daniil_boiko Profile Banner
Daniil Boiko Profile
Daniil Boiko

@daniil_boiko

Followers
297
Following
190
Media
9
Statuses
66

ML-researcher, AI in chemistry

San Francisco, US
Joined May 2017
Don't wanna be here? Send us removal request.
@daniil_boiko
Daniil Boiko
29 days
RT @AnanikovLab: 🧲Magnetic stirrers - used daily in millions of labs - may silently sabotage reproducibility. Our @JACS_Au article describe….
0
27
0
@daniil_boiko
Daniil Boiko
1 month
RT @_xjdr: you should legally be required to disclose what quantization level you are serving your current model at like it was a nutrition….
0
184
0
@daniil_boiko
Daniil Boiko
4 months
RT @ML_Chem: Discovering organic reactions with a machine-learning-powered deciphering of tera-scale mass spectrometry data #machinelearnin….
0
5
0
@daniil_boiko
Daniil Boiko
4 months
RT @bravo_abad: Discovering new reactions from terabyte-scale mass spectrometry data with a machine learning approach. Large experimental d….
0
9
0
@daniil_boiko
Daniil Boiko
4 months
RT @zeldapoem: How many reasons do you need to move to San Francisco
0
249
0
@daniil_boiko
Daniil Boiko
5 months
I guess not citing prior work is all you need….
0
0
4
@daniil_boiko
Daniil Boiko
8 months
Most useful website in the internet
2
0
7
@daniil_boiko
Daniil Boiko
9 months
(7/n) And finally, thanks 🙌 to all the coauthors and everyone who has supported this work.
0
1
3
@daniil_boiko
Daniil Boiko
9 months
(6/n) But this is only beginning and there is still a lot of work to be done. You can play with this platform at and reach out if you have any questions or excited about this research direction.
1
1
3
@daniil_boiko
Daniil Boiko
9 months
(5/n) Having all that in mind, we have built a system that takes a substrate, selects its neighbors in chemical space, looks up known reactivity, collects enzymes and their neighbors in enzyme space, and finally a separate model reranks this list to produce final output. 🤖
Tweet media one
1
1
7
@daniil_boiko
Daniil Boiko
9 months
(4/n) . of course, it's not always the case, so some screening will be required. What we want here is that a researcher finds working biocatalyst sooner ⏲️, than later.
1
1
4
@daniil_boiko
Daniil Boiko
9 months
(3/n) So, what's next? We need to somehow recommend 🧠enzymes that might work for a particular substrate. Here we exploit two very simple ideas — similar substrates should have similar reactivity and similar enzymes should have similar reactivity as well. And . .
1
1
4
@daniil_boiko
Daniil Boiko
9 months
(2/n) For building such a system, one would need a big enough dataset 💾 first. The preprint introduces an enzyme library 📚, aKGLib1, and a dataset, BioCatSet1, that contains information about reactivity of enzymes from the library against a set of more than 100 substrates.
1
1
4
@daniil_boiko
Daniil Boiko
9 months
At @gpggrp we published a preprint in collaboration with @NarayanLab and particularly awesome @Apatoneh. #ML #AI #chemistry #science. The paper introduces a ML-driven platform for guiding biocatalyst selection in small molecule synthesis. But how does it work? 🧵 (1/n).
1
1
15
@daniil_boiko
Daniil Boiko
9 months
RT @Apatoneh: Excited to share an awesome collab between the @NarayanLab ang @gpggrp! Check out our preprint on CATNIP, using ML to help ch….
0
15
0
@daniil_boiko
Daniil Boiko
9 months
Wrote an article on how you can host LLM tools using @modal_labs .
Tweet media one
0
0
1
@daniil_boiko
Daniil Boiko
10 months
RT @martyamark: Cursor is:.- Great for bad coders.- Bad for great coders.
0
146
0
@daniil_boiko
Daniil Boiko
11 months
(5/n) The paper is available at
0
1
1