Generative Artificial Intelligence GPT-4 Accelerates Knowledge Mining and Machine Learning for Synthetic Biology

A standards perspective on genomic data reusability and reproducibility

Genomic and metagenomic sequence data provides an unprecedented ability to re-examine findings, offering a transformative potential for advancing research, developing computational tools, enhancing clinical applications, and fostering scientific collaboration. However, effective and ethical reuse of genomics data is hampered by numerous technical and social challenges. The International Microbiome and Multi'Omics Standards Alliance (IMMSA, https://www.microbialstandards.org/) and the Genomic Standards Consortium (GSC, https://gensc.org) hosted a 5-part seminar series "A Year of Data Reuse" in 2024 to explore challenges and opportunities of data reuse and reproducibility across disparate domains of the genomic sciences. Addressing these challenges will require a multifaceted approach, including common metadata reporting, clear communication, standardized protocols, improved data management infrastructure, ethical guidelines, and collaborative policies that prioritize transparency and accessibility. We offer strategies to enable responsible and technically feasible data reuse, recognition of data reproducibility challenges, and emphasizing the importance of cross-disciplinary efforts in the pursuit of open science and data-driven innovation.

Recent advances in genome mining and synthetic biology for discovery and biosynthesis of natural products

Natural products have long served as critical raw materials in chemical and pharmaceutical manufacturing, primarily which can provide superior scaffolds or intermediates for drug discovery and development. Over the last century, natural products have contributed to more than a third of therapeutic drug production. However, traditional methods of producing drugs from natural products have become less efficient and more expensive over the past few decades. The combined utilization of genome mining and synthetic biology based on genome sequencing, bioinformatics tools, big data analytics, genetic engineering, metabolic engineering, and systems biology promises to counter this trend. Here, we reviewed recent (2020-2023) examples of genome mining and synthetic biology used to resolve challenges in the production of natural products, such as less variety, poor efficiency, and low yield. Additionally, the emerging efficient tools, design principles, and building strategies of synthetic biology and its application prospects in NPs synthesis have also been discussed.

Evaluating GPT Models for Automated Literature Screening in Wastewater-Based Epidemiology

Methods to quantitatively synthesize findings across multiple studies is an emerging need in wastewater-based epidemiology (WBE), where disease tracking through wastewater analysis is performed at broad geographical locations using various techniques to facilitate public health responses. Meta-analysis provides a rigorous statistical procedure for research synthesis, yet the manual process of screening large volumes of literature remains a hurdle for its application in timely evidence-based public health responses. Here, we evaluated the performance of GPT-3, GPT-3.5, and GPT-4 models in automated screening of publications for meta-analysis in the WBE literature. We show that the chat completion model in GPT-4 accurately differentiates papers that contain original data from those that did not with texts of the Abstract as the input at a Precision of 0.96 and Recall of 1.00, exceeding current quality standards for manual screening (Recall = 0.95) while costing less than $0.01 per paper. GPT models performed less accurately in detecting studies reporting relevant sampling location, highlighting the value of maintaining human intervention in AI-assisted literature screening. Importantly, we show that certain formulation and model choices generated nonsensical answers to the screening tasks, while others did not, urging the attention to robustness when employing AI-assisted literature screening. This study provided novel performance evaluation data on GPT models for document screening as a step in meta-analysis, suggesting AI-assisted literature screening a useful complementary technique to speed up research synthesis in WBE.

Non-conventional yeasts: promising cell factories for organic acid bioproduction

Microbial production of organic acids has been hindered by the poor acid tolerance of microorganisms and the high costs of waste salt reprocessing. The robustness of non-conventional microorganisms in an acidic environment makes it possible to produce organic acids at low pH and greatly simplifies downstream processing. In this review we discuss the environmental adaptability features of non-conventional yeasts, as well as the latest developments in genomic engineering strategies that have facilitated metabolic engineering of these strains. We also use selected examples of three-carbon (C3), C4, and C6 organic acids to illustrate the ongoing efforts and challenges of using non-conventional yeasts for organic acid production. This review provides theoretical guidance for the construction of highly robust organic acid producers.

