About

Lukas Mueller is an adjunct professor in the School of Integrative Plant Science, Plant Breeding and Genetics Section. His lab designs and implements databases that assist scientists in their research and plant breeders in more efficient crop improvement. The databases and software developed by his group make transcriptomic, genotypic, and phenotypic data from thousands of experiments accessible to the public, often focusing on under-researched staple crops from food-insecure regions. Mueller's research involves the use of Genomic Selection, which employs high-throughput genotyping technologies such as genotyping-by-sequencing (GBS) and large phenotyping data sets to rapidly predict desirable traits in new plant crosses. His lab collaborates on various projects, including the creation of Cassavabase for cassava breeders in Africa, coordinating the Solanaceae Genomics Network, and developing breeding databases for crops like yam, sweet potato, and banana. He is involved in multiple genome sequencing projects for crops such as tomato, coffee, petunia, and Nicotiana benthamiana. His work aims to organize and make accessible the large amounts of biological data generated by advances in sequencing technologies, thereby facilitating crop improvement and supporting research in food-insecure regions.

Research topics

• Genetics
• Biology
• Computational biology
• Botany
• Evolutionary biology

Selected publications

• Correction: DeltaBreed: A BrAPI-centric breeding data information system

  PLoS ONE · 2026-01-22

  articleOpen access

  [This corrects the article DOI: 10.1371/journal.pone.0324104.].

  PublisherOA PDFDOI

• SGN and BreedBase

  2026-03-04

  book-chapter1st authorCorresponding

  Tomato is an important model for many aspects of plant biology, including plant defense, fruit ripening, and development. Sequencing of the tomato genome led to the creation of a genome database for tomato and other Solanaceae crops, the SGN database (https://solgenomics.net/). In recent years, this database has been expanded to include breeding functions, made crop agnostic, and released as Breedbase (https://breedbase.org/). Modern breeding methods integrate next-generation sequencing and phenomics to identify plants with the best characteristics and greatest genetic merit for use as parents in subsequent breeding cycles to ultimately create improved cultivars with high adoption rates by farmers. This data-driven approach hinges on strong foundations in data management, quality control, and analytics—aspects in which Breedbase excels. Because of the complexity of the breeding process, breeding databases also tend to be complex, often difficult to use, and expensive to implement and maintain. By contrast, Breedbase has user-friendly web interface enabling users to better manage and leverage data for decision-making, all within a fully integrated digital ecosystem, applicable to tomato and many other crops.

  PublisherDOI

• Genomic Predicted cross performance: a tool for optimizing parental combinations in breeding programs

  Database · 2025-01-01

  articleOpen accessSenior author

  BACKGROUND: Genomic prediction is an effective method for shortening breeding cycles and accelerating genetic gains. Traditionally, genomic prediction has focused on estimating 'additive' breeding values for individual genotypes. However, for many breeding programmes, predicting the cross-performance of parental combinations may provide greater value. RESULTS: We present the genomic predicted cross-performance (GPCP) tool, which utilizes a mixed linear model based on additive and directional dominance. This tool is available within the BreedBase environment and as an R package. We assessed its effectiveness against classical genomic estimated breeding values (GEBVs) using simulated traits that exhibit varying dominance effects and on four yam traits. The GPCP tool proved superior to traditional methods for traits with significant dominance effects, effectively identifying optimal parental combinations and enhancing crossing strategies. This article outlines how the tool is implemented and emphasizes situations where predicting cross-performance is more advantageous than depending solely on GEBVs. CONCLUSIONS: The GPCP tool provides a robust solution for predicting cross-performance, offering significant advantages for breeding programmes targeting traits influenced by dominance. It is particularly useful for clonally propagated crops, where inbreeding depression and heterosis are prevalent and reciprocal recurrent selection is impractical.

  PublisherDOI

• An interactive gene expression atlas for mango

  Acta Horticulturae · 2025-01-01

  article
  PublisherDOI

• Radiomics-based prediction of HCC response to atezolizumab/bevacizumab.

