Recognition of Molecular Structure of Phosphonium Salts from the Visual Appearance of Material with Deep Learning Can Reveal Subtle Homologs DOI
Daniil A. Boiko, Daria M. Arkhipova, Valentine P. Ananikov

et al.

Small, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 10, 2024

Abstract Determining molecular structures is foundational in chemistry and biology. The notion of discerning simply from the visual appearance a material remained almost unthinkable until advent machine learning. This paper introduces pioneering approach bridging materials (both at micro‐ nanostructural levels) with traditional chemical structure analysis methods. Quaternary phosphonium salts are opted as model compounds, given their significant roles diverse medicinal fields ability to form homologs only minute intermolecular variances. research results successful creation neural network capable recognizing electron microscopy images material. performance evaluated related nature studied chemicals. Additionally, unsupervised domain transfer tested method use resulting on optical images, well test models trained directly. robustness further using complex system salt mixtures. To best authors' knowledge, this study offers first evidence feasibility nearly indistinguishable structures.

Language: Английский

Top 20 influential AI-based technologies in chemistry DOI Creative Commons
Valentine P. Ananikov

Artificial Intelligence Chemistry, Journal Year: 2024, Volume and Issue: 2(2), P. 100075 - 100075

Published: July 27, 2024

The beginning and ripening of digital chemistry is analyzed focusing on the role artificial intelligence (AI) in an expected leap chemical sciences to bring this area next evolutionary level. analytic description selects highlights top 20 AI-based technologies 7 broader themes that are reshaping field. It underscores integration tools such as machine learning, big data, twins, Internet Things (IoT), robotic platforms, smart control processes, virtual reality blockchain, among many others, enhancing research methods, educational approaches, industrial practices chemistry. significance study lies its focused overview how these innovations foster a more efficient, sustainable, innovative future sciences. This article not only illustrates transformative impact but also draws new pathways chemistry, offering broad appeal researchers, educators, industry professionals embrace advancements for addressing contemporary challenges

Language: Английский

Citations

8
Deep generative modeling of annotated bacterial biofilm images DOI Creative Commons

Angelina A. Holicheva,

Konstantin S. Kozlov,

Daniil A. Boiko

et al.

npj Biofilms and Microbiomes, Journal Year: 2025, Volume and Issue: 11(1)

Published: Jan. 14, 2025

Biofilms are critical for understanding environmental processes, developing biotechnology applications, and progressing in medical treatments of various infections. Nowadays, a key limiting factor biofilm analysis is the difficulty obtaining large datasets with fully annotated images. This study introduces versatile approach creating synthetic images employing deep generative modeling techniques, including VAEs, GANs, diffusion models, CycleGAN. Synthetic can significantly improve training computer vision models automated analysis, as demonstrated application Mask R-CNN detection model. The represents advance field research, offering scalable solution generating high-quality data working different strains microorganisms at stages formation. Terabyte-scale be easily generated on personal computers. A web provided on-demand generation

Language: Английский

Citations

0
Top 20 Influential AI-Based Technologies in Chemistry DOI Creative Commons
Valentine P. Ananikov

Published: April 12, 2024

The beginning and ripening of digital chemistry is analyzed focusing on the role artificial intelligence (AI) in an expected leap chemical sciences to bring this area next evolutionary level. analytic description selects highlights top 20 AI-based technologies 7 broader themes that are reshaping field. It underscores integration tools such as machine learning, big data, twins, Internet Things (IoT), robotic platforms, smart control processes, virtual reality blockchain, among many others, enhancing research methods, educational approaches, industrial practices chemistry. significance study lies its focused overview how these innovations foster a more efficient, sustainable, innovative future sciences. This article not only illustrates transformative impact but also draws new pathways chemistry, offering broad appeal researchers, educators, industry professionals embrace advancements for addressing contemporary challenges

Language: Английский

Citations

2
Microfluidic Platform with Precisely Controlled Hydrodynamic Parameters and Integrated Features for Generation of Microvortices to Accurately Form and Monitor Biofilms in Flow DOI Creative Commons

Keqing Wen,

Anna A. Gorbushina, Karin Schwibbert

et al.

ACS Biomaterials Science & Engineering, Journal Year: 2024, Volume and Issue: 10(7), P. 4626 - 4634

Published: June 21, 2024

Microorganisms often live in habitats characterized by fluid flow, and their adhesion to surfaces industrial systems or clinical settings may lead pipe clogging, microbially influenced corrosion, material deterioration, food spoilage, infections, human illness. Here, a novel microfluidic platform was developed investigate biofilm formation under precisely controlled (i) cell concentration, (ii) temperature, (iii) flow conditions. The central unit is single-channel designed ensure ultrahomogeneous condition its area, where features, e.g., with trapping properties, can be incorporated. In comparison static macroflow chamber assays for studies, chips allow situ monitoring of various regimes have better environment control smaller sample requirements. Flow simulations experiments fluorescent particles were used simulate bacteria the calculating velocity direction at microscale level. combination analysis strain injection showed that microtraps placed center channel efficient capturing determined positions study how conditions, especially microvortices, affect formation. exhibited improved performances terms homogeneity robustness vitro We anticipate presented suitable broad, versatile, high-throughput studies

Language: Английский

Citations

2
Recognition of Molecular Structure of Phosphonium Salts from the Visual Appearance of Material with Deep Learning Can Reveal Subtle Homologs DOI
Daniil A. Boiko, Daria M. Arkhipova, Valentine P. Ananikov

et al.

Small, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 10, 2024

Abstract Determining molecular structures is foundational in chemistry and biology. The notion of discerning simply from the visual appearance a material remained almost unthinkable until advent machine learning. This paper introduces pioneering approach bridging materials (both at micro‐ nanostructural levels) with traditional chemical structure analysis methods. Quaternary phosphonium salts are opted as model compounds, given their significant roles diverse medicinal fields ability to form homologs only minute intermolecular variances. research results successful creation neural network capable recognizing electron microscopy images material. performance evaluated related nature studied chemicals. Additionally, unsupervised domain transfer tested method use resulting on optical images, well test models trained directly. robustness further using complex system salt mixtures. To best authors' knowledge, this study offers first evidence feasibility nearly indistinguishable structures.

Language: Английский

Citations

1