Partial least squares-discriminant analysis (PLS-DA) is a versatile algorithm that can be used for predictive and descriptive modelling as well as for discriminative variable selection. However, versatility is both a blessing and a curse and the user needs to optimize a wealth of parameters before reaching reliable and valid outcomes. Over the past two decades, PLS-DA has demonstrated great success in modelling high-dimensional datasets for diverse purposes, e.g. product authentication in food analysis, diseases classification in medical diagnosis, and evidence analysis in forensic science. Despite that, in practice, many users have yet to grasp the essence of constructing a valid and reliable PLS-DA model. As the technology progresses, across every discipline, datasets are evolving into a more complex form, i.e. multi-class, imbalanced and colossal. Indeed, the community is welcoming a new era called big data. In this context, the aim of the article is two-fold: (a) to review, outline and describe the contemporary PLS-DA modelling practice strategies, and (b) to critically discuss the respective knowledge gaps that have emerged in response to the present big data era. This work could complement other available reviews or tutorials on PLS-DA, to provide a timely and user-friendly guide to researchers, especially those working in applied research.

Partial least squares-discriminant analysis (PLS-DA) for classification of high-dimensional (HD) data: a review of contemporary practice strategies and knowledge gaps

Machine learning is shaping up our lives in many ways. In analytical sciences, machine learning provides an unprecedented opportunity to extract information from complex or big datasets in chromatography, mass spectrometry, NMR, and spectroscopy, among others. This is especially the case in Raman and surface-enhanced Raman scattering (SERS) techniques where vibrational spectra of complex chemical mixtures are acquired as large datasets for the analysis or imaging of chemical systems. The classical linear methods of processing the information no longer suffice and thus machine learning methods for extracting the chemical information from Raman and SERS experiments have been implemented recently. In this review, we will provide a brief overview of the most common machine learning techniques employed in Raman, a guideline for new users to implement machine learning in their data analysis process, and an overview of modern applications of machine learning in Raman and SERS.

Deep learning and artificial intelligence methods for Raman and surface-enhanced Raman scattering

The past two decades have witnessed a rapid development of microreactors. A substantial number of reactions have been tested in microchemical systems, revealing the advantages of controlled residence time, enhanced transport efficiency, high product yield, and inherent safety. This review defines the microchemical system and describes its components and applications as well as the basic structures of micromixers. We focus on mixing, flow dynamics, and mass and heat transfer in microreactors along with three strategies for scaling up microreactors: parallel numbering-up, consecutive numbering-up, and scale-out. We also propose a possible methodology to design microchemical systems. Finally, we provide a summary and future prospects.

Design and Scaling Up of Microchemical Systems: A Review.

Alternative data mining/machine learning methods for the analytical evaluation of food quality and authenticity – A review

On the utilization of principal component analysis in laser-induced breakdown spectroscopy data analysis, a review

Chemometrics tools used in analytical chemistry: An overview

Application of RP–HPLC method in dissolution testing and statistical evaluation by NASSAM for simultaneous estimation of tertiary combined dosages forms ☆

A RP HPLC method for estimation of sildenafil citrate (SC) in tablet dosage form and seminal fluid was developed and validated. Best resolution was obtained with column Waters Spherisorb® C18 bonded silica, (5 µm, 4.6 x 250 mm) at 230 nm with retention time of 5.01 min. The mobile phase used was TEA (0.2%) pH adjusted at 3 with OPA and ACN (60:40) with flow rate of 1.0 mL/min. The method for estimation of sildenafil citrate in tablet dosage form was found to be linear, accurate, precise, sensitive and selective. Whereas the bioanalytical estimation of SC in seminal fluid was found to be in the range of 100 ng/mL to 10µg/mL. Method was found to be highly sensitive as LOD and LOQ were found to 0.3 µg/ml and 0.9µg/ml. The repeatability and reproducibility were within the range i.e. less than 2%.The accuracy of the method was 99.3%. The percentage purity was calculated for market formulation was 102.8%. The internal standard used for bioanalytical methods was Diclofenac sodium. The drug was extracted from seminal fluid by protein precipitation using ACN as precipitating agent. The linearity range was from 100.0ng/mL to 2.0µg/mL. The LOD and LOQ were found to 0.03µg/mL and 0.1µg/mL. The repeatability and reproducibility were within the range i.e. % RSD less than 15%. The accuracy of the method was 90.36%.and the extraction efficiency was found to be 98.25%. The stability of drug was found to be within the range i.e. less the 15%.

