AIMC Journal:
bioRxiv

Showing 161 to 170 of 4935 articles

DAPHNE: A global database of pest herbivores and their natural enemies

bioRxiv
Anticipating and managing the impact of herbivorous pests requires evidence-based knowledge about the interactions between pests and their natural enemies. Knowledge of species' ecologies and biological interactions are typically disseminated in unst...

Tri-Modality Representation Learning for Molecular Property Prediction

bioRxiv
Accurate molecular property prediction requires effective molecular representations that can describe a molecule from multiple complementary perspectives. Existing deep learning approaches typically use SMILES strings, two-dimensional molecular graph...

PanVasc Research for AI assisted evidence analysis in panvascular intervention

bioRxiv
Panvascular intervention research requires evidence workflows that preserve source identity, outcome definitions and observation windows. We developed PanVasc Research, an executable research framework, and evaluated a fixed local Qwen3-4B model usin...

A Thermodynamic Theory of Axon Guidance: Navigation Through High-Entropy Signaling States

bioRxiv
Precise neural circuit formation requires growth cones to integrate multiple, sometimes competing, guidance signals into persistent yet adaptable movement. Here, we propose a theoretical framework that recasts axon guidance as a thermodynamically reg...

A plasma metabolomics workflow for breast cancer detection using quantitative GC/MS and machine learning

bioRxiv
Blood-based metabolomic profiling has been widely investigated for breast cancer (BC) detection; however, clinical implementation remains limited due to variability in sample handling, analytical reproducibility, and overfitting during statistical an...

Analyzing Genomic Foundation Models for Viral Sequence Identification

bioRxiv
Rapid and accurate identification of viral sequences underpins clinical diagnostics, epidemiological surveillance, and the safety testing of biological products, yet the established alignment-based methods such as BLAST are inherently closed-set, wit...

Empirical Validation of Composite Fractional Noise Models in Nanopore Signals

bioRxiv
Nanopore sensors have transformed single-molecule analysis, enabling real-time detection of biomolecules with unprecedented resolution. Understanding and modelling noise in nanopore sensing is essential to unlocking their full analytical potential. A...

UniWave-2: A Hybrid Model for Nucleic Acid Waveform Feature Extraction Enhanced by Fourier and Wavelet Transforms

bioRxiv
Motivation: Traditional methods primarily rely on statistical features such as k-mers and GC content, making it difficult to capture complex internal relationships within sequences. Deep learning models typically rely on discrete encodings, leading t...

Benchmarking single-cell foundation models for aging biology

bioRxiv
Single cell foundation models (scFMs) provide representations of cellular states, but their utility across biological questions in aging research remains unclear. We established a benchmark of cellular representations for aging research, evaluating t...

Targeted finetuning enables co-folding models to learn ligand-induced protein conformational states

bioRxiv
Advances in protein structure prediction have enabled all-atom protein-ligand co-folding models that predict bound conformations directly from sequence and small-molecule structure. However, these models often fail to generalize to novel binding site...