iiinova — where your digital self keeps evolving

GitHub - JEFworks-Lab/STARIT: Spatial Transcriptomics As Rasterized Tensors (STARIT)

By providing an alternative representation of molecular-resolution spatial transcriptomics data, we hope STARIT will enable the identification of novel cell-states. Congrats to Dee Velazquez for leading this work 👏 🥳 STARIT is available as a Python package. Try it out: github.com/JEFworks-Lab...

github.com

Spatial Transcriptomics As Rasterized Tensors (STARIT) - JEFworks-Lab/STARIT

020

Using real imaging-based spatial transcriptomics (MERFISH) data of bacteria, STARIT identifies cells with similar overall exp magnitude but distinct subcellular organization: showing more punctuated vs diffuse transcript localization for flagellar subunits, with potential functional consequences.

In this updated preprint, we show STARIT can delineate smooth trajectories with continuous changes in subcellular localization, is robust to partial volume capture under certain conditions, and is compatible with a range of AI feature extractors.

100

Imaging-based spatial transcriptomics is often represented as cell-level gene counts, overlooking subcellular spatial variation. STARIT creates an image-based representation, allowing us to use computer vision AI models to identify cell states with distinct subcellular localization patterns.

Spatial Transcriptomics As Rasterized Image Tensors (STARIT) characterizes cell states with subcellular molecular heterogeneity

Excited to share a substantial update to our preprint on STARIT (Spatial Transcriptomics As Rasterized Image Tensors), a framework for enabling computer vision AI analysis of spatial transcriptomics data for characterizing subcellular heterogeneity. Preprint: v2 www.biorxiv.org/content/10.6...

biorxiv.org

Imaging-based spatially resolved transcriptomics (imSRT) technologies provide high-throughput molecular-resolution spatial characterization of genes within cells. Conventional analysis methods to iden...

152

Dr. Jean Fan @jef.works · 01/09/2026

Our paper on spatial transcriptomic profiling of cold ischemia in mouse kidneys is now published open-access in Genome Biology: link.springer.com/article/10.1... We hope these insights help us understand cold-storage injury in kidney transplants + inform future temporal ST analyses. Congrats team 🥳

040

Dr. Jean Fan @jef.works · 04/08/2026

I'm currently running the most sophisticated agentic network (pregnancy). Within the span of 40 weeks, my biological agents (cells) will read 3 billion letters of instructions (DNA) to autonomously assemble a new human being. When will AI agents catch up? 😉 #biologyisamazing

0192

Dr. Jean Fan @jef.works · 27/07/2026

Continuing my observations of the neoliberal academic ecosystem with more post-tenure shenanigans, here is a video of my commentary on artificial intelligence among university professors: youtu.be/SNsIHRmTb44

youtu.be

Artificial Intelligence among University Professors

YouTube video by Prof. Jean Fan

072

Dr. Jean Fan @jef.works · 21/07/2026

In this @nature.com news article, I reflect on the last 10 years of spatial transcriptomics to highlight the feedback loop between industry and academia in our unified efforts to push the boundaries of science towards improving human health: www.nature.com/articles/d41...

0208

Dr. Jean Fan @jef.works · 16/07/2026

Many of us profs are struggling w/ AI use by students. But a source of frustration I didn't anticipate: AI use by colleagues. Because if I had wanted an AI’s opinion, I too can prompt ChatGPT 🙄 More in my reflection on "Artificial Intelligence among University Professors" jean.fan/2026/07/16/a...

073

Dr. Jean Fan @jef.works · 06/07/2026

Happy 20th birthday to PLOS Computational Biology 🎂 In this perspective, as an editor for the Genomics section, I offer a data-driven reflection on how genomics research within the journal has evolved over the years by analyzing trends in submitted research papers: journals.plos.org/ploscompbiol...

journals.plos.org

Another 10 years of PLOS Computational Biology: A data-driven reflection on trends in genomics research

Since the founding of PLOS Computational Biology 20 years ago, genomics research has advanced at a remarkable pace. In this 20th anniversary commentary, as an Editor for the Journal Section of Genomic...

