Machine learning-based prediction of SARS-CoV-2 bioactivity: integrating IC50 regression and activity classification using multi-task neural networks [0.03%]
基于机器学习的SARS-CoV-2生物活性预测：使用多任务神经网络结合IC50回归和活性分类
Aya I Maiyza,Sohila Osama,Hanan A Hassan
Aya I Maiyza
Accurate prediction of compound bioactivity is essential for accelerating antiviral drug discovery and reducing experimental costs. Machine learning (ML) methods have shown considerable promise in modeling structure-activity relationships a...
Residual-stream geometry of single-cell foundation models carries incremental gene-regulatory signal across tissues [0.03%]
单细胞基础模型的剩余流几何结构可在组织间传递基因调控信号增量
Ihor Kendiukhov
Ihor Kendiukhov
Background: Single-cell foundation models such as scGPT and Geneformer learn rich representations of gene expression programs, but whether these representations encode gene regulatory relationships beyond expression-level...
Mol2Image: an enhanced DDI prediction framework leveraging drug molecular descriptors [0.03%]
基于药物分子描述符的增强型DDI预测框架 Mol2Image
Nourhan Helmy,Huda Amin Maghawry,Nagwa Badr
Nourhan Helmy
Drug-drug interactions (DDIs) are a critical safety issue in clinical practice, as they can lead to severe and often unpredictable adverse effects. This risk becomes significantly higher in multi-drug therapies, which are increasingly used ...
Interpretable prediction of DNA replication origins in S. cerevisiae using DNABERT and DNABERT-2 [0.03%]
基于DNABERT和DNABERT-2的模式识别酵母DNA复制起始位点及其可解释性研究
Zohreh Piroozeh,Ildem Akerman,Olga V Kalinina et al.
Zohreh Piroozeh et al.
Background: DNA replication is a biological process in which a single DNA molecule is duplicated, initiating from multiple genomic sites known as replication origins. Identifying replication origins and analyzing their un...
Bayesian brain edge-based connectivity (BBeC): a Bayesian model for brain edge-based connectivity inference [0.03%]
基于边缘的脑连接性的贝叶斯模型(BBeC)
Zijing Li,Chenhao Zeng,Shufei Ge
Zijing Li
Background: Brain connectivity analysis based on magnetic resonance imaging is crucial for understanding neurological mechanisms. However, edge-based connectivity inference faces significant challenges, particularly the c...
DB-IRES: a deep learning model based on ensemble learning for predicting internal ribosome entry sites [0.03%]
基于集成学习的深度模型预测内源性核糖体进入位点(DB-IRES)
Pengxuan Song,Mingwei Sun,Jianhua Jia
Pengxuan Song
Background: Internal ribosome entry sites (IRES) are cap-independent translation initiation elements present in specific viral and cellular mRNAs. They facilitate direct ribosome recruitment for protein synthesis, bypassi...
Multi-cohort consensus clustering identifies three distinct transcriptomic endotypes in sepsis [0.03%]
多队列共识聚类在脓毒症中识别出三种不同的转录组内型
Naixun Chi,Siyu Mu,Xin Jin et al.
Naixun Chi et al.
Background: Sepsis is a heterogeneous syndrome in which patients with the same clinical diagnosis may harbour different host immune responses. Existing transcriptomic endotyping frameworks differ in gene selection, cluste...
A deep learning architecture for combining and imputing heterogeneous metabolomics datasets [0.03%]
一种结合和填补异构代谢组数据集的深度学习架构
Sadi Celik,Baris Can,Mehmet Ali Erdogan et al.
Sadi Celik et al.
Public metabolomics databases offer a large number of datasets. Combined analysis of these data sets may better capture complex molecular mechanisms in diseases. However, most datasets include measurements for only a very small fraction of ...
PG2: algorithms and a web-based tool for effective layout and visual analysis of pangenome graphs [0.03%]
PG2：用于泛基因组图的有效布局和可视化分析的算法和网络工具
Görkem Kadir Solun,Ugur Dogrusoz,Zülal Bingöl et al.
Görkem Kadir Solun et al.
Background: The advent of cost-effective whole-genome assembly has enabled the creation of comprehensive pangenomes with resolved haplotypes across various organisms. This technological leap drives the refinement of tailo...
Prioritising search for virtual screening via preliminary interpretable low-feature likelihood-based rankings of drug-target activity measures [0.03%]
基于药靶活性测量的初步可解释低特征概率排序在虚拟筛选中的优先搜索方法
Riccardo Curcio,Toni Mancini,Enrico Tronci
Riccardo Curcio
Background: Current AI-based Virtual Screening (VS) methods seek to manage ultra-large molecular libraries. To this end, they develop increasingly efficient heuristics to rank ligands by their predicted activity against a...