Machine learning‐based prediction of enzyme substrate scope: Application to bacterial nitrilases

Descriptor-augmented machine learning for enzyme-chemical interaction predictions

Descriptors play a pivotal role in enzyme design for the greener synthesis of biochemicals, as they could characterize enzymes and chemicals from the physicochemical and evolutionary perspective. This study examined the effects of various descriptors on the performance of Random Forest model used for enzyme-chemical relationships prediction. We curated activity data of seven specific enzyme families from the literature and developed the pipeline for evaluation the machine learning model performance using 10-fold cross-validation. The influence of protein and chemical descriptors was assessed in three scenarios, which were predicting the activity of unknown relations between known enzymes and known chemicals (new relationship evaluation), predicting the activity of novel enzymes on known chemicals (new enzyme evaluation), and predicting the activity of new chemicals on known enzymes (new chemical evaluation). The results showed that protein descriptors significantly enhanced the classification performance of model on new enzyme evaluation in three out of the seven datasets with the greatest number of enzymes, whereas chemical descriptors appear no effect. A variety of sequence-based and structure-based protein descriptors were constructed, among which the esm-2 descriptor achieved the best results. Using enzyme families as labels showed that descriptors could cluster proteins well, which could explain the contributions of descriptors to the machine learning model. As a counterpart, in the new chemical evaluation, chemical descriptors made significant improvement in four out of the seven datasets, while protein descriptors appear no effect. We attempted to evaluate the generalization ability of the model by correlating the statistics of the datasets with the performance of the models. The results showed that datasets with higher sequence similarity were more likely to get better results in the new enzyme evaluation and datasets with more enzymes were more likely beneficial from the protein descriptor strategy. This work provides guidance for the development of machine learning models for specific enzyme families.

A multimodal Transformer Network for protein-small molecule interactions enhances predictions of kinase inhibition and enzyme-substrate relationships

The activities of most enzymes and drugs depend on interactions between proteins and small molecules. Accurate prediction of these interactions could greatly accelerate pharmaceutical and biotechnological research. Current machine learning models designed for this task have a limited ability to generalize beyond the proteins used for training. This limitation is likely due to a lack of information exchange between the protein and the small molecule during the generation of the required numerical representations. Here, we introduce ProSmith, a machine learning framework that employs a multimodal Transformer Network to simultaneously process protein amino acid sequences and small molecule strings in the same input. This approach facilitates the exchange of all relevant information between the two molecule types during the computation of their numerical representations, allowing the model to account for their structural and functional interactions. Our final model combines gradient boosting predictions based on the resulting multimodal Transformer Network with independent predictions based on separate deep learning representations of the proteins and small molecules. The resulting predictions outperform recently published state-of-the-art models for predicting protein-small molecule interactions across three diverse tasks: predicting kinase inhibitions; inferring potential substrates for enzymes; and predicting Michaelis constants KM. The Python code provided can be used to easily implement and improve machine learning predictions involving arbitrary protein-small molecule interactions.

A method for the systematic selection of enzyme panel candidates by solving the maximum diversity problem

Enzymes are being increasingly exploited for their potential as industrial biocatalysts. Establishing a portfolio of useful biocatalysts from large and diverse protein family is challenging and a systematic method for candidate selection promises to aid in this task. Moreover, accurate enzyme functional annotation can only be confidently guaranteed through experimental characterisation in the laboratory. The selection of catalytically diverse enzyme panels for experimental characterisation is also an important step for shedding light on the currently unannotated proteins in enzyme families. Current selection methods often lack efficiency and scalability, and are usually non-systematic. We present a novel algorithm for the automatic selection of subsets from enzyme families. A tabu search algorithm solving the maximum diversity problem for sequence identity was designed and implemented, and applied to three diverse enzyme families. We show that this approach automatically selects panels of enzymes that contain high richness and relative abundance of the known catalytic functions, and outperforms other methods such as k-medoids.

