scholarly journals ZF-AutoML: An Easy Machine-Learning-Based Method to Detect Anomalies in Fluorescent-Labelled Zebrafish

Inventions ◽  
2019 ◽  
Vol 4 (4) ◽  
pp. 72
Author(s):  
Ryota Sawaki ◽  
Daisuke Sato ◽  
Hiroko Nakayama ◽  
Yuki Nakagawa ◽  
Yasuhito Shimada
Keyword(s):  
Machine Learning ◽  
Image Analysis ◽  
High Throughput ◽  
High Throughput Screening ◽  
Large Scale ◽  
Fluorescent Protein ◽  
Learning Program ◽  
High Throughput Analysis ◽  
Easy Method ◽  
High Fecundity

Background: Zebrafish are efficient animal models for conducting whole organism drug testing and toxicological evaluation of chemicals. They are frequently used for high-throughput screening owing to their high fecundity. Peripheral experimental equipment and analytical software are required for zebrafish screening, which need to be further developed. Machine learning has emerged as a powerful tool for large-scale image analysis and has been applied in zebrafish research as well. However, its use by individual researchers is restricted due to the cost and the procedure of machine learning for specific research purposes. Methods: We developed a simple and easy method for zebrafish image analysis, particularly fluorescent labelled ones, using the free machine learning program Google AutoML. We performed machine learning using vascular- and macrophage-Enhanced Green Fluorescent Protein (EGFP) fishes under normal and abnormal conditions (treated with anti-angiogenesis drugs or by wounding the caudal fin). Then, we tested the system using a new set of zebrafish images. Results: While machine learning can detect abnormalities in the fish in both strains with more than 95% accuracy, the learning procedure needs image pre-processing for the images of the macrophage-EGFP fishes. In addition, we developed a batch uploading software, ZF-ImageR, for Windows (.exe) and MacOS (.app) to enable high-throughput analysis using AutoML. Conclusions: We established a protocol to utilize conventional machine learning platforms for analyzing zebrafish phenotypes, which enables fluorescence-based, phenotype-driven zebrafish screening.

Accelerated Discovery of High-Refractive-Index Polyimides via First-Principles Molecular Modeling, Virtual High-Throughput Screening, and Data Mining

2019 ◽  
Author(s):  
Mohammad Atif Faiz Afzal ◽  
Mojtaba Haghighatlari ◽  
Sai Prasad Ganesh ◽  
Chong Cheng ◽  
Johannes Hachmann
Keyword(s):  
Data Mining ◽  
Refractive Index ◽  
High Throughput ◽  
First Principles ◽  
High Throughput Screening ◽  
Large Scale ◽  
Computational Study ◽  
High Refractive Index ◽  
Structural Features ◽  
Learning Program

<div>We present a high-throughput computational study to identify novel polyimides (PIs) with exceptional refractive index (RI) values for use as optic or optoelectronic materials. Our study utilizes an RI prediction protocol based on a combination of first-principles and data modeling developed in previous work, which we employ on a large-scale PI candidate library generated with the ChemLG code. We deploy the virtual screening software ChemHTPS to automate the assessment of this extensive pool of PI structures in order to determine the performance potential of each candidate. This rapid and efficient approach yields a number of highly promising leads compounds. Using the data mining and machine learning program package ChemML, we analyze the top candidates with respect to prevalent structural features and feature combinations that distinguish them from less promising ones. In particular, we explore the utility of various strategies that introduce highly polarizable moieties into the PI backbone to increase its RI yield. The derived insights provide a foundation for rational and targeted design that goes beyond traditional trial-and-error searches.</div>

scholarly journals Establishing a Novel High-Throughput Conditioning-Free HSC Transplant Model in Zebrafish

Blood ◽  
2019 ◽  
Vol 134 (Supplement_1) ◽  
pp. 4423-4423
Author(s):  
Ellen Fraint ◽  
Teresa V. Bowman
Keyword(s):  
Stem Cell ◽  
High Throughput ◽  
Large Scale ◽  
Fluorescent Protein ◽  
Conflicts Of Interest ◽  
High Fecundity ◽  
Hematopoietic Stem ◽  
Transplantation Model ◽  
Hsc Transplantation ◽  
Marrow Cells

