Feiyang Huang
@fyng.bsky.social
Applied ML in living things, PhD-ing CompBio @MSKCC with Wesley Tansey
Prev JHU
Prev JHU
Reposted by Feiyang Huang
Pleased to share our preprint from the Tansey lab at @mskcancercenter.bsky.social: the Pan-PreClinical (PPC) project.
To mitigate biases in immortalized cell line screens, we curated an atlas of >2M experiments in ~2k patient-derived ex vivo constructs using 3k+ drugs.
Interactive web portal here
To mitigate biases in immortalized cell line screens, we curated an atlas of >2M experiments in ~2k patient-derived ex vivo constructs using 3k+ drugs.
Interactive web portal here
A Pan-Cancer Ex Vivo Drug Screen Atlas for Functional Precision Oncology https://www.biorxiv.org/content/10.64898/2026.02.14.705918v1
February 18, 2026 at 9:21 PM
Pleased to share our preprint from the Tansey lab at @mskcancercenter.bsky.social: the Pan-PreClinical (PPC) project.
To mitigate biases in immortalized cell line screens, we curated an atlas of >2M experiments in ~2k patient-derived ex vivo constructs using 3k+ drugs.
Interactive web portal here
To mitigate biases in immortalized cell line screens, we curated an atlas of >2M experiments in ~2k patient-derived ex vivo constructs using 3k+ drugs.
Interactive web portal here
Reposted by Feiyang Huang
We are excited to introduce mRNABench, a comprehensive benchmarking suite that we used to evaluate the representational capabilities of 18 families of nucleotide foundation models on mature mRNA specific tasks.
Paper: doi.org/10.1101/2025...
Code: github.com/morrislab/mR...
A 🧵
Paper: doi.org/10.1101/2025...
Code: github.com/morrislab/mR...
A 🧵
mRNABench: A curated benchmark for mature mRNA property and function prediction
Messenger RNA (mRNA) is central in gene expression, and its half-life, localization, and translation efficiency drive phenotypic diversity in eukaryotic cells. While supervised learning has widely bee...
doi.org
July 15, 2025 at 7:09 PM
We are excited to introduce mRNABench, a comprehensive benchmarking suite that we used to evaluate the representational capabilities of 18 families of nucleotide foundation models on mature mRNA specific tasks.
Paper: doi.org/10.1101/2025...
Code: github.com/morrislab/mR...
A 🧵
Paper: doi.org/10.1101/2025...
Code: github.com/morrislab/mR...
A 🧵
Canjam'25 feels like yet another ML conference
February 22, 2025 at 8:10 PM
Canjam'25 feels like yet another ML conference