Data-Driven Protein Engineering for Improving Catalytic Activity and Selectivity

Protein engineering is essential for altering the substrate scope, catalytic activity and selectivity of enzymes for applications in biocatalysis. However, traditional approaches, such as directed evolution and rational design, encounter the challenge in dealing with the experimental screening process of a large protein mutation space. Machine learning methods allow the approximation of protein fitness landscapes and the identification of catalytic patterns using limited experimental data, thus providing a new avenue to guide protein engineering campaigns. In this concept article, we review machine learning models that have been developed to assess enzyme-substrate-catalysis performance relationships aiming to improve enzymes through data-driven protein engineering. Furthermore, we prospect the future development of this field to provide additional strategies and tools for achieving desired activities and selectivities.

Predictive Minisci late stage functionalization with transfer learning

Structural diversification of lead molecules is a key component of drug discovery to explore chemical space. Late-stage functionalizations (LSFs) are versatile methodologies capable of installing functional handles on richly decorated intermediates to deliver numerous diverse products in a single reaction. Predicting the regioselectivity of LSF is still an open challenge in the field. Numerous efforts from chemoinformatics and machine learning (ML) groups have made strides in this area. However, it is arduous to isolate and characterize the multitude of LSF products generated, limiting available data and hindering pure ML approaches. We report the development of an approach that combines a message passing neural network and 13C NMR-based transfer learning to predict the atom-wise probabilities of functionalization for Minisci and P450-based functionalizations. We validated our model both retrospectively and with a series of prospective experiments, showing that it accurately predicts the outcomes of Minisci-type and P450 transformations and outperforms the well-established Fukui-based reactivity indices and other machine learning reactivity-based algorithms.

Structure-guided metagenome mining to tap microbial functional diversity

Scientists now have access to millions of accurate three-dimensional (3D) models of protein structures. How do we leverage 3D structural models to learn about microbial functions encoded in metagenomes? Here, we review recent developments using protein structural features to mine metagenomes from diverse environments ranging from the human gut to soil and ocean viromes. We compare 3D protein structural methods to characterize antibiotic resistance phenotypes, nutrient cycling, and host-drug-microbe interactions. Broadly, we encourage the scientific community to look beyond global sequence and structure alignments by considering fine-grained descriptors such as distance to ligand, active site, and tertiary interactions between amino acid residues scaling to microbiomes. Finally, we highlight structure-inspired approaches to chart new areas of microbial protein-coding sequence space.

A new paradigm in lignocellulolytic enzyme cocktail optimization: Free from expert-level prior knowledge and experimental datasets

Effectively pairing diverse lignocellulolytic enzyme cocktails with intricately structured lignocellulosic substrates is an enduring challenge for science and technology. To date, extensive trial-and-error remains the primary approach and no deep-learning methods were developed to address it due to limited experimental data and incomplete expert-level knowledge of enzyme-cocktail-substrate structure-dynamics-function relationships. Here, a novel model is developed to tackle this issue in efficient, cost-effective, and high-throughput manners. It needs no pre-labeled datasets, instead utilizing simple features, eliminating the reliance on expert-level prior knowledge of reaction mechanisms. Experimentally optimal combinations were found within predicted ranges of tailor-made combinations with precision of 91.98%, covering 80.00% of overall top-100. Practical tests demonstrated its effectiveness in narrowing down potential optimal combinations, speeding up targeted screening, and enabling efficient degradation of lignocellulosic biomass. The method has good applications in artificial proteins biosynthesis from low-value lignocellulosic straw, providing alternative solutions for biomass biorefining challenges in complex enzyme-cocktail-substrate interactions.

