Ethan Gao
@greysonc98
Followers
9
Following
18
Media
0
Statuses
15
Excited to share our new work, collaborated with Microsoft Research. Causal disentanglement for single-cell representations and controllable counterfactual generation
biorxiv.org
Conducting disentanglement learning on single-cell omics data offers a promising alternative to traditional black-box representation learning by separating the semantic concepts embedded in a...
0
0
0
Machine learning has made incredible breakthroughs, but our theoretical understanding lags behind. We take a step towards unravelling its mystery by explaining why the phenomenon of disentanglement arises in generative latent variable models. Blog post: https://t.co/yqJaAbGH4I
2
12
56
7 million pairs! A great resource for TCR-antigen interaction. TRAIT: A Comprehensive Database for T-cell Receptor-Antigen Interactions https://t.co/QIztPtbZQn
2
15
55
Excited to share our new work!
📢@greysonc98, @Kejing_Dong and colleagues present STAMP, a tool for genetic perturbation prediction that also exhibits robust generalizability when applied to previously unseen cell lines. https://t.co/pZRHc8jvFl ➡️ https://t.co/DCbBpGeGuq
0
0
0
Unified cross-modality integration and analysis of TÂ cell receptors and TÂ cell transcriptomes by low-resource-aware representation learning
cell.com
Gao et al. have proposed a novel multimodal integration framework for integrating scRNA-seq and TCR-seq to explore T cell diversity. This framework can be applied to a series of downstream tasks,...
0
7
5
✨New review alert!✨ Ever wondered how biological dendritic mechanisms could advance machine learning and neuro-inspired computing? Well, we did, and we've written a review article to explore just that @YiotaPoirazi @_RomanMakarov ! Check out the 🧵👇 1/5
1
24
95
Multi-omics: the next arena for big data in biology For the first time in history, we can measure life's ingredients at a large scale: DNA → genomics RNA → transcriptomics Protein → proteomics Can we unite these data modalities and understand them in context of one another?
3
76
307
PerturBase: a comprehensive database for single-cell perturbation data analysis and visualization
0
9
43
5/ STAMP can also be applied to identify key genes and regulatory relationships in new cell line with small samples and precisely detect different genetic interactions.
0
0
0
4/ STAMP can also serve as a robust, objective and generalizable benchmark framework for evaluating different genetic perturbation prediction models
0
0
0
3/ With flexibility of STAMP, we explore the impact of gene embeddings in genetic perturbation task, particularly the potential of mainstream large single cell foundation models.
0
0
0
2/ We explicitly categorize the genetic perturbation prediction tasks into three distinct challenges, consisting of (1) predicting single genetic perturbation, (2) predicting multiple genetic perturbation and (3) predicting genetic perturbation across cell line
0
0
0
1/ We introduce a novel AI paradigm into the genetic perturbation prediction task, i.e. task decomposition-based learning. This task can be naturally decomposed into three subtasks: (1) identifying DEGs, (2) determining directions of DEGs and (3) estimating the changes of DEGs
0
0
0
Excited to share STAMP, our new work in genetic perturbation prediction task! https://t.co/gtnK3SZAtS
biorxiv.org
Deciphering cellular responses to genetic perturbations is fundamental for a wide array of biomedical applications, ranging from uncovering gene roles and interactions to unraveling effective...
5
1
2