Skip To Main Content
Dewei Hu on Muck Rack

Dewei Hu

As seen in: Nature, BioRxiv, medRxiv
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work. Claim your profile
Back to Dewei Hu’s profile

Articles by Dewei Hu

Contrastive alignment transfers proteomic predictive signals to metabolomics data

|
By Dewei Hu, Chiara Rohrer, Marc Pielies Avelli
| medRxiv
S.R. is the founder and owner of BioAI, has performed consulting for Sidera Bio ApS and QuantumCell ApS, and is a co-founder and shareholder of Phenora Health ApS. L.J.J. is an employee of ZS Associates. The authors declare no other competing financial interests. I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.
Open in Who Shared View Duplicates (68) Issue with article?

Molecular maps of diseases from omics data and network embeddings

|
By Dewei Hu, Anna-Lisa Schaap-Johansen, Julia Villarroel, Clara Christina Ekebjærg, Simon Rasmussen, Daniel Hansen, Rasmus Wernersson, Lars Jensen
| Nature Verified
Abstract Identifying disease-relevant proteins and pathways remains a fundamental challenge in understanding disease mechanisms and supporting therapeutic development. While omics analyses can provide valuable insights, they typically consider each gene/protein separately rather than at the level of biological systems. This can be addressed by combining the omics data with protein networks.
Open in Who Shared Issue with article?

SPACE: STRING proteins as complementary embeddings

|
By Dewei Hu, Damian Szklarczyk, Christian von Mering, Lars Jensen
| BioRxiv
Abstract Representation learning has revolutionized sequence-based prediction of protein function and subcellular localization. Protein networks are an important source of information complementary to sequences, but they have proven challenges being used in machine learning, especially in a cross-species setting. To address this, we leveraged the STRING database of protein networks and orthology relations for 1,322 eukaryotes to generate network-based cross-species protein embeddings.
Open in Who Shared Issue with article?
Show More