041

Dr. Jean Fan @jef.works · 02/07/2026

Thick-tissue spatial transcriptomics with 3DEEP-HybISS in skin enabled pseudotemporal molecular mapping of hair follicle organogenesis via natural asynchrony of follicle development: www.cell.com/cell/fulltex... Explore the data for yourself: jef.works/CellCarto-3D... Congrats to @kalhorlab + team

050

Dr. Jean Fan @jef.works · 30/05/2026

As academic audit culture grows (now NIH pre-approvals for conferences and foreign collaborators), I hope students will remember there is another way: an academia built around mutual trust and obligation through collective effort. My take on the neoliberal academic ecosystem: youtu.be/PGO4qgfm7DU

youtu.be

University Professors in the Neoliberal Academic Ecosystem

YouTube video by Prof. Jean Fan

070

Dr. Jean Fan @jef.works · 04/05/2026

In this blog post, I demo how I went from a question ➡️ "how have gas prices changed in different regions across the US over time?" ➡️ to using AI to find relevant data ➡️ to using AI to vibe code this data visualization to answer my question: jef.works/blog/2026/05... Try it out for yourself!

020

Dr. Jean Fan @jef.works · 23/04/2026

Before cameras, only painters could "capture reality." After, people said cameras would replace painters. But painting evolved. Now, people say AI will replace programmers. So, I reflect on things painting in the age of cameras can teach us about coding in the age of AI: jean.fan/2026/04/22/a...

030

We also improved our interactive website to explore this data and results so take a look for yourself: jef.works/CellCarto-Co... Congrats to Sami Singh, Dee Velazquez, with Hamid Rabb + team 🎉

000

Our spatiotemporal transcriptomic analysis thus identified coordinated molecular changes within metabolic pathways deep within the cold ischemic kidney, highlighting potential opportunities for new insights beyond those available from superficial biopsy-focused tissue examinations.

100

Our spatiotemporal molecular analysis reveals an unexpected metabolic response: genes involved in oxygen-dependent oxidative phosphorylation are upregulated in the hypoxic inner medulla, a region that typically relies on glycolysis. Now corroborated by protein-level evidence from immunofluorescence.

100

Increased durations of cold ischemia is implicated in poor transplant outcomes, but the molecular mechanisms remain unclear. Using spatial transcriptomics, we profiling cold ischemia injury using a mouse model to identify temporally-resolved gene expression changes in a compartment-specific manner.

Dr. Jean Fan @jef.works · 17/04/2026

We've updated our preprint characterizing the spatiotemporal impact of cold ischemia in mouse kidney to better understand the molecular underpinnings of cold-storage injury in kidney transplants. Check it out: www.biorxiv.org/content/10.1... 🧵👇

121

What's your "scientific origin story"? In this video essay, I share mine from a keynote to graduating high school students: youtu.be/JXXIilLEmSg Every story has an origin, including yours. Through education, you gain the skills to shape this story & choose which parts you may one day like to share.

youtu.be

Writing your scientific origin story #videoessay #graduation #keynote

YouTube video by Prof. Jean Fan

000

Dr. Jean Fan @jef.works · 01/04/2026

Check out this article from TheScientist profiling our development of the Mentorship Index as a proxy for a researcher’s contribution to mentoring junior scholars The M-Index: A New Metric Puts Mentorship in the Spotlight the-scientist.com/the-m-index-... Calculate yours: jef.works/Mentorship-I...

the-scientist.com

The M-Index: A New Metric Puts Mentorship in the Spotlight | The Scientist

The Mentorship Index aims to provide a quantifiable proxy of how researchers support junior scientists, offering a new way to evaluate academic impact.

010

Dr. Jean Fan @jef.works · 15/03/2026

Just finished teaching another semester of Genomic Data Visualization! 🥳 This semester, I integrated AI-assisted vibe coding. Some students used AI to excel beyond the mechanics of coding. Others struggled in ways I did not expect. I reflect on my blog: jean.fan/2026/03/15/v...

jean.fan

Jean Fan | Personal site

Personal website of Prof. Jean Fan

3171

At the time (by year as a coarse cutoff). Relevant code is in `async function countPriorWorks(authorId, beforeYear)` Else, first authors who stay in academia (continue publishing) will have high pub counts vs those who leave (no longer publish). The metric would capture something very different.

200

Awesome! Yes, I rely on openalex.org There are definitely some double counts (particularly preprints). Also if either your name or your trainee's name is very common, I currently do not do anything to disambiguate contributions from other people with the same name.

openalex.org

OpenAlex

100

The M-index isn’t meant to replace holistic evaluation of mentoring abilities. But such metrics can help surface something I care about in ways that existing metrics like the h-index doesn’t capture. If we don’t create metrics that reflect our values, we cede that ground to metrics that may not.

