AUTHOR=Li Liangzhi , Zhou Lei , Jiang Chengying , Liu Zhenghua , Meng Delong , Luo Feng , He Qiang , Yin Huaqun TITLE=AI-driven pan-proteome analyses reveal insights into the biohydrometallurgical properties of Acidithiobacillia JOURNAL=Frontiers in Microbiology VOLUME=14 YEAR=2023 URL=https://www.frontiersin.org/journals/microbiology/articles/10.3389/fmicb.2023.1243987 DOI=10.3389/fmicb.2023.1243987 ISSN=1664-302X ABSTRACT=

Microorganism-mediated biohydrometallurgy, a sustainable approach for metal recovery from ores, relies on the metabolic activity of acidophilic bacteria. Acidithiobacillia with sulfur/iron-oxidizing capacities are extensively studied and applied in biohydrometallurgy-related processes. However, only 14 distinct proteins from Acidithiobacillia have experimentally determined structures currently available. This significantly hampers in-depth investigations of Acidithiobacillia’s structure-based biological mechanisms pertaining to its relevant biohydrometallurgical processes. To address this issue, we employed a state-of-the-art artificial intelligence (AI)-driven approach, with a median model confidence of 0.80, to perform high-quality full-chain structure predictions on the pan-proteome (10,458 proteins) of the type strain Acidithiobacillia. Additionally, we conducted various case studies on de novo protein structural prediction, including sulfate transporter and iron oxidase, to demonstrate how accurate structure predictions and gene co-occurrence networks can contribute to the development of mechanistic insights and hypotheses regarding sulfur and iron utilization proteins. Furthermore, for the unannotated proteins that constitute 35.8% of the Acidithiobacillia proteome, we employed the deep-learning algorithm DeepFRI to make structure-based functional predictions. As a result, we successfully obtained gene ontology (GO) terms for 93.6% of these previously unknown proteins. This study has a significant impact on improving protein structure and function predictions, as well as developing state-of-the-art techniques for high-throughput analysis of large proteomic data.