Trends in artificial intelligence, machine learning, and chemometrics applied to chemical data

Houhou, Rola; Bocklitz, Thomas

doi:10.1002/ansa.202000162

Cited by 80 publications

(40 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, Principal Component Analysis (PCA) is a multivariate statistical method to group variables and highlight their relative contributions to other variables based on variance. In contrast, machine learning algorithms based on supervised learning are available, which provide extensive and reliable datasets and can offer significant advantages over traditional chemometrics methods with regards to the prediction of VOC responses,; Random Forest is one example [ 256 , 257 ].…”

Section: Exploiting Voc-mediated Signalling For Future Sustainable Ag...mentioning

confidence: 99%

Stress-Induced Volatile Emissions and Signalling in Inter-Plant Communication

Midzi

Jeffery

Baumann

et al. 2022

Plants

View full text Add to dashboard Cite

The sessile plant has developed mechanisms to survive the “rough and tumble” of its natural surroundings, aided by its evolved innate immune system. Precise perception and rapid response to stress stimuli confer a fitness edge to the plant against its competitors, guaranteeing greater chances of survival and productivity. Plants can “eavesdrop” on volatile chemical cues from their stressed neighbours and have adapted to use these airborne signals to prepare for impending danger without having to experience the actual stress themselves. The role of volatile organic compounds (VOCs) in plant–plant communication has gained significant attention over the past decade, particularly with regard to the potential of VOCs to prime non-stressed plants for more robust defence responses to future stress challenges. The ecological relevance of such interactions under various environmental stresses has been much debated, and there is a nascent understanding of the mechanisms involved. This review discusses the significance of VOC-mediated inter-plant interactions under both biotic and abiotic stresses and highlights the potential to manipulate outcomes in agricultural systems for sustainable crop protection via enhanced defence. The need to integrate physiological, biochemical, and molecular approaches in understanding the underlying mechanisms and signalling pathways involved in volatile signalling is emphasised.

show abstract

Section: Exploiting Voc-mediated Signalling For Future Sustainable Ag...mentioning

confidence: 99%

Stress-Induced Volatile Emissions and Signalling in Inter-Plant Communication

Midzi

Jeffery

Baumann

et al. 2022

Plants

View full text Add to dashboard Cite

show abstract

“…The ability of machine learning and deep learning to extract and decode the NIR signal from noise has been demonstrated to be effective, particularly in terms of quantitative analysis [30]. Hence approaches like machine learning and/or deep learning are employed [32,[61][62][63] wherein the raw NIR spectral data was utilized directly.…”

Section: Interpretation Of Nir Spectra Of Api Excipients and Blend-ni...mentioning

confidence: 99%

Machine Learning-Enabled NIR Spectroscopy in Assessing Powder Blend Uniformity: Clear-Up Disparities and Biases Induced by Physical Artefacts

Muthudoss¹,

Tewari

Rui³

et al. 2022

AAPS PharmSciTech

View full text Add to dashboard Cite

NIR spectroscopy is a non-destructive characterization tool for the blend uniformity (BU) assessment. However, NIR spectra of powder blends often contain overlapping physical and chemical information of the samples. Deconvoluting the information related to chemical properties from that associated with the physical effects is one of the major objectives of this work. We achieve this aim in two ways. Firstly, we identified various sources of variability that might affect the BU results. Secondly, we leverage the machine learning-based sophisticated data analytics processes. To accomplish the aforementioned objectives, calibration samples of amlodipine as an active pharmaceutical ingredient (API) with the concentrations ranging between 67 and 133% w/w (dose ~ 3.6% w/w), in powder blends containing excipients, were prepared using a gravimetric approach and assessed using NIR spectroscopic analysis, followed by HPLC measurements. The bias in NIR results was investigated by employing data quality metrics (DQM) and bias-variance decomposition (BVD). To overcome the bias, the clustered regression (non-parametric and linear) was applied. We assessed the model’s performance by employing the hold-out and k-fold internal cross-validation (CV). NIR-based blend homogeneity with low mean absolute error and an interval estimates of 0.674 (mean) ± 0.218 (standard deviation) w/w was established. Additionally, bootstrapping-based CV was leveraged as part of the NIR method lifecycle management that demonstrated the mean absolute error (MAE) of BU ± 3.5% w/w and BU ± 1.5% w/w for model generalizability and model transferability, respectively. A workflow integrating machine learning to NIR spectral analysis was established and implemented. Graphical Abstract Impact of various data learning approaches on NIR spectral data

show abstract

“…Therefore, the search for the best preprocessing method is vital, considering its impact on the subsequently performed data analysis and its outcome. These preprocessing methods can be employed to either remove noise contributions, replace missing values, interpret or remove baselines, or even a combination of these targets [ 61 , 62 , 63 ]. Variable selection methods, on the other hand, can guide the choice of method in practical data analysis [ 64 ].…”

Section: Chemometricsmentioning

confidence: 99%

The Application of Chemometrics in Metabolomic and Lipidomic Analysis Data Presentation for Halal Authentication of Meat Products

et al. 2022

View full text Add to dashboard Cite

The halal status of meat products is an important factor being considered by many parties, especially Muslims. Analytical methods that have good specificity for the authentication of halal meat products are important as quality assurance to consumers. Metabolomic and lipidomic are two useful strategies in distinguishing halal and non-halal meat. Metabolomic and lipidomic analysis produce a large amount of data, thus chemometrics are needed to interpret and simplify the analytical data to ease understanding. This review explored the published literature indexed in PubMed, Scopus, and Google Scholar on the application of chemometrics as a tool in handling the large amount of data generated from metabolomic and lipidomic studies specifically in the halal authentication of meat products. The type of chemometric methods used is described and the efficiency of time in distinguishing the halal and non-halal meat products using chemometrics methods such as PCA, HCA, PLS-DA, and OPLS-DA is discussed.

show abstract

Trends in artificial intelligence, machine learning, and chemometrics applied to chemical data

Cited by 80 publications

References 67 publications

Stress-Induced Volatile Emissions and Signalling in Inter-Plant Communication

Stress-Induced Volatile Emissions and Signalling in Inter-Plant Communication

Machine Learning-Enabled NIR Spectroscopy in Assessing Powder Blend Uniformity: Clear-Up Disparities and Biases Induced by Physical Artefacts

The Application of Chemometrics in Metabolomic and Lipidomic Analysis Data Presentation for Halal Authentication of Meat Products

Contact Info

Product

Resources

About