Genki N. Kanda, Taku Tsuzuki, Motoki Terada, Noriko Sakai, Naohiro Motozawa, Tomohiro Masuda, Mitsuhiro Nishida, Chihaya T. Watanabe, Tatsuki Higashi, Shuhei A. Horiguchi, Taku Kudo, Motohisa Kamei, Genshiro A. Sunagawa, Kenji Matsukuma, Takeshi Sakurada, Yosuke Ozawa, Masayo Takahashi, Koichi Takahashi, Tohru Natsume

Elife. 2022 Jun 28;11:e77007. doi:10.7554/eLife.77007

Robotic Search for Optimal Cell Culture in Regenerative Medicine

Uses the Maholo LabDroid and Batch Bayesian optimization (BBO) to screen a 7-dimensions parameter space.

Godfrey AG, Masquelin T, Hemmerle H.

Drug Discov Today. 2013 Sep;18(17-18):795-802. doi:10.1016/j.drudis.2013.03.001

A remote-controlled adaptive medchem lab: an innovative approach to enable drug discovery in the 21st Century.

Automated Synthesis Laboratory (ASL)

Steiner S, Wolf J, Glatzel S, Andreou A, Granda JM, Keenan G, Hinkley T, Aragon-Camarasa G, Kitson PJ, Angelone D, Cronin L.

Science. 2019 Jan 11;363(6423):eaav2211. doi: 10.1126/science.aav2211.

Organic synthesis in a modular robotic system driven by a chemical programming language.

“The physical routing that links the connected modules is described in [GraphML]”. Hardware-unknowing domain-specific language (DSL) is compiled in robot commands, so that the same DSL instructions can be executed on robots with different layouts but same equipment. The commands are first simulated to check for potential issues such as overfilling, etc. Valves etc. are connected to and commanded by the computer.

Coley CW, Thomas DA 3rd, Lummiss JAM, Jaworski JN, Breen CP, Schultz V, Hart T, Fishman JS, Rogers L, Gao H, Hicklin RW, Plehiers PP, Byington J, Piotti JS, Green WH, Hart AJ, Jamison TF, Jensen KF.

Science. 2019 Aug 9;365(6453):eaax1566. doi:10.1126/science.aax1566

A robotic platform for flow synthesis of organic compounds informed by AI planning.

An algorithm proposes a synthetic route for a robotic flow chemistry platform, an expect makes practical amendments for safety or efficiency, and the robot assembles the flow platform and runs the synthesis. Practical challenges remain, such as predicting solubility of the products to avoid clogging the pipes with precipitates.

Mikulak-Klucznik B, Gołębiowska P, Bayly AA, Popik O, Klucznik T, Szymkuć S, Gajewska EP, Dittwald P, Staszewska-Krajewska O, Beker W, Badowski T, Scheidt KA, Molga K, Mlynarski J, Mrksich M, Grzybowski BA.

Nature. 2020 Dec;588(7836):83-88. doi:10.1038/s41586-020-2855-y

Computational planning of the synthesis of complex natural products.

Searches for the shortest path in a graph of compounds. “computational synthesis planning”. “the program has been taught [100,000] mechanism-based reaction rules” “inclusion of [...] heuristics that prescribe how to strategize over multiple steps, taking into account how certain reaction choices imply succession (or elimination) of other transformations.” “allowing [...] to overcome local maxima” In a “Turing test“, evaluators could not distinguish plannings made by human and those made by the program. “When needed, organic chemists performing the syntheses were allowed to adjust reaction conditions [...] for the sake of optimization.”

Fuqua T, Jordan J, van Breugel ME, Halavatyi A, Tischer C, Polidoro P, Abe N, Tsai A, Mann RS, Stern DL, Crocker J.

Nature. 2020 Nov;587(7833):235-239. doi:10.1038/s41586-020-2816-5

Dense and pleiotropic regulatory information in a developmental enhancer

Study of the E3N enhancer of the shavenbaby (svb) gene. Immunohistochemistry automated with liquid handling robots. “sequence conservation is not an accurate predictor of the quantitative roles of individual sites in the E3N enhancer” “most mutations in E3N led to changes in transcriptional outputs, suggesting that regulatory information is distributed densely within this enhancer”

Meckin R.

Sci Technol Human Values. 2020 Nov;45(6):1220-1241. doi:10.1177/0162243919893757

Changing Infrastructural Practices: Routine and Reproducibility in Automated Interdisciplinary Bioscience.

Synthetic biologists studied by a sociologist.

A mobile robotic chemist.

Nature. 2020 Jul;583(7815):237-241. doi:10.1038/s41586-020-2442-2

Burger B, Maffettone PM, Gusev VV, Aitchison CM, Bai Y, Wang X, Li X, Alston BM, Li B, Clowes R, Rankin N, Harris B, Sprick RS, Cooper AI.

“The robot uses laser scanning and touch feedback, rather than a vision system. It can therefore operate in complete darkness, if needed.“ “The robot operated autonomously over eight days, performing 688 experiments within a ten-variable experimental space, driven by a batched Bayesian search algorithm.”

AI Magazine, Spring 2016, Vol 37, No 1, pp 39–49

Hiroaki Kitano

Artificial Intelligence to Win the Nobel Prize and Beyond: Creating the Engine for Scientific Discovery

“Deep phenotyping”, “combinatorial hypothesis generation”, “advanced intelligence”.