ProGAN: Protein solubility generative adversarial nets for data augmentation in DNN framework

Reconstituted Cell-free Translation Systems for Exploring Protein Folding and Aggregation

Protein folding is crucial for achieving functional three-dimensional structures. However, the process is often hampered by aggregate formation, necessitating the presence of chaperones and quality control systems within the cell to maintain protein homeostasis. Despite a long history of folding studies involving the denaturation and subsequent refolding of translation-completed purified proteins, numerous facets of cotranslational folding, wherein nascent polypeptides are synthesized by ribosomes and folded during translation, remain unexplored. Cell-free protein synthesis (CFPS) systems are invaluable tools for studying cotranslational folding, offering a platform not only for elucidating mechanisms but also for large-scale analyses to identify aggregation-prone proteins. This review provides an overview of the extensive use of CFPS in folding studies to date. In particular, we discuss a comprehensive aggregation formation assay of thousands of Escherichia coli proteins conducted under chaperone-free conditions using a reconstituted translation system, along with its derived studies.

Empowering Capacitive Devices: Harnessing Transfer Learning for Enhanced Data-Driven Optimization

Developing data-driven models has found successful applications in engineering tasks, such as material design, process modeling, and process monitoring. In capacitive devices like deionization and supercapacitors, there exists potential for applying this data-driven machine learning (ML) model in optimizing its potential use in energy-efficient separations or energy generation. However, these models are faced with limited datasets, and even in large quantities, the datasets are incomplete, limiting their potential use for successful data-driven modeling. Here, the success of transfer learning in resolving the challenges with limited datasets was exploited. A two-step data-driven ML modeling framework named ImputeNet involving training with ML-imputed datasets and then with clean datasets was explored. Through data imputation and transfer learning, it is possible to develop a data-driven model with acceptable metrics mirroring experimental measurements. By using the model, optimization studies using the genetic algorithm were implemented to analyze the solution under the Pareto optimality. This early insight can be used in the initial stage of experimental measurements to rapidly identify experimental conditions worthy of further investigation. Moreover, we expect that the insights from these results will drive accurate predictive modeling in other fields including healthcare, genomic data analysis, and environmental monitoring with incomplete datasets.

Meta learning addresses noisy and under-labeled data in machine learning-guided antibody engineering

Machine learning-guided protein engineering is rapidly progressing; however, collecting high-quality, large datasets remains a bottleneck. Directed evolution and protein engineering studies often require extensive experimental processes to eliminate noise and label protein sequence-function data. Meta learning has proven effective in other fields in learning from noisy data via bi-level optimization given the availability of a small dataset with trusted labels. Here, we leverage meta learning approaches to overcome noisy and under-labeled data and expedite workflows in antibody engineering. We generate yeast display antibody mutagenesis libraries and screen them for target antigen binding followed by deep sequencing. We then create representative learning tasks, including learning from noisy training data, positive and unlabeled learning, and learning out of distribution properties. We demonstrate that meta learning has the potential to reduce experimental screening time and improve the robustness of machine learning models by training with noisy and under-labeled training data.

VirusHound-I: prediction of viral proteins involved in the evasion of host adaptive immune response using the random forest algorithm and generative adversarial network for data augmentation

Throughout evolution, pathogenic viruses have developed different strategies to evade the response of the adaptive immune system. To carry out successful replication, some pathogenic viruses encode different proteins that manipulate the molecular mechanisms of host cells. Currently, there are different bioinformatics tools for virus research; however, none of them focus on predicting viral proteins that evade the adaptive system. In this work, we have developed a novel tool based on machine and deep learning for predicting this type of viral protein named VirusHound-I. This tool is based on a model developed with the multilayer perceptron algorithm using the dipeptide composition molecular descriptor. In this study, we have also demonstrated the robustness of our strategy for data augmentation of the positive dataset based on generative antagonistic networks. During the 10-fold cross-validation step in the training dataset, the predictive model showed 0.947 accuracy, 0.994 precision, 0.943 F1 score, 0.995 specificity, 0.896 sensitivity, 0.894 kappa, 0.898 Matthew's correlation coefficient and 0.989 AUC. On the other hand, during the testing step, the model showed 0.964 accuracy, 1.0 precision, 0.967 F1 score, 1.0 specificity, 0.936 sensitivity, 0.929 kappa, 0.931 Matthew's correlation coefficient and 1.0 AUC. Taking this model into account, we have developed a tool called VirusHound-I that makes it possible to predict viral proteins that evade the host's adaptive immune system. We believe that VirusHound-I can be very useful in accelerating studies on the molecular mechanisms of evasion of pathogenic viruses, as well as in the discovery of therapeutic targets.

Identification of cell-type-specific genes in multimodal single-cell data using deep neural network algorithm

The emergence of single-cell RNA sequencing (scRNA-seq) technology makes it possible to measure DNA, RNA, and protein in a single cell. Cellular Indexing of Transcriptomes and Epitopes by sequencing (CITE-seq) is a powerful multimodal single-cell research innovation, allowing researchers to capture RNA and surface protein expression on the same cells. Currently, identification of cell-type-specific genes in CITE-seq data is still challenging. In this study, we obtained a set of CITE-seq datasets from Kaggle database, which included the sequencing dataset of seven cell types during bone marrow stem cell differentiation. We used Student's t-test to analyze these transcription RNAs and pick out 133 significantly differentially expressed genes (DEGs) among all cell types. Functional enrichment revealed that these DEGs were strongly associated with blood-related diseases, providing important insights into the cellular heterogeneity within bone marrow stem cells. The relation between RNA and protein levels was performed by deep neural network (DNN) model and achieved a high prediction score of 0.867. Based on their coefficients in the DNN model, three genes (LGALS1, CENPV, TRIM24) were identified as cell-type-specific genes in erythrocyte progenitor. Our works provide a novel perspective regarding the differentiation of stem cells in the bone marrow and provide valuable insights for further research in this field.

Machine Learning Methods for Small Data Challenges in Molecular Science

Small data are often used in scientific and engineering research due to the presence of various constraints, such as time, cost, ethics, privacy, security, and technical limitations in data acquisition. However, big data have been the focus for the past decade, small data and their challenges have received little attention, even though they are technically more severe in machine learning (ML) and deep learning (DL) studies. Overall, the small data challenge is often compounded by issues, such as data diversity, imputation, noise, imbalance, and high-dimensionality. Fortunately, the current big data era is characterized by technological breakthroughs in ML, DL, and artificial intelligence (AI), which enable data-driven scientific discovery, and many advanced ML and DL technologies developed for big data have inadvertently provided solutions for small data problems. As a result, significant progress has been made in ML and DL for small data challenges in the past decade. In this review, we summarize and analyze several emerging potential solutions to small data challenges in molecular science, including chemical and biological sciences. We review both basic machine learning algorithms, such as linear regression, logistic regression (LR), k-nearest neighbor (KNN), support vector machine (SVM), kernel learning (KL), random forest (RF), and gradient boosting trees (GBT), and more advanced techniques, including artificial neural network (ANN), convolutional neural network (CNN), U-Net, graph neural network (GNN), Generative Adversarial Network (GAN), long short-term memory (LSTM), autoencoder, transformer, transfer learning, active learning, graph-based semi-supervised learning, combining deep learning with traditional machine learning, and physical model-based data augmentation. We also briefly discuss the latest advances in these methods. Finally, we conclude the survey with a discussion of promising trends in small data challenges in molecular science.

Accelerating therapeutic protein design with computational approaches toward the clinical stage

Therapeutic protein, represented by antibodies, is of increasing interest in human medicine. However, clinical translation of therapeutic protein is still largely hindered by different aspects of developability, including affinity and selectivity, stability and aggregation prevention, solubility and viscosity reduction, and deimmunization. Conventional optimization of the developability with widely used methods, like display technologies and library screening approaches, is a time and cost-intensive endeavor, and the efficiency in finding suitable solutions is still not enough to meet clinical needs. In recent years, the accelerated advancement of computational methodologies has ushered in a transformative era in the field of therapeutic protein design. Owing to their remarkable capabilities in feature extraction and modeling, the integration of cutting-edge computational strategies with conventional techniques presents a promising avenue to accelerate the progression of therapeutic protein design and optimization toward clinical implementation. Here, we compared the differences between therapeutic protein and small molecules in developability and provided an overview of the computational approaches applicable to the design or optimization of therapeutic protein in several developability issues.

