Controlled sulfation of mixed-linkage glucan by Response Surface Methodology for the development of biologically applicable polysaccharides.

Endogenous and exogenous sulfated polysaccharides exhibit potent biological activities, including inhibiting blood coagulation and protein interactions. Controlled chemical sulfation of alternative polysaccharides holds promise to overcome limited availability and heterogeneity of naturally sulfated polysaccharides. Here, we established reaction parameters for the controlled sulfation of the abundant cereal polysaccharide, mixed-linkage ß(1,3)/ß(1,4)-glucan (MLG), using Box-Behnken Design of Experiments (BBD) and Response Surface Methodology (RSM). The optimization of the degree-of-substitution (DS) was externally validated through the production of sulfated MLGs (S-MLGs) with observed DS and Mw values deviating less than 20% and 30% from the targeted values, respectively. Simultaneous optimization of DS and Mw resulted in the same range of deviation from the targeted value. S-MLGs with DS > 1 demonstrated a modest anticoagulation effect versus heparin, and a greater P-selectin affinity than fucoidan. As such, this work provides a route to medically important polymers from an economical agricultural polysaccharide.

Enhancing reaction-based de novo design using a multi-label reaction class recommender.

Reaction-based de novo design refers to the in-silico generation of novel chemical structures by combining reagents using structural transformations derived from known reactions. The driver for using reaction-based transformations is to increase the likelihood of the designed molecules being synthetically accessible. We have previously described a reaction-based de novo design method based on reaction vectors which are transformation rules that are encoded automatically from reaction databases. A limitation of reaction vectors is that they account for structural changes that occur at the core of a reaction only, and they do not consider the presence of competing functionalities that can compromise the reaction outcome. Here, we present the development of a Reaction Class Recommender to enhance the reaction vector framework. The recommender is intended to be used as a filter on the reaction vectors that are applied during de novo design to reduce the combinatorial explosion of in-silico molecules produced while limiting the generated structures to those which are most likely to be synthesisable. The recommender has been validated using an external data set extracted from the recent medicinal chemistry literature and in two simulated de novo design experiments. Results suggest that the use of the recommender drastically reduces the number of solutions explored by the algorithm while preserving the chance of finding relevant solutions and increasing the global synthetic accessibility of the designed molecules.

Anthropogenic biases in chemical reaction data hinder exploratory inorganic synthesis.

Most chemical experiments are planned by human scientists and therefore are subject to a variety of human cognitive biases1, heuristics2 and social influences3. These anthropogenic chemical reaction data are widely used to train machine-learning models4 that are used to predict organic5 and inorganic6,7 syntheses. However, it is known that societal biases are encoded in datasets and are perpetuated in machine-learning models8. Here we identify as-yet-unacknowledged anthropogenic biases in both the reagent choices and reaction conditions of chemical reaction datasets using a combination of data mining and experiments. We find that the amine choices in the reported crystal structures of hydrothermal synthesis of amine-templated metal oxides9 follow a power-law distribution in which 17% of amine reactants occur in 79% of reported compounds, consistent with distributions in social influence models10-12. An analysis of unpublished historical laboratory notebook records shows similarly biased distributions of reaction condition choices. By performing 548 randomly generated experiments, we demonstrate that the popularity of reactants or the choices of reaction conditions are uncorrelated to the success of the reaction. We show that randomly generated experiments better illustrate the range of parameter choices that are compatible with crystal formation. Machine-learning models that we train on a smaller randomized reaction dataset outperform models trained on larger human-selected reaction datasets, demonstrating the importance of identifying and addressing anthropogenic biases in scientific data.

Prediction of synthetic accessibility based on commercially available compound databases.

A compound's synthetic accessibility (SA) is an important aspect of drug design, since in some cases computer-designed compounds cannot be synthesized. There have been several reports on SA prediction, most of which have focused on the difficulties of synthetic reactions based on retro-synthesis analyses, reaction databases and the availability of starting materials. We developed a new method of predicting SA using commercially available compound databases and molecular descriptors. SA was estimated from the probability of existence of substructures consisting of the compound in question, the number of symmetry atoms, the graph complexity, and the number of chiral centers of the compound. The probabilities of the existence of given substructures were estimated based on a compound library. The predicted SA results reproduced the expert manual assessments with a Pearson correlation coefficient of 0.56. Since our method required a compound database and not a reaction database, it should be easy to customize the prediction for compound vendors. The correlation between the sales price of approved drugs and the SA values was also examined and found to be weak. The price most likely depends on the total cost of development and other factors.