Hematopoietic stem cell (HSC) transplantation is a widely used treatment for a range of malignant and non-malignant disorders in children and adults, although the risk of morbidity and mortality still remains unacceptably high. Preclinical modeling of HSC transplantation is critical to uncover the biological components that underlie poor patient outcomes. Zebrafish is a vertebrate animal model with high genetic and cellular conservation with human hematopoiesis with many advantages to discover regulators of HSC transplantation biology, such as high fecundity, short generation time, and lower cost of husbandry. Although prior zebrafish transplantation experiments have demonstrated feasibility, a high-throughput model that achieves robust, reproducible, high-level chimerism is lacking. We have developed a novel HSC transplantation model that fills that gap utilizing the bloodless runx1 W84X mutant zebrafish, which are devoid of endogenous HSCs. As a result, most embryos die 8-12 days post fertilization (dpf) due to the absence of definitive hematopoiesis. We hypothesized that the empty HSC niche and lack of a definitive immune system would prevent graft rejection, making robust HSC engraftment possible. We transplanted donor marrow cells that ubiquitously expressed green fluorescent protein (ubi:GFP) via intravascular injection into runx1 homozygous mutants and heterozygotes at 2dpf. Sham-injected and uninjected embryos served as negative controls. We transplanted an average of 100-200 recipients per experimental day. Survival was significantly improved in transplanted runx1 mutants, with 64% surviving in the transplanted cohort compared to 5% in the sham-injected controls, suggesting HSC transplantation likely supplied these fish with a functional hematopoietic compartment critical for survival. Donor-derived adult marrow chimerism was quantified by flow cytometry at 8 weeks post-transplantation. Successful engraftment was defined as >5% GFP+ myeloid cells. Over 99% of animals meeting this criterion also showed robust multi-lineage engraftment in the lymphoid and erythroid compartments. Over 70% of runx1 mutant recipients were engrafted compared to only 3% of the runx1 heterozygotes. The myeloid chimerism of engrafted mutant fish was 84% (+/-25%), while the single engrafted heterozygous control had only 21% myeloid chimerism. Transplanted fish remained robustly engrafted >6 months post-transplant. The runx1 mutants supported HSC self-renewal, as the GFP+ marrow cells from primary recipients were able to robustly engraft secondary runx1 mutant hosts. We also demonstrated that competitive transplantation in runx1 mutants can be used to measure HSC frequency, a critical feature needed to functionally and quantitatively assess HSC potential following genetic or pharmacological perturbations. These data demonstrate that the runx1 mutant zebrafish is an advantageous HSC transplantation host that allows quantification of long-term serially-repopulating bona fide HSCs. The advantages of our zebrafish transplantation model will allow the real-time visualization of stem cell trafficking and homing in a healthy, uninjured niche and the ability to perform large-scale screens to identify drugs that modify engraftment. This system will provide unprecedented insight into both the donor and host factors needed for robust HSC engraftment that will be helpful in improving human HSC graft outcomes. Disclosures No relevant conflicts of interest to declare.

scholarly journals A fluorescence-based high-throughput screening method for cytokinin translocation mutants

Plant Methods ◽  
2020 ◽  
Vol 16 (1) ◽  
Author(s):  
Mengyuan Zhang ◽  
Bingli Ding ◽  
Jiangzhe Zhao ◽  
Penghong Zhang ◽  
Yujia Li ◽  
...  
Keyword(s):  
High Throughput ◽  
Stress Responses ◽  
High Throughput Screening ◽  
Large Scale ◽  
Fluorescent Protein ◽  
Imaging System ◽  
Screening Method ◽  
Cytokinin Signaling ◽  
Phenotypic Analysis ◽  
Long Distance

