Kdaj in kje: 20. december 2018 ob 13.30 v FAMNIT-VP1
Presenter: Marinka žITNIK
Marinka žitnik je podoktorska raziskovalka na področju računalništva na Stanford Univerzi, kjer sodeluje z Juretom Leskovcem in z biomedicinskimi raziskovalnimi oddelki po vsem svetu. Je tudi podoktorska raziskovalka Chan Zuckerberg Biohub.
Njene raziskave se osredotočajo na strojno učenje v biomedicinskih znanostih, s poudarkom na velikih mrešah interakcij med biomedicinskimi subjekti – npr. proteini, zdravili, boleznimi in bolniki. Te mreše izkorišča za raziskovanje milijonov odnosov med milijoni subjektov in razvija nove metode kombiniranja strojnega učenja s statističnimi metodami in raziskavami omrešij.
S svojimi metodami odgovarja na pereča znanstvena vprašanja, na primer, kako Darwinova evolucija spreminja molekularne mreše in kako podatkovni algoritmi pospešujejo znanstvena odkritja; svoje uporablja metode za reševanje problemov, kot na primer, katera zdravila in kombinacije zdravil so varne za bolnike, katere molekule bodo zdravile katere bolezni, kako se lahko novorojenčke prenaša med bolnišnicami in kako ti prenosi vplivajo nanje.
Title: Deep Learning for Network Medicine
Abstract:
Networks pervade medical research and practice. The primary challenge is how to learn on biomedical networks that involve rich interactions, spanning from the molecular scale all the way to the societal scale encompassing all human interactions. However, prevailing deep learning algorithms are designed for data with a regular, grid-like structure and cannot exploit rich interactions, the essence of biomedical networks.
In this talk, I will discuss methods that learn how to embed nodes in rich biomedical networks as points in a low-dimensional embedding space, where the geometry of this space is optimized to reflect the structure of interactions between the nodes. These embeddings methods are at the technical core of Decagon, the first approach for predicting side effects of drug combinations, not merely of individual drugs. Decagon composes a massive network describing how proteins in our bodies interact with each other and how different drugs affect these proteins. Decagon’s deep embedding method uses the network to identify patterns in how side effects arise based on how drugs target different proteins. Today, in many cases, it is unknown what side effects might arise from adding another drug to a patient’s personal pharmacy, and Decagon has the potential to lead to more effective and safer healthcare.
Seminar bo potekal v angleškem jeziku.
Vabljeni!
