@arvind0422

Life will find a way!

 Stanford, CA
Joined May 2015
  • Tweets9
  • Following58
  • Followers38
1Media
Arvind Kumar retweeted
Kishore Jaganathan@kjaganathaOct 8
Incredibly, incredibly excited to introduce SpliceAI2, the next generation of splicing prediction! 🧬🚀🧵
7
36
4
99
8,918
In a saturation MPRA of the MAPT promoter, PromoterAI tracked measured variant effects, supporting its use for prioritizing pathogenic promoter variants. biorxiv.org/content/10.64898…
1
2
3
689
When linear models and deep learning give the same results, orders of magnitude more training data are needed nature.com/articles/s41592-0… ;

Deep-learning-based gene perturbation effect prediction does not yet outperform simple linear...

Nature Methods - The analysis presented in this Brief Communication shows that, despite their complexity, current deep learning models do not outperform linear baselines in predicting gene...

nature.com
3
17
1
73
15,602
Reminder to benchmark fancy deep learning models against linear baselines, especially when training data is lacking: nature.com/articles/s41467-0…

Performance of deep-learning-based approaches to improve polygenic scores

Nature Communications - Polygenic scores aim to capture genetic risk but may miss nonlinear genetic and environmental interactions. Here, the authors show that neural networks detect limited...

nature.com
2
11
1,177
We're thrilled to introduce PromoterAI — a tool for accurately identifying promoter variants that impact gene expression. 🧵 (1/)
9
136
8
514
66,459
Our single-cell, pan-cancer analysis of open chromatin in human cancers, done in collaboration with TCGA and the Chang and Corces labs (among others including Illumina), is out in Science today. Congrats to Laksshman Sundaram and all authors! science.org/doi/10.1126/scie…

Single-cell chromatin accessibility reveals malignant regulatory programs in primary human cancers

To identify cancer-associated gene regulatory changes, we generated single-cell chromatin accessibility landscapes across eight tumor types as part of The Cancer Genome Atlas. Tumor chromatin...

science.org
2
80
1
302
26,870
Our team's work on Gnomix for Local ancestry inference will be presented today at #ASHG2021 from 2:30PM PT to 3:30 PM. A big thanks to #ASHG2021 for the Reviewer's Choice award!! Congrats to @_danielmas, @alexGioannidis & @HelgiHilmars!
1
8
29
Why use Gnomix, our new local ancestry algorithm for big data? 1. Fastest, works w/ biobank scale data & whole genomes 2. Highest resolution, can find small, ancient segments 3. Most accurate 4. Performs phase error correction (& quickly) 5. Easy to use github.com/AI-sandbox/gnomix
bioRxiv@biorxivpreprint22 Sep 2021
High Resolution Ancestry Deconvolution for Next Generation Genomic Data biorxiv.org/cgi/content/shor… #bioRxiv
3
42
3
108
Best Paper Prize at our AI for Affordable Healthcare workshop at @iclr_conf goes to "XGMix: Local-Ancestry Inference with Stacked XGBoost" - a method to diversify genetic research beyond European ancestry: biorxiv.org/content/10.1101/… #AI4AH #ICLR2020 @CanonMedicalEDI @bioandemerging

XGMix: Local-Ancestry Inference with Stacked XGBoost

Genomic medicine promises increased resolution for accurate diagnosis, for personalized treatment, and for identification of population-wide health burdens at rapidly decreasing cost (with a genotype...

biorxiv.org
6
1
10
Load more