Abstract Background Cytokinins are one kind of phytohormones essential for plant growth, development and stress responses. In the past half century, significant progresses have been made in the studies of cytokinin signal transduction and metobolic pathways, but the mechanism of cytokinin translocation is poorly understood. Arabidopsis (Arabidopsis thaliana) response regulator 5 (ARR5) is a type-A response factor in cytokinin signaling which is induced by cytokinins and has been used as a reporter gene for the endogenous cytokinins in Arabidopsis. Here, we report a fluorescence-based high-throughput method to screen cytokinin translocation mutants using an ethyl methyl sulfone (EMS) mutagenesis library generated with ARR5::eGFP transgenic plants. Results The seedlings with enhanced green fluorescent protein (GFP) signal in roots were screened in a luminescence imaging system (LIS) in large scale to obtain mutants with over-accumulated cytokinins in roots. The selected mutants were confirmed under a fluorescence microscopy and then performed phenotypic analysis. In this way, we obtained twelve mutants with elevated GFP signal in the roots and further found three of them displayed reduced GFP signal in the aerial tissues. Two of the mutants were characterized and proved to be the atabcg14 allelic mutants which are defective in the long-distance translocation of root-synthesized cytokinins. Conclusions We provide a strategy for screening mutants defective in cytokinin translocation, distribution or signaling. The strategy can be adapted to establish a system for screening mutants defective in other hormone transporters or signaling components using a fluorescence reporter.

Learning Binding Affinity from Augmented High Throughput Screening Data

2013 ◽  
pp. 364-385
Author(s):  
Nicos Angelopoulos ◽  
Andreas Hadjiprocopis ◽  
Malcolm D. Walkinshaw
Keyword(s):  
Machine Learning ◽  
Binding Affinity ◽  
High Throughput ◽  
High Throughput Screening ◽  
Large Scale ◽  
Bayesian Model Averaging ◽  
Model Averaging ◽  
Machine Learning Techniques ◽  
High Dimensional ◽  
Learning Techniques

In high throughput screening a large number of molecules are tested against a single target protein to determine binding affinity of each molecule to the target. The objective of such tests within the pharmaceutical industry is to identify potential drug-like lead molecules. Current technology allows for thousands of molecules to be tested inexpensively. The analysis of linking such biological data with molecular properties is thus becoming a major goal in both academic and pharmaceutical research. This chapter details how screening data can be augmented with high-dimensional descriptor data and how machine learning techniques can be utilised to build predictive models. The pyruvate kinase protein is used as a model target throughout the chapter. Binding affinity data from a public repository provide binding information on a large set of screened molecules. The authors consider three machine learning paradigms: Bayesian model averaging, Neural Networks, and Support Vector Machines. The authors apply algorithms from the three paradigms to three subsets of the data and comment on the relative merits of each. They also used the learnt models to classify the molecules in a large in-house molecular database that holds commercially available chemical structures from a large number of suppliers. They discuss the degree of agreement in compounds selected and ranked for three algorithms. Details of the technical challenges in such large scale classification and the ability of each paradigm to cope with these are put forward. The application of machine learning techniques to binding data augmented by high-dimensional can provide a powerful tool in compound testing. The emphasis of this work is on making very few assumptions or technical choices with regard to the machine learning techniques. This is to facilitate application of such techniques by non-experts.

Accelerated Discovery of High-Refractive-Index Polyimides via First-Principles Molecular Modeling, Virtual High-Throughput Screening, and Data Mining

2019 ◽  
Author(s):  
Mohammad Atif Faiz Afzal ◽  
Mojtaba Haghighatlari ◽  
Sai Prasad Ganesh ◽  
Chong Cheng ◽  
Johannes Hachmann
Keyword(s):  
Data Mining ◽  
Refractive Index ◽  
High Throughput ◽  
First Principles ◽  
High Throughput Screening ◽  
Large Scale ◽  
Computational Study ◽  
High Refractive Index ◽  
Structural Features ◽  
Learning Program

