Tinyi Chu (@tinyichu) profile picture

Assistant Professor, University of Virginia | @NIH K99/R00 Fellow

Charlottesville, VA
Joined July 2016
Hiring postdocs in my new lab @ UVA — computational biology + ML. The Mission: We develop modern machine learning, including generative modeling, physics-informed neural networks and neural differential equation, to decode single-cell, spatial and liquid biopsy data. Our goal is to uncover the complex cellular and tissue dynamics underlying cancer, inflammation, and tissue senescence. Our Philosophy: Mentorship as Collaboration 🤝 In our lab, trainees are collaborators, not assistants. You can expect direct technical engagement in algorithm development, genuine intellectual exchange, and co-ownership of the science. The PI is deeply committed to providing hands-on training in grant writing and supporting your path to an independent career. Who We Are Looking For: 🔹 Ph.D. in Computer Science, Applied Math, Statistics, Physics, Computational Biology or a related quantitative field. 🔹 Proficiency in PyTorch (or equivalent deep learning frameworks). 🔹 Biological background is a plus, but NOT required! We strongly encourage candidates from purely computational backgrounds to apply—domain-specific biology can be acquired on the job. What We Offer: ✨ Fully funded positions backed by an NIH R00 Award and substantial UVA startup funds. ✨ Rich GPU/HPC computing infrastructure. ✨ A vibrant, highly collaborative environment in beautiful Charlottesville, VA. If you are passionate about building the next generation of AI tools for spatial and single-cell biology, let’s connect! 📩 How to Apply: Send your CV and a brief cover letter to [email protected] 🌐 Full Job Description & Lab Vision: tchulab.org Please feel free to share or tag anyone in your network who might be a great fit! #postdoc #compbio #MachineLearning #singlecell #genomics #academicjobs
2
5
1
22
2,376
Grateful to @NCIHTAN #HTAN for featuring my work! Excited to announce that the next version of BayesPrism is coming soon—stay tuned!
This Post is from an account that no longer exists. Learn more
21
2,309
I’m excited to share part of the computational analysis where we combined BayesPrism and Hotspot to prioritize cell-type-specific spatially variable genes and gene expression modules.
3
3
25
4,851
Notably, the top spatially variable gene, Ascl1, emerged as the driver transcription factor of the NEPC phenotype, highlighting the potential of spatially variable gene identification in prioritizing genes driving lineage plasticity and tumor heterogeneity.
1
1
251
Kudos to @RRomero_PhD for publishing fascinating work on the lineage plasticity of prostate cancer. It’s been an incredible learning experience with @RRomero_PhD , @CharlesSawyers and @dana_peer.
6
542
Thrilled by @dana_peer talk at @AACR ! My algorithm, scClock (Single Cell Clonal Lineage Of Copy Number Kinetics), showed its prowess in reconstructing clonal trees using snRNA-seq and WES of rapid autopsy from PDAC patients (in collaboration with Chris Iacobuzio @ciacobu)#AACR24
2
1
18
1,016
Thrilled to attend my first and final in-person Damon Runyon Retreat during my postdoc training. It was a joy to connect with fellow researchers and staff. A heartfelt thank you to the @DamonRunyon Foundation for their unwavering support throughout my journey #damonrunyonretreat
1
20
3,178
Delighted to share that BayesPrism consistently ranks as the top-performing deconvolution approach in another independent benchmark studies. 🌟 If you or someone you know can benefit from my work, feel free to share this link: nature.com/articles/s43018-0…
Another independent benchmark of deconvolution tools ranks BayesPrism as the top performing. Gratifying to see the many years @tinyichu spent developing BayesPrism paying off! nature.com/articles/s41467-0…
5
2
31
8,230
Huge congratulations to Jay Mahat @DigbijayMahat and other members of the Sharp lab. This is the breakthrough method I've been anticipating since my time at Danko lab. 🌟
1
7
1,885
Congratulations to Tom on his publication! Nothing is more satisfying than witnessing BayesPrism in action in clinical trials, identifying pivotal markers that can potentially benefit cancer patients. #PrecisionMedicine #Bioinformatics #CancerResearch #BayesPrism
Replying to @_tom_dot_com
We first made synthetic samples (pseudobulk) to test which deconvolution method worked best using LUD2015-005 scRNAseq as reference- BayesPrism performed best on our data (thx @tinyichu @charlesdanko et al!). We also used real-world spike-in experiments to confirm its accuracy.
2
1
11
2,816
Tom is an early user of BayesPrism post-preprint. His research showcases monocytes as strong indicators for esophageal adenocarcinoma response to immunochemotherapy. Check out his publication at doi.org/10.1016/j.ccell.2023…
2
239
All postdocs in my lab are paid in the range of 85-95K. One of the reasons I can't go beyond is (reverse) equity concerns from HR. I would ideally pay them 105-115K. I think that's how much I could afford based on funding I can pull in & reducing lab size to a functional minimum.
oh you’re hiring a grad student/postdoc? don’t be shy babe show us the salary
31
73
12
856
332,529
Thrilled to see that BayesPrism performs robustly across different scRNA-seq references, and even surprisingly yields quite concordant deconvolution results between microarray and bulk RNA-seq.
Deconvolution reveals compositional differences in high-grade serous ovarian cancer subtypes biorxiv.org/cgi/content/shor… #bioRxiv
1
6
987
Kudos to the @IwijnDeVlaminck group, @LoyConor and co-authors! Beautiful work that showcased enormous translational potential of cfRNA. Thrilled to see BayesPrism succeed in cfRNA deconvolution in your @CellRepMed paper, and eager for future BayesPrism advancement in this area.
1
8
704
Thrilled to have been part of this beautiful study of human skin tissue from @DrShrutiNaik 's group. Exciting to see how BayesPrism and SpaceFold generalized to skin tissue. Can't wait to see where this takes us! #SpatialTranscriptomics
1
2
10
2,550
Tinyi Chu retweeted
Bullying as a career tool is akin to a tumor - it grows for the sake of growth, never finding satisfaction or happiness. In the end, it harms not only the host but also the perpetrator. #EmpathyMatters
"Bullying is a means for mediocre scientists to rise to the top. Some star academics reached their position because they are bullies, not in spite of it." - Excellent piece about bullying in academia (and really any other professional environment). nature.com/articles/s41562-0…
1
2
19
13,800