CS PHD student @ UToronto | AI for biology
Joined April 2018
- Tweets 78
- Following 673
- Followers 126
- Likes 949
8 Photos and videos
Rex Ma retweeted
Jun 8
New Science Blog: Why has AI advanced faster in coding than in biology?
To agents, bio databases are like cities built before cars—maddening to drive in because they're designed for different traffic.
How do we build infrastructure agents can use?
anthropic.com/research/agent…
319
500
3,682
723,740
What a clear explanation of OPD!
Jun 4
On-Policy Distillation is the most active new research direction being explored in RL for LLMs. Had the chance to discuss how it works with Dwarkesh and why it fits so nicely into large-scale pipelines.
23
Rex Ma retweeted
May 19
We are releasing Carbon: a crazy fast DNA model
Carbon is 275x faster than the next best model. So fast you can process the whole human genome on a single GPU in <2 days.
Here are the tricks we used:
When modelling DNA sequences a lot of the performance comes down to tokenizing the sequences in a smart way. BPE tokenizer struggle because there are no whitespaces and character (called base in DNA) level tokenizers waste a lot of compute on too many tokens.
Carbon is built with a unique tokenizer: we split sequences in chunks of 6 bases, but during both training and inference we can work with single base resolution. That's similar to having word tokens but resolving them at the character level. All possible thanks to the DNA tokens unique structure.
The architecture combined with the tokenizer makes the model 275x faster than the previous SoTA (Evo2) at this size.
We built an interactive demo so you can explore how the model can generate DNA sequences, investigate the structure of genes, predict the effect of mutations, generate and fold proteins and even reconstruct parts of the tree of life.
huggingface.co/spaces/Huggin…
77
279
1,929
402,296
TML has found a niche direction
May 11
People talk, listen, watch, think, and collaborate at the same time, in real time. We've designed an AI that works with people the same way.
We share our approach, early results, and a quick look at our model in action.
thinkingmachines.ai/blog/int…
1
31
High quality sleep is actually the best medicine
Apr 27
go to bed
right now
i know the build is almost finished
the eval can wait til morning
the agent will still be failing tomorrow
you won't figure out why it's hallucinating
yes your coworker ships on 4 hrs of sleep
they also hallucinate a lot
off you go
38
A weekly jab in the belly is generating more revenue than the entire AI industry.
Ozempic Mounjaro: $71B in 2025.
OpenAI Anthropic: $29B.
And they've barely started. ~2% of the 800 million eligible patients can currently access them.
h/t @DrSamuelBHume
57
199
1,117
548,506
Rex Ma retweeted
Apr 20
Wet lab validation is critical for actual success of AI models in biology!🧪
Apr 20
Have you wondered what the wet lab success rates are for current AI-driven protein design models? Look no further!
In our new open access review, @KevinKaichuang, @avapamini, @SarahAlamdari, and I report wet lab success rates for *over 200* different protein design tasks 🧬💻
1
8
48
8,435
Congrats Phil!
Apr 17
Excited to share Orthrus is now published in Nature Methods! This was a work from our PhDs in which we showed 3 things:
- There's lots of room for new biologically grounded self-supervised objectives
- The "y - intercept" in scaling is important! We show that representations from 10 million parameter Orthrus outperform a 7 billion parameter model, 700 its size.
- Orthrus works in the low-data regime where data acquisition is especially expensive: low throughput experimental data and clinical trials
Ian and I are now building BlankBio to apply these ideas at a bigger scale. I'm going to be at AACR get in touch if you want to chat!
3
100
Rex Ma retweeted
Mar 20
BioReason-Pro, the second model in our BioReason series is here! Congratulations @adibvafa, @arman1sa, @Radii2323, and the entire BioReason team!
2
17
48
7,128
Rex Ma retweeted
Mar 20
What if AI could explain why a protein is a kinase, not just tell you it is?
We built just that.
BioReason-Pro is a multimodal LLM that reasons about protein function — walking through domains, interactions, and biological context to make predictions you can actually evaluate.
3
9
53
7,627
Rex Ma retweeted
Mar 20
today we launched bioreason-pro, try using it:
app.bioreason.net
11
41
197
55,834
Come talk to your protein at 🔥
bioreason.net
Proteins can now talk.
Introducing BioReason-Pro, the first reasoning model for protein function.
A thread🧵
2
9
1,559
Rex Ma retweeted
Mar 20
1/7 First of all, big shoutout to co-authors on modeling (@MKarimzade, @neal_ravindra, @RexMa9, @HAOTIANCUI1, @LeeTaliq), huge appreciation to data generation (Lexi, @alerasool, Adam) and bioinformatics team (@_annhuang), and leadership for vision and direction (@BoWang87, @inCiChu)!
Preprint is now live on bioRxiv: biorxiv.org/content/10.64898…
All models start from high-quality data.
Our X-cell is up at @biorxiv_bioinfo !
Read our full paper at biorxiv.org/content/10.64898…
Part of the data and the model weights will be shared soon. stay tuned!
1
11
33
6,885
2026 may be the year AI starts to truly reason about biology.
AlphaFold helped close the sequence → structure gap.
The next frontier is sequence → functions.
Today, together with @genophoria and the team at @arcinstitute , we’re releasing BioReason-Pro — the first multimodal reasoning model for protein function prediction.
15
76
303
70,446
Rex Ma retweeted
Mar 20
Over 250 million protein sequences are known, but fewer than 0.1% have confirmed functions. Today, @genophoria, @BoWang87 & team introduce BioReason-Pro, a multimodal reasoning model that predicts protein function and explains its reasoning like an expert would.
13
125
527
62,656
Rex Ma retweeted
Mar 17
Massive push from the dream team 🫡 walkthrough coming soon!
Today we’re announcing X-Cell — Xaira’s first step toward a virtual cell. 🧬
A foundation model that predicts how gene expression changes under causal perturbations — across cell types, conditions, and even unseen biology.
This is not trained on observational atlases.
It is trained on interventions.
🧵👇
1
6
28
3,821
Rex Ma retweeted
Mar 17
1/ So excited to have had the opportunity of contributing to this magnificent effort! Foundation models of observational transcriptome often memorize gene co-expression networks without understanding the underlying logic. Genetic perturbation datasets make it possible to
Today we’re announcing X-Cell — Xaira’s first step toward a virtual cell. 🧬
A foundation model that predicts how gene expression changes under causal perturbations — across cell types, conditions, and even unseen biology.
This is not trained on observational atlases.
It is trained on interventions.
🧵👇
1
4
14
2,840