Deep learning in spectral analysis: Modeling and imaging

Liu, Xuyang; An, Hongle; Cai, Wensheng; Shao, Xueguang

doi:10.1016/j.trac.2024.117612

Cited by 11 publications

(3 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The black-box nature of deep learning has always been a challenge. , To address this issue, many interpretable methods have been developed, among which perturbation-based methods are commonly used. , By perturbing different input features and monitoring the changes in predictions, key features can be identified. To enhance the interpretability of the AttenGpKa model, each heavy atom is masked to observe the corresponding changes in p K a values, thereby identifying key atoms or groups related to p K a values.…”

Section: Results and Discussionmentioning

confidence: 99%

See 1 more Smart Citation

AttenGpKa: A Universal Predictor of Solvation Acidity Using Graph Neural Network and Molecular Topology

An,

Liu,

Cai

et al. 2024

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

Rapid and accurate calculation of acid dissociation constant (pK a ) is crucial for designing chemical synthesis routes, optimizing catalysts, and predicting chemical behavior. Despite recent progress in machine learning, predicting solvation acidity, especially in nonaqueous solvents, remains challenging due to limited experimental data. This challenge arises from treating experimental values in different solvents as distinct data domains and modeling them separately. In this work, we treat both the solutes and solvents equally from a perspective of molecular topology and propose a highly universal framework called AttenGpKa for predicting solvation acidity. AttenGpKa is trained using 26,522 experimental pK a values from 60 pure and mixed solvents in the iBonD database. As a result, our model can simultaneously predict the pK a values of a compound in various solvents, including pure water, pure nonaqueous, and mixed solvents. AttenGpKa achieves universality by using graph neural networks and attention mechanisms to learn complex effects within solute and solvent molecules. Furthermore, encodings of both solute and solvent molecules are adaptively fused to simulate the influence of the solvent on acid dissociation. AttenGpKa demonstrates robust generalization in extensive validations. The interpretability studies further indicate that our model has effectively learnt electronic and solvent effects. A free-to-use software is provided to facilitate the use of AttenGpKa for pK a prediction.

show abstract

Section: Results and Discussionmentioning

confidence: 99%

“…The black-box nature of deep learning has always been a challenge. 48,49 To address this issue, many interpretable methods have been developed, among which perturbation-based methods are commonly used. 50,51 By perturbing different input features and monitoring the changes in predictions, key features can be identified.…”

Section: ■ Results and Discussionmentioning

confidence: 99%

AttenGpKa: A Universal Predictor of Solvation Acidity Using Graph Neural Network and Molecular Topology

An,

Liu,

Cai

et al. 2024

J. Chem. Inf. Model.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The initiatives of hyperspectral imaging (HSI) represent imminent forms of technological knowledge and inter-disciplinary inventions that are strikingly inspiring as these can be utilized in the detection of abnormalities across a range of utilizations [1][2][3][4][5][6][7][8]. With the help of advanced and state-of-the-art hyperspectral sensors, covering a wide spectral range, more data is available, and the complexity beyond the conventional human visual power or imaging technology is overcome.…”

Section: Introductionmentioning

confidence: 99%

Charting the evolution: bibliometric perspectives on anomaly detection within hyperspectral domains

Obaideen,

Bonny,

AlShabi

2024

Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imaging XXX

View full text Add to dashboard Cite

In this article the results of the disruption module in the hyperspectral image field are analyzed and present itself. The aim is to see the major concerns, techniques and potential areas that can be researched as topics in the bibliometric method. Highly specified hyper-spectral spectroscopy that can simultaneously analyze the spectral data beyond the visual spectrum down even to the nanoscale. It can be used for various reasons, including environmental management, agriculture, and mineralogy. Unlike small data systems, where patterns are simple to identify, in large scale systems, where there is huge data quantity to study, there should be a wide variety of complexity of algorithms to use in reliable anomaly detection. This research bases its methodology on a two-layer mechanism which is simply to conduct very thorough literature review and deep bibliometric analysis to showcase the innovations in the field of anomaly detection of hyperspectral radar. The role of the states of estimation and the parameters, trained and objective, filtered, control rules, and fuzzy logic are some aspects, among the many, that is coming to the fore during the anomaly detection process. This paper aims to carry out a detailed analysis to mainly focus on the technical and methodological advancements that have reshaped the research area. It also shows that priority should be given to this aspect and that anime detection is the most challenging part of hyperspectral. What is more, this process gives numerous valuable signals about potential routes for future research. The results point to the dominant feature of the developed strategy and analysis which was mostly based on the special of multi-dimensional and transdisciplinary thinking.

show abstract

Rapid assessment of heavy metal accumulation capability of Sedum alfredii using hyperspectral imaging and deep learning

Lu,

Nie,

Guo

et al. 2024

Ecotoxicology and Environmental Safety

View full text Add to dashboard Cite

Deep learning in spectral analysis: Modeling and imaging

Cited by 11 publications

References 68 publications

AttenGpKa: A Universal Predictor of Solvation Acidity Using Graph Neural Network and Molecular Topology

AttenGpKa: A Universal Predictor of Solvation Acidity Using Graph Neural Network and Molecular Topology

Charting the evolution: bibliometric perspectives on anomaly detection within hyperspectral domains

Rapid assessment of heavy metal accumulation capability of Sedum alfredii using hyperspectral imaging and deep learning

Contact Info

Product

Resources

About