ESM‐scan—A tool to guide amino acid substitutions DOI Creative Commons
Massimo G. Totaro, Uršula Vide,

Regina Zausinger

и другие.

Protein Science, Год журнала: 2024, Номер 33(12)

Опубликована: Ноя. 20, 2024

Protein structure prediction and (re)design have gone through a revolution in the last 3 years. The tremendous progress these fields has been almost exclusively driven by readily available machine learning algorithms applied to protein folding sequence design problems. Despite advancements, predicting site-specific mutational effects on stability function remains an unsolved problem. This is persistent challenge, mainly because free energy of large systems very difficult compute with absolute accuracy subtle changes structures are hard capture computational models. Here, we describe implementation use ESM-Scan, which uses ESM zero-shot predictor scan entire sequences for preferential amino acid changes, thus enabling silico deep scanning experiments. We benchmark ESM-Scan its predictive capabilities functionality using three publicly datasets proceed experimentally testing tool's performance challenging test case blue-light-activated diguanylate cyclase from Methylotenera species (MsLadC), where it accurately predicted importance highly conserved residue region involved allosteric product inhibition. Our experimental results show that ESM-zero shot model capable inferring set substitutions their correlation between fitness results. at https://huggingface.co/spaces/thaidaev/zsp.

Язык: Английский

Opportunities and Challenges for Machine Learning-Assisted Enzyme Engineering DOI Creative Commons
Jason Yang, Francesca-Zhoufan Li, Frances H. Arnold

и другие.

ACS Central Science, Год журнала: 2024, Номер 10(2), С. 226 - 241

Опубликована: Фев. 5, 2024

Enzymes can be engineered at the level of their amino acid sequences to optimize key properties such as expression, stability, substrate range, and catalytic efficiency-or even unlock new activities not found in nature. Because search space possible proteins is vast, enzyme engineering usually involves discovering an starting point that has some desired activity followed by directed evolution improve its "fitness" for a application. Recently, machine learning (ML) emerged powerful tool complement this empirical process. ML models contribute (1) discovery functional annotation known protein or generating novel with functions (2) navigating fitness landscapes optimization mappings between associated values. In Outlook, we explain how complements discuss future potential improved outcomes.

Язык: Английский

Процитировано

78
ESM-Scan - a tool to guide amino acid substitutions DOI Creative Commons
Massimo G. Totaro, Uršula Vide,

Regina Zausinger

и другие.

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2023, Номер unknown

Опубликована: Дек. 12, 2023

ABSTRACT Protein structure prediction and (re)design have gone through a revolution in the last three years. The tremendous progress these fields has been almost exclusively driven by readily available machine-learning algorithms applied to protein folding sequence design problems. Despite advancements, predicting site-specific mutational effects on stability function remains an unsolved problem. This is persistent challenge mainly because free energy of large systems very difficult compute with absolute accuracy subtle changes structures are also hard capture computational models. Here, we describe implementation use ESM-Scan, which uses ESM zero-shot predictor scan entire sequences for preferential amino acid changes, thus enabling in-silico deep scanning experiments. We benchmark ESM-Scan its predictive capabilities functionality using publicly datasets proceed experimentally evaluating tool’s performance challenging test case blue-light-activated diguanylate cyclase from Methylotenera species ( Ms LadC). used predict conservative highly conserved region this enzyme responsible allosteric product inhibition. Our experimental results show that ESM-zero shot model emerges as robust method inferring impact substitutions, especially when evolutionary functional insights intertwined. at https://huggingface.co/spaces/thaidaev/zsp

Язык: Английский

Процитировано

1
ESM‐scan—A tool to guide amino acid substitutions DOI Creative Commons
Massimo G. Totaro, Uršula Vide,

Regina Zausinger

и другие.

Protein Science, Год журнала: 2024, Номер 33(12)

Опубликована: Ноя. 20, 2024

Protein structure prediction and (re)design have gone through a revolution in the last 3 years. The tremendous progress these fields has been almost exclusively driven by readily available machine learning algorithms applied to protein folding sequence design problems. Despite advancements, predicting site-specific mutational effects on stability function remains an unsolved problem. This is persistent challenge, mainly because free energy of large systems very difficult compute with absolute accuracy subtle changes structures are hard capture computational models. Here, we describe implementation use ESM-Scan, which uses ESM zero-shot predictor scan entire sequences for preferential amino acid changes, thus enabling silico deep scanning experiments. We benchmark ESM-Scan its predictive capabilities functionality using three publicly datasets proceed experimentally testing tool's performance challenging test case blue-light-activated diguanylate cyclase from Methylotenera species (MsLadC), where it accurately predicted importance highly conserved residue region involved allosteric product inhibition. Our experimental results show that ESM-zero shot model capable inferring set substitutions their correlation between fitness results. at https://huggingface.co/spaces/thaidaev/zsp.

Язык: Английский

Процитировано

0