LBLucas Busta

Lucas Busta

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Lucas Busta has a total of 70 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Small language models enable rapid and accurate extraction of structured data from unstructured text: An example with plants and their specialized metabolites

    by Lucas Busta, Alan R. Oyler

    Transformer-based large language models are receiving considerable attention because of their ability to analyse scientific literature. Small language models (SLMs), however, also have potential in this area as they have smaller compute footprints and allow users to keep data in-house. Here, we quantitatively evaluate the ability of SLMs to: (i) score references according to project-specific relevance and (ii) extract and structuring data from unstructured sources (scientific abstracts). By comparing SLMs’ outputs against those of a human on hundreds of abstracts, we found that (i) SLMs can effectively filter literature and extract structured information relatively accurately (error rates as low as 10%), but not with perfect yield (as low as 50% in some cases), (ii) that there are tradeoffs between accuracy, model size and computing requirements and (iii) that clearly written abstracts are needed to support accurate data extraction. We recommend advanced prompt engineering techniques, full-text resources and model distillation as future directions.


  • Open Access

    Small language models enable rapid and accurate extraction of structured data from unstructured text: an example with plants and their specialized metabolites

    by Lucas Busta, Alan R. Oyler

    Transformer-based large language models are receiving considerable attention because of their ability to analyze scientific literature. Small language models (SLMs), however, also have potential in this area, have smaller compute footprints, and allow users to keep data in-house. Here, we quantitatively evaluate the ability of SLMs to: (i) score references according to project-specific relevance and (ii) extract and structuring data from unstructured sources (scientific abstracts). By comparing SLMs’ outputs against those of a human on hundreds of abstracts, we found that (i) SLMs can effectively filter literature and extract structured information relatively accurately (error rates as low as 10%), but not with perfect yield (as low as 50% in some cases), (ii) that there are tradeoffs between accuracy, model size, and computing requirements, and (iii) that clearly written abstracts are needed to support accurate data extraction. We recommend advanced prompt engineering techniques, full-text resources, and model distillation as future directions.


  • Open Access

    Advancing plant metabolic research by using large language models to expand databases and extract labeled data

    by Rachel Knapp, Braidon Johnson, Lucas Busta

    Premise: Recently, plant science has seen transformative advances in scalable data collection for sequence and chemical data. These large datasets, combined with machine learning, have demonstrated that conducting plant metabolic research on large scales yields remarkable insights. A key next step in increasing scale has been revealed with the advent of accessible large language models, which, even in their early stages, can distill structured data from the literature. This brings us closer to creating specialized databases that consolidate virtually all published knowledge on a topic.Methods: Here, we first test different combinations of prompt engineering techniques and language models in the identification of validated enzyme–product pairs. Next, we evaluate the application of automated prompt engineering and retrieval‐augmented generation to identify compound–species associations. Finally, we build and determine the accuracy of a multimodal language model–based pipeline that transcribes images of tables into machine‐readable formats.Results: When tuned for each specific task, these methods perform with high (80–90%) or modest (50%) accuracies for enzyme–product pair identification and table image transcription, but with lower false‐negative rates than previous methods (decreasing from 55% to 40%) for compound–species pair identification.Discussion: We enumerate several suggestions for researchers working with language models, among which is the importance of the user's domain‐specific expertise and knowledge.


  • Open Access

    Wax Bloom Dynamics on Sorghum bicolor Under Different Environmental Stresses Reveal Signaling Modules Associated With Wax Production

    by Madison Larson, Marshall Hampton, Lucas Busta

    Epicuticular wax blooms are associated with improved drought resistance in many species, including Sorghum bicolor. While the role of wax in drought resistance is well‐known, we report new insights into how light and drought dynamically influence wax production. We investigated how wax quantity and composition are modulated over time and in response to different environmental stressors, as well as the molecular and genetic mechanisms involved in such. We combined an in vitro wax induction protocol with GC–MS and RNA‐seq measurements to propose a putative signaling pathway for wax bloom induction in sorghum. We also explored the potential of spectrophotometry to aid in monitoring wax bloom dynamics. Spectrophotometric analysis showed primary differences in reflectance between bloom‐rich and bloomless tissue surfaces in the 230–500 nm range of the spectrum, corresponding to the blue color channel of photographic data. Our smartphone‐based system detected significant differences in wax production between control and shade treatment groups, demonstrating its potential for candidate screening. Overall, our data suggest that wax extrusion can be rapidly modulated in response to light, occurring within days compared to the months required for the changes observed under greenhouse drought/simulated shade conditions. These results highlight the dynamic nature of wax modulation in response to varying environmental stimuli, especially light and water availability.


