Search

Artificial Intelligence is revolutionizing many aspects of the pharmaceutical industry. Deep learning models are now routinely applied to guide drug discovery projects leading to faster and improved findings, but there are still many tasks with enormous unrealized potential. One such task is the reaction yield prediction. Every year more than one fifth of all synthesis attempts result in product yields which are either zero or too low. This equates to chemical and human resources being spent on activities which ultimately do not progress the programs, leading to a triple loss when accounting for the cost of opportunity in time wasted. In this work we pre-train a BERT model on more than 16 million reactions from 4 different data sources, and fine tune it to achieve an uncertainty calibrated global yield prediction model. This model is an improvement upon state of the art not just from the increase in pre-train data but also by introducing a new embedding layer which solves a few limitations of SMILES and enables integration of additional information such as equivalents and molecule role into the reaction encoding, the model is called BERT Enriched Embedding (BEE). The model is benchmarked on an open-source dataset against a state-of-the-art synthesis focused BERT showing a near 20-point improvement in r2 score. The model is fine-tuned and tested on an internal company data benchmark, and a prospective study shows that the application of the model can reduce the total number of negative reactions (yield under 5%) ran in Janssen by at least 34%. Lastly, we corroborate the previous results through experimental validation, by directly deploying the model in an on-going drug discovery project and showing that it can also be used successfully as a reagent recommender due to its fast inference speed and reliable confidence estimation, a critical feature for industry application.

The stereoselective preparation of a novel 4′-spirocyclopropyl nucleoside analogue has been developed by using a semibenzilic Favorskii rearrangement of a 4′-(2-chloro-3-oxocyclobutyl)spirofuranose as a key step. These chiral spirocyclic intermediates, readily obtained on a multigram scale from chiral-pool starting materials, were shown to be highly suitable precursors for achieving full stereoselectivity in the reduction–ring contraction sequence. The downstream introduction of a nucleobase through Vorbrüggen glycosylation successfully resulted in the formation of the corresponding novel 4′-spirocyclic nucleoside analogue in a stereospecific manner.

The synthesis of cyclopropyl pinacol boronic esters from dibromocyclopropanes via Matteson–Pasto rearrangement is reported. The method is readily scalable and shows limited levels of stereoinduction, with a selectivity that is in part complementary to that observed in existing stereoselective borylcyclopropanation strategies. The method can be used to rapidly access borylcyclopropanes as interesting building blocks for diversely functionalized cyclopropanes.

Cyclopropane fusion of the only rotatable carbon-carbon bond in furanosyl nucleosides (i.e., exocyclic 4'-5') is a powerful design strategy to arrive at conformationally constrained analogues. Herein, we report a direct stereodivergent route toward the synthesis of the four possible configurations of 4-spirocyclopropane furanoses, which have been transformed into the corresponding 4'-spirocyclic adenosine analogues. The latter showed differential inhibition of the protein methyltransferase PRMT5-MEP50 complex, with one analogue inhibiting more effectively than adenosine itself, demonstrating the utility of rationally probing 4'-5' side chain orientations.

Novel C-4′,C-5′ cyclobutane-fused spirocyclic ribonucleoside analogues were prepared. Thermal [2 + 2] cycloaddition between dichloroketene and readily derived 4′-exo-methylene furanoses afforded a first entry to the required constrained ribofuranoses, relying on a carbonyl transposition sequence. Alternatively, an unusual stereoselective ionic [2 + 2] cycloaddition using methyl propiolate promoted by methylaluminoxane gave a complementary, more direct approach to such ribofuranoses. Further conversion to the constrained adenosine analogues revealed promising structure-dependent inhibition of the protein methyltransferase PRMT5:MEP50 complex in the (sub)micromolar range.