<div>We present a high-throughput computational study to identify novel polyimides (PIs) with exceptional refractive index (RI) values for use as optic or optoelectronic materials. Our study utilizes an RI prediction protocol based on a combination of first-principles and data modeling developed in previous work, which we employ on a large-scale PI candidate library generated with the ChemLG code. We deploy the virtual screening software ChemHTPS to automate the assessment of this extensive pool of PI structures in order to determine the performance potential of each candidate. This rapid and efficient approach yields a number of highly promising leads compounds. Using the data mining and machine learning program package ChemML, we analyze the top candidates with respect to prevalent structural features and feature combinations that distinguish them from less promising ones. In particular, we explore the utility of various strategies that introduce highly polarizable moieties into the PI backbone to increase its RI yield. The derived insights provide a foundation for rational and targeted design that goes beyond traditional trial-and-error searches.</div>

Learning Binding Affinity from Augmented High Throughput Screening Data

2011 ◽  
pp. 212-234
Author(s):  
Nicos Angelopoulos ◽  
Andreas Hadjiprocopis ◽  
Malcolm D. Walkinshaw
Keyword(s):  
Machine Learning ◽  
Binding Affinity ◽  
High Throughput ◽  
High Throughput Screening ◽  
Large Scale ◽  
Bayesian Model Averaging ◽  
Model Averaging ◽  
Machine Learning Techniques ◽  
High Dimensional ◽  
Learning Techniques

In high throughput screening a large number of molecules are tested against a single target protein to determine binding affinity of each molecule to the target. The objective of such tests within the pharmaceutical industry is to identify potential drug-like lead molecules. Current technology allows for thousands of molecules to be tested inexpensively. The analysis of linking such biological data with molecular properties is thus becoming a major goal in both academic and pharmaceutical research. This chapter details how screening data can be augmented with high-dimensional descriptor data and how machine learning techniques can be utilised to build predictive models. The pyruvate kinase protein is used as a model target throughout the chapter. Binding affinity data from a public repository provide binding information on a large set of screened molecules. The authors consider three machine learning paradigms: Bayesian model averaging, Neural Networks, and Support Vector Machines. The authors apply algorithms from the three paradigms to three subsets of the data and comment on the relative merits of each. They also used the learnt models to classify the molecules in a large in-house molecular database that holds commercially available chemical structures from a large number of suppliers. They discuss the degree of agreement in compounds selected and ranked for three algorithms. Details of the technical challenges in such large scale classification and the ability of each paradigm to cope with these are put forward. The application of machine learning techniques to binding data augmented by high-dimensional can provide a powerful tool in compound testing. The emphasis of this work is on making very few assumptions or technical choices with regard to the machine learning techniques. This is to facilitate application of such techniques by non-experts.

scholarly journals Deep mutational scanning by FACS-sorting of encapsulated E. coli micro-colonies

2018 ◽  
Author(s):  
Lars Behrendt ◽  
Amelie Stein ◽  
Shiraz Ali Shah ◽  
Karsten Zengler ◽  
Søren J. Sørensen ◽  
...  
Keyword(s):  
Amino Acid ◽  
High Throughput ◽  
High Throughput Screening ◽  
Fluorescent Protein ◽  
Single Cells ◽  
Fluorescence Signal ◽  
Amino Acid Substitutions ◽  
Nucleotide Exchange ◽  
High Throughput Analysis ◽  
Wide Range

