Lightnews — Scholar-powered news

Reposted by Kevin K. Yang 楊凱筌

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 5d

Test the activity of 300+ natural enzymes against 100+ substrates, discover 200+ new enzymatic reactions, and train machine learning models to predict which enzymes can do which reactions.

@aepaton.bsky.social @gabegomes.bsky.social @alisonnarayan.bsky.social

www.nature.com/articles/s41...

1 12 53

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 5d

Thank you! Excellent work!

2

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 5d

Test the activity of 300+ natural enzymes against 100+ substrates, discover 200+ new enzymatic reactions, and train machine learning models to predict which enzymes can do which reactions.

@aepaton.bsky.social @gabegomes.bsky.social @alisonnarayan.bsky.social

www.nature.com/articles/s41...

1 12 53

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 12d

Combine multimer structure prediction and an antibody language model to design de novo antibodies with nanomolar binding affinity.

@synbiogaolab.bsky.social @brianhie.bsky.social

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

3 19

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 19d

Oh they at least didn't ask me to do that

1

Reposted by Kevin K. Yang 楊凱筌

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 20d

Out of 7 papers in my NeurIPS Benchmarks and Datasets Track area, the PCs overruled my recommendation on 3?!

2 1 5

Reposted by Kevin K. Yang 楊凱筌

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 20d

Genome language models can generate new, high-fitness bacteriophages!

@samuelhking.bsky.social @claudiadriscoll.bsky.social
@david-li.bsky.social @danguo.bsky.social @adititm.bsky.social Garyk Brixi @maxewilkinson.bsky.social @brianhie.bsky.social

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

2 9 31

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 20d

Out of 7 papers in my NeurIPS Benchmarks and Datasets Track area, the PCs overruled my recommendation on 3?!

2 1 5

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 20d

Genome language models can generate new, high-fitness bacteriophages!

@samuelhking.bsky.social @claudiadriscoll.bsky.social
@david-li.bsky.social @danguo.bsky.social @adititm.bsky.social Garyk Brixi @maxewilkinson.bsky.social @brianhie.bsky.social

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

2 9 31

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 23d

The posting is unfortunately not super clear on this, but please apply if you want to do BioML research, especially around machine learning for molecular biology and bioengineering!

I get sad if there are no applicants with this profile in the pool!

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 25d

If you're an undergrad and want to intern with me, this is where you need to apply!

Microsoft Research @msftresearch.bsky.social · 26d

The Microsoft Research Undergraduate Internship Program offers 12-week internships in our Redmond, NYC, or New England labs for rising juniors and seniors who are passionate about technology. Apply by October 6: msft.it/6015scgSJ

1 6 6

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 25d

If you're an undergrad and want to intern with me, this is where you need to apply!

Microsoft Research @msftresearch.bsky.social · 26d

The Microsoft Research Undergraduate Internship Program offers 12-week internships in our Redmond, NYC, or New England labs for rising juniors and seniors who are passionate about technology. Apply by October 6: msft.it/6015scgSJ

5 6

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 28d

Train a protein structure predictor that can handle 29 non-canonical amino acids, then use it to design binders with non-canonical amino acids that reduce immunogenicity.

@panhammarstrom.bsky.social @patrickbryant1.bsky.social

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

2 22

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · Sep 5

A joint sequence-structure diffusion model for transmembrane proteins!

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

8

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · Sep 3

A compelling review of how ML/AI could help in the quest to find an enzyme for every reaction.

@jsunn-y.bsky.social @francescazfl.bsky.social Yueming Long @francesarnold.bsky.social

www.cell.com/cell-systems...

6 20

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · Aug 25

Typical Ohio activity

15

Reposted by Kevin K. Yang 楊凱筌

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · Aug 12

Ramblings of a mad AC

1. If you're reviewing a benchmarks and dataset paper, you should look at the dataset and make sure it's not full of garbage.

2. Biological datasets are especially prone to subtle garbage.

1 1 11

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · Aug 12

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

Accelerating protein design by scaling experimental characterization

Recent advances in de novo protein design have greatly outpaced standard protein biochemistry workflows, and experimental testing has been a bottleneck in the validation of new designs and methodologi...

www.biorxiv.org

4

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · Aug 12

The @uwproteindesign.bsky.social's experimental pipeline behind models like RFdiffusion and ProteinMPNN:

- A rapid, scalable, pipeline for producing and characterizing proteins
- A demultiplexing protocol for converting oligopools to clonal constructs

Jason Qian @lfmilles.bsky.social Basile Wicky

1 3 13

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · Aug 12

5. A long email every other day or so from the PCs with extremely detailed reminders is probably overkill.

1

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · Aug 12

3. Otherwise, your AC basically has to do all the work of a reviewer + the normal AC duties. My area has 7 papers.

4. I imagine it's a bad experience for the authors to spend time addressing reviewer concerns and then have the AC show up with different ones.

1

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · Aug 12

Ramblings of a mad AC

1. If you're reviewing a benchmarks and dataset paper, you should look at the dataset and make sure it's not full of garbage.

2. Biological datasets are especially prone to subtle garbage.

1 1 11

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · Aug 8

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

Evaluating zero-shot prediction of protein design success by AlphaFold, ESMFold, and ProteinMPNN

De novo protein design has enabled the creation of proteins with diverse functionalities that are not found in nature. Despite recent advances, experimental success rates remain inconsistent and conte...

www.biorxiv.org

7

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · Aug 8

A benchmark dataset of 614 experimentally characterized de novo designed monomers from 11 different design studies shows that:
- deep learning structural metrics only weakly predict success
- The score distribution is different for different types of structures

@grocklin.bsky.social

1 10 39

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · Aug 5

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

Scaling down protein language modeling with MSA Pairformer

Recent efforts in protein language modeling have focused on scaling single-sequence models and their training data, requiring vast compute resources that limit accessibility. Although models that use ...

www.biorxiv.org

1 4

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · Aug 5

MSA Pairformer efficiently extracts structure, protein-protein interactions, and mutation effects from MSAs by decomposing the effects of phylogeny and structural contacts.

@yoakiyama.bsky.social Zhidian Zhang @milot.bsky.social @martinsteinegger.bsky.social @sokrypton.org

1 6 32