Paperpile

Referenced Papers (7)

Multimodal masked autoencoders learn transferable representations

Xinyang Geng, Hao Liu, Lisa Lee, Dale Schuurmans, Sergey Levine, Pieter Abbeel

arXiv [cs.CV], 2022

"This paper is used as an example of a text-vision multi-modal masked model to introduce the concept of masking across modalities, which is the core inspiration for the Nona framework."

Referenced at: 03:05

Chromatin position effects assayed by thousands of reporters integrated in parallel

Waseem Akhtar, Johann de Jong, Alexey V Pindyurin, Ludo Pagie, Wouter Meuleman, Jeroen de Ridder

Cell, 2013

"This paper is cited to introduce the TRIP-seq assay, which is used for a downstream evaluation of the context-aware Nona model's ability to predict gene expression upon integration of a reporter gene."

Referenced at: 20:49

Promoter-intrinsic and local chromatin features determine gene repression in LADs

Christ Leemans, Marloes C H van der Zwalm, Laura Brueckner, Federico Comoglio, Tom van Schaik, Ludo Pagie

Cell, 2019

"This citation refers to the dataset used for evaluating the model's performance on TRIP-seq predictions, demonstrating that the context-aware model improves accuracy."

Referenced at: 22:50

Effect of genomic and cellular environments on gene expression noise

Clarice K Y Hong, Avinash Ramu, Siqi Zhao, Barak A Cohen

bioRxiv, 2022

"This citation refers to a more recent dataset used to further validate that adding genomic context information improves the model's TRIP-seq prediction capabilities."

Referenced at: 23:34

Caduceus: Bi-directional equivariant long-range DNA sequence modeling

Yair Schiff, Chia-Hsiang Kao, Aaron Gokaslan, Tri Dao, Albert Gu, Volodymyr Kuleshov

ICML, 2024

"The speaker uses Caduceus as an example of a standard, unconditioned masked DNA language model to contrast its learned features with those of their functionally-informed Nona model."

Referenced at: 29:40

Direct observation of the neural computations underlying a single decision

Natalie A Steinemann, Gabriel M Stine, Eric M Trautmann, Ariel Zylberberg, Daniel M Wolpert, Michael N Shadlen

bioRxiv, 2022

"This paper is cited as evidence for the sequence preference of the Tn5 enzyme used in ATAC-seq, a key concept for the speaker's analysis of genotype prediction from ATAC-seq data."

Referenced at: 41:25

ChromBPNet: bias factorized, base-resolution deep learning models of chromatin accessibility reveal cis-regulatory sequence syntax, transcription factor footprints and regulatory variants

Anusri Pampari, A Shcherbina, Evgeny Z Kvon, Michael Kosicki, Surag Nair, Soumya Kundu

bioRxiv, 2025

"This paper is cited as further evidence for the sequence bias of the Tn5 enzyme, which is foundational to the speaker's work on linking ATAC-seq fragment files back to individual genotypes."

Referenced at: 41:25