Combining retrosynthesis and mixed-integer optimization for minimizing the chemical inventory needed to realize a WHO essential medicines list

The access to essential medicines remains a problem in many low-income countries for logistic and expiration limits, among other factors. Enabling flexible replenishment and easier supply chain management by on demand manufacturing from stored starting materials provides a solution to this challenge. Recent developments in computer-aided chemical synthesis planning have benefited from machine learning in different aspects. In this manuscript, we use those techniques to perform a combined analysis of a WHO essential medicines list to identify synthetic routes that minimize chemical inventory that would be required to synthesize the all the active pharmaceutical ingredients. We use a synthesis planning tool to perform retrosynthetic analyses for 99 targets and solve a mixed-integer programming problem to select a combination of pathways that uses the minimal number of chemicals. This work demonstrates the technical feasibility of reducing storage of active pharmaceutical ingredients to a minimal inventory of starting materials.

[1]  Alán Aspuru-Guzik,et al.  Neural Networks for the Prediction of Organic Chemistry Reactions , 2016, ACS central science.

[2]  Bruhan Kaggwa,et al.  Threats posed by stockpiles of expired pharmaceuticals in low- and middle-income countries: a Ugandan perspective , 2017, Bulletin of the World Health Organization.

[3]  Piotr Dittwald,et al.  Computer-Assisted Synthetic Planning: The End of the Beginning. , 2016, Angewandte Chemie.

[4]  Michael G. Hutchings,et al.  Route Design in the 21st Century: The ICSYNTH Software Tool as an Idea Generator for Synthesis Prediction , 2015 .

[5]  E Schouten,et al.  Drug donations must be strictly regulated , 1995, BMJ.

[6]  Andrea Scozzafava,et al.  Synthesis and crystallographic analysis of new sulfonamides incorporating NO-donating moieties with potent antiglaucoma action. , 2011, Bioorganic & medicinal chemistry letters.

[7]  Regina Barzilay,et al.  Prediction of Organic Reaction Outcomes Using Machine Learning , 2017, ACS central science.

[8]  P. F. Kamba,et al.  Expiry of medicines in supply outlets in Uganda. , 2010, Bulletin of the World Health Organization.

[9]  A. Hill,et al.  Estimated costs of production and potential prices for the WHO Essential Medicines List , 2018, BMJ Global Health.

[10]  David Weininger,et al.  SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules , 1988, J. Chem. Inf. Comput. Sci..

[11]  Pierre Baldi,et al.  ReactionPredictor: Prediction of Complex Chemical Reactions at the Mechanistic Level Using Machine Learning , 2012, J. Chem. Inf. Model..

[12]  Piotr Dittwald,et al.  Computational design of syntheses leading to compound libraries or isotopically labelled targets , 2019, Chemical science.

[13]  F. Caturla,et al.  Synthesis and biological evaluation of 2-phenylpyran-4-ones: a new class of orally active cyclooxygenase-2 inhibitors. , 2004, Journal of medicinal chemistry.

[14]  William H. Green,et al.  Using Machine Learning To Predict Suitable Conditions for Organic Reactions , 2018, ACS central science.

[15]  Gregor Urban,et al.  Deep learning for chemical reaction prediction , 2018 .

[16]  B van der Heide,et al.  Assortment of drugs causes more problems than it solves , 1995, BMJ.

[17]  Isabelle Huys,et al.  Innovative Approaches to Increase Access to Medicines in Developing Countries , 2017, Front. Med..

[18]  Tohru Mizushima,et al.  Structure-activity relationship of celecoxib and rofecoxib for the membrane permeabilizing activity. , 2014, Bioorganic & medicinal chemistry.

[19]  Pieter P. Plehiers,et al.  A robotic platform for flow synthesis of organic compounds informed by AI planning , 2019, Science.

[20]  Bowen Liu,et al.  Retrosynthetic Reaction Prediction Using Neural Sequence-to-Sequence Models , 2017, ACS central science.

[21]  Marwin H. S. Segler,et al.  Neural-Symbolic Machine Learning for Retrosynthesis and Reaction Prediction. , 2017, Chemistry.

[22]  Andy Gray,et al.  Shortages of medicines: a complex global challenge. , 2012, Bulletin of the World Health Organization.

[23]  Constantine Bekas,et al.  “Found in Translation”: predicting outcomes of complex organic chemistry reactions using neural sequence-to-sequence models† †Electronic supplementary information (ESI) available: Time-split test set and example predictions, together with attention weights, confidence and token probabilities. See DO , 2017, Chemical science.

[24]  William H. Green,et al.  Computer-Assisted Retrosynthesis Based on Molecular Similarity , 2017, ACS central science.

[25]  Connor W. Coley,et al.  A graph-convolutional neural network model for the prediction of chemical reactivity , 2018, Chemical science.

[26]  Mike Preuss,et al.  Planning chemical syntheses with deep neural networks and symbolic AI , 2017, Nature.