Lightnews — Scholar-powered news

Dr. Jean Fan @jef.works · 2d

When interviewing for faculty positions, it can feel like there's a "right answer" to "win". But the reality is: there’s no perfect script.

Teach your ideas with clarity and enthusiasm. Trust that your genuine self will resonate more than performing what you think others want.

Find your fit! 🍀

Dr. Jean Fan @jef.works · 2d

Looking to prep for faculty job interviews? Try my Academic Interview Simulator: Faculty Edition. About as realistic as dating sims are to real dating 🤣: www.youtube.com/watch?v=dzv-...

(I'm tinkering w/ AI. Inspired by the Rising Stars workshop for post-docs I just served on. Real advice 👇)

Academic Interview Simulation: Faculty Edition (mockup gameplay) #datingsim #parody #aivideo

YouTube video by Prof. Jean Fan

www.youtube.com

1 4

Dr. Jean Fan @jef.works · 11d

In this blog post, I use #RStats to explore publicly available ICE arrest data. #Dataviz shows recent trend where ICE are primarily targeting/locating people without criminal records in communities.

Code along and take a look for yourself: jef.works/blog/2025/09... #CodeTutorial

2 11

Reposted by Dr. Jean Fan

Keystone Symposia @keystonesymposia.bsky.social · 20d

Wrapping up AI in Molecular Biology, we celebrate 3 Future of Science Fund Award winners: @ryantheshark.bsky.social (@ucberkeleyofficial.bsky.social), Lucy Luo (@nufeinbergmed.bsky.social) & Reet Mishra. Their work shows the bright future of science! 🌟
#KSAIBio26 @drkbio.bsky.social @jef.works

3 7

Dr. Jean Fan @jef.works · 23d

Greetings from beautiful Sante Fe for the AI in Molecular Biology @keystonesymposia.bsky.social #KSAIBio26

Excited to bring together academic and industry leaders in this emerging field to organize, shape trends, influence policy, discuss challenges

If you're around, please come say hi 👋

2 13

Dr. Jean Fan @jef.works · 29d

Congratulations to Caleb Hallinan for leading this work in collaboration with CJ Lucas @jhu.edu @hopkinsengineer.bsky.social

Dr. Jean Fan @jef.works · 29d

While recent efforts to predict spatial transcriptomics from H&E images w/ deep learning have focused on improving modeling approaches, our results highlight that improvements in training data quality offers an orthogonal strategy to enhance performance. 7/n

1 2

Dr. Jean Fan @jef.works · 29d

Likewise, to pinpoint what imaging data quality factors may drive these performance differences, we simulated lower-resolution images by applying Gaussian blur to the H&E images to demonstrate that image resolution has a measurable impact on performance and interpretability. 6/n

1

Dr. Jean Fan @jef.works · 29d

Further, we demonstrate how imputation methods intended to rescue sparsity and noise boost performance when evaluated on the held-out test set but decreases performance when evaluated on an independent replicate, suggesting overfitting that limit robustness and generalizability. 5/n

1

Dr. Jean Fan @jef.works · 29d

To pinpoint what molecular data quality factors may drive these performance differences, we performed a series of in silico ablation experiments in which we systematically decrease molecular data to show sparsity and noise as drivers of decreased performance. 4/n

1

Dr. Jean Fan @jef.works · 29d

We train identical models using matched ST datasets from different technologies (Visium vs Xenium) with unique technical constraints that impact data quality. We find that the predictive performance across genes is 38% higher when trained on Xenium data compared to Visium data. 3/n

1

Dr. Jean Fan @jef.works · 29d

Deep learning can predict gene expression from H&E, but performance varies widely, highlighting the need for further investigation into factors that impact prediction performance. Our study assesses the impact of training data quality on the predictive performance. 2/n

1 2

Dr. Jean Fan @jef.works · 29d

High costs motivate efforts to predict spatial transcriptomics from H&E images w/ deep learning. In our recent preprint, we show that noise, sparsity & resolution in ST data impact performance, highlighting the importance of training data quality: www.biorxiv.org/content/10.1...

🧵1/n

1 3 11

Dr. Jean Fan @jef.works · Aug 29

See the previous preprint post for more details: bsky.app/profile/jef....

