In silico material design for OLEDs realizing very fast reverse intersystem crossing

2020 ◽  
Author(s):  
Hironori Kaji
Keyword(s):  
In Silico ◽  
Material Design ◽  
Intersystem Crossing

Enalos Suite of Tools: Enhancing Cheminformatics and Nanoinfor - matics through KNIME

2020 ◽  
Vol 27 (38) ◽  
pp. 6523-6535 ◽  
Author(s):  
Antreas Afantitis ◽  
Andreas Tsoumanis ◽  
Georgia Melagraki
Keyword(s):  
Data Analysis ◽  
Virtual Screening ◽  
In Silico ◽  
Model Development ◽  
In Silico Analysis ◽  
Material Design ◽  
Efficient Solutions ◽  
Biological Data ◽  
Cost Efficient ◽  
Silico Analysis

Drug discovery as well as (nano)material design projects demand the in silico analysis of large datasets of compounds with their corresponding properties/activities, as well as the retrieval and virtual screening of more structures in an effort to identify new potent hits. This is a demanding procedure for which various tools must be combined with different input and output formats. To automate the data analysis required we have developed the necessary tools to facilitate a variety of important tasks to construct workflows that will simplify the handling, processing and modeling of cheminformatics data and will provide time and cost efficient solutions, reproducible and easier to maintain. We therefore develop and present a toolbox of >25 processing modules, Enalos+ nodes, that provide very useful operations within KNIME platform for users interested in the nanoinformatics and cheminformatics analysis of chemical and biological data. With a user-friendly interface, Enalos+ Nodes provide a broad range of important functionalities including data mining and retrieval from large available databases and tools for robust and predictive model development and validation. Enalos+ Nodes are available through KNIME as add-ins and offer valuable tools for extracting useful information and analyzing experimental and virtual screening results in a chem- or nano- informatics framework. On top of that, in an effort to: (i) allow big data analysis through Enalos+ KNIME nodes, (ii) accelerate time demanding computations performed within Enalos+ KNIME nodes and (iii) propose new time and cost efficient nodes integrated within Enalos+ toolbox we have investigated and verified the advantage of GPU calculations within the Enalos+ nodes. Demonstration data sets, tutorial and educational videos allow the user to easily apprehend the functions of the nodes that can be applied for in silico analysis of data.

scholarly journals Masked graph modeling for molecule generation

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Omar Mahmood ◽  
Elman Mansimov ◽  
Richard Bonneau ◽  
Kyunghyun Cho
Keyword(s):  
Drug Discovery ◽  
In Silico ◽  
De Novo ◽  
Graph Model ◽  
Material Design ◽  
Challenging Problem ◽  
Conditional Distributions ◽  
Trade Off ◽  
Graph Modeling ◽  
Different Parts

AbstractDe novo, in-silico design of molecules is a challenging problem with applications in drug discovery and material design. We introduce a masked graph model, which learns a distribution over graphs by capturing conditional distributions over unobserved nodes (atoms) and edges (bonds) given observed ones. We train and then sample from our model by iteratively masking and replacing different parts of initialized graphs. We evaluate our approach on the QM9 and ChEMBL datasets using the GuacaMol distribution-learning benchmark. We find that validity, KL-divergence and Fréchet ChemNet Distance scores are anti-correlated with novelty, and that we can trade off between these metrics more effectively than existing models. On distributional metrics, our model outperforms previously proposed graph-based approaches and is competitive with SMILES-based approaches. Finally, we show our model generates molecules with desired values of specified properties while maintaining physiochemical similarity to the training distribution.

scholarly journals Masked Graph Modeling for Molecule Generation

2021 ◽  
Author(s):  
Omar Mahmood ◽  
Elman Mansimov ◽  
Richard Bonneau ◽  
Kyunghyun Cho
Keyword(s):  
Drug Discovery ◽  
In Silico ◽  
De Novo ◽  
Graph Model ◽  
Material Design ◽  
Challenging Problem ◽  
Conditional Distributions ◽  
Trade Off ◽  
Graph Modeling ◽  
Different Parts

De novo, in-silico design of molecules is a challenging problem with applications in drug discovery and material design. We introduce a masked graph model, which learns a distribution over graphs by capturing conditional distributions over unobserved nodes (atoms) and edges (bonds) given observed ones. We train and then sample from our model by iteratively masking and replacing different parts of initialized graphs.<br>We evaluate our approach on the QM9 and ChEMBL datasets using the GuacaMol distribution-learning benchmark. We find that validity, KL-divergence and Fréchet ChemNet Distance scores are anti-correlated with novelty, and that we can trade off between these metrics more effectively than existing models. On distributional metrics, our model outperforms previously proposed graph-based approaches and is competitive with SMILES-based approaches. Finally, we show our model generates molecules with desired values of specified properties while maintaining physiochemical similarity to the<br>training distribution.

A systematic review with in silico analysis on transcriptomic profile of gallbladder carcinoma

2020 ◽  
Vol 47 (6) ◽  
pp. 398-408
Author(s):  
Sonam Tulsyan ◽  
Showket Hussain ◽  
Balraj Mittal ◽  
Sundeep Singh Saluja ◽  
Pranay Tanwar ◽  
...  
Keyword(s):  
Systematic Review ◽  
Gallbladder Carcinoma ◽  
In Silico ◽  
In Silico Analysis ◽  
Transcriptomic Profile ◽  
Silico Analysis

Common and well-documented Allele List: unverzichtbares Hilfsmittel für die moderne HLA-Typisierung

2019 ◽  
Vol 9 (04) ◽  
pp. 241-245
Author(s):  
Nils Lachmann ◽  
Diana Stauch ◽  
Axel Pruß
Keyword(s):  
In Silico ◽  
Regionale Unterschiede

ZusammenfassungDie Typisierung der humanen Leukozytenantigene (HLA) vor Organ- und hämatopoetischer Stammzelltransplantation zur Beurteilung der Kompatibilität von Spender und Empfänger wird heutzutage in der Regel molekulargenetisch mittels Amplifikation, Hybridisierung oder Sequenzierung durchgeführt. Durch die exponentiell steigende Anzahl an neu entdeckten HLA-Allelen treten vermehrt Mehrdeutigkeiten, sogenannte Ambiguitäten, in der HLA-Typisierung auf, die aufgelöst werden müssen, um zu einem eindeutigen Ergebnis zu gelangen. Mithilfe kategorisierter Allelfrequenzen (häufig, gut dokumentiert und selten) in Form von CWD-Allellisten (CWD: common and well-documented) ist die In-silico-Auflösung von Ambiguitäten durch den Ausschluss seltener Allele als mögliches Ergebnis realisierbar. Ausgehend von einer amerikanischen CWD-Liste existieren derzeit auch eine europäische, deutsche und chinesische CWD-Liste, die jeweils regionale Unterschiede in den Allelfrequenzen erkennbar werden lassen. Durch die Anwendung von CWD-Allelfiltern in der klinischen HLA-Typisierung können Zeit, Kosten und Arbeitskraft eingespart werden.

Sign in / Sign up

Export Citation Format

Share Document