scholarly journals Surface-Related Features Responsible for Cytotoxic Behavior of MXenes Layered Materials Predicted with Machine Learning Approach

Materials ◽  
2020 ◽  
Vol 13 (14) ◽  
pp. 3083
Author(s):  
Maciej E. Marchwiany ◽  
Magdalena Birowska ◽  
Mariusz Popielski ◽  
Jacek A. Majewski ◽  
Agnieszka M. Jastrzębska
Keyword(s):  
Machine Learning ◽  
Transition Metal Oxides ◽  
2D Materials ◽  
Experimental Studies ◽  
Biological Data ◽  
Data Sets ◽  
Toxicological Studies ◽  
Two Factors ◽  
Health Need

To speed up the implementation of the two-dimensional materials in the development of potential biomedical applications, the toxicological aspects toward human health need to be addressed. Due to time-consuming and expensive analysis, only part of the continuously expanding family of 2D materials can be tested in vitro. The machine learning methods can be used—by extracting new insights from available biological data sets, and provide further guidance for experimental studies. This study identifies the most relevant highly surface-specific features that might be responsible for cytotoxic behavior of 2D materials, especially MXenes. In particular, two factors, namely, the presence of transition metal oxides and lithium atoms on the surface, are identified as cytotoxicity-generating features. The developed machine learning model succeeds in predicting toxicity for other 2D MXenes, previously not tested in vitro, and hence, is able to complement the existing knowledge coming from in vitro studies. Thus, we claim that it might be one of the solutions for reducing the number of toxicological studies needed, and allows for minimizing failures in future biological applications.

scholarly journals Predicting the cytotoxicity of MXenes - layered materials - using machine learning methods.

2020 ◽  
Author(s):  
Maciej Marchwiany ◽  
Magdalena Birowska ◽  
Mariusz Popielski ◽  
Jacek A. Majewski ◽  
Agnieszka M. Jastrzębska
Keyword(s):  
Machine Learning ◽  
Transition Metal Oxides ◽  
Experimental Studies ◽  
Surface Oxidation ◽  
Biological Data ◽  
New Drugs ◽  
Synthesis Methods ◽  
Data Sets ◽  
Selection Of

Abstract Background: Prediction of the compound cytotoxicity is a crucial issue in the development of new drugs and potential biomedical applications. Experimental studies are time-consuming and expensive. Machine learning models can quickly predict the cytotoxicity of compounds, by extracting new insights from large materials and biological data sets, and provide further guidance for experimental studies. Results: Here, we identify the most relevant features that are responsible for the cytotoxic behavior of layered MXenes materials. The most important result of our work is the identification of 2D MXenes specific surface parameters as responsible for the potential cytotoxicity of these materials, in particular, the presence of transition metal oxides and Lithium atoms on the surface. After successful verification of the correct predictions of our model,we have also succeeded in predicting toxicity for 2D MXenes not tested in vitro. Hence, we have been able to complement the existing knowledge coming from in vitro studies. Conclusions: Our results allow for the future selection of synthesis methods preventing surface oxidation, which should allow production of non-toxic 2D MXenes. Such materials might find application in many fields of science and technology, especially in biotechnology and nanomedicine.

scholarly journals A deep learning approach for staging embryonic tissue isolates with small data

2020 ◽  
Author(s):  
Adam Pond ◽  
Seongwon Hwang ◽  
Berta Verd ◽  
Benjamin Steventon
Keyword(s):  
Machine Learning ◽  
3D Culture ◽  
Large Data ◽  
Large Data Sets ◽  
Data Sets ◽  
Learning Approaches ◽  
Data Set ◽  
Set Size ◽  
In Vitro Systems

AbstractMachine learning approaches are becoming increasingly widespread and are now present in most areas of research. Their recent surge can be explained in part due to our ability to generate and store enormous amounts of data with which to train these models. The requirement for large training sets is also responsible for limiting further potential applications of machine learning, particularly in fields where data tend to be scarce such as developmental biology. However, recent research seems to indicate that machine learning and Big Data can sometimes be decoupled to train models with modest amounts of data. In this work we set out to train a CNN-based classifier to stage zebrafish tail buds at four different stages of development using small information-rich data sets. Our results show that two and three dimensional convolutional neural networks can be trained to stage developing zebrafish tail buds based on both morphological and gene expression confocal microscopy images, achieving in each case up to 100% test accuracy scores. Importantly, we show that high accuracy can be achieved with data set sizes of under 100 images, much smaller than the typical training set size for a convolutional neural net. Furthermore, our classifier shows that it is possible to stage isolated embryonic structures without the need to refer to classic developmental landmarks in the whole embryo, which will be particularly useful to stage 3D culture in vitro systems such as organoids. We hope that this work will provide a proof of principle that will help dispel the myth that large data set sizes are always required to train CNNs, and encourage researchers in fields where data are scarce to also apply ML approaches.Author summaryThe application of machine learning approaches currently hinges on the availability of large data sets to train the models with. However, recent research has shown that large data sets might not always be required. In this work we set out to see whether we could use small confocal microscopy image data sets to train a convolutional neural network (CNN) to stage zebrafish tail buds at four different stages in their development. We found that high test accuracies can be achieved with data set sizes of under 100 images, much smaller than the typical training set size for a CNN. This work also shows that we can robustly stage the embryonic development of isolated structures, without the need to refer back to landmarks in the tail bud. This constitutes an important methodological advance for staging organoids and other 3D culture in vitro systems. This work proves that prohibitively large data sets are not always required to train CNNs, and we hope will encourage others to apply the power of machine learning to their areas of study even if data are scarce.