PanKB: An interactive microbial pangenome knowledgebase for research, biotechnological innovation, and knowledge mining

The exponential growth of microbial genome data presents unprecedented opportunities for unlocking the potential of microorganisms. The burgeoning field of pangenomics offers a framework for extracting insights from this big biological data. Recent advances in microbial pangenomic research have generated substantial data and literature, yielding valuable knowledge across diverse microbial species. PanKB (pankb.org), a knowledgebase designed for microbial pangenomics research and biotechnological applications, was built to capitalize on this wealth of information. PanKB currently includes 51 pangenomes from 8 industrially relevant microbial families, comprising 8402 genomes, over 500 000 genes and over 7M mutations. To describe this data, PanKB implements four main components: (1) Interactive pangenomic analytics to facilitate exploration, intuition, and potential discoveries; (2) Alleleomic analytics, a pangenomic-scale analysis of variants, providing insights into intra-species sequence variation and potential mutations for applications; (3) A global search function enabling broad and deep investigations across pangenomes to power research and bioengineering workflows; (4) A bibliome of 833 open-access pangenomic papers and an interface with an LLM that can answer in-depth questions using its knowledge. PanKB empowers researchers and bioengineers to harness the potential of microbial pangenomics and serves as a valuable resource bridging the gap between pangenomic data and practical applications.

Network for knowledge Organization (NEKO): An AI knowledge mining workflow for synthetic biology research

Large language models (LLMs) can complete general scientific question-and-answer, yet they are constrained by their pretraining cut-off dates and lack the ability to provide specific, cited scientific knowledge. Here, we introduce Network for Knowledge Organization (NEKO), a workflow that uses LLM Qwen to extract knowledge through scientific literature text mining. When user inputs a keyword of interest, NEKO can generate knowledge graphs to link bioinformation entities and produce comprehensive summaries from PubMed search. NEKO significantly enhance LLM ability and has immediate applications in daily academic tasks such as education of young scientists, literature review, paper writing, experiment planning/troubleshooting, and new ideas/hypothesis generation. We exemplified this workflow's applicability through several case studies on yeast fermentation and cyanobacterial biorefinery. NEKO's output is more informative, specific, and actionable than GPT-4's zero-shot Q&A. NEKO offers flexible, lightweight local deployment options. NEKO democratizes artificial intelligence (AI) tools, making scientific foundation model more accessible to researchers without excessive computational power.

mRNA vaccine sequence and structure design and optimization: Advances and challenges

Messenger RNA (mRNA) vaccines have emerged as a powerful tool against communicable diseases and cancers, as demonstrated by their huge success during the coronavirus disease 2019 (COVID-19) pandemic. Despite the outstanding achievements, mRNA vaccines still face challenges such as stringent storage requirements, insufficient antigen expression, and unexpected immune responses. Since the intrinsic properties of mRNA molecules significantly impact vaccine performance, optimizing mRNA design is crucial in preclinical development. In this review, we outline four key principles for optimal mRNA sequence design: enhancing ribosome loading and translation efficiency through untranslated region (UTR) optimization, improving translation efficiency via codon optimization, increasing structural stability by refining global RNA sequence and extending in-cell lifetime and expression fidelity by adjusting local RNA structures. We also explore recent advancements in computational models for designing and optimizing mRNA vaccine sequences following these principles. By integrating current mRNA knowledge, addressing challenges, and examining advanced computational methods, this review aims to promote the application of computational approaches in mRNA vaccine development and inspire novel solutions to existing obstacles.

Engineering conditional protein-protein interactions for dynamic cellular control

Conditional protein-protein interactions enable dynamic regulation of cellular activity and are an attractive approach to probe native protein interactions, improve metabolic engineering of microbial factories, and develop smart therapeutics. Conditional protein-protein interactions have been engineered to respond to various chemical, light, and nucleic acid-based stimuli. These interactions have been applied to assemble protein fragments, build protein scaffolds, and spatially organize proteins in many microbial and higher-order hosts. To foster the development of novel conditional protein-protein interactions that respond to new inputs or can be utilized in alternative settings, we provide an overview of the process of designing new engineered protein interactions while showcasing many recently developed computational tools that may accelerate protein engineering in this space.

Exploring the potential of large language model-based chatbots in challenges of ribosome profiling data analysis: a review

Ribosome profiling (Ribo-seq) provides transcriptome-wide insights into protein synthesis dynamics, yet its analysis poses challenges, particularly for nonbioinformatics researchers. Large language model-based chatbots offer promising solutions by leveraging natural language processing. This review explores their convergence, highlighting opportunities for synergy. We discuss challenges in Ribo-seq analysis and how chatbots mitigate them, facilitating scientific discovery. Through case studies, we illustrate chatbots' potential contributions, including data analysis and result interpretation. Despite the absence of applied examples, existing software underscores the value of chatbots and the large language model. We anticipate their pivotal role in future Ribo-seq analysis, overcoming limitations. Challenges such as model bias and data privacy require attention, but emerging trends offer promise. The integration of large language models and Ribo-seq analysis holds immense potential for advancing translational regulation and gene expression understanding.