/pdf/rp-hplc-method-development-for-estimation-of-sildenafil-3iao06vxnn.pdf

RP-HPLC Method Development for Estimation of Sildenafil Citrate in Tablets and in Seminal Fluid

Analytical chemistry is the science of modeling quantitative measurements. Basically, it is the quantification of analytes in combined dosage forms samples which exhibits as the crucial part of the subject. Mainly, it is the radical apprehension of practical aspects of analysis, and the ability to identify a problem which cannot be solved by the existing analytical methods/techniques that motivate an analyst to develop creative approaches or new analytical methods. The answer to the all problems faced in analysis is chemometrics. Chemometrics has been defined as elementary tool for the implementation of mathematical and statistical methods to chemical measurements. Chemometric methods are often applied in situations when no sufficient theory is available for describing or solving analysis problems. The aim of chemometrics is to find out hidden relationships exist between the available data and the desired information. The prominent problems in chemistry are: recognition of the chemical structure from spectral data (spectral elucidation), quantitative analysis of chemical substances in complex mixtures (multivariate calibration), and determination of the origin of samples (cluster analysis and classification), and prediction of properties or activities of chemical compounds or technological materials (quantitative structure-activity or structure-property relationships). This literary work includes the basics of chemometrics and its aid to put this novel analytical discipline into application to face the present challenges of analytical chemistry.

/pdf/is-chemo-metrics-showing-the-pathway-for-unsolved-questions-3copt9gse3.pdf

Is Chemo-Metrics Showing the Pathway for Unsolved Questions in Chemical / Drug Analysis?.

The study explains multivariate analytical methods named Classical Least Square (CLS), Inverse Least Square (ILS), and Principle Component Regression (PCR). In general, the term multivariate analysis leads to solving the problem having number of variables and in here it leads to evaluate the different drugs in various combinations. So to evaluate Ambroxol Hydrochloride (AMB), Paracetamol (PCM), Levocetrizine Dihydrochloride (LCZ) and Phenylephrine Hydrochloride (PHE) in pharmaceutical dosage form whether the later contains two, three or all of them. Thus, these methods were also called as multipurpose methods. To reach the goal first 36 different composite mixtures of all drugs were prepared and analyzed through UV- spectrophotometer and above mentioned all the three models (CLS, ILS and PCR) were depicted. The LOD and LOQ values for AMB, PCM, LCZ and PHE from these models were found to be 0.32 μg/mL, 0.29 μg/mL, 0.43μg/mL and 1.15μg/mL and 0.96 μg/mL, 0.87 μg/mL, 1.29 μg/mL and 3.45 μg/mL respectively which is very less than previous conventional methods. Then these models were applied on five different dosage forms having above drugs in binary, tertiary or quaternary combinations and mean recoveries of 101.4%, 100.9 %, 100.2%, 101.3% for CLS; 101.8%, 100.4 %, 100.2%, 100.7% for ILS; 100.8%, 100.3 %, 100.2%, 100.1% for PCR; for AMB , PCM, LCZ and PHE respectively. The statistics were applied to conclude that there is no significant difference between the methods. The accepted t-value (less than 5.42) of marketed samples confirms that these all methods are suitable for routine assay of selected drugs in binary/ tertiary or quaternarycombination.

/pdf/chemo-metric-evaluation-of-levocetrizine-dihydrochloride-4aj1qrjaoi.pdf

Chemo-Metric Evaluation of Levocetrizine Dihydrochloride, Paracetamol, Ambroxol Hydrochloride and Phenylephrine Hydrochloride in Pharmaceutical Dosage Forms.

G.S. Sarma

Papers

Chemometrics tools used in analytical chemistry: An overview

Application of RP–HPLC method in dissolution testing and statistical evaluation by NASSAM for simultaneous estimation of tertiary combined dosages forms ☆

RP-HPLC Method Development for Estimation of Sildenafil Citrate in Tablets and in Seminal Fluid

Is Chemo-Metrics Showing the Pathway for Unsolved Questions in Chemical / Drug Analysis?.

Chemo-Metric Evaluation of Levocetrizine Dihydrochloride, Paracetamol, Ambroxol Hydrochloride and Phenylephrine Hydrochloride in Pharmaceutical Dosage Forms.