Sara Mostafavi

• Reposted by Sara Mostafavi
  
  Anshul Kundaje handle.invalid · Jun 19, 2025
  @saramostafavi.bsky.social (@Genentech) & I (@Stanford) r excited to announce co-advised postdoc positions for candidates with deep expertise in ML for bio (especially sequence to function models, causal perturbational models & single cell models). See details below. Pls RT 1/
  
  Repost Quote post

  View on BlueskyCopy Bluesky URLCopy post URLTranslate postDownload imageShow all post labels
• 
  Sara Mostafavi saramostafavi.bsky.social · Apr 16, 2025
  Some encouraging news for cross-gene generalization of allele effects in S2F models. www.biorxiv.org/content/10.1...
  

  Deep genomic models of allele-specific measurements

  Allele-specific quantification of sequencing data, such as gene expression, allows for a causal investigation of how DNA sequence variations influence cis gene regulation. Current methods for analyzin...

  biorxiv.org
  1

  Repost Quote post

  View on BlueskyCopy Bluesky URLCopy post URLTranslate postShow all post labels
• 
  Sara Mostafavi saramostafavi.bsky.social · Apr 17, 2025
  CC: @lxsasse.bsky.social @xinmingtu.bsky.social
  Repost Quote post

  View on BlueskyCopy Bluesky URLCopy post URLTranslate postShow all post labels
• 
  Sara Mostafavi saramostafavi.bsky.social · Mar 15, 2025
  Our new pre-print, investigating a few important questions when we train S2F models on different types of MPRA datasets. Congrats to Yilun and @xinmingtu.bsky.social www.biorxiv.org/content/10.1...
  

  Investigating Data Size, Sequence Diversity, and Model Complexity in MPRA-based Sequence-to-Function Prediction

  We created the MPRA Dataset Collection (MDC), a curated resource of MPRA data from 12 studies comprising over 150 million labeled DNA subsequences. These datasets include both random and natural genom...

  biorxiv.org
  Repost Quote post

  View on BlueskyCopy Bluesky URLCopy post URLTranslate postShow all post labels
• 
  Sara Mostafavi saramostafavi.bsky.social · Feb 23, 2025
  Our new paper describing a scalable approach for training sequence-to-function models on personal genomes ("personal genome training"), includes our observations on when this works and its limitations. www.biorxiv.org/content/10.1... Congrats: Anna, @xinmingtu.bsky.social , @lxsasse.bsky.social
  

  A scalable approach to investigating sequence-to-expression prediction from personal genomes

  A key promise of sequence-to-function (S2F) models is their ability to evaluate arbitrary sequence inputs, providing a robust framework for understanding genotype-phenotype relationships. However, despite strong performance across genomic loci , S2F models struggle with inter-individual variation. Training a model to make genotype-dependent predictions at a single locus-an approach we call personal genome training-offers a potential solution. We introduce SAGE-net, a scalable framework and software package for training and evaluating S2F models using personal genomes. Leveraging its scalability, we conduct extensive experiments on model and training hyperparameters, demonstrating that training on personal genomes improves predictions for held-out individuals. However, the model achieves this by identifying predictive variants rather than learning a cis-regulatory grammar that generalizes across loci. This failure to generalize persists across a range of hyperparameter settings. These findings highlight the need for further exploration to unlock the full potential of S2F models in decoding the regulatory grammar of personal genomes. Scalable software and infrastructure development will be critical to this progress. ### Competing Interest Statement The authors have declared no competing interest.

  biorxiv.org
  Repost Quote post

  View on BlueskyCopy Bluesky URLCopy post URLTranslate postShow all post labels