  Journal of Clinical Oncology · 2025-01-27

  article

  636 Background: Advanced hepatocellular carcinoma (HCC) treatment has evolved with the introduction of atezolizumab/bevacizumab, showing improved outcomes over sorafenib. However, the response varies among patients, particularly between viral and non-viral etiologies. This study aimed to develop and evaluate multimodal prediction models combining quantitative imaging and clinical markers to predict treatment response in HCC patients. Methods: From March 2020 to May 2023, patients with advanced HCC treated with atezolizumab/bevacizumab were retrospectively identified from six centers in Germany and Austria. Patients underwent baseline contrast-enhanced liver MRI and follow-up imaging to assess therapy response. Machine learning models, including RandomForestClassifier, were developed for radiomics, clinical, and combined datasets. Hyperparameter tuning was performed using RandomizedSearchCV, followed by cross-validation to evaluate model performance. Results: The study included 103 patients, with 70 achieving disease control (DC) and 33 experiencing disease progression (PD). Key findings included significant differences in treatment response and progression-free survival between DC and PD groups. The radiomics model, using 14 selected features, achieved 73.1% accuracy and a ROC AUC of 0.635 on the test set. The clinical model, with 4 selected features, achieved 73% accuracy and a ROC AUC of 0.649 on the test set. The combined model showed improved performance with 69% accuracy and a ROC AUC of 0.753 on the test set. Hyperparameter tuning further enhanced the combined model's accuracy to 80.1% and ROC AUC to 0.771 on the test set. Conclusions: The hybrid model combining clinical and radiological data outperformed individual models, providing better predictions of response to atezolizumab/bevacizumab in HCC patients.

  PublisherDOI

• DeltaBreed: A BrAPI-centric breeding data information system

  PLoS ONE · 2025-12-12 · 2 citations

  articleOpen accessCorresponding

  DeltaBreed is a unified breeding data management system designed by Breeding Insight (BI, Cornell University) to serve the wide diversity of USDA-ARS specialty crop and livestock breeding programs. DeltaBreed has a RESTful microservice architecture that utilizes the BrAPI v2.1 Java Test Server as its primary database. The system is interoperable with many BrAPI-compliant applications (BrApps), including Field Book v6.1.0, and is continually aligned with the most recent BrAPI specifications (BrAPI v2.1). Here we describe the features of DeltaBreed v1.0, a minimum viable product, and how we aligned data capture and validation with community standards. We highlight the modules for management of germplasm, observation variables, experiments and observations, genotypic sample submission, and a prototype genomic database that supports polyploid and multiallelic genomic data, as well as SNP data. Several test cases are illustrated to demonstrate the successes and challenges of interoperability with other open-source BrAPI-enabled software packages. We also discuss expansion and enhancement plans for future DeltaBreed versions, as well as outline possible solutions to known limitations. To our knowledge, DeltaBreed is the first species-agnostic, fully BrAPI-compliant breeding data management system built for transactional use.

  PublisherDOI

• Field trial analyses of wheat and cassava benefit from spatial correction

  2025-06-04

  preprintOpen access

  Spatial variation is a major source of error in agricultural field experiments affecting genotype performance prediction. Implementing statistical models that account for spatial effects can improve the prediction of genotype performance. This study evaluated the impact of the B-spline spatial correction method on the estimation of genetic parameters and AIC values in two distinct crops – wheat and cassava – using four models: Block, Block + Spatial, Block + Marker, and Block + Marker + Spatial. Analyses were performed on data from 136 and 68 trials obtained from the T3/WheatCAP and Cassavabase databases, respectively. The results demonstrated that correcting for spatial variation, regardless of marker information, increased the heritability estimate of grain yield, test weight, plant height, powdery mildew, stripe rust, and bacterial streak disease in wheat. Similar increases were observed in cassava for dry matter content, dry yield, and plant height. However, no increase was observed for cassava mosaic disease or bacterial blight. Models incorporating spatial correction in both crops consistently provided the best fit based on AIC values across all traits in wheat and cassava. These results were consistent whether or not marker effects were fitted in the models. This showed the importance of spatial correction in field experiment analysis.

