BioLLM: A standardized framework for integrating and benchmarking single-cell foundation models [0.03%]
BioLLM：单细胞基础模型的集成和基准测试的标准框架
Ping Qiu,Qianqian Chen,Hua Qin et al.
Ping Qiu et al.
The application and evaluation of single-cell foundation models (scFMs) present significant challenges due to heterogeneous architectures and coding standards. To address this, we introduce BioLLM (biological large language model), a unifie...
Focused learning by antibody language models using preferential masking of non-templated regions [0.03%]
基于非模板区域优先屏蔽的抗体语言模型聚焦学习方法
Karenna Ng,Bryan Briney
Karenna Ng
Existing antibody language models (AbLMs) are pre-trained using a masked language modeling (MLM) objective with uniform masking probabilities. While these models excel at predicting germline residues, they often struggle with mutated and no...
Frederik F Flöther,Daniel Blankenberg,Maria Demidik et al.
Frederik F Flöther et al.
Biomarkers play a central role in medicine's gradual progress toward proactive, personalized precision diagnostics and interventions. However, finding biomarkers that provide very early indicators of a change in health status, for example, ...
MediSim: Multi-granular simulation for enriching longitudinal, multi-modal electronic health records [0.03%]
MediSim：纵向多模态电子健康记录的多重仿真增强方法
Brandon Theodorou,Cao Xiao,Lucas Glass et al.
Brandon Theodorou et al.
We introduce MediSim, a multi-modal generative model for simulating and augmenting electronic health records across multiple modalities, including structured codes, clinical notes, and medical imaging. MediSim employs a multi-granular, auto...
Beatrice Savoldi,Jasmijn Bastings,Luisa Bentivogli et al.
Beatrice Savoldi et al.
Gender bias in machine translation (MT) has been studied for over a decade, a time marked by societal, linguistic, and technological shifts. With the early optimism for a quick solution in mind, we review over 100 studies on the topic and u...
Tokenized and continuous embedding compressions of protein sequence and structure [0.03%]
蛋白质序列和结构的token化及连续嵌入压缩
Amy X Lu,Wilson Yan,Kevin K Yang et al.
Amy X Lu et al.
Existing protein machine learning representations typically model either the sequence or structure distribution, with the other modality implicit. Here, we characterize an embedding of the joint distribution of protein sequence and structur...
Cluster-based human-in-the-loop strategy for improving machine learning-based circulating tumor cell detection in liquid biopsy [0.03%]
基于集群的人机交互策略，可提升机器学习技术在液体活检中检测循环肿瘤细胞的效果
Hümeyra Husseini-Wüsthoff,Sabine Riethdorf,Andreas Schneeweiss et al.
Hümeyra Husseini-Wüsthoff et al.
In liquid biopsy, detecting and differentiating circulating tumor cells (CTCs) and non-CTCs in metastatic cancer patients' blood samples remains challenging. The current gold standard often involves tedious manual examination of extensive i...
Lauren Higa,Youping Deng
Lauren Higa
Women have been instrumental in shaping data science from its earliest days. This opinion highlights both the achievements and the ongoing challenges faced by women in the field, emphasizing that a wide range of perspectives and backgrounds...
Discovering the nuclear localization signal universe through a deep learning model with interpretable attention units [0.03%]
基于具有可解释性注意单元的深度学习模型发现核定位信号宇宙
Yi-Fan Li,Xiaoyong Pan,Hong-Bin Shen
Yi-Fan Li
We describe NLSExplorer, an interpretable approach for nuclear localization signal (NLS) prediction. By utilizing the extracted information on nuclear-specific sites from the protein language model to assist in NLS detection, NLSExplorer ac...
Banghao Chen,Zhaofeng Zhang,Nicolas Langrené et al.
Banghao Chen et al.
This review explores the role of prompt engineering in unleashing the capabilities of large language models (LLMs). Prompt engineering is the process of structuring inputs, and it has emerged as a crucial technique for maximizing the utilit...