Machine learning guided cell-free expression maps the biochemical landscape of carbonic anhydrase
機械学習を用いた無細胞発現系による炭酸脱水酵素の生化学的ランドスケープのマッピング (AI 翻訳)
Lazar JT, Komp E, Martinez I, Zolkin K, Notin PM, Saleh S, Landwehr G, Kim K, Tian A, Shapero B, Karim AS, Marks D, Beckham GT, Jewett MC
🤖 gxceed AI 要約
日本語
炭酸脱水酵素はCO2水和反応を高速で触媒し、産業的CO2回収への応用が期待される。本論文では、無細胞発現とガス状CO2比色アッセイを組み合わせたハイスループットプラットフォームを開発し、炭酸脱水酵素のフィットネスランドスケープを網羅的に解析した。96種の天然ホモログから耐熱性変異体を同定し、4,365の単一アミノ酸置換を評価。機械学習モデルを用いて95℃で活性を維持する最優良酵素を設計した。
English
Carbonic anhydrases are promising for industrial carbon capture due to their high CO2 hydration rates. This paper presents a high-throughput cell-free platform with a colorimetric assay to map the fitness landscape of carbonic anhydrases. They identified a thermostable variant from Aquificota, tested over 4,365 single mutations, and used zero-shot and supervised machine learning to engineer an enzyme retaining activity at 95°C.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本ではCCUS技術の実用化が進んでおり、特に2050年カーボンニュートラル達成に向けてCO2回収の効率化が重要課題。本論文のような酵素工学の進展は、安価で高性能なバイオベースのCO2回収プロセスの開発に寄与する可能性があり、日本の産業界や研究機関が注視すべき成果である。
In the global GX context
Globally, CCUS is a critical technology for decarbonization, but its cost remains high. This work demonstrates a novel machine-learning-guided enzyme engineering pipeline that could significantly reduce the cost of biological carbon capture by improving enzyme stability and activity. The approach is relevant to TCFD/ISSB frameworks that emphasize technological innovation for climate mitigation.
👥 読者別の含意
🔬研究者:This paper offers a high-throughput method for generating sequence-function data and benchmarking protein language models, which is valuable for the synthetic biology and enzyme engineering community.
🏢実務担当者:Companies developing biological carbon capture technologies can use the identified robust variants and the ML-guided design pipeline to accelerate their own enzyme development.
📄 Abstract（原文）
Carbonic anhydrases are among the fastest known biocatalysts, reversibly facilitating the hydration of CO2 to HCO3- at rates up to 10 7 s -1 , which warrants their investigation for industrial carbon capture technologies. However, engineering carbonic anhydrases to maintain stability under harsh industrial process conditions remains a key challenge, and sequence-to-function datasets compatible with machine learning to inform forward engineering are lacking. Here, we developed a high-throughput platform that couples cell-free gene expression with a gaseous CO2 colorimetric assay to map the fitness landscapes of carbonic anhydrases. From 96 diverse natural homologs, we identified a robust variant from the Aquificota phylum and conducted an exhaustive mutational scan and functional assessment of this enzyme at 70C and 90C, covering >99% of all single-amino acid substitutions (totaling 4,365 mutations assayed in 39,285 reactions). This biochemical landscape was used to benchmark 22 zero-shot protein fitness models and identify critical mutations that improved enzyme stability at 90C by more than three-fold. We then used both zero-shot protein language models and supervised learning to filter 419 model-generated variants from a ProteinMPNN library of 100,000 sequences, leading to a best-in-class enzyme that retained activity after incubation at 95C. This work demonstrates that integrating cell-free enzyme engineering with machine learning enables opportunities for high-throughput experimental measurements to benchmark and improve protein language models, accelerate design loops, and expand functional exploration within protein families where experimental information is limited.
🔗 Provenance — このレコードを発見したソース
- Research Square https://doi.org/10.64898/2026.07.07.736810first seen 2026-07-09 04:26:57
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。