Journal Article

Computational planning of the synthesis of complex natural products

Dittwald, Piotr, Gołębiowska, Patrycja, Gajewska, Ewa P., Badowski, Tomasz, Mlynarski, Jacek, Grzybowski, Bartosz A., Popik, Oskar, Staszewska-Krajewska, Olga, Molga, Karol, Klucznik, Tomasz, Beker, Wiktor, Bayly, Alison A., Szymkuć, Sara, Scheidt, Karl A., Mikulak-Klucznik, Barbara, Mrksich, Milan

2020

Overview

Training algorithms to computationally plan multistep organic syntheses has been a challenge for more than 50 years 1 – 7 . However, the field has progressed greatly since the development of early programs such as LHASA 1 , 7 , for which reaction choices at each step were made by human operators. Multiple software platforms 6 , 8 – 14 are now capable of completely autonomous planning. But these programs ‘think’ only one step at a time and have so far been limited to relatively simple targets, the syntheses of which could arguably be designed by human chemists within minutes, without the help of a computer. Furthermore, no algorithm has yet been able to design plausible routes to complex natural products, for which much more far-sighted, multistep planning is necessary 15 , 16 and closely related literature precedents cannot be relied on. Here we demonstrate that such computational synthesis planning is possible, provided that the program’s knowledge of organic chemistry and data-based artificial intelligence routines are augmented with causal relationships 17 , 18 , allowing it to ‘strategize’ over multiple synthetic steps. Using a Turing-like test administered to synthesis experts, we show that the routes designed by such a program are largely indistinguishable from those designed by humans. We also successfully validated three computer-designed syntheses of natural products in the laboratory. Taken together, these results indicate that expert-level automated synthetic planning is feasible, pending continued improvements to the reaction knowledge base and further code optimization. A synthetic route-planning algorithm, augmented with causal relationships that allow it to strategize over multiple steps, can design complex natural-product syntheses that are indistinguishable from those designed by human experts.

• Publisher: Nature Publishing Group UK,Nature Publishing Group
• Subject: 119/118 / 639/638/403/977 / 639/638/549 / 639/638/549/973 / 639/638/630 / Algorithms / Artificial intelligence / Artificial Intelligence - standards / Automation - methods / Automation - standards / Benzylisoquinolines - chemical synthesis / Benzylisoquinolines - chemistry / Biological Products - chemical synthesis / Chemistry Techniques, Synthetic - methods / Chemistry Techniques, Synthetic - standards / Chemistry, Organic - methods / Chemistry, Organic - standards / Chemists / Computation / Computer applications / Cost estimates / Design / Humanities and Social Sciences / Indans - chemical synthesis / Indans - chemistry / Indole Alkaloids - chemical synthesis / Indole Alkaloids - chemistry / Knowledge Bases / Knowledge bases (artificial intelligence) / Lactones - chemical synthesis / Lactones - chemistry / Logic / Macrolides - chemical synthesis / Macrolides - chemistry / multidisciplinary / Natural products / Optimization / Organic chemistry / Reproducibility of Results / Science / Science (multidisciplinary) / Sesquiterpenes - chemical synthesis / Sesquiterpenes - chemistry / Software - standards / Tetrahydroisoquinolines - chemical synthesis / Tetrahydroisoquinolines - chemistry