Výsledky vyhledávání - "Marinka, Zitnik"

Akademický článek

Evaluating explainability for graph neural networks

Autor: Chirag Agarwal, Owen Queen, Himabindu Lakkaraju, Marinka Zitnik

Publikováno v: Scientific Data, Vol 10, Iss 1, Pp 1-18 (2023)

Abstract As explanations are increasingly used to understand the behavior of graph neural networks (GNNs), evaluating the quality and reliability of GNN explanations is crucial. However, assessing the quality of GNN explanations is challenging as exi

Externí odkaz: https://doaj.org/article/993af0bc7ead4318aa8097ae16a3be21

Zobrazit plný text záznamu

Akademický článek

Building a knowledge graph to enable precision medicine

Autor: Payal Chandak, Kexin Huang, Marinka Zitnik

Publikováno v: Scientific Data, Vol 10, Iss 1, Pp 1-16 (2023)

Measurement(s) knowledge graph • Relation Code • textual entity Technology Type(s) machine learning • computational modeling technique

Externí odkaz: https://doaj.org/article/a173e11db88c48ca96c21a86ff2deee1

Zobrazit plný text záznamu

Akademický článek

Enhancing convolutional neural network predictions of electrocardiograms with left ventricular dysfunction using a novel sub-waveform representation

Autor: Hossein Honarvar, PhD, Chirag Agarwal, PhD, Sulaiman Somani, MD, Akhil Vaid, MD, Joshua Lampert, MD, Tingyi Wanyan, PhD, Vivek Y. Reddy, MD, Girish N. Nadkarni, MD, Riccardo Miotto, PhD, Marinka Zitnik, PhD, Fei Wang, PhD, Benjamin S. Glicksberg, PhD

Publikováno v: Cardiovascular Digital Health Journal, Vol 3, Iss 5, Pp 220-231 (2022)

Background: Electrocardiogram (ECG) deep learning (DL) has promise to improve the outcomes of patients with cardiovascular abnormalities. In ECG DL, researchers often use convolutional neural networks (CNNs) and traditionally use the full duration of

Externí odkaz: https://doaj.org/article/7106b3c922994d84a741ddc460870603

Zobrazit plný text záznamu

Akademický článek

Comparison of BERT implementations for natural language processing of narrative medical documents

Autor: Alexander Turchin, Stanislav Masharsky, Marinka Zitnik

Publikováno v: Informatics in Medicine Unlocked, Vol 36, Iss , Pp 101139- (2023)

Background and objectives: Bidirectional Encoder Representations from Transformers (BERT) word embedding models have been successfully used for many natural language processing (NLP) tasks, including medical named entity recognition. However, there a

Externí odkaz: https://doaj.org/article/beb89fff45354be983345db4ca5c25f0

Zobrazit plný text záznamu

Akademický článek

Co-evolution based machine-learning for predicting functional interactions between human genes

Autor: Doron Stupp, Elad Sharon, Idit Bloch, Marinka Zitnik, Or Zuk, Yuval Tabach

Publikováno v: Nature Communications, Vol 12, Iss 1, Pp 1-14 (2021)

With the rise in number of eukaryotic species being fully sequenced, large scale phylogenetic profiling can give insights on gene function, Here, the authors describe a machine-learning approach that integrates co-evolution across eukaryotic clades t

Externí odkaz: https://doaj.org/article/59ff6a7933cf40ff80afbe2c5b1265df

Zobrazit plný text záznamu

Akademický článek

Leveraging the Cell Ontology to classify unseen cell types

Autor: Sheng Wang, Angela Oliveira Pisco, Aaron McGeever, Maria Brbic, Marinka Zitnik, Spyros Darmanis, Jure Leskovec, Jim Karkanias, Russ B. Altman

Publikováno v: Nature Communications, Vol 12, Iss 1, Pp 1-11 (2021)

Classifying cells into unseen cell types remains challenging in scRNA-seq analysis. Here we show that Cell Ontology enables an accurate classification of unseen cell types through considering the cell type relationships in the Cell Ontology graph.

Externí odkaz: https://doaj.org/article/1d09fe5933a6428fb050655243e85aa0

Zobrazit plný text záznamu

Akademický článek

Identification of potent inhibitors of SARS-CoV-2 infection by combined pharmacological evaluation and cellular network prioritization

Publikováno v: iScience, Vol 25, Iss 9, Pp 104925- (2022)

Summary: Pharmacologically active compounds with known biological targets were evaluated for inhibition of SARS-CoV-2 infection in cell and tissue models to help identify potent classes of active small molecules and to better understand host-virus in

Externí odkaz: https://doaj.org/article/068bfd3f57e5455390b1fab422a6998a

Zobrazit plný text záznamu

Akademický článek

Identification of disease treatment mechanisms through the multiscale interactome

Autor: Camilo Ruiz, Marinka Zitnik, Jure Leskovec

Publikováno v: Nature Communications, Vol 12, Iss 1, Pp 1-15 (2021)

Most diseases disrupt multiple proteins, and drugs treat such diseases by restoring the functions of the disrupted proteins; how drugs restore these functions, however, is often unknown. Here, the authors develop the multiscale interactome, a powerfu

Externí odkaz: https://doaj.org/article/28f8ca7de94d4f08a6693d3cd37dc25a

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání