Contents lists available at ScienceDirect Biotechnology Advances journal homepage: www.elsevier.com/locate/biotechadv Research review paper Microalgae with artifcial intelligence: A digitalized perspective on genetics, systems and products Sin Yong Teng a , Guo Yong Yew b , Kateřina Sukačová c , Pau Loke Show b, ⁎ , Vítězslav Máša a, ⁎ , Jo-Shu Chang d,e,f a Brno University of Technology, Institute of Process Engineering, Technická 2896/2, 616 69, Brno, Czech Republic b Department of Chemical and Environmental Engineering, Faculty of Science and Engineering, University of Nottingham Malaysia, Jalan Broga, 43500 Semenyih, Selangor, Malaysia c Global Change Research Institute of the Czech Academy of Sciences, Bělidla 986/4a, Brno 603 00, Czech Republic d Department of Chemical and Materials Engineering, College of Engineering, Tunghai University, Taichung 407, Taiwan e Department of Chemical Engineering, National Cheng Kung University, Tainan 701, Taiwan f Research Center for Smart Sustainable Circular Economy, Tunghai University, Taichung 407, Taiwan ARTICLE INFO Keywords: Microalgae Artifcial intelligence Genetic engineering Process optimization System design Process integration ABSTRACT With recent advances in novel gene-editing tools such as RNAi, ZFNs, TALENs, and CRISPR-Cas9, the possibility of altering microalgae toward designed properties for various application is becoming a reality. Alteration of microalgae genomes can modify metabolic pathways to give elevated yields in lipids, biomass, and other components. The potential of such genetically optimized microalgae can give a “domino efect” in further providing optimization leverages down the supply chain, in aspects such as cultivation, processing, system design, process integration, and revolutionary products. However, the current level of understanding the functional information of various microalgae gene sequences is still primitive and insufcient as microalgae genome sequences are long and complex. From this perspective, this work proposes to link up this knowledge gap between microalgae genetic information and optimized bioproducts using Artifcial Intelligence (AI). With the recent acceleration of AI research, large and complex data from microalgae research can be properly ana- lyzed by combining the cutting-edge of both felds. In this work, the most suitable class of AI algorithms (such as active learning, semi-supervised learning, and meta-learning) are discussed for diferent cases of microalgae applications. This work concisely reviews the current state of the research milestones and highlight some of the state-of-art that has been carried out, providing insightful future pathways. The utilization of AI algorithms in microalgae cultivation, system optimization, and other aspects of the supply chain is also discussed. This work opens the pathway to a digitalized future for microalgae research and applications. 1. Introduction Microalgae are industrially important unicellular organisms with photosynthesis potential to convert carbon dioxide, sunlight, and nu- trients into carbohydrates, lipid, and potentially many industrially important compounds (Chew et al., 2017). As a source of modern bioenergy, microalgae are regarded as the third generation of biofuels due to its theoretical carbon-neutral lifecycle (Dragone et al., 2010), non-competitiveness with agricultural or food crops, and possibilities for vertical and high-density cultivation system designs. In this feld, microalgae can produce a wide range of fuel such as biodiesel (Chisti, 2008), jet-fuel (Bwapwa et al., 2018a, 2017), hydrogen (Benemann, 2000), syngas (Beneroso et al., 2013), etc. Moreover, microalgae can be harvested and processed to act as raw material for protein-rich food, natural dyes, pharmaceutical products (Khan et al., 2018), etc. Due to a large plethora of diferent microalgae species and strains (Araujo et al., 2011), there are many possibilities of microalgae property that can be cultivated, giving diferent functionality. In the current microalgae research-to-commercialization value chain, the research procedure by identifying the functionality and purpose of microalgae application. Subsequently, high-throughput screening of microalgae strains is carried out by batch experimentation (Taleb et al., 2015). Although previous experimentation and literature data can be used for screening, it is common that the operating https://doi.org/10.1016/j.biotechadv.2020.107631 Received 26 July 2020; Received in revised form 8 September 2020; Accepted 8 September 2020 ⁎ Corresponding authors. E-mail addresses: Sin.Yong.Teng@vut.cz (S.Y. Teng), keby5ygy@nottingham.edu.my (G.Y. Yew), sukacova.k@czechglobe.cz (K. Sukačová), PauLoke.Show@nottingham.edu.my (P.L. Show), masa@fme.vutbr.cz (V. Máša), changjs@mail.ncku.edu.tw (J.-S. Chang). Biotechnology Advances 44 (2020) 107631 Available online 12 September 2020 0734-9750/ © 2020 Published by Elsevier Inc. T