A study of Turkish emotion classification with pretrained language models

2021 ◽  
pp. 016555152098550
Author(s):  
Alaettin Uçan ◽  
Murat Dörterler ◽  
Ebru Akçapınar Sezer
Keyword(s):  
Machine Learning ◽  
Language Model ◽  
Experimental Studies ◽  
Classification Performance ◽  
Research Field ◽  
Language Models ◽  
Classification Model ◽  
Data Sets ◽  
Emotion Classification ◽  
Model Approach

Emotion classification is a research field that aims to detect the emotions in a text using machine learning methods. In traditional machine learning (TML) methods, feature engineering processes cause the loss of some meaningful information, and classification performance is negatively affected. In addition, the success of modelling using deep learning (DL) approaches depends on the sample size. More samples are needed for Turkish due to the unique characteristics of the language. However, emotion classification data sets in Turkish are quite limited. In this study, the pretrained language model approach was used to create a stronger emotion classification model for Turkish. Well-known pretrained language models were fine-tuned for this purpose. The performances of these fine-tuned models for Turkish emotion classification were comprehensively compared with the performances of TML and DL methods in experimental studies. The proposed approach provides state-of-the-art performance for Turkish emotion classification.

scholarly journals PyBDA: a command line tool for automated analysis of big biological data sets

2019 ◽  
Vol 20 (1) ◽  
Author(s):  
Simon Dirmeier ◽  
Mario Emmenlauer ◽  
Christoph Dehio ◽  
Niko Beerenwinkel
Keyword(s):  
Machine Learning ◽  
High Performance ◽  
Single Cells ◽  
Automated Analysis ◽  
Biological Data ◽  
Machine Learning Algorithms ◽  
Data Sets ◽  
Command Line ◽  
Command Line Tool ◽  
High Performance Computing Cluster

Abstract Background Analysing large and high-dimensional biological data sets poses significant computational difficulties for bioinformaticians due to lack of accessible tools that scale to hundreds of millions of data points. Results We developed a novel machine learning command line tool called PyBDA for automated, distributed analysis of big biological data sets. By using Apache Spark in the backend, PyBDA scales to data sets beyond the size of current applications. It uses Snakemake in order to automatically schedule jobs to a high-performance computing cluster. We demonstrate the utility of the software by analyzing image-based RNA interference data of 150 million single cells. Conclusion PyBDA allows automated, easy-to-use data analysis using common statistical methods and machine learning algorithms. It can be used with simple command line calls entirely making it accessible to a broad user base. PyBDA is available at https://pybda.rtfd.io.

Ultrastructural investigations of MDL 19,660-induced effects on the canine platelet and megakaryocyte

1990 ◽  
Vol 48 (3) ◽  
pp. 374-375
Author(s):  
D.E. Loudy ◽  
J. Sprinkle-Cavallo ◽  
J.T. Yarrington ◽  
F.Y. Thompson ◽  
J.P. Gibson
Keyword(s):  
Antidepressant Drug ◽  
Beagle Dogs ◽  
Long Term Effects ◽  
Short Term ◽  
Platelet Counts ◽  
Toxicological Studies ◽  
Induced Aggregation ◽  
Internal Architecture

Previous short term toxicological studies of one to two weeks duration have demonstrated that MDL 19,660 (5-(4-chlorophenyl)-2,4-dihydro-2,4-dimethyl-3Hl, 2,4-triazole-3-thione), an antidepressant drug, causes a dose-related thrombocytopenia in dogs. Platelet counts started to decline after two days of dosing with 30 mg/kg/day and continued to decrease to their lowest levels by 5-7 days. The loss in platelets was primarily of the small discoid subpopulation. In vitro studies have also indicated that MDL 19,660: does not spontaneously aggregate canine platelets and has moderate antiaggregating properties by inhibiting ADP-induced aggregation. The objectives of the present investigation of MDL 19,660 were to evaluate ultrastructurally long term effects on platelet internal architecture and changes in subpopulations of platelets and megakaryocytes.Nine male and nine female beagle dogs were divided equally into three groups and were administered orally 0, 15, or 30 mg/kg/day of MDL 19,660 for three months. Compared to a control platelet range of 353,000- 452,000/μl, a doserelated thrombocytopenia reached a maximum severity of an average of 135,000/μl for the 15 mg/kg/day dogs after two weeks and 81,000/μl for the 30 mg/kg/day dogs after one week.