  • Open Access

    A new spin on chemotaxonomy: Using non‐proteogenic amino acids as a test case

    by Makenzie Gibson, William Thives Santos, Alan R. Oyler, Lucas Busta, Craig A. Schenck

    Premise: Specialized metabolites serve various roles for plants and humans. Unlike core metabolites, specialized metabolites are restricted to certain plant lineages; thus, in addition to their ecological functions, specialized metabolites can serve as diagnostic markers of plant lineages.Methods: We investigated the phylogenetic distribution of plant metabolites using non‐proteogenic amino acids (NPAA). Species–NPAA associations for eight NPAAs were identified from the existing literature and placed within a phylogenetic context using R packages and the Interactive Tree of Life. To confirm and extend the literature‐based NPAA distribution, we selected azetidine‐2‐carboxylic acid (Aze) and screened over 70 diverse plants using gas chromatography–mass spectrometry (GC‐MS).Results: Literature searches identified 163 NPAA‐relevant articles, which were manually inspected to identify 822 species–NPAA associations. NPAAs were mapped at the order and genus level, revealing that some NPAAs are restricted to single orders, whereas others are present across divergent taxa. The observed distribution of Aze across plants and ancestral state reconstruction suggests a convergent evolutionary history.Discussion: Although reliance on chemotaxonomy has decreased in recent years, there is still value in placing metabolites within a phylogenetic context to understand the evolutionary processes of plant chemical diversification. This approach can be applied to metabolites present in any organism and compared at a range of taxonomic levels.


  • Open Access

    A molecular representation system with a common reference frame for analyzing triterpenoid structural diversity

    by Nicole Babineau, Le Thanh Dien Nguyen, Davis Mathieu, Clint McCue, Nicholas Schlecht, Taylor Abrahamson, Björn Hamberger, Lucas Busta


  • Open Access

    Advancing Plant Metabolic Research By Using Large Language Models To Expand Databases And Extract Labelled Data

    by Rachel Knapp, Braidon Johnson, Lucas Busta

    Premise: Recently, plant science has seen transformative advances in scalable data collection for sequence and chemical data. These large datasets, combined with machine learning, revealed that conducting plant metabolic research on large scales yields remarkable insights. A key next step in increasing scale has been revealed with the advent of accessible large language models, which, even in their early stages, can distill structured data from literature. This brings us closer to creating specialized databases that consolidate virtually all published knowledge on a topic. Methods: Here, we first test different prompt engineering technique / language model combinations in the identification of validated enzyme-product pairs. Next, we evaluate automated prompt engineering and retrieval augmented generation applied to identifying compound-species associations. Finally, we build and determine the accuracy of a multimodal language model-based pipeline that transcribes images of tables into machine-readable formats. Results: When tuned for each specific task, these methods perform with high accuracies (80-90 percent for enzyme-product pair identification and table image transcription), or with modest accuracies (50 percent) but lower false-negative rates than previous methods (down to 40 percent from 55 percent) for compound-species pair identification. Discussion: We enumerate several suggestions for working with language models as researchers, among which is the importance of the user’s domain-specific expertise and knowledge. Significance Statement: Scientific databases have played a major role in advancing metabolic research. However, even today’s advanced databases are incomplete and/or are not built to best suit certain research tasks. Here, we explored and evaluated the use of large language models and various prompt engineering techniques to expand and subset existing databases in task-specific ways. Our results illustrate the potential for high-accuracy additions and restructurings of existing databases using language models, assuming the specific methods by which the models are used are tuned and validated for the specific task. These findings are important because they outline a method by which we could greatly expand existing databases and rapidly tailor them to specific research efforts, leading to greater research productivity and effective utilization of past research findings. All authors collected data, analyzed data, prepared the manuscript, and approved its final version. The authors declare that they have no competing interests.


  • Open Access

    Wax bloom dynamics on Sorghum bicolor under different environmental stresses reveal signaling modules associated with wax production

    by Madison Larson, Marshall Hampton, Lucas Busta

    Epicuticular wax blooms are associated with improved drought resistance in many species, including Sorghum bicolor . While the role of wax in drought resistance is well known, we report new insights into how light and drought dynamically influence wax production. We investigated how wax quantity and composition are modulated over time and in response to different environmental stressors, as well as the molecular and genetic mechanisms involved in such. Gas chromatography-mass spectrometry and photographic results showed that sorghum leaf sheath wax load and composition were altered in mature plants grown under drought and simulated shade, though this phenomenon appears to vary by sorghum cultivar. We combined an in vitro wax induction protocol with GC-MS and RNA-seq measurements to identify a draft signaling pathway for wax bloom induction in sorghum. We also explored the potential of spectrophotometry to aid in monitoring wax bloom dynamics. Spec-trophotometric analysis showed primary differences in reflectance between bloom-rich and bloomless tissue surfaces in the 230-500nm range of the spectrum, corresponding to the blue color channel of photographic data. Our smartphone-based system detected significant differences in wax production between control and shade treatment groups, demonstrating its potential for candidate screening. Overall, our data suggest that wax extrusion can be rapidly modulated in response to light, occurring within days compared to the months required for the changes observed under greenhouse drought/simulated shade conditions. These results highlight the dynamic nature of wax modulation in response to varying environmental stimuli, especially light and water availability. Significance Statement: Agricultural crops require significant freshwater for irrigation, making food security vulnerable to drought. Epicuticular wax blooms are associated with drought tolerance in many plants, including Sorghum bicolor . We investigated how environmental factors like light and drought influence wax production in sorghum. Wax production, composition, and gene expression were compared between sorghum exposed to different environmental stressors, reavealing dynamic modulation of wax production in response to environmental stress as well as signaling genes potentially involved in regulating wax production. These findings broaden our understanding of wax-related drought tolerance mechanisms, providing a foundation for future efforts to enginner crops with improved climate resilience.