Nucleotide augmentation for machine learning-guided protein engineering

Summary

Machine learning-guided protein engineering is a rapidly advancing field. Despite major experimental and computational advances, collecting protein genotype (sequence) and phenotype (function) data remains time- and resource-intensive. As a result, the quality and quantity of training data are often a limiting factor in developing machine learning models. Data augmentation techniques have been successfully applied to the fields of computer vision and natural language processing; however, there is a lack of such augmentation techniques for biological sequence data. Towards this end, we develop nucleotide augmentation (NTA), which leverages natural nucleotide codon degeneracy to augment protein sequence data via synonymous codon substitution. As a proof of concept for protein engineering, we test several online and offline augmentation implementations to train machine learning models with benchmark datasets of protein genotype and phenotype, revealing performance gains on par and surpassing benchmark models using a fraction of the training data. NTA also enables substantial improvements for classification tasks under heavy class imbalance.

Availability and implementation

The code used in this study is publicly available at https://github.com/minotm/NTA.

Supplementary information

Supplementary data are available at Bioinformatics Advances online.

Antimicrobial Peptides Prediction method based on sequence multidimensional feature embedding

Antimicrobial peptides (AMPs) are alkaline substances with efficient bactericidal activity produced in living organisms. As the best substitute for antibiotics, they have been paid more and more attention in scientific research and clinical application. AMPs can be produced from almost all organisms and are capable of killing a wide variety of pathogenic microorganisms. In addition to being antibacterial, natural AMPs have many other therapeutically important activities, such as wound healing, antioxidant and immunomodulatory effects. To discover new AMPs, the use of wet experimental methods is expensive and difficult, and bioinformatics technology can effectively solve this problem. Recently, some deep learning methods have been applied to the prediction of AMPs and achieved good results. To further improve the prediction accuracy of AMPs, this paper designs a new deep learning method based on sequence multidimensional representation. By encoding and embedding sequence features, and then inputting the model to identify AMPs, high-precision classification of AMPs and Non-AMPs with lengths of 10–200 is achieved. The results show that our method improved accuracy by 1.05% compared to the most advanced model in independent data validation without decreasing other indicators.

Protein Design: From the Aspect of Water Solubility and Stability

Water solubility and structural stability are key merits for proteins defined by the primary sequence and 3D-conformation. Their manipulation represents important aspects of the protein design field that relies on the accurate placement of amino acids and molecular interactions, guided by underlying physiochemical principles. Emulated designer proteins with well-defined properties both fuel the knowledge-base for more precise computational design models and are used in various biomedical and nanotechnological applications. The continuous developments in protein science, increasing computing power, new algorithms, and characterization techniques provide sophisticated toolkits for solubility design beyond guess work. In this review, we summarize recent advances in the protein design field with respect to water solubility and structural stability. After introducing fundamental design rules, we discuss the transmembrane protein solubilization and de novo transmembrane protein design. Traditional strategies to enhance protein solubility and structural stability are introduced. The designs of stable protein complexes and high-order assemblies are covered. Computational methodologies behind these endeavors, including structure prediction programs, machine learning algorithms, and specialty software dedicated to the evaluation of protein solubility and aggregation, are discussed. The findings and opportunities for Cryo-EM are presented. This review provides an overview of significant progress and prospects in accurate protein design for solubility and stability.

Protein Science Meets Artificial Intelligence: A Systematic Review and a Biochemical Meta-Analysis of an Inter-Field

