Publications

2025

  1. Engineering TEV Protease Specificity: An Exploration of Machine Learning and High-Throughput Experimentation for Protein Design
    Vikram Sundar
    Massachusetts Institute of Technology, 2025
    PhD Thesis

2024

  1. FLIGHTED: Inferring Fitness Landscapes from Noisy High-Throughput Experimental Data
    Vikram Sundar, Boqiang Tu, Lindsey Guan, and 1 more author
    bioRxiv, 2024
  2. An ultra-high-throughput method for measuring biomolecular activities
    Boqiang Tu, Vikram Sundar, and Kevin Esvelt
    bioRxiv, 2024
  3. A New Ultra-High-Throughput Assay for Measuring Protein Fitness
    Vikram Sundar, Boqiang Tu, Lindsey Guan, and 1 more author
    In ICLR Workshop: Generative and Experimental Perspectives for Biomolecular Design, 2024
    Oral presentation

2023

  1. FLIGHTED: Inferring Fitness Landscapes from Noisy High-Throughput Data
    Vikram Sundar, Boqiang Tu, Lindsey Guan, and 1 more author
    In NeurIPS Workshop: Machine Learning and Structural Biology, 2023

2022

  1. Neural Network-Derived Potts Models for Structure-Based Protein Design using Backbone Atomic Coordinates and Tertiary Motifs
    Alex Li, Mindren Lu, Israel Desta, and 3 more authors
    Protein Science, 2022

2021

  1. TERMinator: A Neural Framework for Structure-Based Protein Design using Tertiary Repeating Motifs
    Alex Li, Vikram Sundar, Gevorg Grigoryan, and 1 more author
    In NeurIPS Workshop: Machine Learning and Structural Biology, 2021

2020

  1. Attribution Methods Reveal Flaws in Fingerprint-Based Virtual Screening
    Vikram Sundar and Lucy Colwell
    In ICML Workshop: ML Interpretability for Scientific Discovery, 2020
  2. Using Single Protein/Ligand Binding Models to Predict Active Ligands for Unseen Proteins
    Vikram Sundar and Lucy Colwell
    bioRxiv, 2020
  3. The Effect of Debiasing Protein-Ligand Binding Data on Generalization
    Vikram Sundar and Lucy Colwell
    J Chem Inf Model, 2020

2019

  1. Using Single Protein/Ligand Binding Models to Predict Active Ligands for Previously Unseen Proteins
    Vikram Sundar and Lucy Colwell
    In NeurIPS Workshop: Machine Learning and the Physical Sciences, 2019
  2. Using Machine Learning to Predict Protein/Ligand Interactions
    Vikram Sundar
    University of Cambridge, 2019
    MPhil Thesis

2018

  1. Bounds on Errors in Observables Computed from Molecular Dynamics Simulations
    Vikram Sundar
    Harvard University, 2018
    Senior Thesis
  2. Reproducing Quantum Probability Distributions at the Speed of Classical Dynamics: A New Approach for Developing Force-Field Functors
    Vikram Sundar, David Gelbwaser-Klimovsky, and Alán Aspuru-Guzik
    J Phys Chem Lett, 2018