Company Filing History:
Years Active: 2021-2023
Title: Natalie Telis: Innovator in Genetic Phenotype Prediction
Introduction
Natalie Telis is a prominent inventor based in Mountain View, CA, known for her contributions to the field of genetic research and phenotype prediction. With a total of 3 patents, she has made significant strides in utilizing machine learning and genetic data to enhance our understanding of individual traits.
Latest Patents
One of her latest patents is titled "Estimation of phenotypes using DNA, pedigree, and historical data." This patent discloses techniques for predicting an individual's traits by accessing both DNA and non-DNA features to generate a feature vector. This vector is then inputted into a machine learning model that predicts the trait based on inheritance and community predictions. Additionally, it identifies enriched record collections within a genetic community by comparing community counts and background counts.
Another notable patent is "Prediction of phenotypes using recommender systems." In this innovation, a computing server employs recommender systems to predict phenotypes based on survey responses, environmental factors, and genetic data. The server constructs a matrix of phenotype values and utilizes collaborative filtering to predict undetermined phenotypes of target individuals, enhancing the accuracy of genetic predictions.
Career Highlights
Natalie Telis is currently employed at Ancestry.com DNA, LLC, where she applies her expertise in genetics and machine learning. Her work focuses on developing innovative solutions that leverage genetic data to provide insights into individual traits and ancestry.
Collaborations
Some of her notable coworkers include Ahna R Girshick and Julie M Granka, who contribute to the collaborative environment at Ancestry.com DNA, LLC.
Conclusion
Natalie Telis stands out as an influential inventor in the realm of genetic research, with her patents paving the way for advancements in phenotype prediction. Her work continues to impact the field significantly, showcasing the potential of combining genetics with machine learning.