Proteins are some of the most fascinating and challenging molecules in the universe, and they pose a big challenge for artificial intelligence. The implementation of machine learning/AI in protein science gives rise to a world of knowledge adventures in the workhorse of the cell and proteome homeostasis, which are essential for making life possible. This opens up epistemic horizons thanks to a coupling of human tacit–explicit knowledge with machine learning power, the benefits of which are already tangible, such as important advances in protein structure prediction. Moreover, the driving force behind the protein processes of self-organization, adjustment, and fitness requires a space corresponding to gigabytes of life data in its order of magnitude. There are many tasks such as novel protein design, protein folding pathways, and synthetic metabolic routes, as well as protein-aggregation mechanisms, pathogenesis of protein misfolding and disease, and proteostasis networks that are currently unexplored or unrevealed. In this systematic review and biochemical meta-analysis, we aim to contribute to bridging the gap between what we call binomial artificial intelligence (AI) and protein science (PS), a growing research enterprise with exciting and promising biotechnological and biomedical applications. We undertake our task by exploring “the state of the art” in AI and machine learning (ML) applications to protein science in the scientific literature to address some critical research questions in this domain, including What kind of tasks are already explored by ML approaches to protein sciences? What are the most common ML algorithms and databases used? What is the situational diagnostic of the AI–PS inter-field? What do ML processing steps have in common? We also formulate novel questions such as Is it possible to discover what the rules of protein evolution are with the binomial AI–PS? How do protein folding pathways evolve? What are the rules that dictate the folds? What are the minimal nuclear protein structures? How do protein aggregates form and why do they exhibit different toxicities? What are the structural properties of amyloid proteins? How can we design an effective proteostasis network to deal with misfolded proteins? We are a cross-functional group of scientists from several academic disciplines, and we have conducted the systematic review using a variant of the PICO and PRISMA approaches. The search was carried out in four databases (PubMed, Bireme, OVID, and EBSCO Web of Science), resulting in 144 research articles. After three rounds of quality screening, 93 articles were finally selected for further analysis. A summary of our findings is as follows: regarding AI applications, there are mainly four types: 1) genomics, 2) protein structure and function, 3) protein design and evolution, and 4) drug design. In terms of the ML algorithms and databases used, supervised learning was the most common approach (85%). As for the databases used for the ML models, PDB and UniprotKB/Swissprot were the most common ones (21 and 8%, respectively). Moreover, we identified that approximately 63% of the articles organized their results into three steps, which we labeled pre-process, process, and post-process. A few studies combined data from several databases or created their own databases after the pre-process. Our main finding is that, as of today, there are no research road maps serving as guides to address gaps in our knowledge of the AI–PS binomial. All research efforts to collect, integrate multidimensional data features, and then analyze and validate them are, so far, uncoordinated and scattered throughout the scientific literature without a clear epistemic goal or connection between the studies. Therefore, our main contribution to the scientific literature is to offer a road map to help solve problems in drug design, protein structures, design, and function prediction while also presenting the “state of the art” on research in the AI–PS binomial until February 2021. Thus, we pave the way toward future advances in the synthetic redesign of novel proteins and protein networks and artificial metabolic pathways, learning lessons from nature for the welfare of humankind. Many of the novel proteins and metabolic pathways are currently non-existent in nature, nor are they used in the chemical industry or biomedical field.

Data-Driven Synthetic Cell Factories Development for Industrial Biomanufacturing

Revolutionary breakthroughs in artificial intelligence (AI) and machine learning (ML) have had a profound impact on a wide range of scientific disciplines, including the development of artificial cell factories for biomanufacturing. In this paper, we review the latest studies on the application of data-driven methods for the design of new proteins, pathways, and strains. We first briefly introduce the various types of data and databases relevant to industrial biomanufacturing, which are the basis for data-driven research. Different types of algorithms, including traditional ML and more recent deep learning methods, are also presented. We then demonstrate how these data-based approaches can be applied to address various issues in cell factory development using examples from recent studies, including the prediction of protein function, improvement of metabolic models, and estimation of missing kinetic parameters, design of non-natural biosynthesis pathways, and pathway optimization. In the last section, we discuss the current limitations of these data-driven approaches and propose that data-driven methods should be integrated with mechanistic models to complement each other and facilitate the development of synthetic strains for industrial biomanufacturing.