Mapping of specialized metabolite terms onto a plant phylogeny using text mining and large language models

Plants produce a staggering array of chemicals that are the basis for organismal function and important human nutrients and medicines. However, it is poorly defined how these compounds evolved and are distributed across the plant kingdom, hindering a systematic view and understanding of plant chemical diversity. Recent advances in plant genome/transcriptome sequencing have provided a well-defined molecular phylogeny of plants, on which the presence of diverse natural products can be mapped to systematically determine their phylogenetic distribution. Here, we built a proof-of-concept workflow where previously reported diverse tyrosine-derived plant natural products were mapped onto the plant tree of life. Plant chemical-species associations were mined from literature, filtered, evaluated through manual inspection of over 2500 scientific articles, and mapped onto the plant phylogeny. The resulting "phylochemical" map confirmed several highly lineage-specific compound class distributions, such as betalain pigments and Amaryllidaceae alkaloids. The map also highlighted several lineages enriched in dopamine-derived compounds, including the orders Caryophyllales, Liliales, and Fabales. Additionally, the application of large language models, using our manually curated data as a ground truth set, showed that post-mining processing can largely be automated with a low false-positive rate, critical for generating a reliable phylochemical map. Although a high false-negative rate remains a challenge, our study demonstrates that combining text mining with language model-based processing can generate broader phylochemical maps, which will serve as a valuable community resource to uncover key evolutionary events that underlie plant chemical diversity and enable system-level views of nature's millions of years of chemical experimentation.

Enhancing Orthopedic Knowledge Assessments: The Performance of Specialized Generative Language Model Optimization

OBJECTIVE

This study aimed to evaluate and compare the effectiveness of knowledge base-optimized and unoptimized large language models (LLMs) in the field of orthopedics to explore optimization strategies for the application of LLMs in specific fields.

METHODS

This research constructed a specialized knowledge base using clinical guidelines from the American Academy of Orthopaedic Surgeons (AAOS) and authoritative orthopedic publications. A total of 30 orthopedic-related questions covering aspects such as anatomical knowledge, disease diagnosis, fracture classification, treatment options, and surgical techniques were input into both the knowledge base-optimized and unoptimized versions of the GPT-4, ChatGLM, and Spark LLM, with their generated responses recorded. The overall quality, accuracy, and comprehensiveness of these responses were evaluated by 3 experienced orthopedic surgeons.

RESULTS

Compared with their unoptimized LLMs, the optimized version of GPT-4 showed improvements of 15.3% in overall quality, 12.5% in accuracy, and 12.8% in comprehensiveness; ChatGLM showed improvements of 24.8%, 16.1%, and 19.6%, respectively; and Spark LLM showed improvements of 6.5%, 14.5%, and 24.7%, respectively.

CONCLUSION

The optimization of knowledge bases significantly enhances the quality, accuracy, and comprehensiveness of the responses provided by the 3 models in the orthopedic field. Therefore, knowledge base optimization is an effective method for improving the performance of LLMs in specific fields.

Generative artificial intelligence performs rudimentary structural biology modeling

Natural language-based generative artificial intelligence (AI) has become increasingly prevalent in scientific research. Intriguingly, capabilities of generative pre-trained transformer (GPT) language models beyond the scope of natural language tasks have recently been identified. Here we explored how GPT-4 might be able to perform rudimentary structural biology modeling. We prompted GPT-4 to model 3D structures for the 20 standard amino acids and an α-helical polypeptide chain, with the latter incorporating Wolfram mathematical computation. We also used GPT-4 to perform structural interaction analysis between the anti-viral nirmatrelvir and its target, the SARS-CoV-2 main protease. Geometric parameters of the generated structures typically approximated close to experimental references. However, modeling was sporadically error-prone and molecular complexity was not well tolerated. Interaction analysis further revealed the ability of GPT-4 to identify specific amino acid residues involved in ligand binding along with corresponding bond distances. Despite current limitations, we show the current capacity of natural language generative AI to perform basic structural biology modeling and interaction analysis with atomic-scale accuracy.

Machine learning: an advancement in biochemical engineering

One of the most remarkable techniques recently introduced into the field of bioprocess engineering is machine learning. Bioprocess engineering has drawn much attention due to its vast application in different domains like biopharmaceuticals, fossil fuel alternatives, environmental remediation, and food and beverage industry, etc. However, due to their unpredictable mechanisms, they are very often challenging to optimize. Furthermore, biological systems are extremely complicated; hence, machine learning algorithms could potentially be utilized to improve and build new biotechnological processes. Gaining insight into the fundamental mathematical understanding of commonly used machine learning algorithms, including Support Vector Machine, Principal Component Analysis, Partial Least Squares and Reinforcement Learning, the present study aims to discuss various case studies related to the application of machine learning in bioprocess engineering. Recent advancements as well as challenges posed in this area along with their potential solutions are also presented.

