Enterprise AI Analysis
Genome Mining of Acinetobacter nosocomialis J2 Using Artificial Intelligence Reveals a Highly Efficient Acid Phosphatase for Phosphate Solubilisation
Authors: Kaixu Chen, Huiling Huang, Xiao Yu, Jing Zhang, Chunming Zhou, Zhong Yao, Zheng Xu, Yang Liu, Yang Sun
Publication Date: 2026-01-21
Abstract: Excessive application of chemical fertilisers has led to soil phosphorus immobilisation and aquatic eutrophication, making the development of highly efficient acid/neutral phosphatases crucial for sustainable phosphorus utilisation. In this study, we systematically investigated strain J2, which was isolated from phosphate-contaminated soil in Laoshan, Nanjing, China. 16S rRNA gene sequence analysis identified this strain as Acinetobacter nosocomialis J2, with 99.78% sequence similarity. Whole-genome sequencing generated a 3.83 Mb genome with a GC content of 38.59%, revealing multiple phospho-metabolism-related enzyme genes, including phospholipase C and a/ß-hydrolases. A large language model-based protein representation learning strategy was employed to mine acid/neutral phosphatase genes from the genome, in which the model learned contextual and functional features from known phosphatase sequences and was used to identify semantically similar genes within the J2 genome. This approach predicted nine phosphatase candidate sequences, including AnACPase, a putative acid/neutral phosphatase. Biochemical characterisation showed that AnACPase exhibits optimal activity at pH 6.0 and 50 °C, with a Km value of 0.2454 mmol/L for the p-NPP substrate, indicating high substrate affinity. Mn2+ and Ni2+ significantly enhanced enzyme activity, whereas Cu2+ and Zn2+ strongly inhibited it. Soil remediation experiments further validated the application potential of AnACPase, which solubilised 171.56 mg/kg of phosphate within seven days. Overall, this study highlights the advantages of deep learning-assisted genome mining for functional enzyme discovery and provides a novel technological pathway for the bioremediation of phosphorus-polluted soils.
Keywords: Acinetobacter nosocomialis, genome, artificial intelligence, acid/neutral phosphatases, bioremediation
Revolutionizing Phosphate Remediation with AI-Driven Enzyme Discovery
This research pioneers the use of Large Language Models (LLMs) and Artificial Intelligence (AI) for genome mining, leading to the discovery of AnACPase, a highly efficient acid/neutral phosphatase from Acinetobacter nosocomialis J2. This enzyme offers a promising solution for bioremediation of phosphorus-polluted soils, addressing critical environmental challenges posed by agricultural runoff and eutrophication.
0
Sequence Similarity to A. nosocomialis J2
0
Genome Size
0
Phosphatase Candidates Identified by AI
0
Phosphate Solubilized in 7 days by AnACPase
Deep Analysis & Enterprise Applications
Select a topic to dive deeper, then explore the specific findings from the research, rebuilt as interactive, enterprise-focused modules.
AI-Driven Genome Mining
The study innovatively applies a large language model (LLM)-based protein representation learning strategy to identify potential acid/neutral phosphatase genes. This approach leverages contextual and functional features from known phosphatase sequences, enabling the identification of semantically similar genes even with low sequence identity, a significant advancement over traditional homology-based methods like BLAST or HMMER.
This method successfully predicted nine phosphatase candidate sequences from the Acinetobacter nosocomialis J2 genome, including AnACPase, which was subsequently validated experimentally. This highlights AI's capability to discover functionally related but evolutionarily divergent enzymes, greatly enhancing the efficiency of enzyme discovery.
AnACPase Enzyme Characterization
Biochemical characterisation of AnACPase revealed optimal activity at pH 6.0 and 50 °C. It demonstrated high substrate affinity with a Km value of 0.2454 mmol/L for the p-NPP substrate. This classifies AnACPase as a metal-dependent hydrolase, consistent with purple acid phosphatase (PAP) family enzymes.
The enzyme's activity was significantly enhanced by Mn2+ and Ni2+, suggesting their role as cofactors, while Cu2+ and Zn2+ strongly inhibited activity, likely due to competitive binding or oxidative modification. This detailed characterization provides insights into its catalytic mechanism and potential for industrial applications.
Bioremediation Potential
Soil remediation experiments validated AnACPase's application potential, showing it solubilised 171.56 mg/kg of phosphate within seven days under non-optimized laboratory conditions. This demonstrates the enzyme's ability to remain functional in a complex soil matrix, offering a supplementary strategy for phosphate management.
The findings suggest a novel technological pathway for the bioremediation of phosphorus-polluted soils, which is critical for sustainable phosphorus utilization and mitigating environmental issues like aquatic eutrophication caused by excessive chemical fertilizer application.
AI-Assisted Enzyme Discovery & Validation Workflow
Strain Isolation & Pre-screening (Phosphate-contaminated soils, Laoshan, Nanjing)
→
16S rRNA & Whole-Genome Sequencing (Acinetobacter nosocomialis J2 identified)
→
LLM-Based Protein Representation Learning (Contextual & functional feature extraction from known phosphatases)
→
Semantic Similarity Search (Identify 9 candidate phosphatase genes in J2 genome, incl. AnACPase)
→
Heterologous Expression & Purification (AnACPase in E. coli BL21(DE3))
→
Biochemical Characterization (Optimal pH/temp, Km, metal ion effects)
→
Soil Remediation Validation (171.56 mg/kg phosphate solubilized in 7 days)
| Feature | Traditional Methods | AI-Driven Genome Mining (This Study) |
|---|---|---|
| Primary Mechanism | Sequence homology, conserved domain alignment (BLAST, HMMER) | LLM-based protein representation learning, semantic similarity |
| Identification Scope | Well-characterized families, close homologues | Distantly related enzymes, novel classes with low sequence identity |
| Efficiency | Can be labor-intensive for novel functions | Efficient candidate prioritization, accelerates discovery |
| Output | Annotated genes based on known motifs | Functionally similar genes with high semantic confidence |
| Limitations |
|
|
Quantifying the Impact: Reduced Environmental Remediation Costs
Implementing AI-driven enzyme discovery for bioremediation can significantly reduce manual labor and chemical costs associated with traditional phosphorus removal methods. Estimate your potential savings.
Potential Annual Savings
$0
Annual Hours Reclaimed
0
Phased Rollout for Bioremediation Solutions
Phase 1: AI Model Customization & Data Integration
Tailor the LLM-based genome mining model to specific environmental remediation needs and integrate relevant genomic and environmental metadata. Establish data pipelines for continuous learning.
Phase 2: Enzyme Optimization & Production Scaling
Utilize AI to further engineer AnACPase for enhanced stability, activity, and substrate specificity. Develop large-scale fermentation processes for cost-effective enzyme production.
Phase 3: Field Trials & Regulatory Approval
Conduct controlled field trials in phosphorus-polluted environments to validate efficacy and environmental safety. Secure necessary regulatory approvals for widespread application.
Phase 4: Commercial Deployment & Monitoring
Deploy AnACPase-based bioremediation solutions across affected sites. Implement continuous monitoring and AI-driven feedback loops to optimize long-term performance and adaptation.
Ready to Transform Your Operations?
Leverage cutting-edge AI for enzyme discovery and sustainable environmental solutions. Our team is ready to help you implement these advanced biotechnologies.
Ready to Get Started?
Book Your Free Consultation.
Let's Discuss Your AI Strategy!
Lets Discuss Your Needs
Select a Date
Sun
Mon
Tue
Wed
Thu
Fri
Sat