- Background
- What we're looking for
- What we can offer you
- Who we are
- Q&A
"Digital Twins” are digital representations of real world objects using structured, machine readable data.
Isolated and targeted studies on plants investigate specific conditions, tissues, or species. We see promise in integrating the data from those studies with models in order to create a "Digital Twin", that would provide a holistic picture of plant physiology.
Applications can include plant growth models, understanding of pesticide absorption, distribution, metabolism and excretion (ADME), mode of action, and understanding of resistance development.
A "Digital Twin" solution would enable the creation of customized modeling pipelines over a unitary data and modeling architecture, for example, to identify the role a gene or a set of genes plays in combination with environmental conditions for the occurrence of a certain phenotype.
A "Digital Twin" of a plant would incorporate data and information at different anatomic levels, including data from proteomics, metabolomics, genomics, transcriptomics, as well as comprehensive gene annotation, associated phenotypes, and known interactions with chemicals. This data can be sourced from public databases and literature, but also from internal experiments.
Knowledge graphs excel at capturing the complexity of the real world, and they store information in a way that’s intuitive and are an ideal way to model "digital twin" data.
BASF is seeking graph-based building and model-querying technologies that can be applied to model plants. We are also looking for large-language models and methods to integrate data from different physiological levels and different plants. We are open to partnering on earlier-stage research to achieve these objectives "from the ground up" or identifying partners with existing solutions.
- Graph-based building and querying technologies that can be applied to model plants.
- Methods to integrate data from different physiological levels and different conditions applicable to plants.
- Algorithms that combine -omics data (proteomics, metabolomics, genomics, and transcriptomics) and labeled data over different physiological scales, that can be used for segregation of physiological effects in relation to effector or root cause.
- Large-language models that interact with graph models, applicable to plant biology.
- Proposals leveraging expertise and tools developed for other systems (human or animal models) that may be adapted to plant systems are welcome.
- Methods to integrate data from different plants like duckweed (Lemna), Arabidopsis thaliana, Alopecurus myosuroides, Amaranthus palmeri, Glycine max, Brassica napus, and Triticum aestivum.
- Methods to integrate -omics data (proteomics, metabolomics, genomics, and transcriptomics) from different plants by creating an unified gene ortholog system.
- Human or animal specific models if they cannot be adapted to plants.
- Models that cannot incorporate -omics (proteomics, metabolomics, genomics, and transcriptomics) data sets.
- Models that cannot transfer learnings from one model plant to another.
As a global chemical company, we operate in diverse markets with varying requirements. To ensure responsible conduct and maintain our license to operate, we are guided by our core values and standards. These values shape our daily actions and foster respectful relationships with colleagues, customers, and partners.
Our teams are committed to putting health and safety first, making sustainability a part of every decision, and meeting strict compliance and environmental standards. We embrace diversity—in people, perspectives, and experiences—and promote open feedback grounded in honesty, respect, and trust. We see setbacks as opportunities to learn and improve.
Learn more
The Q&A is now closed.
Other recommended requests
delivered to your inbox.