Synthetic Approaches to New Drugs Approved during 2018

Flick, Andrew C.; Leverett, Carolyn A.; Ding, Hong X.; McInturff, Emma; Fink, Sarah; Helal, Christopher J.; DeForest, Jacob C.; Morse, Peter D.; Mahapatra, Subham; O’Donnell, Christopher J

doi:10.1021/acs.jmedchem.0c00345

“…(b) Comparison of the route found by the model trained on the USPTO dataset with the literature route for Amenamevir. 37 The model can suggest a route comparable to the literature, differing in the sequence of steps and using similar reactions to those in the literature. The predicted route is found in 3.26 seconds.…”

Section: Reaction Datasets and Template Extractionmentioning

confidence: 92%

“…† The route predicted using the model trained on the USPTO dataset to Amenamevir is compared to the literature route. 37 Both routes vary in the order of the steps they take, with the predicted route preferring a standard amide coupling over the amide Schotten-Baumann. However, the predicted route displays reactivity conicts as deprotonation of the amine in the second step competes with the amide coupling.…”

Section: Exemplary Synthetic Routesmentioning

confidence: 99%

Datasets and Their Influence on the Development of Computer Assisted Synthesis Planning Tools in the Pharmaceutical Domain

Thakkar

¹

,

Kogej²,

Reymond³

et al. 2019

Preprint

View full text Add to dashboard Cite

<p>Computer Assisted Synthesis Planning (CASP) has gained considerable interest as of late. Herein we investigate a template-based retrosynthetic planning tool, trained on a variety of datasets consisting of up to 17.5 million reactions. We demonstrate that models trained on datasets such as internal Electronic Laboratory Notebooks (ELN), and the publicly available United States Patent Office (USPTO) extracts, are sufficient for the prediction of full synthetic routes to compounds of interest in medicinal chemistry. As such we have assessed the models on 1,731 compounds from 41 virtual libraries for which experimental results were known. Furthermore, we show that accuracy is a misleading metric for assessment of the ‘filter network’, and propose that the number of successfully applied templates, in conjunction with the overall ability to generate full synthetic routes be examined instead. To this end we found that the specificity of the templates comes at the cost of generalizability, and overall model performance. This is supplemented by a comparison of the underlying datasets and their corresponding models.</p>

show abstract

“…Amenamevir. 35 The model can suggest a route comparable to the literature, differing in the sequence of steps and using similar reactions to those in the literature. The predicted route is found in 3.26 seconds.…”

Section: Figure 5: A) Comparison To the Exemplary Synthesis Shown By mentioning

confidence: 92%

“…The route predicted using the model trained on the USPTO dataset to Amenamevir is compared to the literature route. 35 Both routes vary in the order of the steps they take, with the predicted route preferring a standard amide coupling over the amide Schotten-Baumann.…”

Section: Exemplary Synthetic Routesmentioning

confidence: 99%

Datasets and Their Influence on the Development of Computer Assisted Synthesis Planning Tools in the Pharmaceutical Domain

Thakkar

¹

,

Kogej

²

,

Reymod

³

et al. 2019

Preprint

View full text Add to dashboard Cite

<p>Computer Assisted Synthesis Planning (CASP) has gained considerable interest as of late. Herein we investigate a template-based retrosynthetic planning tool, trained on a variety of datasets consisting of up to 17.5 million reactions. We demonstrate that models trained on datasets such as internal Electronic Laboratory Notebooks (ELN), and the publicly available United States Patent Office (USPTO) extracts, are sufficient for the prediction of full synthetic routes to compounds of interest in medicinal chemistry. As such we have assessed the models on 1,731 compounds from 41 virtual libraries for which experimental results were known. Furthermore, we show that accuracy is a misleading metric for assessment of the ‘filter network’, and propose that the number of successfully applied templates, in conjunction with the overall ability to generate full synthetic routes be examined instead. To this end we found that the specificity of the templates comes at the cost of generalizability, and overall model performance. This is supplemented by a comparison of the underlying datasets and their corresponding models.</p>

show abstract

“…An important annual review of approved new drugs, as seen from the viewpoint of synthesis, has now reached year 2015 (Flick et al 2017). We have reviewed the changing face of organic synthesis with special emphasis on the current century, dealing with natural products, synthetics and their use as drugs (Brocksom et al 2015).…”

Section: Introductionmentioning

confidence: 99%

Impact of continuous flow chemistry in the synthesis of natural products and active pharmaceutical ingredients

Souza

¹

,

Galaverna

²

,

Souza

³

et al. 2018

An. Acad. Bras. Ciênc.

View full text Add to dashboard Cite

We present a comprehensive review of the advent and impact of continuous flow chemistry with regard to the synthesis of natural products and drugs, important pharmaceutical products and definitely responsible for a revolution in modern healthcare. We detail the beginnings of modern drugs and the large scale batch mode of production, both chemical and microbiological. The introduction of modern continuous flow chemistry is then presented, both as a technological tool for enabling organic chemistry, and as a fundamental research endeavor. This part details the syntheses of bioactive natural products and commercial drugs.

show abstract

Synthetic Approaches to New Drugs Approved during 2018

Cited by 47 publications

References 215 publications

Datasets and Their Influence on the Development of Computer Assisted Synthesis Planning Tools in the Pharmaceutical Domain

Datasets and Their Influence on the Development of Computer Assisted Synthesis Planning Tools in the Pharmaceutical Domain

Datasets and Their Influence on the Development of Computer Assisted Synthesis Planning Tools in the Pharmaceutical Domain

Impact of continuous flow chemistry in the synthesis of natural products and active pharmaceutical ingredients

Contact Info

Product

Resources

About