Evaluation of the Physicochemical and Functional Properties of Aquasoya (Glycine max Merr.) Powder for Vegan Muffin Preparation

Recent concerns on health and sustainability have prompted the use of legumes as a source of plant-based proteins, resulting in the application of their cooking water as a substitute for egg whites. In this study, the cooking water of yellow soybeans was powdered, and, subsequently, the nutritional and functional characteristics of powders from yellow soybeans (YSP), chickpeas (CHP), and egg whites (EWP) were compared. The main components of these powders (total polyphenol, total carbohydrate, and protein), along with their hydration properties (hygroscopicity, water solubility index, and water/oil holding capacities), and emulsifying and foaming properties, were identified. The muffins prepared with YSP, CHP, and EWP were analyzed to determine their basic characteristics, such as volume, baking loss, and sensory attributes. The results of the powder analyses indicated that YSP was significantly superior to CHP and EWP, particularly in terms of holding capacities, and emulsion and foam stabilities. The sensory evaluation results showed that there was no statistically significant difference in overall acceptance among the muffin samples. Therefore, YSP can be used as an alternative to CHP or EWP, and applied as a novel ingredient in various vegan products.

Greenhouse gas emission estimation from municipal wastewater using a hybrid approach of generative adversarial network and data-driven modelling

Greenhouse gas (GHG) emissions including carbon dioxide (CO₂), methane (CH₄), and nitrous oxide (N₂O) created via wastewater treatment processes are not easily modeled given the non-linearity and complexity of biological processes. These factors are also impacted by limited data availability making the development of artificial data generation algorithms, such as a generative adversarial network (GAN), useful for determination of GHG emission rate estimates (EREs). The main objective of this study was to develop a hybrid approach of using GAN and regression modelling to determine GHG EREs from a cold-region biological nutrient removal (BNR) municipal wastewater treatment plant (MWTP) in which the aerobic reactor has previously been established as the main GHG emission source. To our knowledge, this is the first application of GAN used for MWTP modelling purposes. The EREs were generated from laboratory-scale reactors used in conjunction with facility-monitored operating parameters to develop the GAN and regression models. Results showed that regression models provided reasonable EREs using parameters including hydraulic retention time (HRT), temperature, total organic carbon, and dissolved oxygen (DO) concentrations for CO₂ EREs; HRT, temperature, DO and phosphate (PO₄^3-) concentrations for CH₄ EREs; and temperature, DO, and nitrogen (nitrite, nitrate, and ammonium) concentrations for N₂O EREs. Additionally, the addition of 100 GAN-created virtual data points improved regression model metrics including increased correlation coefficient and index agreement values, and decreased root mean square error values. Clearly, virtual data augmentation using GAN is a valuable resource in supplementation of limited data for improved modelling outcomes. Genetic algorithm optimization was also used to determine operating parameter modifications resulting in potential for minimization (or maximization) of GHG emissions.

A Deep Learning Approach with Data Augmentation to Predict Novel Spider Neurotoxic Peptides

As major components of spider venoms, neurotoxic peptides exhibit structural diversity, target specificity, and have great pharmaceutical potential. Deep learning may be an alternative to the laborious and time-consuming methods for identifying these peptides. However, the major hurdle in developing a deep learning model is the limited data on neurotoxic peptides. Here, we present a peptide data augmentation method that improves the recognition of neurotoxic peptides via a convolutional neural network model. The neurotoxic peptides were augmented with the known neurotoxic peptides from UniProt database, and the models were trained using a training set with or without the generated sequences to verify the augmented data. The model trained with the augmented dataset outperformed the one with the unaugmented dataset, achieving accuracy of 0.9953, precision of 0.9922, recall of 0.9984, and F1 score of 0.9953 in simulation dataset. From the set of all RNA transcripts of Callobius koreanus spider, we discovered neurotoxic peptides via the model, resulting in 275 putative peptides of which 252 novel sequences and only 23 sequences showing homology with the known peptides by Basic Local Alignment Search Tool. Among these 275 peptides, four were selected and shown to have neuromodulatory effects on the human neuroblastoma cell line SH-SY5Y. The augmentation method presented here may be applied to the identification of other functional peptides from biological resources with insufficient data.

