molecular representations into continuous vector space to later generate from it new molecular structures with desired properties. Here the Attention-based Sequence-to-Sequence model is added to “spellcheck” and correct generated structures while the oversampling in the continuous space allows generating candidate structures with desired distribution for properties and molecular descriptors even for small reference datasets. We further use computer simulation to validate the desired properties in the numerical experiment. With the focus on the drug design, such pipeline allows generating novel structures with control of SAS (Synthetic Accessibility Score) and a series of ADME metrics that assess the drug-likeliness. </p> </div> </div> </div>

Higher-Order and Mixed Discrete Derivatives such as a Novel Graph- Theoretical Invariant for Generating New Molecular Descriptors

2019 ◽  
Vol 19 (11) ◽  
pp. 944-956 ◽  
Author(s):  
Oscar Martínez-Santiago ◽  
Yovani Marrero-Ponce ◽  
Ricardo Vivas-Reyes ◽  
Mauricio E.O. Ugarriza ◽  
Elízabeth Hurtado-Rodríguez ◽  
...  
Keyword(s):  
Molecular Descriptors ◽  
3D Qsar ◽  
Higher Order ◽  
Molecular Structures ◽  
Qsar Modeling ◽  
Statistical Parameters ◽  
Molecular Graphs ◽  
New Family ◽  
Mixed Derivatives ◽  
Discrete Derivative

Background: Recently, some authors have defined new molecular descriptors (MDs) based on the use of the Graph Discrete Derivative, known as Graph Derivative Indices (GDI). This new approach about discrete derivatives over various elements from a graph takes as outset the formation of subgraphs. Previously, these definitions were extended into the chemical context (N-tuples) and interpreted in structural/physicalchemical terms as well as applied into the description of several endpoints, with good results. Objective: A generalization of GDIs using the definitions of Higher Order and Mixed Derivative for molecular graphs is proposed as a generalization of the previous works, allowing the generation of a new family of MDs. Methods: An extension of the previously defined GDIs is presented, and for this purpose, the concept of Higher Order Derivatives and Mixed Derivatives is introduced. These novel approaches to obtaining MDs based on the concepts of discrete derivatives (finite difference) of the molecular graphs use the elements of the hypermatrices conceived from 12 different ways (12 events) of fragmenting the molecular structures. The result of applying the higher order and mixed GDIs over any molecular structure allows finding Local Vertex Invariants (LOVIs) for atom-pairs, for atoms-pairs-pairs and so on. All new families of GDIs are implemented in a computational software denominated DIVATI (acronym for Discrete DeriVAtive Type Indices), a module of KeysFinder Framework in TOMOCOMD-CARDD system. Results: QSAR modeling of the biological activity (Log 1/K) of 31 steroids reveals that the GDIs obtained using the higher order and mixed GDIs approaches yield slightly higher performance compared to previously reported approaches based on the duplex, triplex and quadruplex matrix. In fact, the statistical parameters for models obtained with the higher-order and mixed GDI method are superior to those reported in the literature by using other 0-3D QSAR methods. Conclusion: It can be suggested that the higher-order and mixed GDIs, appear as a promissory tool in QSAR/QSPRs, similarity/dissimilarity analysis and virtual screening studies.

Ultrasonic Torsion Welding of Aging Resistant Al/CFRP Joints - Concepts, Mechanical and Microstructural Properties

2017 ◽  
Vol 742 ◽  
pp. 395-400 ◽  
Author(s):  
Florian Staab ◽  
Frank Balle ◽  
Johannes Born
Keyword(s):  
Mechanical Properties ◽  
Process Parameters ◽  
Materials Science ◽  
Dissimilar Materials ◽  
Material Design ◽  
Ultrasonic Welding ◽  
Fatigue Properties ◽  
Aviation Industry ◽  
Efficient Design ◽  
Engineering Structures

Multi-material-design offers high potential for weight saving and optimization of engineering structures but inherits challenges as well, especially robust joining methods and long-term properties of hybrid structures. The application of joining techniques like ultrasonic welding allows a very efficient design of multi-material-components to enable further use of material specific advantages and are superior concerning mechanical properties.The Institute of Materials Science and Engineering of the University of Kaiserslautern (WKK) has a long-time experience on ultrasonic welding of dissimilar materials, for example different kinds of CFRP, light metals, steels or even glasses and ceramics. The mechanical properties are mostly optimized by using ideal process parameters, determined through statistical test planning methods.This gained knowledge is now to be transferred to application in aviation industry in cooperation with CTC GmbH and Airbus Operations GmbH. Therefore aircraft-related materials are joined by ultrasonic welding. The applied process parameters are recorded and analyzed in detail to be interlinked with the resulting mechanical properties of the hybrid joints. Aircraft derived multi-material demonstrators will be designed, manufactured and characterized with respect to their monotonic and fatigue properties as well as their resistance to aging.

scholarly journals Thermodynamically stable [4 + 2] cycloadducts of lanthanum-encapsulated endohedral metallofullerenes

