Systematic benchmarking of tools for CpG methylation detection from Nanopore sequencing biorxiv.org/content/10.110… by Zaka Yuen

Looking for a postdoc? We are hiring!

New kernel-based PSI method! with Tobias Freidling (University of Cambridge), Benjamin Poignard (Osaka University), Hector Climente (RIKEN AIP) Héctor Climente

#postdoc position available at Biologie ENS IBENS to work under my supervision on #networks -based multi-omics integration in #singlecell. Project in collaboration with @BaudotAnais Please #RT

Breathe in, breathe out. #ワーケーション #遊ぶ広報 #吉野町 #吉野暮らし

Fangyu Liu (Fangyu Liu) will present tomorrow “Learning Text Representations from Pre-trained Language Models via Contrastive Learning and Self-Distillation”. More details and registration, here: …c59ed978213830355fc8978.doorkeeper.jp/events/134212

Want to bootstrap your sentence similarity model for free? Check out our #ICLR2022 paper Trans-Encoder – jointly learning dual- and cross-encoders through self-distillation, achieving a new SotA on unsupervised STS. Paper, code, models released: arxiv.org/abs/2109.13059 🧵:

Statisticians can be brutal sometimes. Truly insightful read on the assumptions of hypothesis testing: frontiersin.org/articles/10.33….

Lotfi Slim (Lotfi Slim) from NVIDIA will talk next Tuesday about Genomics in the era of Machine Learning. More details and registration: …c59ed978213830355fc8978.doorkeeper.jp/events/134921

I probably should have written this years ago, but here are some MLOps principles I think every ML platform (codebase, data management platform) should have: 1/n

We have started a new machine learning unit at the Okinawa Institute of Science and Technology! groups.oist.jp/mlds I would like to thank my family, students, postdocs, advisors, mentors, letter writers, and friends. Without their support, it wouldn't have been possible.

New work from Héctor Climente, Min Oh & team, using cutting-edge ML models, shows that circulating proteomics information improves CVD risk prediction beyond conventional clinical risk factors. Check it out here: medrxiv.org/content/10.110…

I am happy to share our work of the past few months, on improving cardiovascular disease risk prediction. Our models leverage plasma proteomics from the UK Biobank, as well as traditional risk factors. They are highly accurate and explainable. medrxiv.org/content/10.110…

I have been using uv to manage my Python projects lately. Faster setups, better reproducibility, and it even trimmed down my stack. Here's a short tutorial if you're curious: hclimente.eu/blog/python-uv/

I've spent the last few weeks digging into InstaDeep's Nucleotide Transformer DNA language model using Hugging Face 🤗 If you're keen on seeing how LLM libraries can be applied to DNA, my latest post breaks it all down. Give it a read: hclimente.eu/blog/hf-transf…

🚨 NEW RESEARCH! ⚕️ 🩺 🖥️ Climente-Gonzalez, Oh et al. develop an interpretable #ML model that integrates plasma proteomics with clinical risk factors to improve risk prediction for CVD 🫀 . nature.com/articles/s4385… Héctor Climente nkoell.bsky.social Chuan Li Joanna Howson