  • Open Access

    A molecular representation system with a common reference frame for natural products pathway discovery and structural diversity tasks

    by Nicole Babineau, Le Thanh Dien Nguyen, Davis Mathieu, Clint McCue, Nicholas Schlecht, Taylor Abrahamson, Björn Hamberger, Lucas Busta

    Researchers have uncovered hundreds of thousands of natural products, many of which contribute to medicine, materials, and agriculture. However, missing knowledge of the biosynthetic pathways to these products hinders their expanded use. Nucleotide sequencing is key in pathway elucidation efforts, and analyses of natural products’ molecular structures, though seldom discussed explicitly, also play an important role by suggesting hypothetical pathways for testing. Structural analyses are also important in drug discovery, where many molecular representation systems – methods of representing molecular structures in a computer-friendly format – have been developed. Unfortunately, pathway elucidation investigations seldom use these representation systems. This gap is likely because those systems are primarily built to document molecular connectivity and topology, rather than the absolute positions of bonds and atoms in a common reference frame, the latter of which enables chemical structures to be connected with potential underlying biosynthetic steps. Here, we present a unique molecular representation system built around a common reference frame. We tested this system using triterpenoid structures as a case study and explored the system’s applications in biosynthesis and structural diversity tasks. The common reference frame system can identify structural regions of high or low variability on the scale of atoms and bonds and enable hierarchical clustering that is closely connected to underlying biosynthesis. Combined with phylogenetic distribution information, the system illuminates distinct sources of structural variability, such as different enzyme families operating in the same pathway. These characteristics outline the potential of common reference frame molecular representation systems to support large-scale pathway elucidation efforts. Significance Statement Studying natural products and their biosynthetic pathways aids in identifying, characterizing, and developing new therapeutics, materials, and biotechnologies. Analyzing chemical structures is key to understanding biosynthesis and such analyses enhance pathway elucidation efforts, but few molecular representation systems have been designed with biosynthesis in mind. This study developed a new molecular representation system using a common reference frame, identifying corresponding atoms and bonds across many chemical structures. This system revealed hotspots and dimensions of variation in chemical structures, distinct overall structural groups, and parallels between molecules’ structural features and underlying biosynthesis. More widespread use of common reference frame molecular representation systems could hasten pathway elucidation efforts.

  • Open Access

    Herbarium specimens as tools for exploring the evolution of fatty acid‐derived natural products in plants

    by Emma Fitzgibbons, Jacob Lastovich, Samuel Scott, Nicole Groth, Amanda L. Grusz, Lucas Busta

    SUMMARY: Plants synthesize natural products via lineage‐specific offshoots of their core metabolic pathways, including fatty acid synthesis. Recent studies have shed light on new fatty acid‐derived natural products and their biosynthetic pathways in disparate plant species. Inspired by this progress, we set out to develop tools for exploring the evolution of fatty‐acid derived products. We sampled multiple species from all major clades of euphyllophytes, including ferns, gymnosperms, and angiosperms (monocots and eudicots), and we show that the compositional profiles (though not necessarily the total amounts) of fatty‐acid derived surface waxes from preserved plant specimens are consistent with those obtained from freshly collected tissue in a semi‐quantitative and sometimes quantitative manner. We then sampled herbarium specimens representing 57 monocot species to assess the phylogenetic distribution and evolution, of two fatty acid‐derived natural products found in that clade: beta‐diketones and alkylresorcinols. These chemical data, combined with analyses of 26 monocot genomes, revealed a co‐occurrence (though not necessarily a causal relationship) between whole genome duplication and the evolution of diketone synthases from an ancestral alkylresorcinol synthase‐like polyketide synthase. Limitations of using herbarium specimen wax profiles as proxies for those of fresh tissue seem likely to include effects from loss of epicuticular wax crystals, effects from preservation techniques, and variation in wax chemical profiles due to genotype or environment. Nevertheless, this work reinforces the widespread utility of herbarium specimens for studying leaf surface waxes (and possibly other chemical classes) and reveals some of the evolutionary history of fatty acid‐derived natural products within monocots.