High-throughput screening for improved microbial cell factories, perspective and promise

Leavell, Michael D.; Singh, Amoolya H.; Kaufmann-Malaga, Benjamin B

doi:10.1016/j.copbio.2019.07.002

Cited by 57 publications

(29 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Overfitting risk: Low Interpretation: High Features/sample: High Implementation: Easy Collinear data RF-Random Forest [3] analysis and show the ability of ML to resolve nonlinear relationships and process large heterogeneous datasets. Moreover, we will focus on supervised ML approaches that provide quantitative predictions and are suitable for hypothesis-driven research [1].…”

Section: Supervised ML Modelmentioning

confidence: 99%

Machine Learning Applications for Mass Spectrometry-Based Metabolomics

et al. 2020

View full text Add to dashboard Cite

The metabolome of an organism depends on environmental factors and intracellular regulation and provides information about the physiological conditions. Metabolomics helps to understand disease progression in clinical settings or estimate metabolite overproduction for metabolic engineering. The most popular analytical metabolomics platform is mass spectrometry (MS). However, MS metabolome data analysis is complicated, since metabolites interact nonlinearly, and the data structures themselves are complex. Machine learning methods have become immensely popular for statistical analysis due to the inherent nonlinear data representation and the ability to process large and heterogeneous data rapidly. In this review, we address recent developments in using machine learning for processing MS spectra and show how machine learning generates new biological insights. In particular, supervised machine learning has great potential in metabolomics research because of the ability to supply quantitative predictions. We review here commonly used tools, such as random forest, support vector machines, artificial neural networks, and genetic algorithms. During processing steps, the supervised machine learning methods help peak picking, normalization, and missing data imputation. For knowledge-driven analysis, machine learning contributes to biomarker detection, classification and regression, biochemical pathway identification, and carbon flux determination. Of important relevance is the combination of different omics data to identify the contributions of the various regulatory levels. Our overview of the recent publications also highlights that data quality determines analysis quality, but also adds to the challenge of choosing the right model for the data. Machine learning methods applied to MS-based metabolomics ease data analysis and can support clinical decisions, guide metabolic engineering, and stimulate fundamental biological discoveries.

show abstract

Section: Supervised ML Modelmentioning

confidence: 99%

Machine Learning Applications for Mass Spectrometry-Based Metabolomics

et al. 2020

View full text Add to dashboard Cite

show abstract

“…High-throughput screening (HTS) is a critical tool to expand biomedical knowledge of small molecules that can be used for the drug discovery industry [ 13 ]. The high-throughput analytical technologies enable us to evaluate the biological functions of large amounts of chemicals or natural materials in the shortest amount of time by integrating chemical analyses, modeling, and machine learning that can result in marketed pharmaceutical products in the lowest cost production [ 14 ]. In this study, we utilized high-throughput screening assays to identify antioxidant and anticancer potentials of phenolic compounds found in black walnuts.…”

Section: Introductionmentioning

confidence: 99%

Profiling Anticancer and Antioxidant Activities of Phenolic Compounds Present in Black Walnuts (Juglans nigra) Using a High-Throughput Screening Approach

Roy

Foote³

et al. 2020

Molecules

View full text Add to dashboard Cite

Our recent studies have demonstrated multiple health-promoting benefits from black walnut kernels. These biological functions of black walnuts are likely associated with their bioactive constituents. Characterization of phenolic compounds found in black walnut could point out underexplored bioactive activities of black walnut extracts and promote the development of novel applications of black walnut and its by-products. In the present study, we assessed bioactivity profiles of phenolic compounds identified in the kernels of black walnuts using a high-throughput screening (HTS) approach. Black walnut phenolic compounds were evaluated in terms of their total antioxidant capacity, antioxidant response element (ARE) induction, and anticancer activities. The anticancer activities were identified by evaluating the effects of the phenolic compounds on the growth of the tumorigenic alveolar epithelial cells (A549) and non-tumorigenic lung fibroblast cells (MRC-5). Out of 16 phenolic compounds tested, several compounds (penta-O-galloyl-β-d-glucose, epicatechin gallate, quercetin, (–)-epicatechin, rutin, quercetin 3-β-d-glucoside, gallic acid, (+)-catechin, ferulic acid, syringic acid) exerted antioxidant activities that were significantly higher compared to Trolox, which was used as a control. Two phenolic compounds, penta-O-galloyl-β-d-glucose and quercetin 3-β-d-glucoside, exhibited antiproliferative activities against both the tumorigenic alveolar epithelial cells (A549) and non-tumorigenic lung fibroblast cells (MRC-5). The antioxidant activity of black walnut is likely driven not only by penta-O-galloyl-β-d-glucose but also by a combination of multiple phenolic compounds. Our findings suggested that black walnut extracts possibly possess anticancer activities and supported that penta-O-galloyl-β-d-glucose could be a potential bioactive agent for the cosmetic and pharmaceutical industries.

show abstract

“…The test phase relies on high-throughput analytics employing parallel cultivation platforms in microwell format 36 or microfluidic droplets 37 and the monitoring of reporter outputs like fluorescent proteins or liquid chromatography–mass spectrometry (LC-MS) analytics for compound detection. To further increase throughput, we might see methods like automated laser-assisted rapid evaporative ionization MS (LA-REIMS) used more in the future.…”

Section: The Design-build-test-learn Cycle In Synthetic Biologymentioning

confidence: 99%