@i_m_rive

Machine Learning practitioner in the AI x Bio space @arcinstitute | ex @illumina, @carnegiemellon, @iitroorkee

 Mountain View, CA
linkedin.com/in/rive001
Joined April 2018
  • Tweets44
  • Following161
  • Followers71
This is my first ever post on X! And I’d love to share my first ever preprinted work PIE - Perturbation is Everything! Generalizing across unseen cellular and experimental conditions is challenging but essential to therapeutics discovery. Our latest model PIE addresses this challenge by simplifying the learning objective and leveraging curated biological knowledge from public databases. PIE generalizes across a combinatorial space of perturbation studies, unseen cell lines and unseen perturbations. Check out the preprint at doi.org/10.64898/2026.10.02.… Huge shoutout to the team at @arcinstitute for driving this project:@abhinadduri , @beabevi_ , @basak_ersln , @davey_burke , @genophoria , @yusufroohani .
Arc Institute
@arcinstituteOct 5
Most perturbation models learn only from experiments. Our new model, PIE, also draws on decades of curated biological knowledge to predict which genes respond to a perturbation, even in biological contexts and for perturbations it has never seen.
3
9
2
37
5,468
Rishi Verma retweeted
Eric Nguyen
@exnxOct 16
I'm excited to share that @tri_dao has joined @RadicalNumerics as a scientific advisor! Tri and I were labmates at Stanford's Hazy Research, where he pioneered advances in efficient ML systems (FlashAttention). Scaling AI across multimodal biological data demands entirely new approaches to ML systems, and Tri will help guide our research at this frontier. Welcome aboard, Tri! Read more: radicalnumerics.ai/blog/tri-…

Tri Dao joins Radical Numerics as scientific advisor

Tri Dao, Co-Founder and Chief Scientist of Together AI and creator of FlashAttention and Mamba, joins Radical Numerics as scientific advisor on ML systems, optimization, and scaling.

radicalnumerics.ai
7
11
232
11,317
Rishi Verma retweeted
Hani Goodarzi
@genophoriaOct 13
We assembled the Avengers to tackle the grammar of RBP-RNA interactions, especially how structure shapes who binds what: @MKarimzade, Lisa Fish, Heather Karner, @jjohlin, Ali Emadi, @drklly, @BoWang87, @hsnajafabadi, @LeonettiManuel
Arc Institute
@arcinstituteOct 13
RNA-binding proteins (RBPs) recognize RNA by sequence and shape, but which matters varies by site. Introducing Pythia, an interpretable AI model trained on a new high-resolution atlas of 67 RBPs—a collaboration between the @genophoria lab, @czbiohub, @UCSF, @Calico, and @vectorinst.
4
18
4
75
6,605
Rishi Verma retweeted
Prima Mente
@PrimaMenteOct 8
Today we're launching the Alzheimer's Translation Challenge, a global AI competition to discover new therapeutic hypotheses for Alzheimer's disease. At its core is a new 150M cell atlas of neurons, astrocytes, and microglia across different genetic backgrounds under combinatorial perturbations, with multi-modal readouts. The data will be made available through the AD workbench, Hugging Face and Prima Mente's modeling platform. The challenge is led by @PrimaMente and @AlzData in collaboration with @nvidia, @huggingface, @nebiusai, Talisman Therapeutics, @UltimaGenomics, @cellanome, @PrimeIntellect, @GoodfireAI, and @boltz_bio. In 1906, Alois Alzheimer described a new disease of the brain. After 120 years of progress, we still don't fully understand what drives this disease. We want to change that. Participants will use the dataset to build AI models, assessed through a series of evals from general benchmarks to more complex tasks. Top teams will be shortlisted, and their experimental hypotheses tested in Prima Mente's wet lab. Teams win when their hypotheses demonstrate the predicted molecular and functional effect.
14
44
16
202
51,917
Rishi Verma retweeted
Georgia Channing
@cgeorgiawOct 8
Today, we're releasing the Carbon Annotation Database and the model behind it, Carbon-A. We've used this model to discover 566.34 million new gene candidates across 22,617 species, thousands of which have never been studied like this before. We wet-lab validated a number of these new genes in well-studied species, such as in cats, chicken, and arabidopsis (plant), with our partners at Active Site and @UCSD, with more extensive wet lab results on previously-unstudied genomes coming soon.
12
59
10
329
41,183
Rishi Verma retweeted
Rushil Gupta@RushilGupta15Oct 7
Active learning practitioners choose an acquisition strategy before any labeling, but the best one changes with dataset, model, and task. What if we didn't have to pick just one? Introducing FractAL, a soft-strategy selection method (w/ @_romain_lopez_ ) arxiv.org/abs/2610.05544