DASH: Dynamic Attention-Based Substructure Hierarchy for Partial Charge Assignment

We present a robust and computationally efficient approach for assigning partial charges of atoms in molecules. The method is based on a hierarchical tree constructed from attention values extracted from a graph neural network (GNN), which was trained to predict atomic partial charges from accurate quantum-mechanical (QM) calculations. The resulting dynamic attention-based substructure hierarchy (DASH) approach provides fast assignment of partial charges with the same accuracy as the GNN itself, is software-independent, and can easily be integrated in existing parametrization pipelines, as shown for the Open force field (OpenFF). The implementation of the DASH workflow, the final DASH tree, and the training set are available as open source/open data from public repositories.

Machine Learning Enables Prediction of Pyrrolysyl-tRNA Synthetase Substrate Specificity

Knowledge about the substrate scope for a given enzyme is informative for elucidating biochemical pathways and also for expanding applications of the enzyme. However, no general methods are available to accurately predict the substrate specificity of an enzyme. Pyrrolysyl-tRNA synthetase (PylRS) is a powerful tool for incorporating various noncanonical amino acids (NCAAs) into proteins, which enabled us to probe, image, rationally engineer, and evolve protein structure and function. However, the incorporation of a new NCAA typically requires the selection of large libraries of PylRS with randomized mutations at active sites, and this process requires multiple rounds of selection for each new substrate. Therefore, a single aminoacyl-tRNA synthetase with broad substrate promiscuity is ideal to facilitate widespread applications of the genetic NCAA incorporation technique. Herein, machine learning models were developed to predict the substrate specificity of PylRS to accept novel NCAAs that could be incorporated into proteins by three PylRS mutants. The models were built from a training set of 285 unique enzyme-substrate pairs of three PylRS mutants including IFRS, BtaRS, and MFRS against 95 NCAAs. The best BaggingTree (BT) model was then used for virtually screening a NCAAs library containing 1474 phenylalanine, tyrosine, tryptophan, and alanine analogues, and 156 NCAAs were predicted to be accepted by at least one of the three PylRS mutants. Then, 27 NCAAs including 24 positive and 3 negative substrates were experimentally tested for their activities, and 20 of the 24 positive substrates showed weak or strong activity and were accepted by at least one PylRS mutant, among which 11 NCAAs were never reported to be incorporated into proteins before. Three negative substrates did not show any activity. Experimental results suggested that the BT model provides a three-class classification accuracy of 0.69 and a binary classification accuracy of 0.86. This study expanded the substrate scope of three PylRS variants and provided a framework for developing machine learning models to predict substrate specificity of other PylRS variants.

Global plastic upcycling during and after the COVID-19 pandemic: The status and perspective

Plastic pollution has become one of the most pressing environmental issues worldwide since the vast majority of post-consumer plastics are hard to degrade in the environment. The coronavirus disease (COVID-19) pandemic had disrupted the previous effort of plastic pollution mitigation to a great extent due to the overflow of plastic-based medical waste. In the post-pandemic era, the remaining challenge is how to motivate global action towards a plastic circular economy. The need for one package of sustainable and systematic plastic upcycling approaches has never been greater to address such a challenge. In this review, we summarized the threat of plastic pollution during COVID-19 to public health and ecosystem. In order to solve the aforementioned challenges, we present a shifting concept, regeneration value from plastic waste, that provides four promising pathways to achieve a sustainable circular economy: 1) Increasing reusability and biodegradability of plastics; 2) Transforming plastic waste into high-value products by chemical approaches; 3) The closed-loop recycling can be promoted by biodegradation; 4) Involving renewable energy into plastic upcycling. Additionally, the joint efforts from different social perspectives are also encouraged to create the necessary economic and environmental impetus for a circular economy.

A general model to predict small molecule substrates of enzymes based on machine and deep learning

For most proteins annotated as enzymes, it is unknown which primary and/or secondary reactions they catalyze. Experimental characterizations of potential substrates are time-consuming and costly. Machine learning predictions could provide an efficient alternative, but are hampered by a lack of information regarding enzyme non-substrates, as available training data comprises mainly positive examples. Here, we present ESP, a general machine-learning model for the prediction of enzyme-substrate pairs with an accuracy of over 91% on independent and diverse test data. ESP can be applied successfully across widely different enzymes and a broad range of metabolites included in the training data, outperforming models designed for individual, well-studied enzyme families. ESP represents enzymes through a modified transformer model, and is trained on data augmented with randomly sampled small molecules assigned as non-substrates. By facilitating easy in silico testing of potential substrates, the ESP web server may support both basic and applied science.

