@BibekarParth @jeffreyjgray @sokrypton @RosettaCommons @Hegelrast Also, I’d like to generally thank the carbohydrate/glycobiology community at large, with a notable appreciation for the amazing DIONYSUS dataset that was constructed by Dr Aria Gheeraert and Dr @TatianaGalochk1 , which this work heavily relies on!.

@BibekarParth @jeffreyjgray @sokrypton Id like to thank the @RosettaCommons at large- especially Yijie Luo and @Hegelrast for providing us with their designed carbohydrate non-binder dataset (which they used to train their CLIMBS algorithm, also just published on BioRxiv!).

@BibekarParth I’d like to thank my PI Dr @jeffreyjgray and co-mentor Dr. Ronald L Schnaar for their advise on this project. I’d also like to thank @sokrypton for implementing PiCAP and CAPSIF2 on the ROSIE server.

@BibekarParth If you’d like to use CAPSIF2 or PiCAP, you can do so freely at our github link: or you can use our server on ROSIE: !

We also provide an updated model of our CAPSIF, a model for predicting carbohydrate binding regions of proteins. Comparing CAPSIF2 with @BibekarParth’s PeSTo-Carbs, where their model outperforms CAPSIF2 on the TS90 dataset, but CAPSIF2 modestly outperforms P-C on a larger dataset

So: 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!

PiCAP does well on the test set -- but how does it do on other datasets that aren’t 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!

To 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 designed proteins and antibodies

It all started by asking just a simple question: “What proteins bind carbohydrates?” 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 proteins in humans that bind carbs.

I’m 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 and @RonaldSchn37100 .

RT @bikemorebmore: Today with sponsor @Embry4Delegate we launched the fight to bring justice to vulnerable road users by replacing Maryland….

RT @TWOT100:

In this paper, our contribution leveraged AlphaFold 2 and our software CAPSIF to predict the residues of these proteins that interact with carbohydrates! Very excited by this work and the possibilities of this novel dataset in the near future!.

In this work, Dr. Gao-Lan Zhang and the Schnaar lab determined the interactome of cell surface proteins and a gangliosides revealing immense detail to proteome understanding of carbohydrate binding.

Very excited by our recent collaboration with the Schnaar Lab at Hopkins: The Human Ganglioside Interactome in Live Cells Revealed Using Clickable Photoaffinity Ganglioside Probes.

I'm happy to share with everyone some work that I've recently assisted where we improved the thermostability of an arabinofuranosidase. Cheers to Manoela Martins for leading this amazing project!.

RT @FrontBioinf: New Research: Structure-based neural network protein–carbohydrate interaction predictions at the residue level #Bioinforma….

And then use the code from here:.

I'm happy to announce that our most recent paper, "Structure-based neural network protein–carbohydrate interaction predictions at the residue level" has been published in Frontiers! Read it here:.

This project was first conceptualized by Sudhanshu Shanker, who I worked closely with, and advised by our mentor @jeffreyjgray . For more results, check out our preprint on bioRxiv!.