Alan Nawzad Amin

I'm Alan Nawzad Amin! I work on statistical models built on modern, large databases of biological sequences. My projects either build models that can leverage these datasets in new ways, or seek to understand why these models work.

Bio: I am a faculty fellow at the Courant Institute at New York University, working with the Wilson lab. In the summer of 2023, I was a postdoc at Jura bio. I completed my PhD in the Harvard Systems Biology program supervised by Debora Marks in 2023. I graduated with a BS in Biochemistry and Mathematics from the University of Toronto in 2019. A link to my CV. A link to a research statement (2023).

Contact: Please feel free to reach out to me at alanamin@nyu.edu! On Twitter @AlanNawzadAmin.

Selected works

* denotes equal contribution

Building scalable, flexible models of large sequence data

Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequences. paper, code
    Amin A N, Gruver N*, Kuang Y*, Li Y*, Elliott H, McCarter C, Raghu A, Greenside P, Wilson A G. Preprint, 2024. spotlight and outstanding poster award at AIDrugX workshop at Neurips 2024

Manufacturing-Aware Generative Model Architectures Enable Biological Sequence Design and Synthesis at Petascale. paper, code
    Weinstein E N*, Gollub M G*, Slabodkin A*, Gardner C L, Dobbs K, Cui X-B, Amin A N, Church G M, Wood E B. Preprint, 2024.

Scalable and Flexible Causal Discovery with an Efficient Test for Adjacency. paper, code
    Amin A N, Wilson A G. ICML, 2024

Kernels with Guaranteed Flexibility for Reliable Machine Learning on Biological Sequences. paper, code
    Amin A N, Weinstein E N*, Marks D S*. arXiv, 2023. Student Research Award at 2023 New England Statistics Symposium

A generative nonparametric Bayesian model for whole genomes. paper, code
    Amin A N*, Weinstein E N*, Marks D S. NeurIPS, 2021.

Understanding and evaluating models of sequence data

Kernel-Based Evaluation of Conditional Biological Sequence Models. paper
    Glaser P, Paul S, Hummer A M, Deane C M, Marks D S, Amin A N. ICML, 2024.

A Kernelized Stein Discrepancy for Biological Sequences. paper, code
    Amin A N, Weinstein E N*, Marks D S*. ICML, 2023.

Non-identifiability and the blessings of misspecification in models of molecular fitness and phylogeny. paper
    Weinstein E N*, Amin A N*, Frazer J, Marks D S. NeurIPS, 2022. Oral

Teaching

CSCI-102: Data structures Fall 2024. Reach out if you’re an undergrad at NYU and would like to be a grader this fall!

CSCI-102: Data structures Spring 2024. Website