  PublisherOA PDFDOI

• DeltaBreed: A BrAPI-centric breeding data information system

  bioRxiv (Cold Spring Harbor Laboratory) · 2025-04-24

  preprintOpen access

  Abstract DeltaBreed is a unified breeding data management system designed by Breeding Insight (BI, Cornell University) to serve the wide diversity of USDA-ARS specialty crop and animal breeding programs. DeltaBreed has a RESTful microservice architecture that utilizes the BrAPI Java Test Server as its primary database. The system is interoperable with many BrAPI-compliant applications (BrApps), including Field Book, and is continually aligned with the most recent BrAPI specifications. Here, we describe the features of DeltaBreed and provide several interoperability test cases to illustrate successes and challenges encountered during development. We also discuss future expansion and enhancement plans for DeltaBreed, as well as outline possible solutions to known limitations.

  PublisherOA PDFDOI

• BrAPI v2: real-world applications for data integration and collaboration in the breeding and genetics community

  Database · 2025-01-01 · 4 citations

  articleOpen access

  Population growth and the impacts of climate change are placing increasing pressure on global agriculture and breeding programmes. Recent advancements in phenotyping techniques, genotyping technologies, and predictive modelling are accelerating genetic gains in breeding programmes, helping researchers and breeders develop improved crops more efficiently. However, these advancements have also led to an overwhelming torrent of fragmented data, creating significant challenges in data integration and management. To address this issue, the Breeding Application Programming Interface (BrAPI) project was established as a standardized data model for breeding data. BrAPI is an international, community-driven effort that facilitates interoperability among databases and tools, improving the sharing and interpretation of breeding-related data. This open-source standard is software-agnostic and can be used by anyone interested in breeding, phenotyping, germplasm, genotyping, and agronomy data management. This manuscript provides an overview of the BrAPI project, highlighting the significant progress made in the development of the data standard and the expansion of its community. It also presents a showcase of the wide variety of BrAPI-compatible tools that have been built to enhance breeding and research activities, demonstrating how the project is advancing agricultural innovation and data management practices.

  PublisherOA PDFDOI

• Post-composing ontology terms for efficient phenotyping in plant breeding

  Database · 2025-01-01 · 1 citations

  articleOpen accessSenior author

  Ontologies are widely used in databases to standardize data, improving data quality, integration, and ease of comparison. Within ontologies tailored to diverse use cases, post-composing user-defined terms reconciles the demands for standardization on the one hand and flexibility on the other. In many instances of Breedbase, a digital ecosystem for plant breeding designed for genomic selection, the goal is to capture phenotypic data using highly curated and rigorous crop ontologies, while adapting to the specific requirements of plant breeders to record data quickly and efficiently. For example, post-composing enables users to tailor ontology terms to suit specific and granular use cases such as repeated measurements on different plant parts and special sample preparation techniques. To achieve this, we have implemented a post-composing tool based on orthogonal ontologies providing users with the ability to introduce additional levels of phenotyping granularity tailored to unique experimental designs. Post-composed terms are designed to be reused by all breeding programs within a Breedbase instance but are not exported to the crop reference ontologies. Breedbase users can post-compose terms across various categories, such as plant anatomy, treatments, temporal events, and breeding cycles, and, as a result, generate highly specific terms for more accurate phenotyping.

  PublisherDOI

Frequent coauthors

• Surya Saha

  Ithaca College

  281 shared

• Prashant S. Hosmani

  Ithaca College

  179 shared

• Mirella Flores-Gonzalez

  Ithaca College

  159 shared

• Naama Menda

  Ithaca College

  137 shared

• Wayne B. Hunter

  U.S. Horticultural Research Laboratory

  115 shared

• Susan J. Brown

  108 shared

• Susan R. Strickler

  Center for Plant Conservation

  108 shared

• Tom D’Elia

  101 shared

Awards & honors

• Cornell CALS faculty recognized among most influential scien…