Soft Strategy Selection for Batch-Mode Active Learning

Real-world deployment of active learning typically forces practitioners to choose an acquisition strategy before any data is labeled. This is a daunting task: strategy performance varies widely...

arxiv.org
1
7
3
46
8,168
Incredibly, incredibly excited to introduce SpliceAI2, the next generation of splicing prediction! 🧬🚀🧵
7
36
4
99
9,035
Two days ago, I had 3 followers. Now I have 30. Comment below if you want to know how I grew 10x :P
1
1
5
170
Rishi Verma retweeted
Tyler
@rezoundousOct 5
Opus 5.5 cured my depression
23
17
2
474
20,809
And preferably Irodov so you can find your people
Anusha
@__acbraingenomeOct 5
carry a book wherever you go
1
113
Rishi Verma retweeted
Yusuf Roohani
@yusufroohaniOct 5
There are two major issues holding back perturbation models from generalizing across conditions: system representation and signal identification
1
6
1
37
6,239
Rishi Verma retweeted
Dave Burke
@davey_burkeOct 5
At Arc we have a compounding delivery cycle for our AI/bio models, with model candidates every 6 months. Sometimes we have spinoffs where we explore ideas and cherry pick ideas forward. PIE is one such example. It explores how far we can push using prior biological knowledge sources to make direct differential expression predictions. Useful result as we build towards more general cell simulators. Congrats @i_m_rive, @genophoria, @yusufroohani and team.
Arc Institute
@arcinstituteOct 5
Most perturbation models learn only from experiments. Our new model, PIE, also draws on decades of curated biological knowledge to predict which genes respond to a perturbation, even in biological contexts and for perturbations it has never seen.
3
5
39
4,459
Rishi Verma retweeted
Hani Goodarzi
@genophoriaOct 5
Check out PIE! Our latest perturbation generalization model from @arcinstitute. Congratulations to everyone, but especially @i_m_rive and @yusufroohani!
Arc Institute
@arcinstituteOct 5
Most perturbation models learn only from experiments. Our new model, PIE, also draws on decades of curated biological knowledge to predict which genes respond to a perturbation, even in biological contexts and for perturbations it has never seen.
1
9
1
51
3,235
Rishi Verma retweeted
Arc Institute
@arcinstituteOct 5
The code is on GitHub, with model checkpoints and data on Hugging Face. Learn more about PIE from co-authors @i_m_rive and @genophoria: arcinstitute.org/news/pie Or access the preprint: biorxiv.org/content/10.64898…

PIE: A model that draws on curated biological knowledge to predict responses in unseen conditions |...

A truly useful virtual cell model should be able to predict how cells respond in conditions it has never seen.

arcinstitute.org
2
11
1,418
Most models are specialized to be evaluated on unseen contexts or unseen perturbations, not both. The grey columns in the figure indicate regimes where these models could not be evaluated natively. PIE’s flexible architecture and data representation methodology allows generalization across both axes, even simultaneously.
Arc Institute
@arcinstituteOct 5
Replying to @arcinstitute
On the Replogle-Nadig dataset, PIE was up to 3.2x better than the strongest baseline at identifying differentially expressed genes, with the biggest gain on unseen perturbations. It still made meaningful predictions when context and perturbation were both unseen.
2
134
Perturbation datasets are limited by scale and sparsity. ML models need to leverage prior biological knowledge to augment their representation of the biological system and perturbation/interference. PIE draws inspiration from the Perceiver IO architecture and ingests a variable set of heterogeneous knowledge sources, each with its own shape. The gene vocabulary isn’t consistent across perturbation datasets. Instead of restricting the model to an intersection of genes measured across datasets or imputing measurements, PIE leverages natural language descriptions of genes to represent them, therefore being able to generalize to genes it hasn’t seen before in training.
Arc Institute
@arcinstituteOct 5
Replying to @arcinstitute
PIE does this by turning public databases (Cellosaurus, NCBI Gene, Gene Ontology, DepMap, PubChem) into inputs. Each gene is represented by its text description, so PIE works across the different gene sets measured in different studies.
91
PS: I'm not the only one wearing a jacket :P
Ray and Stephanie Lane Computational Biology Dept.@CMUCompBio20 Aug 2019
Welcome to our newest class of #MSAS, #MSCB and @CMUPittCompBio students!!! #backtoschool #CMUsocial
📢📢HUGE ANNOUNCEMENT -- PLS SHARE📢📢 I'm teaching a free online course: "Programming for Lovers", starting October 14! I'm giving up to $2,500 to charitable causes in CS education: ($0.10 for every sign-up). Join us! To enroll: canvas.instructure.com/enrol… 👇More details below👇
6
34
9
59
Load more