AbstractWe present a method for high-throughput screening of protein variants where the signal is enhanced by micro-encapsulation of single cells into 20-30 μm agarose beads. Cells inside beads are propagated using standard agitation in liquid media and grow clonally into micro-colonies harboring several hundred bacteria. We have, as a proof-of-concept, analyzed random amino acid substitutions in the five C-terminal β-strands of the Green Fluorescent Protein (GFP). Starting from libraries of variants, each bead represents a clonal line of cells that can be separated by Fluorescence Activated Cell Sorting (FACS). Pools representing collections of individual variants with desired properties are subsequently analyzed by deep sequencing. Notably, the encapsulation approach described holds the potential for high-throughput analysis of systems where the fluorescence signal from a single cell is insufficient for detection. Fusion to GFP, or use of fluorogenic substrates, allows coupling protein levels or activity to sequence for a wide range of proteins. Here we analyzed more than 10,000 individual variants to gauge the effect of mutations on GFP-fluorescence. In the mutated region, we observed virtually all amino acid substitutions that are accessible by single nucleotide exchange. Lastly, we assessed the performance of biophysical protein stability predictors, FoldX and Rosetta, in predicting the outcome of the experiment. Both tools display good performance on average, suggesting that loss of thermodynamic stability is a key mechanism for the observed variation of the mutants. This, in turn, suggests that deep mutational scanning datasets may be used to more efficiently fine-tune such predictors, especially for mutations poorly covered by current biophysical data.

scholarly journals Critical Review of Processing and Classification Techniques for Images and Spectra in Microplastic Research

2020 ◽  
Vol 74 (9) ◽  
pp. 989-1010 ◽  
Author(s):  
Win Cowger ◽  
Andrew Gray ◽  
Silke H. Christiansen ◽  
Hannah DeFrond ◽  
Ashok D. Deshpande ◽  
...  
Keyword(s):  
Machine Learning ◽  
Image Analysis ◽  
High Throughput ◽  
High Throughput Screening ◽  
Supplementary Information ◽  
Gas Chromatography Mass Spectrometry ◽  
Spectral Processing ◽  
Double Blind ◽  
Pyrolysis Gas ◽  
Machine Learning Classification

Microplastic research is a rapidly developing field, with urgent needs for high throughput and automated analysis techniques. We conducted a review covering image analysis from optical microscopy, scanning electron microscopy, fluorescence microscopy, and spectral analysis from Fourier transform infrared (FT-IR) spectroscopy, Raman spectroscopy, pyrolysis gas–chromatography mass–spectrometry, and energy dispersive X-ray spectroscopy. These techniques were commonly used to collect, process, and interpret data from microplastic samples. This review outlined and critiques current approaches for analysis steps in image processing (color, thresholding, particle quantification), spectral processing (background and baseline subtraction, smoothing and noise reduction, data transformation), image classification (reference libraries, morphology, color, and fluorescence intensity), and spectral classification (reference libraries, matching procedures, and best practices for developing in-house reference tools). We highlighted opportunities to advance microplastic data analysis and interpretation by (i) quantifying colors, shapes, sizes, and surface topologies with image analysis software, (ii) identifying threshold values of particle characteristics in images that distinguish plastic particles from other particles, (iii) advancing spectral processing and classification routines, (iv) creating and sharing robust spectral libraries, (v) conducting double blind and negative controls, (vi) sharing raw data and analysis code, and (vii) leveraging readily available data to develop machine learning classification models. We identified analytical needs that we could fill and developed supplementary information for a reference library of plastic images and spectra, a tutorial for basic image analysis, and a code to download images from peer reviewed literature. Our major findings were that research on microplastics was progressing toward the use of multiple analytical methods and increasingly incorporating chemical classification. We suggest that new and repurposed methods need to be developed for high throughput screening using a diversity of approaches and highlight machine learning as one potential avenue toward this capability.

Large-scale High-throughput Screening Revealed 5'-(carbonylamino)-2,3'- bithiophene-4'-carboxylate as Novel Template for Antibacterial Agents

2020 ◽  
Vol 17 (5) ◽  
pp. 716-724
Author(s):  
Yan A. Ivanenkov ◽  
Renat S. Yamidanov ◽  
Ilya A. Osterman ◽  
Petr V. Sergiev ◽  
Vladimir A. Aladinskiy ◽  
...  
Keyword(s):  
Antibacterial Activity ◽  
High Throughput ◽  
High Throughput Screening ◽  
Large Scale ◽  
Antibacterial Agents ◽  
Sos Response ◽  
Luciferase Assay ◽  
Translational Machinery ◽  
E Coli ◽  
New Class

