Source

Protein sequence-to-structure learning Is this the end(-to-end revolution)
onlinelibrary.wiley.com/doi/abs/10.1...

I'm not sure. LinkedIn makes me cringe, it feels so inorganic to me. On the other hand, my Twitter algorithm recommends really good stuff about proteins, microbes, and AI. In contrast, the algorithm of 🦋 is bad :( and the good content (I.e. Science) mostly comes from reposts by our colleagues.

13/13

BindCraft
nature.com/articles/s41...

A recent conference about BindCraft
youtube.com/watch?v=qQih...

Boltzdesign1
www.biorxiv.org/content/10.1...

12/13 Bindcraft started as a binder design tutorial for the Boston Protein Design and Modeling Club, and it evolved into one of the most promising tools in AI-based protein design. And Importantly, it is open-source!🤗

Congrats to all the authors!

11/13 The authors have gone a step further and are currently developing BoltzDesign1, which instead of designing binders, focuses on biomolecular interactions between proteins and small molecules. However, one of the main limitations of both AIs is their high computational cost.

10/13 Bindcraft’s capabilities have also been validated by other labs and, perhaps most notably, in an international binder design competition organized by a company called AdaptyvBio, where Bindcraft won.
adaptyvbio.com/blog/po104

9/13 the most important results IMO was the determination of atomic structures of four binders, where in all cases, the computational designs were highly consistent with the experimentally determined ones.

8/13 They designed binders targeting:
*proteins with no known binding sites
*membrane proteins , which are much harder than intra/extra-cellular proteins
*proteins lacking evolutionary information
*proteins that interact with DNA/RNA
*medically relevant proteins such as those causing allergies

7/13 Then it uses ProteinMPNN to optimize for solubility, increasing the chances of experimental success. Finally, uses AF2 to predict the structure. To demonstrate Bindcraft’s utility, the authors carried out many wet-lab experiments, something not as common as I would like.

6/13 Bindcraft takes advantage of this by first proposing a random seq and predicting its structure to assess how well it interacts with the target protein. It then uses info from each interaction, successful or not, to optimize the seqs until it arrives at a credible interaction

5/13 Bindcraft is an improved version of AlphaFold2, specifically AF-Multimer, which predicts the structure of protein complexes. Having been trained on thousands of structures, AF-Multimer learned to identify which sites are most likely to form protein–protein interactions.

4/13 Bindcraft designs both the sequence and structure of binders, achieving a success rate between 10-100%, since designing large or complex binders is more challenging. This is enormous, considering that our previous best physics/biochemistry-based methods reached a 0.1%.

3/13 We have learned how to design PPI so that one protein, called a binder, can bind to another and regulate it. e.g., cancer drugs are binders. However, designing binders requires yrs of research and detailed biomolecular knowledge. So, what if we teach an AI to design binders?

2/13 Proteins carry out many functions on their own, but when they interact with each other, they generate a diversity of mechanisms that expand and regulate those functions. PPI arose over millions of years of evolution, giving rise to processes as complex as metabolism.