Rising — Salient

SPARK: Bayesian structure learning of enhancer-based gene regulatory networks from single-cell multiomics data and prior knowledge

1d · Masaki, N., Acharya, S., Malysheva, V., et al. · biorxiv

method development benchmarked top 9% noveltop 5% open

Surfaced because: benchmarked against baselines.

scTGCL: A Transformer-Based Graph Contrastive Learning Approach for Efficiently Clustering Single-Cell RNA-seq Data

1d · Khan, M. S. A., Kabir, M. H., Faisal, M. M. · biorxiv

method development code benchmarked top 1% open

Surfaced because: open code, benchmarked against baselines.

flodl-bio: First Rust data, transformers and model layer for entire deep learning on biological sequences

1d · Sablok, G., de Stefanis, F. · biorxiv

method development code benchmarked top 1% open

Surfaced because: open code, benchmarked against baselines.

A latent space thermodynamic model of cell differentiation

2d · Poursina, A., Hajhashemi, S., Saberi, A., et al. · biorxiv

method development benchmarked top 5% open

Surfaced because: benchmarked against baselines.

Mapping bioimage-analysis software adoption in microscopy

1d · Shakespeare, T., Saraiva, B. M., Cunha, I., et al. · biorxiv

method development top 3% novel

Surfaced because: matches the platform's topic region.

Coarse-graining metabolic networks via feature learning reveals cross-species growth predictors

3d · Zhu, A., Ho, P.-Y. · biorxiv

method development

Surfaced because: matches the platform's topic region.

Exhaustive white blood cell extraction and profiling across whole-slide images of blood and bone marrow smears

1d · Deutges, M., Ghete, T., Namsaraeva, A., et al. · medrxiv

method development

Surfaced because: matches the platform's topic region.

Cytoplasmic genomes change allelic expression bias in plant seeds independently of parental imprinting: evidence for cytonuclear regulatory epistasis in Arabidopsis thaliana

1d · McKeown, P. C., Motienoparvar, P., Lai, L., et al. · biorxiv

method development

Surfaced because: matches the platform's topic region.

Chromosome-scale nuclear and mitochondrial genome assemblies reveal extreme genome compartmentalization in the hazelnut pathogen Anisogramma anomala

1d · Zaccaron, A. Z., Sondreli, K. L., LeBoldus, J. M., et al. · biorxiv

method development

Surfaced because: matches the platform's topic region.

Predicting Protein-Protein Interactions Using Vectorized Sequence Descriptors and Machine Learning Classifiers

1d · Bhat, R., Kumari, V., Kaira, V. S., et al. · biorxiv

method development benchmarked top 5% open

Surfaced because: benchmarked against baselines.

Overcoming segmentation bottlenecks in brain tissue for spatial proteomic inference at population scale

3d · You, L., Durbin, J. L., Meng, G., et al. · biorxiv

method development benchmarked top 5% open

Surfaced because: benchmarked against baselines.

Interpreting Short Tandem Repeat Variations with Plant Genomic Foundation Models in Olive

1d · Xia, F., Pakdel, M. H., Mazinani, M. H., et al. · biorxiv

method development

Surfaced because: matches the platform's topic region.

RFind-sc maps single cells onto biological axes defined by external gene signatures

1d · Murano, T., Miyakawa, T. · biorxiv

method development

Surfaced because: matches the platform's topic region.

Physics-driven self-supervised learning for quantitative high-fidelity structured illumination microscopy

3d · Tang, Y., Luo, Z., Zhu, X., et al. · biorxiv

method development

Surfaced because: matches the platform's topic region.

Characterization of heterogeneous bioinformatics training needs in the AI era

1d · van Geest, G., Di Cola, V., Zahn, M., et al. · biorxiv

method development

Surfaced because: matches the platform's topic region.

Haplotype-based fine-mapping of variant associations for complex traits

3d · Massarat, A. R., Lamkin, M., Mirmira, T., et al. · biorxiv

method development

Surfaced because: matches the platform's topic region.

Astrolabe: Programmable all-atom biomolecular design through cross-context coordination and structural intervention

4d · Zeng, Z., Xu, C. · biorxiv

method development benchmarked top 5% open

Surfaced because: benchmarked against baselines.

spaTransfer: transfer learning for single-cell and spatial transcriptomics data using non-negative matrix factorization

3d · Fang, C., Montgomery, K. D., Maguire, S. E., et al. · biorxiv

method development

Surfaced because: matches the platform's topic region.

The Sensitivity of 13C-Metabolic Flux Analysis to Biomass Composition Underscores the Need for Accurate Biomass Formulation in Escherichia coli

4d · Cai, Y., Antoniewicz, M. R. · biorxiv

method development

Surfaced because: matches the platform's topic region.

Prediction transfer does not imply reliability transfer in single-cell foundation models

1d · Park, H. J., Sriram, A., Luo, T., et al. · biorxiv

method development

Surfaced because: matches the platform's topic region.

ALHENA, an H&E encoder distilled from transcriptomic foundation models for multi-scale slide analysis

2d · Giraud-Sauveur, F., Blampey, Q., Marza, P., et al. · biorxiv

method development

Surfaced because: matches the platform's topic region.

A genetically informed atlas of transcriptomic programs from massive human RNA-seq compendia

4d · Subirana-Granes, M., Zhang, H., Nandi, S., et al. · biorxiv

method development top 1% novel

Surfaced because: matches the platform's topic region.

Building computational benchmarks: an Omnibenchmark reimplementation of a single-cell preprocessing pipeline evaluation

1d · Choudhury, A., Kitak, T., Carrillo, B., et al. · biorxiv

method development benchmarked top 5% open

Surfaced because: benchmarked against baselines.

A Vast Navigable Protein Sequence Subspace

5d · Sinai, S., Gane, A., Jain, N., et al. · biorxiv

method development top 1% novel

Surfaced because: matches the platform's topic region.

Reference-free isoform discovery links unannotated RNA processing to disease risk

4d · Buen Abad Najar, C. F., Xie, D., Feng, R., et al. · biorxiv

method development top 10% novel

Surfaced because: matches the platform's topic region.

Metabolic blueprints of monocultures enable prediction and design of synthetic microbial consortia

4d · Bald, S., Nelson, R., Zhang, J., et al. · biorxiv

method development

Surfaced because: matches the platform's topic region.

biHash: bisulfite-aware recursive nucleotide hashing

3d · wong, j., Birol, I. · biorxiv

method development

Surfaced because: matches the platform's topic region.

Centered cross-context perturbation transfer on the public 2025 Virtual Cell Challenge benchmark

2d · Luan, H., Chen, L., Yu, G., et al. · biorxiv

method development benchmarked top 5% open

Surfaced because: benchmarked against baselines.

Evaluating the added value of sequence models in noncoding RNA assays: a baseline-aware framework

2d · Guo, R., Shan, W., Liu, R., et al. · biorxiv

method development benchmarked top 5% open

Surfaced because: benchmarked against baselines.

RiboDFM: Robust RNA sequence design using backbone-conditioned discrete flow matching

4d · Liu, X., An, X., Peng, Z., et al. · biorxiv

method development benchmarked top 5% open

Surfaced because: benchmarked against baselines.