Iβd like to thank my PI Dr @jeffreyjgray.bsky.social
and co-mentor Dr. Ronald L Schnaar for their advise on this project. Iβd also like to thank Sergey Lyskov for implementing the ROSIE server!
@swcanner.bsky.social
Part time PhD Candidate, part time freelance photographer, full time ultrarunner
Iβd like to thank my PI Dr @jeffreyjgray.bsky.social
and co-mentor Dr. Ronald L Schnaar for their advise on this project. Iβd also like to thank Sergey Lyskov for implementing the ROSIE server!
I would also like to thank the @rosettacommons.bsky.social at large, especially Yijie Luo for providing us with their designed carbohydrate non-binder dataset (which they used to train their CLIMBS algorithm, also just published on BioRxiv!).
17.03.2025 18:02 β π 0 π 0 π¬ 1 π 0If youβd like to use CAPSIF2 or PiCAP, you can do so freely at our github link: github.com/Graylab/picap or you can use our server on ROSIE: r2.graylab.jhu.edu/apps/ !
17.03.2025 18:00 β π 0 π 0 π¬ 0 π 0We also provide an updated model of our CAPSIF, a model for predicting carbohydrate binding regions of proteins. Comparing CAPSIF2 with @parthbibekar.bsky.socialβs PeSTo-Carbs, finding their model outperforms CAPSIF2 on the TS90 dataset, but, CAPSIF2 modestly outperforms P-C on a larger dataset.
17.03.2025 17:59 β π 1 π 0 π¬ 1 π 0Now that the stage is set: what proteins bind to carbohydrates? We used PiCAP on three proteomes: E. Coli, mice, and humans and found that PiCAP predicts 35-40% of proteins bind to carbohydrates. And we provide a table of all proteins and their predictions for open scientific use and validation!
17.03.2025 17:56 β π 0 π 0 π¬ 1 π 0PiCAP does well on the test set -- but how does it do on other datasets that arenβt manually sculpted? We compare PiCAP to LectomeXplore finding a 99.5% agreement between the methods. We also interrogated the ganglioside interactome finding that PiCAP has a strong correlation with the experiments!
17.03.2025 17:54 β π 0 π 0 π¬ 1 π 0To do this we developed a deep learning (DL) model named Protein interaction of CArbohydrate Predictor (PiCAP). We find that PiCAP has approximately a 90% accuracy on identifying carbohydrate binding proteins, with limitations primarily on proteins that have reduced evolutionarily evidence (Abs).
17.03.2025 17:52 β π 0 π 0 π¬ 1 π 0It all started by asking just a simple question: βWhat proteins bind carbohydrates?β Lectins bind carbs, but, there are myriads of other proteins that bind carbohydrates (e.g. RTKs). And so we set out to find that out: can we find all the proteins in the human proteome that bind carbohydrates.
17.03.2025 17:51 β π 0 π 0 π¬ 1 π 0Iβm happy to announce my latest paper has been released as a preprint on BioRxiv: Predictions from Deep Learning Propose Substantial Protein-Carbohydrate Interplay. This paper was only able to happen thanks to both @jeffreyjgray.bsky.social and Dr. Ronald L Schnaar
www.biorxiv.org/content/10.1...
a photo of people giving testimony in the House Judiciary Committee
a photo of Delegate Elizabeth Embry and advocates from Bike AAA, Bikemore, and lawyers who testified in favor of comparative negligence for vulnerable road users.
Today with sponsor Del. Elizabeth Embry we launched the fight to bring justice to vulnerable road users by replacing Maryland's contributory negligence standard with a fairer one that recognizes that a human being hit by a car driver suffers more than a driver in a crash.
20.02.2025 03:43 β π 14 π 4 π¬ 2 π 0