In-depth analysis of biocatalysts by microfluidics: An emerging source of data for machine learning

Nowadays, the vastly increasing demand for novel biotechnological products is supported by the continuous development of biocatalytic applications which provide sustainable green alternatives to chemical processes. The success of a biocatalytic application is critically dependent on how quickly we can identify and characterize enzyme variants fitting the conditions of industrial processes. While miniaturization and parallelization have dramatically increased the throughput of next-generation sequencing systems, the subsequent characterization of the obtained candidates is still a limiting process in identifying the desired biocatalysts. Only a few commercial microfluidic systems for enzyme analysis are currently available, and the transformation of numerous published prototypes into commercial platforms is still to be streamlined. This review presents the state-of-the-art, recent trends, and perspectives in applying microfluidic tools in the functional and structural analysis of biocatalysts. We discuss the advantages and disadvantages of available technologies, their reproducibility and robustness, and readiness for routine laboratory use. We also highlight the unexplored potential of microfluidics to leverage the power of machine learning for biocatalyst development.

Discrimination of psychrophilic enzymes using machine learning algorithms with amino acid composition descriptor

Introduction

Psychrophilic enzymes are a class of macromolecules with high catalytic activity at low temperatures. Cold-active enzymes possessing eco-friendly and cost-effective properties, are of huge potential application in detergent, textiles, environmental remediation, pharmaceutical as well as food industry. Compared with the time-consuming and labor-intensive experiments, computational modeling especially the machine learning (ML) algorithm is a high-throughput screening tool to identify psychrophilic enzymes efficiently.

Methods

In this study, the influence of 4 ML methods (support vector machines, K-nearest neighbor, random forest, and naïve Bayes), and three descriptors, i.e., amino acid composition (AAC), dipeptide combinations (DPC), and AAC + DPC on the model performance were systematically analyzed.

Results and discussion

Among the 4 ML methods, the support vector machine model based on the AAC descriptor using 5-fold cross-validation achieved the best prediction accuracy with 80.6%. The AAC outperformed than the DPC and AAC + DPC descriptors regardless of the ML methods used. In addition, amino acid frequencies between psychrophilic and non-psychrophilic proteins revealed that higher frequencies of Ala, Gly, Ser, and Thr, and lower frequencies of Glu, Lys, Arg, Ile,Val, and Leu could be related to the protein psychrophilicity. Further, ternary models were also developed that could classify psychrophilic, mesophilic, and thermophilic proteins effectively. The predictive accuracy of the ternary classification model using AAC descriptor via the support vector machine algorithm was 75.8%. These findings would enhance our insight into the cold-adaption mechanisms of psychrophilic proteins and aid in the design of engineered cold-active enzymes. Moreover, the proposed model could be used as a screening tool to identify novel cold-adapted proteins.

Data-driven enzyme engineering to identify function-enhancing enzymes

Identifying function-enhancing enzyme variants is a 'holy grail' challenge in protein science because it will allow researchers to expand the biocatalytic toolbox for late-stage functionalization of drug-like molecules, environmental degradation of plastics and other pollutants, and medical treatment of food allergies. Data-driven strategies, including statistical modeling, machine learning, and deep learning, have largely advanced the understanding of the sequence-structure-function relationships for enzymes. They have also enhanced the capability of predicting and designing new enzymes and enzyme variants for catalyzing the transformation of new-to-nature reactions. Here, we reviewed the recent progresses of data-driven models that were applied in identifying efficiency-enhancing mutants for catalytic reactions. We also discussed existing challenges and obstacles faced by the community. Although the review is by no means comprehensive, we hope that the discussion can inform the readers about the state-of-the-art in data-driven enzyme engineering, inspiring more joint experimental-computational efforts to develop and apply data-driven modeling to innovate biocatalysts for synthetic and pharmaceutical applications.

