Results 91 to 100 of about 6,104,936 (275)

An epithelial GPR35 isoform supports tumor‐associated transcriptional and metabolic phenotypes

FEBS Letters, EarlyView.
GPR35 generates two functionally distinct isoforms with previously unresolved roles. GPR35‐short mediates immune‐cell chemotaxis, while GPR35‐long is enriched in colorectal cancer epithelium, where it supports increased metabolism, proliferation, and tumor‐associated transcriptional programs.
Jørgen D. Rønneberg, Martine Hjeltnes, Josephine Krieger, Joshua E. Elias, Maria Stensland, Kristian Holm, Xiaojun Jiang, Chuki Khangsar, Tuula A. Nyman, Arthur Kaser, Johannes R. Hov, Tom H. Karlsen, Nicole C. Kaneider, Frode L. Jahnsen, Georg Schneditz   +14 more
wiley   +1 more source

Can Large Language Models Empower Molecular Property Prediction? [PDF]

, 2023
Molecular property prediction has gained significant attention due to its transformative potential in multiple scientific disciplines. Conventionally, a molecule graph can be represented either as a graph-structured data or a SMILES text.
Liang, Hong, Qian, Chen, Tang, Huayi, Yang, Zhirui, Liu, Yong   +4 more
core   +1 more source

Triple Generative Self-Supervised Learning Method for Molecular Property Prediction

Molecular property prediction is an important task in drug discovery, and with help of self-supervised learning methods, the performance of molecular property prediction could be improved by utilizing large-scale unlabeled dataset.
Shourun Pan, Lei Xu, Leiming Xia, Zhen Li   +3 more
core   +1 more source

Structure‐forward targeting of claudins with synthetic binders

FEBS Letters, EarlyView.
Claudins form the paracellular barriers between epithelial and endothelial tissues at tight junctions and are targets for molecular binders with the goal of modulating barrier permeability. Claudin‐binding molecules are relevant in drug delivery or in altering claudin interactions with disease‐causing proteins.
Alex J. Vecchio
wiley   +1 more source

Peripheral lysosomes recruit PLEKHG3 to focal adhesions and restrain protrusion dynamics

FEBS Letters, EarlyView.
Proximity‐dependent labeling at the LAMTOR complex revealed the Rho GEF PLEKHG3 as a lysosome‐proximal protein directing the study toward the influence of lysosome positioning on actin dynamics and cell motility. We show that PLEKHG3 colocalizes with lysosomes at focal adhesion sites and observe that forced peripheral dispersion of lysosomes hinders ...
Rainer Ettelt, Ana‐Maria Sandru, Georg Vucak, Sebastian Didusch, Biljana Riemelmoser, Karin Ehrenreiter, Markus Hartl, Lukas A. Huber, Manuela Baccarini   +8 more
wiley   +1 more source

Knowledge-aware contrastive heterogeneous molecular graph learning.

PLoS Computational Biology
Molecular representation learning is pivotal in predicting molecular properties and advancing drug design. Traditional methodologies, which predominantly rely on homogeneous graph encoding, are limited by their inability to integrate external knowledge ...
Mukun Chen, Jia Wu, Shirui Pan, Fu Lin, Bo Du, Xiuwen Gong, Wenbin Hu   +6 more
doaj   +1 more source

Pairwise learning for molecular property prediction and optimization

Frontiers in Drug Discovery
Pairwise learning is an emerging paradigm in cheminformatics that trains machine-learning models on pairs of molecules and their property differences rather than on individual compounds and absolute values.
Zachary Fralish, Zachary Fralish, Daniel Reker, Daniel Reker   +3 more
doaj   +1 more source

Engineering peptides into antibodies—opportunities and strategies for therapeutic innovation

FEBS Letters, EarlyView.
Peptides and antibodies occupy complementary therapeutic niches. Peptides recognize difficult targets in a compact format, while antibodies add specificity, long half‐life, and effector functions. This review examines strategies that merge both modalities—peptide grafting into loops, terminal and Fc fusions, and bioconjugation—highlighting how ...
Jinling Wang, Ruslana Romaniuk, Hristo L. Svilenov   +2 more
wiley   +1 more source

DCPM-ADMET: fusion of dual-component pre-trained model and molecular fingerprints to enhance drug ADMET properties prediction

Journal of Cheminformatics
The absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties of drugs are critical to their efficacy and safety in clinical trials; however, traditional machine learning methods have limited generalization ability in ADMET ...
Leilei Zhang, Yuchen Zeng, Yue Qi, Kaili Jiang, Xiaofei Zhou, Lu Liang, Jianping Lin   +6 more
doaj   +1 more source

A property–agnostic framework for scalable molecular inverse design via quantum annealing [PDF]

Digital Discovery
Technologies for designing molecules with desired properties have the potential to drive innovation across a wide range of fields. Molecular inverse design typically involves three key tasks: chemical latent space representation, property prediction, and
Yuki Deguchi, Masato Taki
doaj   +1 more source