AI Article Synopsis
- - The study introduces an automated method using image processing and support vector machines (SVM) to efficiently screen mold strains, specifically focusing on Monascus colonies.
- - It achieved an accuracy of 80.6%, which is comparable to traditional methods, and can screen 500 colonies in just 20-30 minutes, making it the fastest published approach.
- - Utilizing this method, researchers identified 13 high-producing strains, with the top strain yielding 2.8 times more pigment and 1.9 times more lovastatin than the original strain.
Article Abstract
This work proposed a new method which applied image processing and support vector machine (SVM) for screening of mold strains. Taking Monascus as example, morphological characteristics of Monascus colony were quantified by image processing. And the association between the characteristics and pigment production capability was determined by SVM. On this basis, a highly automated screening strategy was achieved. The accuracy of the proposed strategy is 80.6 %, which is compatible with the existing methods (81.1 % for microplate and 85.4 % for flask). Meanwhile, the screening of 500 colonies only takes 20-30 min, which is the highest rate among all published results. By applying this automated method, 13 strains with high-predicted production were obtained and the best one produced as 2.8-fold (226 U/mL) of pigment and 1.9-fold (51 mg/L) of lovastatin compared with the parent strain. The current study provides us with an effective and promising method for strain improvement.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1007/s10295-015-1729-z | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Analysis of stomatal characteristics of maize hybrids and their parental inbred lines during critical reproductive periods.
Front Plant Sci
January 2025
Beijing Key Lab of Digital Plant, Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, China.
The stomatal phenotype is a crucial microscopic characteristic of the leaf surface, and modulating the stomata of maize leaves can enhance photosynthetic carbon assimilation and water use efficiency, thereby playing a vital role in maize yield formation. The evolving imaging and image processing technologies offer effective tools for precise analysis of stomatal phenotypes. This study employed Jingnongke 728 and its parental inbred to capture stomatal images from various leaf positions and abaxial surfaces during key reproductive stages using rapid scanning electron microscopy.
View Article and Find Full Text PDFA CONVEX COMPRESSIBILITY-INSPIRED UNSUPERVISED LOSS FUNCTION FOR PHYSICS-DRIVEN DEEP LEARNING RECONSTRUCTION.
Proc IEEE Int Symp Biomed Imaging
May 2024
Electrical and Computer Engineering, University of Minnesota, Minneapolis, Minnesota, USA.
Physics-driven deep learning (PD-DL) methods have gained popularity for improved reconstruction of fast MRI scans. Though supervised learning has been used in early works, there has been a recent interest in unsupervised learning methods for training PD-DL. In this work, we take inspiration from statistical image processing and compressed sensing (CS), and propose a novel convex loss function as an alternative learning strategy.
View Article and Find Full Text PDFExpedient discovery of fluorogenic amino acid-based probes one-pot palladium-catalysed arylation of tyrosine.
Chem Sci
January 2025
School of Chemistry, University of Glasgow Joseph Black Building, University Avenue Glasgow G12 8QQ UK
To overcome the limitations of using large extrinsic chromophores for biological imaging, fluorescent unnatural α-amino acids have been widely adopted as intrinsic peptidic probes. Although various classes have been successfully utilised for imaging applications, novel amino acid probes readily prepared through operationally simple synthetic methodology are still required. Here, we report a new approach for the synthesis of unnatural α-amino acids a one-pot process involving activation and palladium-catalysed arylation of tyrosine.
View Article and Find Full Text PDFDoes the audiogram shape influence the intracochlear recording of Electrocochleography during and after cochlear implantation?
Front Neurosci
January 2025
Department of Otorhinolaryngology, Hannover Medical School, Hanover, Germany.
During cochlear implant (CI) surgery, it is desirable to perform intraoperative measurements such as Electrocochleography (ECochG) to monitor the inner ear function and thereby to support the preservation of residual hearing. However, a significant challenge arises as the recording location of intracochlear ECochG via the CI electrode changes during electrode insertion. This study aimed to investigate the relationships between intracochlear ECochG recordings, the position of the recording contact within the cochlea relative to its anatomy, and the implications for frequency and residual hearing preservation.
View Article and Find Full Text PDFLipid Metabolic Heterogeneity during Early Embryogenesis Revealed by Hyper-3D Stimulated Raman Imaging.
Chem Biomed Imaging
January 2025
College of Biomedical Engineering & Instrument Science, Key Laboratory for Biomedical Engineering of Ministry of Education, Zhejiang University, Hangzhou 310058, China.
Studying embryogenesis is fundamental to understanding developmental biology and reproductive medicine. Its process requires precise spatiotemporal regulations in which lipid metabolism plays a crucial role. However, the spatial dynamics of lipid species at the subcellular level remains obscure due to technical limitations.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!