Dr. Jean Fan @jef.works · Apr 3

We identify evidence of off-target probe binding in the 10x Genomics #Xenium v1 Human Breast Gene Expression Panel, compromising the accuracy of resulting #singlecell #spatialtranscriptomics profiles

See our preprint for more details: www.biorxiv.org/content/10.1...

#AcademicSky

🧵👇 1/n

Evidence of off-target probe binding in the 10x Genomics Xenium v1 Human Breast Gene Expression Panel compromises accuracy of spatial transcriptomic profiling

The accuracy of spatial gene expression profiles generated by probe-based in situ spatially-resolved transcriptomic technologies depends on the specificity with which probes bind to their intended tar...

www.biorxiv.org

2

Dr. Jean Fan @jef.works · Aug 29

Further, we believe this paper will benefit from eLife's continuous post-publication public peer review. We hope this will enable the rapid dissemination of these insights + allow for constructive criticisms from industry + academic experts to be openly considered by all readers.

1 3

Dr. Jean Fan @jef.works · Aug 29

...we chose not to submit this as a Matters Arising since that process requires confidentiality and can be rather lengthy. Given the urgency imposed by the cost and wide usage of these ST technologies, we felt it was more responsible to share this work as quickly as possible.

1 3

Dr. Jean Fan @jef.works · Aug 29

I would also like to note that, given the results presented in our paper, previous results presented in the publication describing the Xenium technology and demonstrated using this gene panel (Janesick et al, Nature Communication, December 2023) are in part erroneous. However...

1 2

Dr. Jean Fan @jef.works · Aug 29

eLife Assessment: "This valuable study identifies and characterizes probe binding errors in a widely used commercial [ST] platform...The authors provide convincing evidence...[T]his work provides an essential quality control resource that will improve data interpretation"

1 2

Dr. Jean Fan @jef.works · Aug 29

Our paper identifying evidence of off-target probe binding in the 10x Genomics Xenium Breast Gene Panel is now available as a reviewed preprint at #eLife

elifesciences.org/reviewed-pre...

We look forward to revising the paper to incorporate reviewer recommendations and other updates 🧵👇

2 8 34

Dr. Jean Fan @jef.works · Aug 19

Final call for posters @keystonesymposia.bsky.social on AI in molecular biology. Deadline August 21

Beyond talks, our program also includes panel discussions on challenges + opportunities for innovation + responsibility in AI-driven biology: keysym.us/KSAIBio26

Hope u can join the conversation!

1 6

Dr. Jean Fan @jef.works · Jul 31

In this interview, I explain how university research, when funded by independent #NIH #NSF federal grants, brings oversight to biotech to fuel innovation while keeping science transparent, reliable, and in service of the public good: hub.jhu.edu/2025/07/30/j...

#ResearchMatters

University labs help power America's biotech innovation ecosystem

Hopkins researcher Jean Fan and her team create open-source tools that help bridge the gap between academic discoveries and life-saving treatments. Cuts to federal funding threaten to break this criti...

hub.jhu.edu

10 27

Dr. Jean Fan @jef.works · Jul 24

People are being arrested by ICE. What countries are they from?

I analyze public data from deportationdata.org/data/ice.html to find increased arrests for immigrants from many countries #FirstTheyCame

Code so you can reproduce these trends for yourself: gist.github.com/JEFworks/1f0...

1 4

Dr. Jean Fan @jef.works · Jul 20

I visualize trends in #ICE #immigration arrests and encounters over time and across select US cities using public data from deportationdata.org/data/ice.html

Here is the #RStats #ggplot code so you can visualize the #dataviz trends in your own city: gist.github.com/JEFworks/0c7...

#codetutorial

4 17

Dr. Jean Fan @jef.works · Jul 17

I received some old microscopy slides from the 1800s, when at-home microscopes made it possible to look at hidden worlds of diatoms, polycystina, and other teeny tiny things.

I made this website so people today can take a look too: microspeci.men

Enjoy! #scienceisforeveryone #microscopy #HistSci

6 18 65

Dr. Jean Fan @jef.works · Jul 12

I use #ggplot #gganimate #Rstats to visualize spatiotemporal trends in public ICE detention data.

Watch ICE detention increase over time: more detainees (bigger dots), more non-criminals (blue → red), and more jails far from the border in 2025.

Code #gist: gist.github.com/JEFworks/899...

#DataViz

1 11 15