Andrew Duncan

Paper: biorxiv.org/content/10.648… GitHub: github.com/microsoft/enha… A huge thank you to the team @alexijielu @KevinKaichuang @lorin_crawford @micaelanonsense @mitchell_lab and Alan Moses.

Interestingly, when trained on length sorted data, EnhancAR can design compact enhancers. These designed enhancers are shorter than their natural counterparts while maintaining predicted activity, offering a new approach for engineering compact enhancer sequences.

Designing enhancers is key for gene therapy but limited by a lack of experimental data. To overcome this, we developed EnhancAR, a generative model trained on 1.7M enhancer homolog families (~230M sequences) to leverage functional information conserved over evolution.

[ON] WAKE UP!!!!!! THIS IS YOUR TIME TORONTO M POSTAL CODES!!!! twitter.com/HRHospital/sta… #VHCDose2 #COVID19ON #vhcON

[ON] 🍾WE HAVE HIT 3000 EVERYONE AT 45 OVERLEA BLVD!!!!🍾 OPEN TO EVERYONE BOTH IN 2003 OR EARLIER LIVING OR WORKING IN TORONTO (M POSTAL CODES) HERE ARE THE BEAUTIFUL PEOPLE ORGANIZING THINGS! 7000 TO GO!!!!! LETS GOOOOOOOOOOOOOOO #COVID19ON #vhcON

Up next at #BoG21. @mitchell_lab -- A flexible repertoire of transcription factor binding sites and a diversity threshold determines enhancer activity in embryonic stem cells. Published in @genomeresearch ➡️🧬ow.ly/mrt030rEDiu

Bioinformatic pipelines

Now available @genomeresearch, we identify sequences that drive enhancer activity in stem cells and use that knowledge to build synthetic enhancers - important findings by @singhgs15, @shanellemullany, and all co-authors, in collaboration with @AMosesLab genome.cshlp.org/content/31/4/5…