Enabling late-stage drug diversification by high-throughput experimentation with geometric deep learning

Late-stage functionalization is an economical approach to optimize the properties of drug candidates. However, the chemical complexity of drug molecules often makes late-stage diversification challenging. To address this problem, a late-stage functionalization platform based on geometric deep learning and high-throughput reaction screening was developed. Considering borylation as a critical step in late-stage functionalization, the computational model predicted reaction yields for diverse reaction conditions with a mean absolute error margin of 4-5%, while the reactivity of novel reactions with known and unknown substrates was classified with a balanced accuracy of 92% and 67%, respectively. The regioselectivity of the major products was accurately captured with a classifier F-score of 67%. When applied to 23 diverse commercial drug molecules, the platform successfully identified numerous opportunities for structural diversification. The influence of steric and electronic information on model performance was quantified, and a comprehensive simple user-friendly reaction format was introduced that proved to be a key enabler for seamlessly integrating deep learning and high-throughput experimentation for late-stage functionalization.

Machine Learning C-N Couplings: Obstacles for a General-Purpose Reaction Yield Prediction

Pd-catalyzed C-N couplings are commonplace in academia and industry. Despite their significance, finding suitable reaction conditions leading to a high yield, for instance, remains a challenging and time-consuming task which usually requires screening over many sets of conditions. To help select promising reaction conditions in the vast space of reagent combinations, machine learning is an emerging technique with a lot of promise. In this work, we assess whether the reaction yield of C-N couplings can be predicted from databases of chemical reactions. We test the generalizability of models both on challenging data splits and on a dedicated experimental test set. We find that, provided the chemical space represented by the training set is not left, the models perform well. However, the applicability domain is quickly left even for simple reactions of the same type, as, for instance, present in our plate test set. The results show that yield prediction for new reactions is possible from the algorithmic side but in practice is hindered by the available data. Most importantly, more data that cover the diversity in reagents are needed for a general-purpose prediction of reaction yields. Our findings also expose a challenge to this field in that it appears to be extremely deceiving to judge models based on literature data with test sets which are split off the same literature data, even when challenging splits are considered.

What can reaction databases teach us about Buchwald-Hartwig cross-couplings?

Despite the widespread and increasing usage of Pd-catalyzed C-N cross couplings, finding good conditions for these reactions can be challenging. Practitioners mostly rely on few methodology studies or anecdotal experience. This is surprising, since the advent of data-driven experimentation and the large amount of knowledge in databases allow for data-driven insight. In this work, we address this by analyzing more than 62 000 Buchwald-Hartwig couplings gathered from CAS, Reaxys and the USPTO. Our meta-analysis of the reaction performance generates data-driven cheatsheets for reaction condition recommendation. It also provides an interactive tool to find rarer ligands with optimal performance regarding user-selected substrate properties. With this we give practitioners promising starting points. Furthermore, we study bias and diversity in the literature and summarize the current state of the reaction data, including its pitfalls. Hence, this work will also be useful for future data-driven developments such as the optimization of reaction conditions via machine learning.

What can reaction databases teach us about Buchwald-Hartwig cross-couplings?

Despite the widespread and increasing usage of Pd-catalyzed C–N cross couplings, finding good conditions for these reactions can be challenging. Practitioners mostly rely on few methodology studies or anecdotal experience. This is surprising, since the advent of data-driven experimentation and the large amount of knowledge in databases allow for data-driven insight. In this work, we address this by analyzing more than 62 000 Buchwald–Hartwig couplings gathered from CAS, Reaxys and the USPTO. Our meta-analysis of the reaction performance generates data-driven cheatsheets for reaction condition recommendation. It also provides an interactive tool to find rarer ligands with optimal performance regarding user-selected substrate properties. With this we give practitioners promising starting points. Furthermore, we study bias and diversity in the literature and summarize the current state of the reaction data, including its pitfalls. Hence, this work will also be useful for future data-driven developments such as the optimization of reaction conditions via machine learning.

An analysis of the entire literature on Pd-catalyzed C–N couplings enables data-driven insight and provides recommendations for reaction conditions.

ChemPager: Now Expanded for Even Greener Chemistry

ChemPager is a freely available data analysis tool for analyzing, comparing and improving synthetic routes. Here, we present an expansion of this application that makes use of the functionality of the PMI Predictor, which the ACS Green Chemistry Institute Pharmaceutical Roundtable has recently published as a web application. This addition enables ChemPager to predict the cumulative process mass intensity of chemical routes, irrespective of their development status, by comparison with a set of reactions executed on large scale. The prediction of this core green chemistry metric aims to improve existing routes and help the decision-making process among route alternatives without the need for experimental data.

A Robust, Recyclable Resin for Decagram Scale Resolution of (±)-Mefloquine and Other Chiral N-Heterocycles

Decagram quantities of enantiopure (+)-mefloquine have been produced via kinetic resolution of racemic mefloquine using a ROMP-gel supported chiral acyl hydroxamic acid resolving agent. The requisite monomer was prepared in a few synthetic steps without chromatography and polymerization was safely performed on a >30 gram scale under ambient conditions. The reagent was readily regenerated and reused multiple times for the resolution of 150 grams of (±)-mefloquine and other chiral N-heterocylces.

Synthesis and stability of oxetane analogs of thalidomide and lenalidomide

Oxetanes are used in drug discovery to enable physicochemical and metabolic property enhancement for the structures to which they are grafted. An imide C═O to oxetane swap on thalidomide and lenalidomide templates provides analogs with similar physicochemical and in vitro properties of the parent drugs, with an important exception: oxetane analog 2 displays a clear differentiation with respect to human plasma stability. The prospect of limiting in vivo stability/metabolism, blocking in vivo racemization, and potentially altering teratogenicity is appealing.

The search for tricyanomethane (cyanoform)

Although listed in organic chemistry textbooks as one of the strongest carbon acids, and in spite of more than a hundred years of attempts to prepare the compound, tricyanomethane (cyanoform) has resisted isolation and characterization, either as the carbon-acid 1 or as the dicyanoketenimine tautomer 2. Only in the vapor phase at very low pressure has the compound been identified from its microwave spectrum. Here we review and partially repeat the preparative work. With the aid of spectroscopic and diffraction methods (including powder diffraction) we have identified some of the products obtained as: hydronium tricyanomethanide (3), (Z)-3-amino-2-cyano-3-iminoacrylimide (4), a co-crystal of 4 with sulfuric acid (or corresponding iminium salt), and an addition product of 2 with hydrochloric acid (5/6). Quantum-mechanical calculations at the MP2/6-311++g(2d,2p) level have been made to assess the relative energies of some of the molecules involved.

A Ru-Catalyzed Tandem Alkyne−Enone Coupling/Michael Addition: Synthesis of 4-Methylene-2,6-cis-tetrahydropyrans

[reaction: see text] A Ru-catalyzed tandem alkyne-enone coupling/Michael addition reaction is reported. It provides an efficient, atom-economic entry to 4-methylene-2,6-cis-tetrahydropyrans from simple, readily available homopropargylic alcohols and beta,gamma-unsaturated enones in good yields. Further functionalization of the resultant vinylsilane leads to the synthesis of either geometrically defined trisubstituted alkene exocyclic to the 2,6-cis-dihydropyran.