7 papers · ranked by Valyu relevance
Giansalvo Cirrincione, Elisa Ficarra, Marta Lovino
Protein language models (pLMs) such as ESM-2 and ProtBERT rely on pretraining corpora of tens to hundreds of millions of sequences and on encoder architectures whose depth, width and number of attention heads are chosen by the practitioner and never revisited during training. The entry cost of state-of-the-art pLMs is…
Amélie Barozet, Vincent Cabeli, Jean Ogier du Terrail, Alexey Rukhovich + 6 more
The development of climate-resilient crops would be greatly accelerated by models able to reason directly over plant genomic sequences and to pinpoint trait-associated regions or loci. Anticipating the impact of DNA base changes (variants) remains challenging, and understanding regulatory mechanisms is still an active…
Xiaoqian Dong, Nandan Chen, Cuilan Dong, Xingxing Wang + 5 more
Internal consistency was estimated using Cronbach’s α coefficient, while reproducibility was examined through split-half reliability and test-retest reliability . Following recent methodological recommendations, recognizing the limitations of Cronbach’s α (e.g., tau-equivalence assumption) , we further evaluated the…
Jackie Rao, Muntadher Jihad, Giulia Biffi, Paul D.W. Kirk
Identifying cell types from single-cell RNA sequencing (scRNA-seq) data typically requires several separate and often uninterpretable steps: dimensionality reduction, batch-correction, clustering, marker-gene identification and the discovery of finer-grained structure. Here we introduce scFLAME (single-cell Factor…
Shengjie Wang, Zongyong Hu, Yunlong Bie, Qijin Yin + 2 more
Single-cell foundation models have shown strong potential for learning transferable representations from large-scale transcriptomic data. However, many existing approaches rely on reconstructing masked gene expression values, creating a potential mismatch between observation-space reconstruction and the goal of…
Linsui Deng, Kejun He, Xianyang Zhang
Mendelian randomization (MR) has been widely used to infer causal relationships between exposures and outcomes in epidemiological studies. However, classical MR assumptions can be violated when genetic variants are associated with outcomes through pathways other than the exposure, leading to uncorrelated and/or…
Brett Kiyota, Chaehyeon Lee, Haoyang Yao, Nozomu Yachie
The rapid expansion of single-cell genomic datasets has led to the compilation of biological resources comprising hundreds of millions of cells across tissues, developmental stages, and disease states. This has underscored the need for scalable and interpretable data representations that preserve the complex…