To put this Mentorship Index to the test, I applied it to evaluate 2 colleagues 😜 h-index: Manolis wins (170 vs 88) M10-index: Lior wins (106 vs 38) Both have invested in achieving different kinds of accomplishments, which can be reflected in these different metrics.

100

My approach: I use openalex.org to count the # of publications for which the scientist served as last author (senior/mentoring role) where the first author (the mentee who led the work) was relatively new to science (proxied by the # of publications associated with their name at that time).

openalex.org

OpenAlex

100

So what do we care about in a senior faculty recruit? For me: mentorship of junior scientists (not just recruiting already-polished senior postdocs). But how do we quantify that?

100

We're recruiting senior faculty! So at faculty meeting, a colleague brought up a candidate who has an h-index of 100. Impressive! But then another colleague pointed out: their last senior-author paper was 10 years ago. This got me thinking about what metrics actually capture and what they miss.

As an alternative to the h-index, I made the Mentorship Index (M-index) to proxy a scientist's contribution to mentoring junior scientists. Ex. M10-index = # last-author publications where the first author had < 10 pubs. Calculate yours: jef.works/Mentorship-I... Blog: jef.works/blog/2026/03... 🧵👇

4103

Check out our preprint with more details, quantifiable metrics, insufficiencies of data imputation, and other insights: www.biorxiv.org/content/10.1... Work led by Caleb Hallinan 🥳 4/4 Previous thread: bsky.app/profile/jef....

biorxiv.org

000

We've now updated our preprint to expand on these results to further demonstrate that these data quality-driven effects are reproducible across: ✅ More spatial transcriptomics datasets ✅ More spatial transcriptomics technologies ✅ Different feature extractors ✅ Alternative model architectures 3/n

100

We previously showed how improving data quality (molecular detection sensitivity, imaging resolution, etc) provides an orthogonal strategy to tuning model architecture in spatial transcriptomics-based predictive modeling. But data imputation intended to improve data quality led to overfitting. 2/n

100

Dr. Jean Fan @jef.works · 22/02/2026

We previously showed how changing training data alone can improve deep learning prediction of spatial transcriptomics gene expression from histology images by +38% (without any changes to model architecture). We've now updated our preprint w/ expanded results: www.biorxiv.org/content/10.1... 🧵1/n

132

I walk through how I vibe → inspect → rethink → hand-fix logic errors → visualize → zero in on genes with quantifiably different spatial patterns between Visium and Xenium that suggest off-target binding. STcompare: github.com/JEFworks-Lab... Additional reading: elifesciences.org/reviewed-pre...

010

Dr. Jean Fan @jef.works · 22/02/2026

In this blog post, I vibe code to apply STcompare to kidneys assayed by two different spatial transcriptomics technologies (Visium vs. Xenium) to identify spatially consistent and differentially patterned genes. Follow along + try it out for yourself: jef.works/blog/2026/02...

130

By shedding light on off-target probe binding + providing a tool to enable prediction, we hope this work will enhance the quality of + improve reproducibility in spatial transcriptomics research 🙌 Caleb Hallinan + team Previous post: bsky.app/profile/jef....

010

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

We thank the editors and reviewers at eLife for their feedback. You can check out their public peer review comments here: elifesciences.org/reviewed-pre...

elifesciences.org

100

GitHub - JEFworks-Lab/off-target-probe-tracker: Pipeline to predict off-target binding via probe sequences

We added new tutorials for our OPT (off-target probe-tracker) tool that aligns probe sequences to transcript sequences to detect potential off-target probe activity: github.com/JEFworks-Lab...

github.com

Pipeline to predict off-target binding via probe sequences - JEFworks-Lab/off-target-probe-tracker

111

Finally, we emphasize that such off-target binding may similarly affect other probe-based gene detection approaches from other commercial vendors given sensitivity vs. specificity tradeoffs. We therefore emphasize the importance of transparency through sharing probe sequences.

We also now demonstrate how to leverage tissue-specific gene expression from atlasing resources like HuBMAP to assess how off-target binding might affect observed gene expression profiles in a specific tissue of interest for custom gene panels.

120

We now clarify the differences between these probe sequences in a new supplementary note. Importantly, this impacts our interpretation of observed results to provide stronger evidence of putative imperfect sequence homology based off-target probe binding.

100

Previously, we used the publicly available Xenium v1 Human Breast Panel probe sequences from the 10x website (pre-April 2025). We now understand that this file erroneously included extra probe sequences that aren't actually used.

100