Alishba Imran
@alishbaimran_
Followers
7K
Following
8K
Media
164
Statuses
2K
CS @berkeley_eecs | curr: ML bio @arcinstitute, research @berkeley_ai | prev: @czbiohub, @tesla, @NVIDIA, founded ML battery startup
toronto
Joined November 2014
The AI for Robotics e-book is out now!🎉. 450 pages, 200+ visuals, 150K words covering perception, 3D sensor fusion, foundation models, transformers & diffusion for control, sim, RL & more. Available now:.Nature Springer: Amazon:
8
15
201
RT @fleetwood___: Dropped the Virtual Cell Challenge Primer on HF. We are shipping transformers support for STATE (the SOTA model for pre….
0
8
0
elegant approach for designing tf payloads for epigenetic reprogramming which enables in silico prediction of cell state changes from sparse combinatorial data:.
reprogramming cells with transcription factors is our most expressive tool for engineering cell state. traditionally, we found TFs by ~guesswork. @icmlconf we're sharing @newlimit's SOTA AI models that can design reprogramming payloads by building on molecular foundation models
0
1
5
This review from the director of AI research at @microsoft perfectly captures why we wrote our book AI for Robotics!. “… reframing classic robotics challenges through a deep learning lens”. We always find reviews/feedback like this really helpful! 🙏
0
0
8
RT @KevinKaichuang: "The body of data available in protein sequences is something fundamentally new in biology and biochemistry, unpreceden….
0
6
0
RT @niteshgarg03: Reading this book, gotta say liking it so far. Traditional robotics books (as important as they are for foundational know….
0
2
0
RT @mattersOfLight: We have a fun update on DynaCLR (, a self-supervised method for learning cell state dynamics fr….
arxiv.org
We report DynaCLR, a self-supervised method for embedding cell and organelle Dynamics via Contrastive Learning of Representations of time-lapse images. DynaCLR integrates single-cell tracking and...
0
6
0
RT @WholeMarsBlog: Some of the most exciting applications of deep learning are in biology. Really fascinating work.
0
6
0
Work done with @edyoshikun, Soorya Pradeep, Ziwen Liu, @mattersOfLight & rest of the team @czbiohub!.
0
0
5
Try it out:.- Code & training pipeline – - Annotation + visualization plugin – - Paper: (4/4).
1
0
4
DynaCLR’s temporal embeddings enable in silico synchronization of asynchronous dynamics like infection, mitosis, and organelle remodeling. Using dynamic time warping, we estimate pseudotime across multiple imaging channels. (3/4)
1
0
3
We use knowledge distillation to scale label-free infection phenotyping: a model trained on 10k fluorescence-labeled cells generates 133k pseudo-labels for phase data, cutting manual labeling 10Ă—. (2/4)
1
0
3
Excited to share our new paper on DynaCLR, a self-supervised model for learning cell dynamics from terabytes of live imaging!. Enables:.- Detection of infection & cell division.- Label-free prediction of states.- Alignment of async cell trajectories.- Organelle remodeling. (1/4)
1
5
136
RT @edyoshikun: Excited to share an update on #DynaCLR—a self-supervised method to learn dynamic cell & organelle embeddings from time-laps….
arxiv.org
We report DynaCLR, a self-supervised method for embedding cell and organelle Dynamics via Contrastive Learning of Representations of time-lapse images. DynaCLR integrates single-cell tracking and...
0
10
0
We’re also excited about this result!. Zero-shot prediction showed clear value of embeddings:.- Pretraining State on Tahoe-100M.- Fully fine-tuning on smaller, noisier datasets.- Led to more accurate perturbation ranking prediction than mean baselines or HVG-trained State models.
The result I'm most excited about from Arc's new State model:. The ability to generalize on zero-shot out-of-distribution predictions after pre-training on the TAHOE-100M data set. Whereas PLMs have seemingly benefitted less from scaling data and model size, this is an inkling
1
5
34
Following the launch of STATE, Arc is launching a new challenge!. Build ML models to predict how human cells respond to perturbations, using our new H1 human embryonic stem cell line data. Check it out:.
Announcing the inaugural Virtual Cell Challenge! Hosted by Arc Institute, and sponsored by Nvidia, 10x, and Ultima, help solve one of biology’s biggest challenges with AI by building cell state models that accurately predict responses to perturbation.
0
0
13
Learned a lot working on this with @abhinadduri, @yusufroohani, @davey_burke, @genophoria and rest of the team!.
0
1
7
Excited to share what I’ve been working on @arcinstitute!. STATE is a transformer-based model trained to predict how cells respond to perturbations, using the largest single-cell perturbation dataset to date: 170M observational and 100M+ perturbational cells across 70 cell lines.
Today @arcinstitute releases State, our first perturbation prediction AI model and an important step towards our goal of a virtual cell. State is designed to learn how to shift cells between states (e.g. “diseased” to “healthy”) using drugs, cytokines, or genetic perturbations
7
13
287
RT @percyliang: Wrapped up Stanford CS336 (Language Models from Scratch), taught with an amazing team @tatsu_hashimoto @marcelroed @neilbba….
0
567
0