Jianbin Chen

Staff Bioinformatics Scientist in @illumina AI lab. Using Deep learning AI to decipher genomics and improve human health.

[Jianbin Chen @Bright_88]

Super excited to share SpliceAI2! ✂️🧬
It predicts splice-site and splice-junction usage, reconstructs complete transcripts, and models tissue- and disease-specific splicing.
Proud to have contributed, and huge credit to the incredible team behind it!
Check out the tweetorial!⬇️

[Kishore Jaganathan @kjaganatha]

Incredibly, incredibly excited to introduce SpliceAI2, the next generation of splicing prediction! 🧬🚀🧵

[Kishore Jaganathan @kjaganatha]

#SpliceAI2 technical deep dive: transcript prediction and training. We perfectly reconstructed the top transcript for 82% of held-out genes. How? Splice graphs, dynamic programming, and long-read RNA-seq. 🧬✂️🧵

[Kyle Farh MD PhD - Illumina AI Lab @KyleFarh]

Excited to announce SpliceAI2:
https://t.co/ymTk8V5R9d

Open model weights:
https://t.co/YKjhJpgE55

Source code:
https://t.co/MDVAdvd9Ti

[Illumina @illumina]

Illumina's genomic AI models now enable researchers to identify 2x as many variants with predicted biological impact.

Identifying these variants and understanding their downstream effects can unlock new biological insights to advance rare disease and drug discovery research. The newest generation of our leading-edge genomic AI models are designed to help researchers assess the functional impact of splice, promoter, and missense variants.

With SpliceAI2, out today, we aim to help researchers advance rare disease research.

In the words of the vice president of BioInsight AI Lab, Kyle Farh: “Illumina is advancing AI to systematically shrink the portion of the genome that remains uninterpretable.”

🔗 Learn more: https://t.co/SpLpP5NVy1

For Research Use Only. Not for use in diagnostic procedures.

[Jianbin Chen @Bright_88]

The blog post: https://t.co/FP99sNplum
Manuscript:
https://t.co/WtJZgSvRtq
Git repo:
https://t.co/trmtFtvU2w

[Jianbin Chen @Bright_88]

Super excited to share SpliceAI2! ✂️🧬
It predicts splice-site and splice-junction usage, reconstructs complete transcripts, and models tissue- and disease-specific splicing.
Proud to have contributed, and huge credit to the incredible team behind it!
Check out the tweetorial!⬇️

[Kishore Jaganathan @kjaganatha]

Incredibly, incredibly excited to introduce SpliceAI2, the next generation of splicing prediction! 🧬🚀🧵

[Gherman Novakovsky (слава Україні! 🇺🇦) @NovakovskyG]

Excited to share my first contribution here at Illumina! We developed PromoterAI, a deep neural network that accurately identifies non-coding promoter variants that disrupt gene expression.🧵 (1/)

[Kishore Jaganathan @kjaganatha]

We're thrilled to introduce PromoterAI — a tool for accurately identifying promoter variants that impact gene expression. 🧵 (1/)

[A*STAR Research @astar_research]

“One bad apple spoils the barrel.” The same applies to liver cancer cells 🍎

Researchers have discovered that these cells have as many as six different subtypes, and the presence of the most aggressive type is a key predictor of patient outcomes.

👉🏻 https://t.co/y684QNegaE

[Jianbin Chen @Bright_88]

Although the key messages were established before I joined Illumina, it took immense effort from our multidisciplinary team to finalize them. A big thank you and congrats to all contributors @weiwei_beijing,@neslihanky Ying, Raden Indah Kendarsari,@waileongtam, Prof Chow & more!

[Jianbin Chen @Bright_88]

We also confirmed the 'bad apple' effect, a long-held suspicion that the most aggressive portion of the tumor significantly impacts patient outcomes. It underscores the importance of sampling more regions of heterogeneous tumors for more accurate prognosis prediction.

[Jianbin Chen @Bright_88]

we connected genomic variations to transcriptomic phenotypes and patient prognosis. Our findings reveal several converged genomic evolutionary paths taken by early HCC, which are linked to specific phenotypes observed later at the time of surgery.

[Jianbin Chen @Bright_88]

After years of pondering and coding (and addressing reviewers' insightful comments), my first corresponding paper is finally online! https://t.co/U5Mfsus53q Using the largest (so far) multi-sector WGS+RNA-seq prospective HCC (liver cancer) cohort,

[Jianbin Chen @Bright_88]

🎉Big congrats to our AI lab colleagues! Four Science papers explore primate genomes & unveil PrimateAI-3D, revolutionizing disease diagnosis & treatment development. As humans are mere branches in the tree of life, wildlife protection is crucial even from pragmatic perspectives.

[Jianbin Chen @Bright_88]

I might be a bit slow to know (mind-blowingly) that gpt could directly write a whole notebook for data processing now. Excellent for publicly available data

[Noteable @noteable_io]

AI is empowering everyone to create data-driven documents.

We're proud to announce our @OpenAI ChatGPT plugin integrating Noteable's interactive notebook platform into ChatGPT.

Ready for the details? Buckle up for an exciting ride! 🧵

[Anthropic @AnthropicAI]

Introducing 100K Context Windows! We’ve expanded Claude’s context window to 100,000 tokens of text, corresponding to around 75K words. Submit hundreds of pages of materials for Claude to digest and analyze. Conversations with Claude can go on for hours or days.

[Yann LeCun @ylecun]

Nice demo of Mojo, a new Python-compatible language with a parallelizing compiler that can import Python libraries.

[Steve Reilly @ReillyLikesIt]

Out today in @ScienceMagazine as part of @ZoonomiaProject : our deep dive on evolutionary DELETIONS in conserved regions. Learn about this counter-intuitive source of mammalian innovation!

Here's a tweetorial on what these surprisingly missing elements are doing in humans

[Elinor Karlsson (elinork.bsky.social) @eenork]

Humans can be... well... a little self-absorbed... our DNA is the MOST SEQUENCED DNA EVER!

SO. MUCH. DATA.

But are we sooooo special?!? #Zoonomia 1/n

[Jianbin Chen @Bright_88]

Have been using it this way and it's really quite comforting

[Eric Topol @EricTopol]

Noteworthy: a new study comparing #ChatGPT vs doctors for responding to patient queries demonstrated clearcut superiority of #AI for improved quality and empathy of responses @JAMAInternalMed
https://t.co/XLO5ripcB2

[SpaceX @SpaceX]

The Starship team is go for prop load. Now targeting 8:20 a.m. CT→ https://t.co/bJFjLCiTbK