Yuval Itan
@ItanLab
Human disease genomics, precision medicine and machine learning. Associate Professor at @IcahnMountSinai
A description of the Human Phenotype Project (HPP), a growing dataset of >13,000 participants (already 28,000 have provided consent for enrollment) that aims at dynamic multi-modal deep phenotyping to better understand health & disease risk👇
One of the most complex regions in the human genome revealed. To me, it was fascinating to combine genome assembly and pangenome graphs (PGR-TK in Fig. 3e) algorithm techniques to uncover the hidden diversity across human populations. #genomics #bioinformatics
*New Open-Access Long Read Resource*. We sequenced 1,019 genomes from the 1000 Genomes Project sample cohort using @nanopore. Sequencing data is available at bit.ly/4m8dlE2. @embl @HHU_de @IMPvienna @CRGenomica nature.com/articles/s4158… [1/8]
A postdoc position is open in my lab to develop AI/ML models for predicting functional effects of genetic variants and to lead large-scale PheWAS in major biobanks. Strong programming skills, a solid publication record, and a background in human genetics are required.
New online! Multiplexed assays of variant effect for clinical variant interpretation bit.ly/4m9IDKO
FAMSA2: 12 M proteins → 40min on 64GB🔥 ⚡️400× faster than Muscle5 and more accurate Protein-universe scale MSA has arrived for desktop🌐
Introducing La-Proteina, a generative AI model that creates complete atomistic protein structures together with their amino acid sequences, scalable upto 800 residues. Built by @NVIDIA Research, in collaboration with @UniofOxford and @Mila_Quebec La-Proteina addresses a key…
30-year @ESIDsociety registry analysis of 30,628 patients' longitudinal datasets show results of robust epidemiological studies on natural courses including diagnosis, treatment, and survival, supporting newborn screening and future AI applications in IEI hubs.la/Q03xH9f90
New ENCODE4 long-read RNA-seq transcripts track for hg38 and mm10. Triplets (e.g. [1,1,3]) indicate start site, exon combination, and stop site for each transcript. Enrichment scores show how these change across tissue and cell line samples. Read more: genome.ucsc.edu/goldenPath/new…
Imanaka, Asano, Okada et al. @HiroshimaUnivEn report the first case of Down syndrome complicated by severe combined immunodeficiency successfully treated with hematopoietic stem cell transplantation. hubs.la/Q03x3ZQh0 #Diagnostics #Therapeutics #InbornErrorsOfImmunity
Grateful to collaborate with an incredible team - @somijemmacho @pnatarajanmd and others - on this important study on evaluating AHA PREVENT in different health care populations
An absolute risk generalizable risk calculator is challenging. Led by @somijemmacho, evaluating AHA PREVENT across 4 academic health systems, we found similar discrimination but variable calibration. A universal absolute risk threshold may not suitably guide.…
Genome Evaluation Pipeline (GEP): A fully-automated quality control tool for parallel evaluation of genome assemblies. #GenomeAssembly #QualityControl #Snakemake #Genomics #Bioinformatics @BioinfoAdv academic.oup.com/bioinformatics…
Superb paper by Megan Cooper and colleagues ! Mosaic STAT5B gain-of-function associated with demyelinating disease and autoimmunity rupress.org/jhi/article/1/…
Evolution of splicing model architectures go.nature.com/3I7QBoS Figure from our recent Review: From computational models of the splicing code to regulatory mechanisms and therapeutic implications (free to read here: rdcu.be/dVNV4)
Read it at the @jhumimmunity !!
.@ALNeehus, Neil Romberg, and @bloodgenes review how genetic variation impacts early B cell development, & discuss inherited rare variants & more common polymorphisms that predispose to B cell-related immune disorders & malignancies hubs.la/Q03tB0zm0
👀 LucaOne: Generalized biological foundation model with unified nucleic acid and protein language nature.com/articles/s4225… 🧬🖥️🧪 github.com/LucaOne/LucaOne
Genome-Wide (GW): an interactive browser for ultrafast chromosome-scale genomics data visualization. nature.com/articles/s4159…
Predicting gene expression from DNA sequence using deep learning models.#GeneExpressionPrediction #GenomeSequences #DeepLearning @NatureRevGenet nature.com/articles/s4157…
Excited to share #AlphaGenome, a start of our AlphaGenome named journey to decipher the regulatory genome! The model matches or exceeds top-performing external models on 24 out of 26 variant evaluations, across a wide range of biological modalities.1/6
I am incredibly sad to learn of the passing of Atul Butte. He was a true giant in our field and a profound inspiration to me and countless others. His vision and contributions have fundamentally shaped biomedical data science. I will miss his boundless energy. RIP my friend.