arXiv AI By Ravisha Rupasinghe, Rajith Vidanaarachchi, Asela Hevapathige, Sachith Seneviratne, Sen-Lin Tang, Saman Halgamuge

Knowledge-Inclusive Adaptive Physics-Informed Neural Network for Microbial Interaction Modelling

Read the original on arXiv AI →

arXiv:2606. 07686v1 Announce Type: cross Abstract: Physics-Informed Neural Network (PINN) is a way of including knowledge in the form of equations in Machine Learning methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning
Jun 30

Friend or Foe

arXiv:2509. 00123v2 Announce Type: replace-cross Abstract: A fundamental challenge in microbial ecology is determining whether bacteria compete or cooperate in different environmental conditions.

By Oleksandr Cherednichenko, Josephine Solowiej-Wedderburn, Laura M. Carroll, Eric Libby
arXiv Machine Learning
Jul 3

Structured Gaussian Processes for Uncertainty-Aware Classification of High-Dimensional, Small-Sampled Omics Data

arXiv:2607. 02103v1 Announce Type: cross Abstract: Classifying heterogeneous omics data remains a fundamental challenge in computational biology, particularly in high-dimensional, small-sample settings where nonlinear interactions dominate and class imbalance further complicates reliable prediction of minority phenotypes.

By Yue Zhang, Nandini Amit Gadhia, Georgios Karagiannis, Michalis Smyrnakis
arXiv Machine Learning
Sep 4

Language-encoded network topology enables large language models to reason about complex networks

The paper introduces BioGlyph, a method that translates network topology into a language of structural roles such as hubs, community cores, and cross-community connectors. By encoding these roles in a universal, interpretable vocabulary, BioGlyph allows large language models to answer structural reasoning questions about networks more accurately—improving system accuracy by up to 26 percentage points compared to edge-based or numerical representations. Experiments across twenty networks in five domains show the approach is especially effective for dense, community-structured networks and reveals biologically meaningful patterns in a budding-yeast protein-interaction network.

By Ucchwas Talukder Utsha, Sakib Mostafa, James Zou, Md Tauhidul Islam