A Multi-Objective Active Learning Platform and Web App for Reaction Optimization

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

<p class="first" id="d583771e152">We report the development of an open-source experimental design via Bayesian optimization platform for multi-objective reaction optimization. Using high-throughput experimentation (HTE) and virtual screening data sets containing high-dimensional continuous and discrete variables, we optimized the performance of the platform by fine-tuning the algorithm components such as reaction encodings, surrogate model parameters, and initialization techniques. Having established the framework, we applied the optimizer to real-world test scenarios for the simultaneous optimization of the reaction yield and enantioselectivity in a Ni/photoredox-catalyzed enantioselective cross-electrophile coupling of styrene oxide with two different aryl iodide substrates. Starting with no previous experimental data, the Bayesian optimizer identified reaction conditions that surpassed the previously human-driven optimization campaigns within 15 and 24 experiments, for each substrate, among 1728 possible configurations available in each optimization. To make the platform more accessible to nonexperts, we developed a graphical user interface (GUI) that can be accessed online through a web-based application and incorporated features such as condition modification on the fly and data visualization. This web application does not require software installation, removing any programming barrier to use the platform, which enables chemists to integrate Bayesian optimization routines into their everyday laboratory practices. </p>

Related collections

Most cited references 47

Record: found
Abstract: not found
Article: not found

Taking the Human Out of the Loop: A Review of Bayesian Optimization

Bobak Shahriari, Kevin Swersky, Ziyu Wang … (2016)

0 comments Cited 811 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Analysis of the structural diversity, substitution patterns, and frequency of nitrogen heterocycles among U.S. FDA approved pharmaceuticals.

Edon Vitaku, David Smith, Jon Njardarson (2014)

Nitrogen heterocycles are among the most significant structural components of pharmaceuticals. Analysis of our database of U.S. FDA approved drugs reveals that 59% of unique small-molecule drugs contain a nitrogen heterocycle. In this review we report on the top 25 most commonly utilized nitrogen heterocycles found in pharmaceuticals. The main part of our analysis is divided into seven sections: (1) three- and four-membered heterocycles, (2) five-, (3) six-, and (4) seven- and eight-membered heterocycles, as well as (5) fused, (6) bridged bicyclic, and (7) macrocyclic nitrogen heterocycles. Each section reveals the top nitrogen heterocyclic structures and their relative impact for that ring type. For the most commonly used nitrogen heterocycles, we report detailed substitution patterns, highlight common architectural cores, and discuss unusual or rare structures.

0 comments Cited 705 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Planning chemical syntheses with deep neural networks and symbolic AI

Mike Preuss, Mark Waller, Marwin H. S. Segler (2018)

To plan the syntheses of small organic molecules, chemists use retrosynthesis, a problem-solving technique in which target molecules are recursively transformed into increasingly simpler precursors. Computer-aided retrosynthesis would be a valuable tool but at present it is slow and provides results of unsatisfactory quality. Here we use Monte Carlo tree search and symbolic artificial intelligence (AI) to discover retrosynthetic routes. We combined Monte Carlo tree search with an expansion policy network that guides the search, and a filter network to pre-select the most promising retrosynthetic steps. These deep neural networks were trained on essentially all reactions ever published in organic chemistry. Our system solves for almost twice as many molecules, thirty times faster than the traditional computer-aided search method, which is based on extracted rules and hand-designed heuristics. In a double-blind AB test, chemists on average considered our computer-generated routes to be equivalent to reported literature routes.