2014 ◽  
Vol 10 ◽  
pp. 714-721 ◽  
Author(s):  
Yuta Takano ◽  
Yuki Nagashima ◽  
M Ángeles Herranz ◽  
Nazario Martín ◽  
Takeshi Akasaka
Keyword(s):  
Thermal Stability ◽  
Material Science ◽  
Molecular Structures ◽  
Spectroscopic Methods ◽  
Dynamic Nmr ◽  
The Novel ◽  
Endohedral Metallofullerenes ◽  
Derivatives Of ◽  
Paramagnetic Properties

The [4 + 2] cycloaddition of o-quinodimethanes, generated in situ from the sultine 4,5-benzo-3,6-dihydro-1,2-oxathiin 2-oxide and its derivative, to La metal-encapsulated fullerenes, La2@C80 or La@C82, afforded the novel derivatives of endohedral metallofullerenes (3a,b, 4a,b and 5b). Molecular structures of the resulting compounds were elucidated using spectroscopic methods such as MALDI–TOF mass, optical absorption, and NMR spectroscopy. The [4 + 2] adducts of La2@C80 (3a,b, and 4a,b) and La@C82 (5b), respectively, retain diamagnetic and paramagnetic properties, as confirmed by EPR spectroscopy. Dynamic NMR measurements of 4a at various temperatures demonstrated the boat-to-boat inversions of the addend. In addition, 5b revealed remarkable thermal stability in comparison with the reported [4 + 2] cycloadduct of pentamethylcyclopentadiene and La@C82 (6). These findings demonstrate the utility of sultines to afford thermodynamically stable endohedral metallofullerene derivatives for the use in material science.

scholarly journals Materials Precursor Score: Modelling Chemists' Intuition for the Synthetic Accessibility of Porous Organic Cages

2021 ◽  
Author(s):  
Steven Bennett ◽  
Filip Szczypiński ◽  
Lukas Turcani ◽  
Michael Briggs ◽  
Rebecca L. Greenaway ◽  
...  
Keyword(s):  
Organic Molecules ◽  
Class Imbalance ◽  
Computational Prediction ◽  
Material Development ◽  
Computational Screening ◽  
Machine Learning Model ◽  
Synthetic Accessibility ◽  
Internal Cavities ◽  
Computational Discovery ◽  
Novel Structures

<div>Computation is increasingly being used to try to accelerate the discovery of new materials. One specific example of this is porous molecular materials, specifically porous organic cages, where the porosity of the materials predominantly comes from the internal cavities of the molecules themselves. The computational discovery of novel structures with useful properties is currently hindered by the difficulty in transitioning from a computational prediction to synthetic realisation. Attempts at experimental validation are often time-consuming, expensive and, frequently, the key bottleneck of material discovery. In this work, we developed a computational screening workflow for porous molecules that includes consideration of the synthetic difficulty of material precursors, aimed at easing the transition between computational prediction and experimental realisation. We trained a machine learning model by first collecting data on 12,553 molecules categorised either as `easy-to-synthesise' or `difficult-to-synthesise' by expert chemists with years of experience in organic synthesis. We used an approach to address the class imbalance present in our dataset, producing a binary classifier able to categorise easy-to-synthesise molecules with few false positives. We then used our model during computational screening for porous organic molecules to bias towards precursors whose easier synthesis requirements would make them promising candidates for experimental realisation and material development. We found that even by limiting precursors to those that are easier-to-synthesise, we are still able to identify cages with favourable, and even some rare, properties. </div>

scholarly journals Some Eccentricity-Based Topological Indices and Polynomials of Poly(EThyleneAmidoAmine) (PETAA) Dendrimers

Processes ◽  
2019 ◽  
Vol 7 (7) ◽  
pp. 433 ◽  
Author(s):  
Jialin Zheng ◽  
Zahid Iqbal ◽  
Asfand Fahad ◽  
Asim Zafar ◽  
Adnan Aslam ◽  
...  
Keyword(s):  
Molecular Descriptors ◽  
Molecular Graph ◽  
Topological Indices ◽  
Molecular Structures ◽  
Connectivity Index ◽  
Connectivity Indices ◽  
Numerical Invariants ◽  
Explicit Representations ◽  
Pharmaceutical Properties

Topological indices have been computed for various molecular structures over many years. These are numerical invariants associated with molecular structures and are helpful in featuring many properties. Among these molecular descriptors, the eccentricity connectivity index has a dynamic role due to its ability of estimating pharmaceutical properties. In this article, eccentric connectivity, total eccentricity connectivity, augmented eccentric connectivity, first Zagreb eccentricity, modified eccentric connectivity, second Zagreb eccentricity, and the edge version of eccentric connectivity indices, are computed for the molecular graph of a PolyEThyleneAmidoAmine (PETAA) dendrimer. Moreover, the explicit representations of the polynomials associated with some of these indices are also computed.

Sign in / Sign up

Export Citation Format

Share Document