no code implementations • 9 Nov 2023 • Farhan Damani, David H Brookes, Theodore Sternlieb, Cameron Webster, Stephen Malina, Rishi Jajoo, Kathy Lin, Sam Sinai
A common scenario involves using a fixed training set to train models, with the goal of designing new samples that outperform those present in the training data.
no code implementations • 4 May 2023 • David H. Brookes, Jakub Otwinowski, Sam Sinai
Here we demonstrate that minimizing contrastive loss functions, such as the Bradley-Terry loss, is a simple and flexible technique for extracting the sparse latent function implied by global epistasis.
no code implementations • 18 Nov 2022 • Lauren Berk Wheelock, Stephen Malina, Jeffrey Gerold, Sam Sinai
The ability to design and optimize biological sequences with specific functionalities would unlock enormous value in technology and healthcare.
1 code implementation • 5 Oct 2020 • Sam Sinai, Richard Wang, Alexander Whatley, Stewart Slocum, Elina Locane, Eric D. Kelsic
In this work, we implement an open-source Fitness Landscape EXploration Sandbox (FLEXS: github. com/samsinai/FLEXS) environment to test and evaluate these algorithms based on their optimality, consistency, and robustness.
no code implementations • 4 Oct 2020 • Sam Sinai, Eric D Kelsic
This primer can serve as a starting point for researchers from different domains that are interested in the problem of searching a sequence space with a model, but are perhaps unaware of approaches that originate outside their field.
2 code implementations • 9 Dec 2017 • Sam Sinai, Eric Kelsic, George M. Church, Martin A. Nowak
Here we present an embedding of natural protein sequences using a Variational Auto-Encoder and use it to predict how mutations affect protein function.
no code implementations • 2 Dec 2016 • Sam Sinai, Jason Olejarz, Iulia A. Neagu, Martin A. Nowak
Compartments are ubiquitous throughout biology, yet their importance stretches back to the origin of cells.