In this paper, we compare the most popular Atom-to-Atom Mapping (AAM) tools: ChemAxon,([1]) Indigo,([2]) RDTool,([3]) NameRXN (NextMove),([4]) and RXNMapper([5]) which implement different AAM algorithms. An open-source RDTool program was optimized, and its modified version ("new RDTool") was considered together with several consensus mapping strategies. The Condensed Graph of Reaction approach was used to calculate chemical distances and develop the "AAM fixer" algorithm for an automatized correction of erroneous mapping. The benchmarking calculations were performed on a Golden dataset containing 1851 manually mapped and curated reactions. The best performing RXNMapper program together with the AMM Fixer was applied to map the USPTO database. The Golden dataset, mapped USPTO and optimized RDTool are available in the GitHub repository https://github.com/Laboratoire-de-Chemoinformatique.

Despite the large variety of modified nucleosides that have been reported, the preparation of constrained 4 '-spirocyclic adenosine analogues has received very little attention. We discovered that the [2+2]-cycloaddition of dichloroketene on readily available 4 '-exo-methylene furanose sugars efficiently results in the diastereoselective formation of novel 4 '-spirocyclobutanones. The reaction mechanism was investigated via density functional theory (DFT) and found to proceed either via a non-synchronous or stepwise reaction sequence, controlled by the stereochemistry at the 3 '-position of the sugar substrate. The obtained dichlorocyclobutanones were converted into nucleoside analogues, providing access to a novel class of chiral 4 '-spirocyclobutyl adenosine mimetics in eight steps from commercially available sugars. Assessment of the biological activity of designed 4 '-spirocyclic adenosine analogues identified potent inhibitors for protein methyltransferase target PRMT5.

A novel class of substituted spiro[3.4]octanes can be accessed via a [2 + 2]-cycloaddition of dichloroketene on a readily prepared exo-methylene cyclopentane building block. This reaction sequence was found to be robust on a multigram scale and afforded a central spirocyclobutanone scaffold for carbocyclic nucleosides. The reactivity of this constrained building block was evaluated and compared to the corresponding 4'-spirocyclic furanose analogues. Density functional theory calculations were performed to support the observed selectivity in the carbonyl reduction of spirocyclobutanone building blocks. Starting from novel spirocyclic intermediates, we exemplified the preparation of an undescribed class of carbocyclic nucleoside analogues and provided a proof of concept for application as inhibitors for the protein methyltransferase target PRMT5.

Here, we discuss a reaction standardization protocol followed by a comparison of popular Atom-to-atom mapping (AAM) tools (ChemAxon, Indigo, RDTool, NextMove and RXNMapper) as well as some consensus AAM strategies. For this purpose, a dataset of 1851 manually curated and mapped reactions was prepared (the Golden dataset) and used as a reference set. It has been found that RXNMapper possesses the highest accuracy, despite the fact that it has some clear disadvantages. Finally, RXNMapper was selected as the best tool, and it was applied to map the USPTO dataset. The standardization protocol used to prepare the data, as well as the data itself are available in the GitHub repository https://github.com/Laboratoire-de-Chemoinformatique.

The quality of experimental data for chemical reactions is a critical consideration for any reaction-driven study. However, the curation of reaction data has not been extensively discussed in the literature so far. Here, we suggest a 4 steps protocol that includes the curation of individual structures (reactants and products), chemical transformations, reaction conditions and endpoints. Its implementation in Python3 using CGRTools toolkit has been used to clean three popular reaction databases Reaxys, USPTO and Pistachio. The curated USPTO database is available in the GitHub repository (Laboratoire-de-Chemoinformatique/Reaction_Data_Cleaning).

Pyrrolotriazines and related fused azaheterocycles have high potential for the synthesis of bioactive compounds, especially as a purine base isoster in carbon linked nucleosides. Although many structurally related compounds have already been synthesized and used in medicinal chemistry, pyrrolo[1,3,5]triazines have barely been described. The present work describes the synthesis of such heterocycles via condensation of 2-amino-3-ethoxycarbonylpyrrole with ethoxycarbonyliso(thio)cyanate. In a brief reactivity study of the obtained fused pyrroles, O- and S-alkylation, ester hydrolysis as well as regioselective bromination at the 6-position was demonstrated.