Molecular Breeding, Journal Year: 2024, Volume and Issue: 44(2)
Published: Feb. 1, 2024
Language: Английский
Chemosphere, Journal Year: 2024, Volume and Issue: 357, P. 141969 - 141969
Published: April 9, 2024
Language: Английский
Citations
12
Journal of Medical and Biological Engineering, Journal Year: 2024, Volume and Issue: 44(2), P. 231 - 243
Published: April 1, 2024
Language: Английский
Citations
12
Current Opinion in Structural Biology, Journal Year: 2024, Volume and Issue: 86, P. 102818 - 102818
Published: April 25, 2024
Deep learning is becoming increasingly relevant in drug discovery, from de novo design to protein structure prediction and synthesis planning. However, it often challenged by the small data regimes typical of certain discovery tasks. In such scenarios, deep approaches-which are notoriously 'data-hungry'-might fail live up their promise. Developing novel approaches leverage power low-data scenarios sparking great attention, future developments expected propel field further. This mini-review provides an overview recent low-data-learning analyzing hurdles advantages. Finally, we venture provide a forecast research directions for discovery.
Language: Английский
Citations
12
APL Machine Learning, Journal Year: 2024, Volume and Issue: 2(1)
Published: Jan. 5, 2024
Fluorescent organic dyes are extensively used in the design and discovery of new materials, photovoltaic cells, light sensors, imaging applications, medicinal chemistry, drug design, energy harvesting technologies, dye pigment industries, pharmaceutical among other things. However, designing synthesizing fluorescent with desirable properties for specific applications requires knowledge chemical physical previously studied molecules. It is a difficult task experimentalists to identify photophysical required molecule at negligible time financial cost. For this purpose, machine learning-based models highly demanding technique estimating may be an alternative approach density functional theory. In study, we 15 single proposed three different hybrid assess dataset 3066 materials predicting properties. The performance these was evaluated using evaluation parameters: mean absolute error, root squared coefficient determination (R2) on test-size data. All achieved highest accuracy 97.28%, 95.19%, 74.01% absorption wavelengths, emission quantum yields, respectively. These resultant outcomes ∼1.9%, ∼2.7%, ∼2.4% higher than recently reported best models’ values same This research promotes quick accurate production applications.
Language: Английский
Citations
11
Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 250, P. 123893 - 123893
Published: April 8, 2024
Language: Английский
Citations
11
Journal of Clinical Microbiology, Journal Year: 2024, Volume and Issue: 62(2)
Published: Jan. 29, 2024
The reliability of Fourier-transform infrared (FT-IR) spectroscopy for
Language: Английский
Citations
10
Artificial Intelligence Chemistry, Journal Year: 2024, Volume and Issue: 2(2), P. 100072 - 100072
Published: July 14, 2024
Artificial intelligence has brought crucial changes to the whole field of natural sciences. Myriads machine learning algorithms have been developed facilitate work experimental scientists. Molecular property prediction and drug synthesis planning become routine tasks. Moreover, inverse design compounds with tunable properties as well on-the-fly autonomous process optimization chemical space exploration became possible in silico. Affordable robotic platforms exist able perform thousands experiments every day, analyzing results tuning protocols. Despite this, most these developments get trapped at stage code or overlooked, limiting their use by Meanwhile, visibility number user-friendly tools technologies available date is too low compensate for this fact, rendering development novel therapeutic inefficient. In Review, we set goal bridge gap between modern scientists improve efficacy. Here survey advanced easy-to-use help medical chemists research, including those integrated technological processes during COVID-19 pandemic motivated need fast yet precise solutions. review how are industry clinics streamline production. These already transform current paradigm scientific thinking revolutionize not only medicinal chemistry, but
Language: Английский
Citations
9
ACS Applied Materials & Interfaces, Journal Year: 2024, Volume and Issue: 16(32), P. 41743 - 41765
Published: Aug. 5, 2024
The proliferation of misleading information and counterfeit products in conjunction with technical progress presents substantial worldwide issues. To address the issue counterfeiting, many tactics, such as use luminous anticounterfeiting systems, have been investigated. Nevertheless, traditional fluorescent compounds a restricted effectiveness. Cellulose nanocrystals (CNCs), known for their renewable nature outstanding qualities, present an excellent opportunity to develop intelligent, optically active materials formed due self-assembly behavior stimuli response. CNCs derivatives-based self-assemblies allow creation adaptable that may be used prevent counterfeiting. These integrate photophysical characteristics components stimuli-responsive behavior, enabling fibers, labels, films, hydrogels, inks. Despite attention, existing frequently fall short practical criteria limited knowledge poor performance comparisons. This review aims provide on latest developments anticounterfeit based derivatives. It also includes scope artificial intelligence (AI) near future. will emphasize potential uses these encourage future investigation this rapidly growing area study.
Language: Английский
Citations
9
Chemical Engineering Journal, Journal Year: 2024, Volume and Issue: 503, P. 158428 - 158428
Published: Dec. 9, 2024
Language: Английский
Citations
9
TrAC Trends in Analytical Chemistry, Journal Year: 2025, Volume and Issue: unknown, P. 118141 - 118141
Published: Jan. 1, 2025
Language: Английский
Citations
1