Redesigning plant specialized metabolism with supervised machine learning using publicly available reactome data

The immense structural diversity of products and intermediates of plant specialized metabolism (specialized metabolites) makes them rich sources of therapeutic medicine, nutrients, and other useful materials. With the rapid accumulation of reactome data that can be accessible on biological and chemical databases, along with recent advances in machine learning, this review sets out to outline how supervised machine learning can be used to design new compounds and pathways by exploiting the wealth of said data. We will first examine the various sources from which reactome data can be obtained, followed by explaining the different machine learning encoding methods for reactome data. We then discuss current supervised machine learning developments that can be employed in various aspects to help redesign plant specialized metabolism.

Beyond sequence: Structure-based machine learning

Recent breakthroughs in protein structure prediction demarcate the start of a new era in structural bioinformatics. Combined with various advances in experimental structure determination and the uninterrupted pace at which new structures are published, this promises an age in which protein structure information is as prevalent and ubiquitous as sequence. Machine learning in protein bioinformatics has been dominated by sequence-based methods, but this is now changing to make use of the deluge of rich structural information as input. Machine learning methods making use of structures are scattered across literature and cover a number of different applications and scopes; while some try to address questions and tasks within a single protein family, others aim to capture characteristics across all available proteins. In this review, we look at the variety of structure-based machine learning approaches, how structures can be used as input, and typical applications of these approaches in protein biology. We also discuss current challenges and opportunities in this all-important and increasingly popular field.

Underground metabolism as a rich reservoir for pathway engineering

Motivation

Bioproduction of value-added compounds is frequently achieved by utilizing enzymes from other species. However, expression of such heterologous enzymes can be detrimental due to unexpected interactions within the host cell. Recently, an alternative strategy emerged, which relies on recruiting side activities of host enzymes to establish new biosynthetic pathways. Although such low-level ‘underground’ enzyme activities are prevalent, it remains poorly explored whether they may serve as an important reservoir for pathway engineering.

Results

Here, we use genome-scale modeling to estimate the theoretical potential of underground reactions for engineering novel biosynthetic pathways in Escherichia coli. We found that biochemical reactions contributed by underground enzyme activities often enhance the in silico production of compounds with industrial importance, including several cases where underground activities are indispensable for production. Most of these new capabilities can be achieved by the addition of one or two underground reactions to the native network, suggesting that only a few side activities need to be enhanced during implementation. Remarkably, we find that the contribution of underground reactions to the production of value-added compounds is comparable to that of heterologous reactions, underscoring their biotechnological potential. Taken together, our genome-wide study demonstrates that exploiting underground enzyme activities could be a promising addition to the toolbox of industrial strain development.

Availability and implementation

The data and scripts underlying this article are available on GitHub at https://github.com/pappb/Kovacs-et-al-Underground-metabolism.

Supplementary information

Supplementary data are available at Bioinformatics online.