Background: The key issue in the development of novel antimicrobials is a rapid expansion of new bacterial strains resistant to current antibiotics. Indeed, World Health Organization has reported that bacteria commonly causing infections in hospitals and in the community, e.g. E. Coli, K. pneumoniae and S. aureus, have high resistance vs the last generations of cephalosporins, carbapenems and fluoroquinolones. During the past decades, only few successful efforts to develop and launch new antibacterial medications have been performed. This study aims to identify new class of antibacterial agents using novel high-throughput screening technique. Methods: We have designed library containing 125K compounds not similar in structure (Tanimoto coeff.< 0.7) to that published previously as antibiotics. The HTS platform based on double reporter system pDualrep2 was used to distinguish between molecules able to block translational machinery or induce SOS-response in a model E. coli system. MICs for most active chemicals in LB and M9 medium were determined using broth microdilution assay. Results: In an attempt to discover novel classes of antibacterials, we performed HTS of a large-scale small molecule library using our unique screening platform. This approach permitted us to quickly and robustly evaluate a lot of compounds as well as to determine the mechanism of action in the case of compounds being either translational machinery inhibitors or DNA-damaging agents/replication blockers. HTS has resulted in several new structural classes of molecules exhibiting an attractive antibacterial activity. Herein, we report as promising antibacterials. Two most active compounds from this series showed MIC value of 1.2 (5) and 1.8 μg/mL (6) and good selectivity index. Compound 6 caused RFP induction and low SOS response. In vitro luciferase assay has revealed that it is able to slightly inhibit protein biosynthesis. Compound 5 was tested on several archival strains and exhibited slight activity against gram-negative bacteria and outstanding activity against S. aureus. The key structural requirements for antibacterial potency were also explored. We found, that the unsubstituted carboxylic group is crucial for antibacterial activity as well as the presence of bulky hydrophobic substituents at phenyl fragment. Conclusion: The obtained results provide a solid background for further characterization of the 5'- (carbonylamino)-2,3'-bithiophene-4'-carboxylate derivatives discussed herein as new class of antibacterials and their optimization campaign.

scholarly journals Identification of a juvenile-hormone signaling inhibitor via high-throughput screening of a chemical library

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Takumi Kayukawa ◽  
Kenjiro Furuta ◽  
Keisuke Nagamine ◽  
Tetsuro Shinoda ◽  
Kiyoaki Yonesu ◽  
...  
Keyword(s):  
Juvenile Hormone ◽  
Cell Line ◽  
Signaling Pathway ◽  
High Throughput ◽  
High Throughput Screening ◽  
Large Scale ◽  
Ex Vivo ◽  
Agricultural Field ◽  
Chemical Library ◽  
Field Development

Abstract Insecticide resistance has recently become a serious problem in the agricultural field. Development of insecticides with new mechanisms of action is essential to overcome this limitation. Juvenile hormone (JH) is an insect-specific hormone that plays key roles in maintaining the larval stage of insects. Hence, JH signaling pathway is considered a suitable target in the development of novel insecticides; however, only a few JH signaling inhibitors (JHSIs) have been reported, and no practical JHSIs have been developed. Here, we established a high-throughput screening (HTS) system for exploration of novel JHSIs using a Bombyx mori cell line (BmN_JF&AR cells) and carried out a large-scale screening in this cell line using a chemical library. The four-step HTS yielded 69 compounds as candidate JHSIs. Topical application of JHSI48 to B. mori larvae caused precocious metamorphosis. In ex vivo culture of the epidermis, JHSI48 suppressed the expression of the Krüppel homolog 1 gene, which is directly activated by JH-liganded receptor. Moreover, JHSI48 caused a parallel rightward shift in the JH response curve, suggesting that JHSI48 possesses a competitive antagonist-like activity. Thus, large-scale HTS using chemical libraries may have applications in development of future insecticides targeting the JH signaling pathway.

Sign in / Sign up

Export Citation Format

Share Document