442 in the window; the type tabs sum to fewer — some papers are unclassified.
HESTIA: Scalable Multimodal Integration of Histology and High-Resolution Spatial Transcriptomics for Robust Spatial Domain Identification
1d ·
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
1d ·
Chen, Y.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
Accurate and efficient prediction of protein conformations with ProtMonomer
1d ·
Si, Y., Zhang, S., Chen, L.
· 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
1d ·
Chuanyang, L., Liu, J., Qiu, X., et al.
· biorxiv
method development
Surfaced because: matches the platform's topic region.
Topologically-based parameter inference for agent-based model selection from spatiotemporal cellular data
3d ·
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.
S2F-Agent: Harnessing sequence-to-function models for verifiable genome interpretation
1d ·
Li, J., Qin, T., Li, J. G., et al.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
scPyviewer: a Python-native interactive viewer from AnnData single-cell data
1d ·
Xuan, H., Huang, Y., Bian, J., et al.
· biorxiv
method development
code
benchmarked
top 1% open
Surfaced because: open code, benchmarked against baselines.
Two evolutionary histories in one nucleus: genome remodeling and allelic regulation underlying heterosis in hybrid oil palm
1d ·
Su, X., Peng, Y., Yang, X., et al.
· biorxiv
method development
Surfaced because: matches the platform's topic region.
Vipsania: Unsupervised Deep Gene Finding
2d ·
Krieg, R., Becker, F., Saenko, S., et al.
· biorxiv
method development
code
top 2% open
Surfaced because: open code.
LRSPAT: A low-rank framework for spatial omics statistics
1d ·
Frost, H. R.
· biorxiv
method development
Surfaced because: matches the platform's topic region.
OmniSplice: detection of non-canonical splicing events from RNA-seq
1d ·
Lannes, R., Li, R. Y., Fingerhut, J. M., et al.
· biorxiv
method development
Surfaced because: matches the platform's topic region.
Chemi-Proteome Language Attention Network Empowers Fragment-Based Ligand Interactome and Binding Sites Discovery with Evidence
2d ·
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
2d ·
Ma, S., Chai, Y., Wu, Y., et al.
· 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
3d ·
Potter, L. A., Trull, A., Kumar, N., et al.
· biorxiv
method development
top 3% novel
Surfaced because: matches the platform's topic region.
PhageTransformer - scalable and accurate host assignments for bacteriophages
2d ·
Siemers, M., Lopez, J. L., Dutilh, B. E.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
FlexiTAC enables controllable PROTAC linker generation across diverse structural settings using a Bayesian flow network with posterior guidance
2d ·
Li, Y., Zhao, Y., Zhou, L., et al.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
Dynamic Hierarchical Interleaved Bloom Filter: An Updatable Index for Large-Scale Fast Sequence Search
2d ·
Seiler, E., Willemsen, M., Piro, V. C., et al.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
OmniScore: Universal Scoring of Diverse Biomolecular Complexes via Equivariant Geometry-Aware Discrete Representation Learning
3d ·
Bui, T.-C., Lee, J., Ko, J.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
PMPNN-DDG: an accurate machine learning-based {triangleup}{triangleup}G prediction pipeline trained on a novel interpretable feature set extracted from ProteinMPNN
5d ·
Jani, R., Ahmed, S.
· biorxiv
method development
code
benchmarked
top 1% open
Surfaced because: open code, benchmarked against baselines.
OmicsFM brings proteomics into the foundation model era
4d ·
Heyndrickx, S., Gabriels, R., Ramadasan, H., et al.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
A pretrained unified model enables cellular functional profile prediction and multi-objective virtual drug screening
4d ·
Chen, R., Huang, L., Qiao, Y., et al.
· biorxiv
method development
Surfaced because: matches the platform's topic region.
Gene expression inference from cell-free DNA using uncertainty-aware deep learning
4d ·
Patton, R. D., McDeed, A. P., Netzley, A., 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
5d ·
Alirezazadeh, P., Kirsch, E. M., Tian, Y., et al.
· biorxiv
method development
top 2% novel
Surfaced because: matches the platform's topic region.
Evaluating the performance of splicing predictors on thousands of synthetic gene variants
5d ·
Bellido Molias, F., Kudla, G.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
BatchRefiner: fast, significant improvement in batch integration of single-cell embeddings with ensemble refinement
6d ·
Schäffer, D. E., Kang, H., Aksu, E. D., et al.
· biorxiv
method development
benchmarked
top 1% noveltop 2% open
Surfaced because: benchmarked against baselines.
Label Noise Limits TCR-pMHC Specificity Prediction: Improved Performance Through AlphaFold3-Based Structural Modeling and Data Denoising
4d ·
Ballesteros-Cuartero, P., Lund, J., Nielsen, M.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
Quantifying the Rearrangement Complexity of Pangenomes
3d ·
Bohnenkaemper, L., Stoye, J.
· biorxiv
method development
Surfaced because: matches the platform's topic region.
scDisent: regulatory-aware disentangled representation learning for multi-omic single-cell analysis
6d ·
Xi, G.
· biorxiv
method development
code
benchmarked
top 1% open
Surfaced because: open code, benchmarked against baselines.
G2T: Tissue Reconstruction from Gene Expression via Embedding-Distance Flow Matching
4d ·
Birk, S., Theis, F. J., Lotfollahi, M.
· biorxiv
method development
benchmarked
top 2% open
Surfaced because: benchmarked against baselines.
AntiSite: Modality Dropout Enables Antibody Paratope Prediction With or Without Structure From a Single Model
5d ·
Papadopoulos, A. M., Alvarez, F., Daras, P.
· biorxiv
method development
code
benchmarked
top 1% open
Surfaced because: open code, benchmarked against baselines.