Large-Language-Model-Based AI Agent for Organic Semiconductor Device Research

Large language models (LLMs) have attracted widespread attention recently, however, their application in specialized scientific fields still requires deep adaptation. Here, an artificial intelligence (AI) agent for organic field-effect transistors (OFETs) is designed by integrating the generative pre-trained transformer 4 (GPT-4) model with well-trained machine learning (ML) algorithms. It can efficiently extract the experimental parameters of OFETs from scientific literature and reshape them into a structured database, achieving precision and recall rates both exceeding 92%. Combined with well-trained ML models, this AI agent can further provide targeted guidance and suggestions for device design. With prompt engineering and human-in-loop strategies, the agent extracts sufficient information of 709 OFETs from 277 research articles across different publishers and gathers them into a standardized database containing more than 10 000 device parameters. Using this database, a ML model based on Extreme Gradient Boosting is trained for device performance judgment. Combined with the interpretation of the high-precision model, the agent has provided a feasible optimization scheme that has tripled the charge transport properties of 2,6-diphenyldithieno[3,2-b:2',3'-d]thiophene OFETs. This work is an effective practice of LLMs in the field of organic optoelectronic devices and expands the research paradigm of organic optoelectronic materials and devices.

Turning waste into treasure: A new direction for low-cost production of lipid chemicals from Thraustochytrids

Thraustochytrids are marine microorganisms known for their fast growth and ability to store lipids, making them useful for producing polyunsaturated fatty acids (PUFAs), biodiesel, squalene, and carotenoids. However, the high cost of production, mainly due to expensive fermentation components, limits their wider use. A significant challenge in this context is the need to balance production costs with the value of the end products. This review focuses on integrating the efficient utilization of waste with Thraustochytrids fermentation, including the economic substitution of carbon sources, nitrogen sources, and fermentation water. This approach aligns with the 3Rs principles (reduction, recycling, and reuse). Furthermore, it emphasizes the role of Thraustochytrids in converting waste into lipid chemicals and promoting sustainable circular production models. The aim of this review is to emphasize the value of Thraustochytrids in converting waste into treasure, providing precise cost reduction strategies for future commercial production.

Safeguarding Mail-Order DNA Synthesis in the Age of Artificial Intelligence

Introduction

Artificial intelligence (AI) tools continue to be developed and used within the life sciences. The impact of these tools on the biosecurity landscape surrounding mail-order DNA synthesis and how to address the impacts have not been critically examined in the literature.

Methods

The impacts of AI-driven chatbots and biological design tools on the biosecurity landscape surrounding mail-order DNA synthesis were analyzed and described. The findings are informed by the authors' experience in the field.

Results

Generally, chatbots lower barriers to access of information that could be misused while biological design tools may provide new abilities to users with the intent of misuse. Six recommendations to the United States Government that attempt to maximize the benefits of these new technologies while mitigating risks are provided.

Conclusion

Mandating mail-order DNA synthesis providers to screen DNA synthesis orders is a critical safeguarding step that should be taken as soon as possible. Over time, biological design tools will reduce the effectiveness of such a regulation and actions should be taken now to limit the negative impacts in the future.

The whack-a-mole governance challenge for AI-enabled synthetic biology: literature review and emerging frameworks

AI-enabled synthetic biology has tremendous potential but also significantly increases biorisks and brings about a new set of dual use concerns. The picture is complicated given the vast innovations envisioned to emerge by combining emerging technologies, as AI-enabled synthetic biology potentially scales up bioengineering into industrial biomanufacturing. However, the literature review indicates that goals such as maintaining a reasonable scope for innovation, or more ambitiously to foster a huge bioeconomy do not necessarily contrast with biosafety, but need to go hand in hand. This paper presents a literature review of the issues and describes emerging frameworks for policy and practice that transverse the options of command-and-control, stewardship, bottom-up, and laissez-faire governance. How to achieve early warning systems that enable prevention and mitigation of future AI-enabled biohazards from the lab, from deliberate misuse, or from the public realm, will constantly need to evolve, and adaptive, interactive approaches should emerge. Although biorisk is subject to an established governance regime, and scientists generally adhere to biosafety protocols, even experimental, but legitimate use by scientists could lead to unexpected developments. Recent advances in chatbots enabled by generative AI have revived fears that advanced biological insight can more easily get into the hands of malignant individuals or organizations. Given these sets of issues, society needs to rethink how AI-enabled synthetic biology should be governed. The suggested way to visualize the challenge at hand is whack-a-mole governance, although the emerging solutions are perhaps not so different either.

EBRC: Enhancing bioeconomy through research and communication

On September 12, 2022, President Biden issued Executive Order 14081 to enable the progress of biomanufacturing and biotechnology. This timely initiative will help overcome many challenging issues, and its potential impacts will be huge. This article discusses eight recommendations to make this US national initiative successful, encourage other nations to consider similar initiatives, and create a better world for the next generations.