Selected Publications
2025
Polygraph: a software framework for the systematic assessment of synthetic regulatory DNA elements. Avantika Lal, Laura Gunsalus, Anay Gupta, Tommaso Biancalani, and Gokcen Eraslan. Genome Biology 26, no. 1 (2025): 114. Read Paper
gReLU: A comprehensive framework for DNA sequence modeling and design. Avantika Lal, Laura Gunsalus, Surag Nair, Tommaso Biancalani, and Gokcen Eraslan. Nature Methods (2025): 1-5. Read Paper
Fine-tuning discrete diffusion models via reward optimization with applications to DNA and protein design. Chenyu Wang, Masatoshi Uehara, Yichun He, Amy Wang, Avantika Lal, Tommi Jaakkola, Sergey Levine, Aviv Regev, Hanchen, and Tommaso Biancalani. The Thirteenth International Conference on Learning Representations (ICLR), 2025. Read Paper
2024
Decoding sequence determinants of gene expression in diverse cellular and disease states. Avantika Lal, Alexander Karollus, Laura Gunsalus, David Garfield, Surag Nair, Alex M. Tseng, M. Grace Gordon et al. bioRxiv (2024). (Accepted at Nature Methods). Read Paper
Bridging model-based optimization and generative modeling via conservative fine-tuning of diffusion models. Masatoshi Uehara, Yulai Zhao, Ehsan Hajiramezanali, Gabriele Scalia, Gokcen Eraslan, Avantika Lal, Sergey Levine, and Tommaso Biancalani. Advances in Neural Information Processing Systems (NeurIPS) 37 (2024): 127511-127535. Read Paper
Designing realistic regulatory DNA with autoregressive language models. Avantika Lal, David Garfield, Tommaso Biancalani, and Gokcen Eraslan. Genome Research 34, no. 9 (2024): 1411-1420. Read Paper
Older
Deep learning-based enhancement of epigenomics data with AtacWorks. Avantika Lal, Zachary D. Chiang, Nikolai Yakovenko, Fabiana M. Duarte, Johnny Israeli, and Jason D. Buenrostro. Nature Communications 12, no. 1 (2021): 1507. Read Paper
Multi-omic tumor data reveal diversity of molecular mechanisms that correlate with survival. Daniele Ramazzotti, Avantika Lal, Bo Wang, Serafim Batzoglou, and Arend Sidow. Nature Communications 9, no. 1 (2018): 1-14. Read Paper
Patents
Genetic mutation detection using deep learning. Johnny Israeli, Avantika Lal, Michael Vella, Nikolai Yakovenko, and Zhen Hu. U.S. Patent 12,094,572, 2024. View Patent
Sequence variation detection using deep learning. Nikolai Yakovenko, Johnny Israeli, Avantika Lal, Michael Vella, and Zhen Hu. U.S. Patent 12,387,817, 2025. View Patent
Peer Review
I serve as a peer reviewer for several journals (e.g. Nature Methods, Nature Genetics, Nucleic Acids Research), conferences (e.g. NeurIPS, ICML, RECOMB), and academic grants.