scispace - formally typeset
A

Anshul Kundaje

Researcher at Stanford University

Publications -  252
Citations -  43164

Anshul Kundaje is an academic researcher from Stanford University. The author has contributed to research in topics: Chromatin & Gene. The author has an hindex of 60, co-authored 203 publications receiving 32299 citations. Previous affiliations of Anshul Kundaje include Microsoft & Columbia University.

Papers
More filters
Proceedings Article

Fourier-transform-based attribution priors improve the interpretability and stability of deep learning models for genomics

Alex M. Tseng, +2 more
TL;DR: The Fourier transform of input-level attribution scores are computed at training-time, and high-frequency components of the Fourier spectrum are penalized to improve deep learning models’ stability, interpretability, and performance on held-out data, especially when training data is severely limited.
Posted ContentDOI

Size-independent mRNA synthesis and chromatin-based partitioning mechanisms generate and maintain constant amounts of protein per cell

Matthew P. Swaffer, +7 more
- 28 Aug 2020 - 
TL;DR: During asymmetric division size-independent transcription is insufficient for size- Independent protein expression and chromatin-binding ensures equal amounts of protein are partitioned to unequally sized cells to maintain size- independent protein amounts.
Posted ContentDOI

Denoising genome-wide histone ChIP-seq with convolutional neural networks

Pang Wei Koh, +2 more
- 07 May 2016 - 
TL;DR: Aconvolutional denoising algorithm, Coda, is introduced that uses convolutional neural networks to learn a mapping from suboptimal to high-quality histone ChIP-seq data, and has the potential to improve data quality at reduced costs.
Posted ContentDOI

Impact of the X chromosome and sex on regulatory variation

Kimberly R. Kukurba, +16 more
- 07 Aug 2015 - 
TL;DR: An analysis of the impact of both sex and the X chromosome on patterns of gene expression identified through transcriptome sequencing of whole blood from 922 individuals identified that genes on the X chromosomes are more likely to have sex-specific expression compared to the autosomal genes.
Journal ArticleDOI

Deciphering colorectal cancer genetics through multi-omic analysis of 100,204 cases and 154,587 controls of European and east Asian ancestries

Ceres Fernandez-Rozadilla, +208 more
- 20 Dec 2022 - 
TL;DR: This article conducted a genome-wide association study meta-analysis of 100,204 colorectal cancer cases and 154,587 controls of European and east Asian ancestry, identifying 205 independent risk associations, of which 50 were unreported.