Experimental Studies on a Recombinant Hirudin, CGP 39393

1991 ◽  
Vol 65 (04) ◽  
pp. 355-359 ◽  
Author(s):  
E Gray ◽  
J Watton ◽  
S Cesmeli ◽  
T W Barrowcliffe ◽  
D P Thomas
Keyword(s):  
Thrombin Generation ◽  
Bleeding Time ◽  
Thrombus Formation ◽  
Experimental Studies ◽  
Venous Stasis ◽  
Antithrombotic Agent ◽  
Recombinant Hirudin ◽  
Excessive Bleeding ◽  
Generation Test

SummaryThe in vitro anticoagulant activities of recombinant desulphatohirudin (r-hirudin) were studied in the activated partial thromboplastin time (APTT) and the thrombin generation test : systems. In the APTT at concentrations below 5 μg/ml, r-hirudin showed a dose-response curye. At concentrations above 5 μg/ml, the plasma became unclottable, but in the thrombin generation test , at least 10 μg/ml of r-hirudin was required for full inhibition of thrombin generation. The antithrombotic effect was assessed using a rabbit venous stasis model; 150 μg/ml r-hirudin completely prevented thrombus formation at 10 and 20 min stasis. At antithrombotic dose, the mean bleeding time ratio measured in a rabbit ear template model, was not prolonged over control values. At higher doses, the bleeding time ratios were higher than those observed for the same dosage of heparin. These data indicate that while r-hirudin is an effective antithrombotic agent, antithrombotic doses have to be carefully titrated to avoid excessive bleeding.

Efficient Prediction of Structural and Electronic Properties of Hybrid 2D Materials Using DFT and Machine Learning

2018 ◽  
Author(s):  
Sherif Tawfik ◽  
Olexandr Isayev ◽  
Catherine Stampfl ◽  
Joseph Shapter ◽  
David Winkler ◽  
...  
Keyword(s):  
Machine Learning ◽  
Band Gap ◽  
Density Functional ◽  
2D Materials ◽  
Van Der Waals ◽  
Building Blocks ◽  
Machine Learning Techniques ◽  
Interlayer Distance ◽  
Computational Screening ◽  
Wide Range

Materials constructed from different van der Waals two-dimensional (2D) heterostructures offer a wide range of benefits, but these systems have been little studied because of their experimental and computational complextiy, and because of the very large number of possible combinations of 2D building blocks. The simulation of the interface between two different 2D materials is computationally challenging due to the lattice mismatch problem, which sometimes necessitates the creation of very large simulation cells for performing density-functional theory (DFT) calculations. Here we use a combination of DFT, linear regression and machine learning techniques in order to rapidly determine the interlayer distance between two different 2D heterostructures that are stacked in a bilayer heterostructure, as well as the band gap of the bilayer. Our work provides an excellent proof of concept by quickly and accurately predicting a structural property (the interlayer distance) and an electronic property (the band gap) for a large number of hybrid 2D materials. This work paves the way for rapid computational screening of the vast parameter space of van der Waals heterostructures to identify new hybrid materials with useful and interesting properties.

Discovery of New AKT1 Inhibitors by Combination of In silico Structure Based Virtual Screening Approaches and Biological Evaluations

2019 ◽  
Author(s):  
Filip Fratev ◽  
Denisse A. Gutierrez ◽  
Renato J. Aguilera ◽  
suman sirimulla
Keyword(s):  
Virtual Screening ◽  
Success Rate ◽  
Protein Interactions ◽  
In Silico ◽  
Biological Data ◽  
In Vitro Binding ◽  
Vitro Binding ◽  
Screening Protocol ◽  
Screening Approaches

AKT1 is emerging as a useful target for treating cancer. Herein, we discovered a new set of ligands that inhibit the AKT1, as shown by in vitro binding and cell line studies, using a newly designed virtual screening protocol that combines structure-based pharmacophore and docking screens. Taking together with the biological data, the combination of structure based pharamcophore and docking methods demonstrated reasonable success rate in identifying new inhibitors (60-70%) proving the success of aforementioned approach. A detail analysis of the ligand-protein interactions was performed explaining observed activities.<br>

Sign in / Sign up

Export Citation Format

Share Document