Accelerating antibiotic discovery through artificial intelligence

By targeting invasive organisms, antibiotics insert themselves into the ancient struggle of the host-pathogen evolutionary arms race. As pathogens evolve tactics for evading antibiotics, therapies decline in efficacy and must be replaced, distinguishing antibiotics from most other forms of drug development. Together with a slow and expensive antibiotic development pipeline, the proliferation of drug-resistant pathogens drives urgent interest in computational methods that promise to expedite candidate discovery. Strides in artificial intelligence (AI) have encouraged its application to multiple dimensions of computer-aided drug design, with increasing application to antibiotic discovery. This review describes AI-facilitated advances in the discovery of both small molecule antibiotics and antimicrobial peptides. Beyond the essential prediction of antimicrobial activity, emphasis is also given to antimicrobial compound representation, determination of drug-likeness traits, antimicrobial resistance, and de novo molecular design. Given the urgency of the antimicrobial resistance crisis, we analyze uptake of open science best practices in AI-driven antibiotic discovery and argue for openness and reproducibility as a means of accelerating preclinical research. Finally, trends in the literature and areas for future inquiry are discussed, as artificially intelligent enhancements to drug discovery at large offer many opportunities for future applications in antibiotic development.

Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits

The central challenge in automated synthesis planning is to be able to generate and predict outcomes of a diverse set of chemical reactions. In particular, in many cases, the most likely synthesis pathway cannot be applied due to additional constraints, which requires proposing alternative chemical reactions. With this in mind, we present Molecule Edit Graph Attention Network (MEGAN), an end-to-end encoder-decoder neural model. MEGAN is inspired by models that express a chemical reaction as a sequence of graph edits, akin to the arrow pushing formalism. We extend this model to retrosynthesis prediction (predicting substrates given the product of a chemical reaction) and scale it up to large data sets. We argue that representing the reaction as a sequence of edits enables MEGAN to efficiently explore the space of plausible chemical reactions, maintaining the flexibility of modeling the reaction in an end-to-end fashion and achieving state-of-the-art accuracy in standard benchmarks. Code and trained models are made available online at https://github.com/molecule-one/megan.

Structure-aware protein solubility prediction from sequence through graph convolutional network and predicted contact map

Protein solubility is significant in producing new soluble proteins that can reduce the cost of biocatalysts or therapeutic agents. Therefore, a computational model is highly desired to accurately predict protein solubility from the amino acid sequence. Many methods have been developed, but they are mostly based on the one-dimensional embedding of amino acids that is limited to catch spatially structural information. In this study, we have developed a new structure-aware method GraphSol to predict protein solubility by attentive graph convolutional network (GCN), where the protein topology attribute graph was constructed through predicted contact maps only from the sequence. GraphSol was shown to substantially outperform other sequence-based methods. The model was proven to be stable by consistent [Formula: see text] of 0.48 in both the cross-validation and independent test of the eSOL dataset. To our best knowledge, this is the first study to utilize the GCN for sequence-based protein solubility predictions. More importantly, this architecture could be easily extended to other protein prediction tasks requiring a raw protein sequence.

Deep Learning in Protein Structural Modeling and Design

Deep learning is catalyzing a scientific revolution fueled by big data, accessible toolkits, and powerful computational resources, impacting many fields, including protein structural modeling. Protein structural modeling, such as predicting structure from amino acid sequence and evolutionary information, designing proteins toward desirable functionality, or predicting properties or behavior of a protein, is critical to understand and engineer biological systems at the molecular level. In this review, we summarize the recent advances in applying deep learning techniques to tackle problems in protein structural modeling and design. We dissect the emerging approaches using deep learning techniques for protein structural modeling and discuss advances and challenges that must be addressed. We argue for the central importance of structure, following the "sequence → structure → function" paradigm. This review is directed to help both computational biologists to gain familiarity with the deep learning methods applied in protein modeling, and computer scientists to gain perspective on the biologically meaningful problems that may benefit from deep learning techniques.

Increasing metabolic pathway flux by using machine learning models

Machine learning is transforming many industries through self-improving models that are fueled by big data and high computing power. The field of metabolic engineering, which uses cellular biochemical network to manufacture useful small molecules, has also witnessed the first wave of machine learning applications in the past five years, covering reaction route design, enzyme selection, pathway engineering and process optimization. This review focuses on pathway engineering, and uses a few recent studies to illustrate (1) how machine learning models can be useful in overcoming an evident rate-limiting step, and (2) how the models may be used to exhaustively search - or guide optimization algorithms to search - a large design space when the cellular regulation of the reaction network is more convoluted.