Transfer Learning Approach to Multitarget QSRR Modeling in RPLC.

QSRR is a valuable technique for the retention time predictions of small molecules. This aims to bridge the gap between molecular structure and chromatographic behavior, offering invaluable insights for analytical chemistry. Given the challenge of simultaneous target prediction with variable experimental conditions and the scarcity of comprehensive data sets for such predictive modelings in chromatography, this study introduces a transfer learning-based multitarget QSRR approach to enhance retention time prediction. Through a comparative study of four models, both with and without the transfer learning approach, the performance of both single and multitarget QSRR was evaluated based on Mean Squared Error (MSE) and R2 metrics. Individual models were also tested for their performance against benchmark studies in this field. The findings suggest that transfer learning based multitarget models exhibit potential for enhanced accuracy in predicting retention times of small molecules, presenting a promising avenue for QSRR modeling. These models will be highly beneficial for optimizing experimental conditions in method development by better retention time predictions in Reversed-Phase Liquid Chromatography (RPLC). The reliable and effective predictive capabilities of these models make them valuable tools for pharmaceutical research and development endeavors.

A multi-target QSRR approach to model retention times of small molecules in RPLC.

Quantitative structure-retention relationship models (QSRR) have been utilized as an alternative to costly and time-consuming separation analyses and associated experiments for predicting retention time. However, achieving 100 % accuracy in retention prediction is unrealistic despite the existence of various tools and approaches. The limitations of vast data availability and time complexity hinder the use of most algorithms for retention prediction. Therefore, in this study, we examined and compared two approaches for modelling retention time using a dataset of small molecules with retention times obtained at multiple conditions, referred to as multi-targets (five pH levels: 2.7, 3.5, 5, 6.5, and 8 at gradient times of 20 min of mobile phase). The first approach involved developing separate models for predicting retention time at each condition (single-target approach), while the second approach aimed to learn a single model for predicting retention across all conditions simultaneously (multi-target approach). Our findings highlight the advantages of the multi-target approach over the single-target modelling approach. The multi-target models are more efficient in terms of size and learning speed compared to the single-target models. These retention prediction models offer two-fold benefits. Firstly, they enhance knowledge and understanding of retention times, identifying molecular descriptors that contribute to changes in retention behaviour under different pH conditions. Secondly, these approaches can be extended to address other multi-target property prediction problems, such as multi-quantitative structure Property(X) relationship studies (mt-QS(X)R).

Risk of hematological malignancies among Chernobyl liquidators.

A case-control study of hematological malignancies was conducted among Chernobyl liquidators (accident recovery workers) from Belarus, Russia and Baltic countries to assess the effect of low- to medium-dose protracted radiation exposures on the relative risk of these diseases. The study was nested within cohorts of liquidators who had worked around the Chernobyl plant in 1986-1987. A total of 117 cases [69 leukemia, 34 non-Hodgkin lymphoma (NHL) and 14 other malignancies of lymphoid and hematopoietic tissue] and 481 matched controls were included in the study. Individual dose to the bone marrow and uncertainties were estimated for each subject. The main analyses were restricted to 70 cases (40 leukemia, 20 NHL and 10 other) and their 287 matched controls with reliable information on work in the Chernobyl area. Most subjects received very low doses (median 13 mGy). For all diagnoses combined, a significantly elevated OR was seen at doses of 200 mGy and above. The excess relative risk (ERR) per 100 mGy was 0.60 [90% confidence interval (CI) -0.02, 2.35]. The corresponding estimate for leukemia excluding chronic lymphoid leukemia (CLL) was 0.50 (90% CI -0.38, 5.7). It is slightly higher than but statistically compatible with those estimated from A-bomb survivors and recent low-dose-rate studies. Although sensitivity analyses showed generally similar results, we cannot rule out the possibility that biases and uncertainties could have led to over- or underestimation of the risk in this study.

Prediction of selectivity for enantiomeric separations of uncharged compounds by capillary electrophoresis involving dual cyclodextrin systems.

The single-isomer polyanionic cyclodextrin (CD) derivative heptakis-6-sulfato-beta-cyclodextrin (HSbetaCD) has been tested as chiral additive for the enantioseparation of non-steroidal anti-inflammatory drugs, such as fenoprofen, flurbiprofen, ibuprofen and ketoprofen, in capillary electrophoresis, using a pH 2.5 phosphoric acid-triethanolamine buffer in the reversed polarity mode. In most cases, the enantiomers of these acidic compounds, present in uncharged form at that pH, were only poorly resolved with HSbetaCD alone. However, the use of HSbetaCD in combination with the neutral CD derivative, heptakis-(2,3,6-tri-O-methyl)-beta-cyclodextrin (TMbetaCD), which has a particularly high enantioselectivity towards these compounds, has led to complete enantioresolution in reasonably low migration times in most cases. Affinity constants for the enantiomers with the two cyclodextrins were determined, using linear regression in a two-step approach. Affinity constants with the charged HSbetaCD were first calculated in single systems while those with the neutral TMbetaCD were determined in dual systems. Selectivity for the enantiomeric separation of these compounds in dual CD systems could be predicted using recently developed mathematical models.