Support vector regression based QSPR for the prediction of retention time of pesticide residues in gas chromatography–mass spectroscopy

Dashtbozorgi, Zahra; Golmohammadi, Hassan; Konoz, Elaheh

doi:10.1016/j.microc.2012.05.003

Cited by 19 publications

(6 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following the specified requirements, five optimal descriptors were obtained. There is a good correlation between these parameters and the half-life of POPs [34]. The meanings of each descriptor are shown in Table 5.…”

Section: Calculation and Filtering Of Molecular Descriptorsmentioning

confidence: 86%

Application of Machine Learning Methods to Predict the Air Half-Lives of Persistent Organic Pollutants

Zhang,

Xie,

Zhang

et al. 2023

Molecules

View full text Add to dashboard Cite

Persistent organic pollutants (POPs) are ubiquitous and bioaccumulative, posing potential and long-term threats to human health and the ecological environment. Quantitative structure–activity relationship (QSAR) studies play a guiding role in analyzing the toxicity and environmental fate of different organic pollutants. In the current work, five molecular descriptors are utilized to construct QSAR models for predicting the mean and maximum air half-lives of POPs, including specifically the energy of the highest occupied molecular orbital (HOMO_Energy_DMol3), a component of the dipole moment along the z-axis (Dipole_Z), fragment contribution to SAscore (SAscore_Fragments), subgraph counts (SC_3_P), and structural information content (SIC). The QSAR models were achieved through the application of three machine learning methods: partial least squares (PLS), multiple linear regression (MLR), and genetic function approximation (GFA). The determination coefficients (R2) and relative errors (RE) for the mean air half-life of each model are 0.916 and 3.489% (PLS), 0.939 and 5.048% (MLR), 0.938 and 5.131% (GFA), respectively. Similarly, the determination coefficients (R2) and RE for the maximum air half-life of each model are 0.915 and 5.629% (PLS), 0.940 and 10.090% (MLR), 0.939 and 11.172% (GFA), respectively. Furthermore, the mechanisms that elucidate the significant factors impacting the air half-lives of POPs have been explored. The three regression models show good predictive and extrapolation abilities for POPs within the application domain.

show abstract

Section: Calculation and Filtering Of Molecular Descriptorsmentioning

confidence: 86%

Application of Machine Learning Methods to Predict the Air Half-Lives of Persistent Organic Pollutants

Zhang,

Xie,

Zhang

et al. 2023

Molecules

View full text Add to dashboard Cite

show abstract

“…At present, China's pesticide proportioning methods have been gradually automated. The variable application technology have the performance like high pesticide utilization, low agricultural costs and low environmental pollution, which become the development direction of application technology [4][5] . However, its variable application equipment , which required for the development of agricultural sensors and control components, is still lack of development.…”

Section: Introductionmentioning

confidence: 99%

Research on precise proportioning method of matrine by applying spectral analysis technique

Jian,

Jisong,

Yongtao

et al. 2023

3rd International Conference on Laser, Optics, and Optoelectronic Technology (LOPET 2023)

View full text Add to dashboard Cite

In this paper, the methodology of real-time pesticide proportioning by spectral analysis technology is proposed for the first time. Used 0.5% Matrine as the research object. The spectral analyzer, flow cuvette, and peristaltic pump, etc., were combined used to create a real-time proportioning model. Specifically, the spectral data, which corresponding to different concentrations of Matrine under the transmission of the same light source, were measured. And then, its effective information was extracted for analysis. Finally, the least squares method was used to create the proportioning model. Through the experimental study, it can be demonstrated that the significant correlation between Matrine concentration and light intensity, with a linear R² of 0.93632, which correspond to the spectrum peak and Matrine concentration range from 659 nm, and 1.2 to 3.2ml/kg, respectively. In this paper, the viability of applying spectrum analysis technology to achieve pesticide formulation was proved. The system structure is simple, and effectively avoid the eliminating sophisticated control algorithms and system modeling, which can serve as a theoretical framework for accurate pesticide formulation.

show abstract

“…In addition, this approach enables the elucidation of the molecular mechanisms of retention phenomena in diverse stationary phases along with the design of new phases with required properties as well as to facilitate protein identification in proteomics studies (Kaliszan, 2007). Thus, several QSPR studies were reported in the literature to predict the t R of pesticide residues (Dashtbozorgi et al, 2013;Torrens & Castellano, 2014;Zdravković et al, 2018). Our research group has also been interested in QSPR studies for the prediction of chromatographic retention indices in the field of food science (foodinformatics) (Rojas et al, 2019;Rojas et al, 2018), as well as the in silico modeling of the water solubility of pesticides (Fioressi et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Foodinformatic prediction of the retention time of pesticide residues detected in fruits and vegetables using UHPLC/ESI Q-Orbitrap

et al. 2021

View full text Add to dashboard Cite

Support vector regression based QSPR for the prediction of retention time of pesticide residues in gas chromatography–mass spectroscopy

Cited by 19 publications

References 58 publications

Application of Machine Learning Methods to Predict the Air Half-Lives of Persistent Organic Pollutants

Application of Machine Learning Methods to Predict the Air Half-Lives of Persistent Organic Pollutants

Research on precise proportioning method of matrine by applying spectral analysis technique

Foodinformatic prediction of the retention time of pesticide residues detected in fruits and vegetables using UHPLC/ESI Q-Orbitrap

Contact Info

Product

Resources

About