SOURCE-LINKED INTELLIGENCE

Biosensing by Sequence-based Activity Inference

CORDIS · observation · Publication date unknown

ve recently invented, we will generate hitherto inaccessible datasets linking over 10^8 transcriptional and translational biosensor sequences with their sensory properties and use these data to train deep learning models that infer biosensor function directly from sequence. This will enable straightforward biosensor design, which we will capitalize on to build a versatile biosensing platform to specifically detect and discriminate molecules from three metabolic compound classes with high potential for bio-based production. Finally, we will apply designed biosensors to engineer new enzymes for CO2-fixation and build dynamic metabolic controllers to obtain superior bacterial strains for the production of flavors and pharmaceuticals. Our novel, data-driven approach will break new grounds in biosensor engineering through synergies between synthetic biology and artificial intelligence paving the way to novel, sustainable bioprocesses. Sequence-Function Mapping, Biosensor, Transcription Factor, Riboswitch

Read original source ↗ Open in workspace

recordType

award

status

TERMINATED

region

EU

value

1499453

unit

EUR