1927 in the window; the type tabs sum to fewer — some papers are unclassified.
RECON infers regions of interest from H&E images and reconstructs whole-slide molecular profiles at single-cell resolution
1d ·
Yang, X., Hao, N., Zhao, R., et al.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
Spatial Transcriptomics As Rasterized Image Tensors (STARIT) characterizes cell states with subcellular molecular heterogeneity
1d ·
Velazquez, D., Hallinan, C., An, R., et al.
· biorxiv
method development
top 10% novel
Surfaced because: matches the platform's topic region.
Data-driven spectroscopic dictionaries and detector-calibrated inference for photon-limited Raman hyperspectral imaging of living cells
1d ·
Yagi, S., Sagami, N., Eshima, I., et al.
· biorxiv
method development
top 1% novel
Surfaced because: matches the platform's topic region.
The first OpenBind release: An open experimental structure-affinity dataset and benchmark for structure-based AI
1d ·
Nelen, J., Khan, O., Adams, E., et al.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
HESTIA: Scalable Multimodal Integration of Histology and High-Resolution Spatial Transcriptomics for Robust Spatial Domain Identification
2d ·
Zhong, Z., Zhu, X., Guo, J., et al.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
A self-supervised DNA foundation model with collapse-resistant multimodal fusion
2d ·
Chen, Y.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
GNMCADS: Sampling For Protein Conformation Diversity With Gaussian Network Model Guided Condition Annealed Diffusion Sampler
1d ·
Uzum, A. S., Haliloglu, T.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
TomatoPGFM: A graph-conditioned foundation model for tomato pangenomes
1d ·
Han, J., yushan, t., Wang, J., et al.
· biorxiv
method development
Surfaced because: matches the platform's topic region.
Accurate and efficient prediction of protein conformations with ProtMonomer
2d ·
Si, Y., Zhang, S., Chen, L.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
Topologically-based parameter inference for agent-based model selection from spatiotemporal cellular data
4d ·
Wenzel, A. R., Haughey, P. M., Nguyen, K. C., et al.
· biorxiv
method development
code
benchmarked
top 10% noveltop 1% open
Surfaced because: open code, benchmarked against baselines.
Scaling recipes for single-cell RNA sequencing foundation models: when do scaling laws hold?
1d ·
Borra, F., Ciro', G., Castellini, A., et al.
· biorxiv
method development
Surfaced because: matches the platform's topic region.
Calibration-free compression brings Evo 2 to its full million-token context on a single GPU
1d ·
Patsakis, M., Tzanakakis, A., Georgakopoulos-Soares, I.
· biorxiv
method development
Surfaced because: matches the platform's topic region.
XpBrew and PanXpresso - automatic RNA-seq processing workflow and comprehensive collection of gene expression data
1d ·
Natarajan, S., Sterling, C., Choudhary, N., et al.
· biorxiv
method development
code
top 2% open
Surfaced because: open code.
PhageTransformer - scalable and accurate host assignments for bacteriophages
3d ·
Siemers, M., Lopez, J. L., Dutilh, B. E.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
nf_xpatial: A Reproducible Framework for Standardized Preprocessing and Clustering of Xenium Data
4d ·
Potter, L. A., Trull, A., Kumar, N., et al.
· biorxiv
method development
top 3% novel
Surfaced because: matches the platform's topic region.
Using sequence-to-function models to interpret archaic hominin introgression
1d ·
Comerford, M., Alvim, I., Johanson, T. M., et al.
· biorxiv
method development
Surfaced because: matches the platform's topic region.
Vipsania: Unsupervised Deep Gene Finding
3d ·
Krieg, R., Becker, F., Saenko, S., et al.
· biorxiv
method development
code
top 2% open
Surfaced because: open code.
PMPNN-DDG: an accurate machine learning-based {triangleup}{triangleup}G prediction pipeline trained on a novel interpretable feature set extracted from ProteinMPNN
6d ·
Jani, R., Ahmed, S.
· biorxiv
method development
code
benchmarked
top 1% open
Surfaced because: open code, benchmarked against baselines.
Chemi-Proteome Language Attention Network Empowers Fragment-Based Ligand Interactome and Binding Sites Discovery with Evidence
3d ·
Liao, B., He, J., zhao, M., et al.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
RegimeFormer: A Large Protein Model of Global Perturbation Regimes
3d ·
Ma, S., Chai, Y., Wu, Y., et al.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
Universal physical principles of protein structural genesis emerge in language-model representation space
2d ·
Chuanyang, L., Liu, J., Qiu, X., et al.
· biorxiv
method development
Surfaced because: matches the platform's topic region.
BatchRefiner: fast, significant improvement in batch integration of single-cell embeddings with ensemble refinement
7d ·
Schäffer, D. E., Kang, H., Aksu, E. D., et al.
· biorxiv
method development
benchmarked
top 1% noveltop 2% open
Surfaced because: benchmarked against baselines.
OmicsFM brings proteomics into the foundation model era
5d ·
Heyndrickx, S., Gabriels, R., Ramadasan, H., et al.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
SPC-Clean: A napari Plugin for Reducing Speckle and Isolated Pixel Noise in Fluorescence Microscopy Images
6d ·
Alirezazadeh, P., Kirsch, E. M., Tian, Y., et al.
· biorxiv
method development
top 2% novel
Surfaced because: matches the platform's topic region.
scDisent: regulatory-aware disentangled representation learning for multi-omic single-cell analysis
7d ·
Xi, G.
· biorxiv
method development
code
benchmarked
top 1% open
Surfaced because: open code, benchmarked against baselines.
A pretrained unified model enables cellular functional profile prediction and multi-objective virtual drug screening
5d ·
Chen, R., Huang, L., Qiao, Y., et al.
· biorxiv
method development
Surfaced because: matches the platform's topic region.
OmniScore: Universal Scoring of Diverse Biomolecular Complexes via Equivariant Geometry-Aware Discrete Representation Learning
4d ·
Bui, T.-C., Lee, J., Ko, J.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
Gene expression inference from cell-free DNA using uncertainty-aware deep learning
5d ·
Patton, R. D., McDeed, A. P., Netzley, A., et al.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
Evaluating the performance of splicing predictors on thousands of synthetic gene variants
6d ·
Bellido Molias, F., Kudla, G.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
A multimodal perturbation atlas defines the phenotypic resolution of cellular morphology.
8d ·
Liu, C., Hillsley, A., Sekhar, M., et al.
· biorxiv
method development
top 3% novel
Surfaced because: matches the platform's topic region.