Fengjun Zhang (@fengjun_zhang) 's Twitter Profile
Fengjun Zhang

@fengjun_zhang

postdoc @soehnleinlab. solo atlas maker. geneticist. developer. AI enthusiast. polyglot: CHN/JPN/ENG/DEU.

ID: 956909227532054528

linkhttps://github.com/fzhang12 calendar_today26-01-2018 15:18:33

194 Tweet

223 Followers

161 Following

Heng Li (@lh3lh3) 's Twitter Profile Photo

Preprint on "Improving spliced alignment by modeling splice sites with deep learning". It describes minisplice for modeling splice signals. Minimap2 and miniprot now optionally use the predicted scores to improve spliced alignment. arxiv.org/abs/2506.12986

Preprint on "Improving spliced alignment by modeling splice sites with deep learning". It describes minisplice for modeling splice signals. Minimap2 and miniprot now optionally use the predicted scores to improve spliced alignment.
arxiv.org/abs/2506.12986
Bo Wang (@bowang87) 's Twitter Profile Photo

🚀 Xaira Therapeutics has just dropped a game-changer for AI-driven biology. Today, we unveiled X-Atlas/Orion, the largest publicly available genome-wide Perturb-seq dataset to date—spanning 8.4 million single cells with perturbations across all ~20,000 human protein-coding

🚀 Xaira Therapeutics has just dropped a game-changer for AI-driven biology.

Today, we unveiled X-Atlas/Orion, the largest publicly available genome-wide Perturb-seq dataset to date—spanning 8.4 million single cells with perturbations across all ~20,000 human protein-coding
Sergi Valverde🌍(under a blue sky) (@svalver) 's Twitter Profile Photo

A new paper in Nature Ecol & Evol by Rosa Fernández et al. shows a #punctuated burst of genome evolution in #annelids as they transitioned from marine to land and freshwater habitats.

A new paper in Nature Ecol &amp; Evol by <a href="/Rosamygale/">Rosa Fernández</a> et al. shows a #punctuated burst of genome evolution in #annelids as they transitioned from marine to land and freshwater habitats.
Fengjun Zhang (@fengjun_zhang) 's Twitter Profile Photo

Is it just me finding 10x data difficult to understand what product authors were referring? some annotated their library as "HTO" but never worked with CR multi (multiplexed but treated as FB instead of CellPlex)

Is it just me finding 10x data difficult to understand what product authors were referring?
some annotated their library as "HTO" but never worked with CR multi (multiplexed but treated as FB instead of CellPlex)
Fengjun Zhang (@fengjun_zhang) 's Twitter Profile Photo

Glad to hear tons of feedback from #Gmeeting2025 Fantastic meeting to learn heterogeneity of granulocytes and the studies of them ☺️

Glad to hear tons of feedback from #Gmeeting2025 
Fantastic meeting to learn heterogeneity of granulocytes and the studies of them ☺️
Fengjun Zhang (@fengjun_zhang) 's Twitter Profile Photo

I had a dream of studying animals when I heard Dr. Jane Goodall’s legacy in my early childhood Back then I never thought I would finish my dissertation in studying animals genomes I thank her so much for her inspirations on that little kid 🥹

『はたらく細胞』公式 (@hataraku_saibou) 's Twitter Profile Photo

『#はたらく細胞』原作・清水茜(清水茜|イエローフレイム)先生より、坂口志文先生のノーベル生理学・医学賞受賞のお祝いイラストをいただきました。坂口先生、本当におめでとうございます!

『#はたらく細胞』原作・清水茜(<a href="/yellow_flame_/">清水茜|イエローフレイム</a>)先生より、坂口志文先生のノーベル生理学・医学賞受賞のお祝いイラストをいただきました。坂口先生、本当におめでとうございます!
antisense. (@razoralign) 's Twitter Profile Photo

Among full pipelines, rapids singlecell was the fastest, whereas OSCA and scrapper achieved the highest clustering accuracy in datasets with known cell identities. Performance differences were largely driven by the choice of highly variable genes (HVGs) and PCA implementation.

Fengjun Zhang (@fengjun_zhang) 's Twitter Profile Photo

My biggest improvement this year was understanding how and when to talk with AI In bioinfo field it’s always about learning new tools urself and AI brings u on a rocket Oh my google+stackoverflow days PhD training needs a reboot in an AI world nature.com/articles/d4158…

Fengjun Zhang (@fengjun_zhang) 's Twitter Profile Photo

I am super impressed by 5.1 now Just threw a vague problem to it cuz I don't want to check line by line myself Did not realize actually there were a lot missing info and I did not explain first It figured out all missing context itself and got me the correct answer Thats a wow