Biofoundry-assisted expression and characterization of plant proteins

Many goals in synthetic biology, including the elucidation and refactoring of biosynthetic pathways and the engineering of regulatory circuits and networks, require knowledge of protein function. In plants, the prevalence of large gene families means it can be particularly challenging to link specific functions to individual proteins. However, protein characterization has remained a technical bottleneck, often requiring significant effort to optimize expression and purification protocols. To leverage the ability of biofoundries to accelerate design-built-test-learn cycles, we present a workflow for automated DNA assembly and cell-free expression of plant proteins that accelerates optimization and enables rapid screening of enzyme activity. First, we developed a phytobrick-compatible Golden Gate DNA assembly toolbox containing plasmid acceptors for cell-free expression using Escherichia coli or wheat germ lysates as well as a set of N- and C-terminal tag parts for detection, purification and improved expression/folding. We next optimized automated assembly of miniaturized cell-free reactions using an acoustic liquid handling platform and then compared tag configurations to identify those that increase expression. We additionally developed a luciferase-based system for rapid quantification that requires a minimal 11-amino acid tag and demonstrate facile removal of tags following synthesis. Finally, we show that several functional assays can be performed with cell-free protein synthesis reactions without the need for protein purification. Together, the combination of automated assembly of DNA parts and cell-free expression reactions should significantly increase the throughput of experiments to test and understand plant protein function and enable the direct reuse of DNA parts in downstream plant engineering workflows.

New Trends in Bioremediation Technologies Toward Environment-Friendly Society: A Mini-Review

Today's environmental balance has been compromised by the unreasonable and sometimes dangerous actions committed by humans to maintain their dominance over the Earth's natural resources. As a result, oceans are contaminated by the different types of plastic trash, crude oil coming from mismanagement of transporting ships spilling it in the water, and air pollution due to increasing production of greenhouse gases, such as CO₂ and CH₄ etc., into the atmosphere. The lands, agricultural fields, and groundwater are also contaminated by the infamous chemicals viz., polycyclic aromatic hydrocarbons, pyrethroids pesticides, bisphenol-A, and dioxanes. Therefore, bioremediation might function as a convenient alternative to restore a clean environment. However, at present, the majority of bioremediation reports are limited to the natural capabilities of microbial enzymes. Synthetic biology with uncompromised supervision of ethical standards could help to outsmart nature's engineering, such as the CETCH cycle for improved CO₂ fixation. Additionally, a blend of synthetic biology with machine learning algorithms could expand the possibilities of bioengineering. This review summarized current state-of-the-art knowledge of the data-assisted enzyme redesigning to actively promote new research on important enzymes to ameliorate the environment.

Applications of artificial intelligence to enzyme and pathway design for metabolic engineering

Metabolic engineering for developing industrial strains capable of overproducing bioproducts requires good understanding of cellular metabolism, including metabolic reactions and enzymes. However, metabolic pathways and enzymes involved are still unknown for many products of interest, which presents a key challenge in their biological production. This challenge can be partly overcome by constructing novel biosynthetic pathways through enzyme and pathway design approaches. With the increase in bio-big data, data-driven approaches using artificial intelligence (AI) techniques are allowing more advanced protein and pathway design. In this paper, we review recent studies on AI-aided protein engineering and design, focusing on directed evolution that uses AI approaches to efficiently construct mutant libraries. Also, recent works of AI-aided pathway design strategies, including template-based and template-free approaches, are discussed.

Methodological Advances to Study Contaminant Biotransformation: New Prospects for Understanding and Reducing Environmental Persistence?

Complex microbial communities in environmental systems play a key role in the detoxification of chemical contaminants by transforming them into less active metabolites or by complete mineralization. Biotransformation, i.e., transformation by microbes, is well understood for a number of priority pollutants, but a similar level of understanding is lacking for many emerging contaminants encountered at low concentrations and in complex mixtures across natural and engineered systems. Any advanced approaches aiming to reduce environmental exposure to such contaminants (e.g., novel engineered biological water treatment systems, design of readily degradable chemicals, or improved regulatory assessment strategies to determine contaminant persistence a priori) will depend on understanding the causal links among contaminant removal, the key driving agents of biotransformation at low concentrations (i.e., relevant microbes and their metabolic activities), and how their presence and activity depend on environmental conditions. In this Perspective, we present the current understanding and recent methodological advances that can help to identify such links, even in complex environmental microbiomes and for contaminants present at low concentrations in complex chemical mixtures. We discuss the ensuing insights into contaminant biotransformation across varying environments and conditions and ask how much closer we have come to designing improved approaches to reducing environmental exposure to contaminants.