Calin Plesa

Cool preprint. Rather than engineering TdT around reversible terminators, they use the natural sugar specificity of an RNA polymerase to achieve terminator-free, template-free single-nucleotide addition. www.researchsquare.com/article/rs-9...

We just preprinted DropSynth-Gold where we replaced PCA with Golden Gate Assembly (GGA) inside emulsion droplets, extending multiplexed gene synthesis to ~3 kb constructs assembled from up to 12 fragments while preserving the scalability of DropSynth. 1/n

Many GGA library assembly methods are limited by the number of orthogonal junctions that can coexist in a shared reaction. DropSynth-Gold performs each assembly in its own droplet. Library scale is determined primarily by barcode diversity, not junction diversity. 5/n

We just preprinted DropSynth-Gold where we replaced PCA with Golden Gate Assembly (GGA) inside emulsion droplets, extending multiplexed gene synthesis to ~3 kb constructs assembled from up to 12 fragments while preserving the scalability of DropSynth. 1/n

We kept everything that makes DropSynth scalable: barcoded bead capture, emulsion compartmentalization, and pooled processing, but replaced PCA with Type IIS Golden Gate Assembly inside droplets. 3/n

We just preprinted DropSynth-Gold where we replaced PCA with Golden Gate Assembly (GGA) inside emulsion droplets, extending multiplexed gene synthesis to ~3 kb constructs assembled from up to 12 fragments while preserving the scalability of DropSynth. 1/n

New lab preprint: if ML struggles with extrapolation, let's expand the diversity of training data with gene synth, DNA shuffling, and ML gen.... also lots of #FluorescentProteins #ProteinEngineering #MachineLearning #SyntheticBiology 1/n

So if you want ML to explore distant optima, don’t just improve the model. Engineer the training distribution. Create diversity experimentally. Validate it functionally. Then let the model interpolate across it. 11/n

New lab preprint: if ML struggles with extrapolation, let's expand the diversity of training data with gene synth, DNA shuffling, and ML gen.... also lots of #FluorescentProteins #ProteinEngineering #MachineLearning #SyntheticBiology 1/n

Diversity metrics (clustering, k-mers, nearest-neighbor identity, mosaic structure, embedding geometry) show: 1) DNA shuffling expands dispersion 2) FACS constrains but preserves breadth 3) ML redistributes occupancy across new regions 9/n

New lab preprint: if ML struggles with extrapolation, let's expand the diversity of training data with gene synth, DNA shuffling, and ML gen.... also lots of #FluorescentProteins #ProteinEngineering #MachineLearning #SyntheticBiology 1/n

We FACS sorted for blue fluorescence creating a high confidence 7,812 seq BFP training set. We fine tuned ProtGPT2 on this and generated 11,000 de novo sequences which were pruned for max diversity to set of 1,500 for synthesis. 7/n

New lab preprint: if ML struggles with extrapolation, let's expand the diversity of training data with gene synth, DNA shuffling, and ML gen.... also lots of #FluorescentProteins #ProteinEngineering #MachineLearning #SyntheticBiology 1/n

We next generated large numbers of new chimeric variants, that bridge distant homologs by DNA shuffling across the entire parental set. This synthetic recombination expanded sequence dispersion. 5/n

New lab preprint: if ML struggles with extrapolation, let's expand the diversity of training data with gene synth, DNA shuffling, and ML gen.... also lots of #FluorescentProteins #ProteinEngineering #MachineLearning #SyntheticBiology 1/n

We hypothesized that by experimentally expanding sequence diversity, we could convert extrapolation into interpolation by expanding the known manifold. 3/n

New lab preprint: if ML struggles with extrapolation, let's expand the diversity of training data with gene synth, DNA shuffling, and ML gen.... also lots of #FluorescentProteins #ProteinEngineering #MachineLearning #SyntheticBiology 1/n

Our BioE dept at @uoknightcampus.bsky.social has an open rank search for two complementary tenure-track faculty positions in Neuroengineering focused on: 1) Experimental & Translational Neuroengineering and 2) Computational & Data-Science Neuroengineering. careers.uoregon.edu/en-us/job/53... ...1/n

Computational & Data-Science Neuroengineering: neural signal processing and analytics, closed-loop behavior tracking, neuromorphic computing and brain-inspired AI, spatial multi-omics analysis ...3/n

Our BioE dept at @uoknightcampus.bsky.social has an open rank search for two complementary tenure-track faculty positions in Neuroengineering focused on: 1) Experimental & Translational Neuroengineering and 2) Computational & Data-Science Neuroengineering. careers.uoregon.edu/en-us/job/53... ...1/n