Bioinformatics

Unsupervised Representation Learning of C. elegans Poses and Behavior Sequences From Microscope Video Recordings

1. Maurice Deserno
2. Katarzyna Bozek

• Curated by eLife

  eLife Assessment

  This valuable study introduces a self-supervised machine learning method to classify C. elegans postures and behaviors directly from video data, offering an alternative to the skeleton-based approaches that rely on often error-prone tracking. This novel approach holds promise for advancing ethology research. That said, the strength of evidence is currently incomplete, as key aspects - including measuring head-tail orientation, increased behavioral interpretability, and quantitative comparisons to established methods - are underdeveloped and would benefit from further validation.

Reviewed by eLife

SCellBOW: AI-Driven Tumor Risk Stratification from Single-Cell Transcriptomics Using Phenotype Algebra

1. Namrata Bhattacharya
2. Anja Rockstroh
3. Sanket Suhas Deshpande
4. Sam Koshy Thomas
5. Anunay Yadav
6. Chitrita Goswami
7. Smriti Chawla
8. Pierre Solomon
9. Cynthia Fourgeux
10. Gaurav Ahuja
11. Brett Hollier
12. Himanshu Kumar
13. Antoine Roquilly
14. Jeremie Poschmann
15. Melanie Lehman
16. Colleen C Nelson
17. Debarka Sengupta

• Curated by eLife

  eLife Assessment

  This manuscript presents an important contribution to the field of single-cell transcriptomic analysis in cancer by introducing a novel computational framework-SCellBOW-which applies embedding techniques from natural language processing to model phenotypic heterogeneity in tumors. The revised version includes new validation experiments and significant clarifications that provide convincing evidence for the method's utility. The authors have benchmarked SCellBOW across diverse datasets, including glioblastoma, breast, and metastatic prostate cancer, and have demonstrated its superior performance compared to existing state-of-the-art methods.

Reviewed by eLife

Decoding Liver Cancer Prognosis: From Multi-omics Subtypes, Prognostic Models to Single Cell Validation

1. Yanbin Wang
2. Yuqi Wu
3. Hong Zhang
4. Xinyue Liu
5. Jing Ling
6. Xiao Zhou
7. Anping Song
8. Li Sun
9. Hong Qiu
10. Xianglin Yuan
11. Hua Xiong
12. Yanmei Zou

• Curated by eLife

  eLife Assessment

  This important revised manuscript presents compelling findings by delineating two molecularly distinct liver cancer subtypes through comprehensive multi-omics integration and constructing a rigorously validated prognostic model. The authors have strengthened the analytical framework and validation across multiple datasets, including single-cell RNA sequencing. The evidence remains robust, with enhanced methodological clarity and expanded validation in both internal and independent cohorts. The revisions have improved the study's rigor and translational relevance.

Reviewed by eLife

Machine learning ensemble identifies distinct age-related response to spaceflight in mammary tissue

1. James A. Casaletto
2. Tyler Zhao
3. Jay Yeung
4. Amaan Ansari
5. Ayush Raj
6. Arnav Mishra
7. Amber Fry
8. Kathryn Sun
9. Sofia Lendahl
10. Willy Guan
11. Abigail Lee
12. Lauren M. Sanders
13. Sylvain V. Costes

Reviewed by PREreview

Hidden GPCR structural transitions addressed by multiple walker supervised molecular dynamics (mwSuMD)

1. Giuseppe Deganutti
2. Ludovico Pipitò
3. Roxana M Rujan
4. Tal Weizmann
5. Peter Griffin
6. Antonella Ciancetta
7. Stefano Moro
8. Christopher A Reynolds

• Curated by eLife

  eLife Assessment

  This study describes an improved adaptive sampling approach, multiple-walker Supervised Molecular Dynamics (mwSuMD), and its application to G protein-coupled receptors (GPCRs), which are the most abundant membrane proteins and key targets for drug discovery. The manuscript provides solid evidence that the mwSuMD approach can assist in the sampling of complex binding processes, leading to useful findings for GPCR activity, including resolution of interactions not seen experimentally. The method has the potential to have broad applicability in structural biology and pharmacology.

Reviewed by eLife

Barcode-free multiplex plasmid sequencing using Bayesian analysis and nanopore sequencing

1. Masaaki Uematsu
2. Jeremy M Baskin

• Curated by eLife

  eLife Assessment

  This study provides an important computational tool for analyzing and deconvoluting a pool of plasmids sequenced without barcoding using nanopore long-read sequencing. The tool, which has been convincingly validated, is readily available to scientists interested in rapid and cost-effective verification of plasmid sequences as well as in scaling up analysis by pooling samples within barcodes.

Reviewed by eLife

Healthy microbiome - moving towards functional interpretation

1. Kinga Zielińska
2. Klas I. Udekwu
3. Witold Rudnicki
4. Alina Frolova
5. Paweł P Łabaj

Reviewed by GigaScience

Genomic and transcriptomic analyses of Heteropoda venatoria reveal the expansion of P450 family for starvation resistance in spider

1. Guoqing Zhang
2. Yiru Wang
3. Hongcen Jiang
4. Yi Wang

Reviewed by GigaScience

A network regularized linear model to infer spatial expression pattern for single cell

1. Chaohao Gu
2. Hu Chen
3. Zhandong Liu

• Curated by eLife

  eLife Assessment

  The study is useful for advancing spatial transcriptomics through its novel regression-based linear model (glmSMA) that integrates single-cell RNA-seq with spatial reference atlases, though its methodological framework remains incomplete regarding spatial communication applications and feature dependence. The approach demonstrates notable utility by enabling higher-resolution cell mapping across multiple biological systems and spatial platforms compared to existing tools.

Reviewed by eLife

Systematic discovery of directional regulatory motifs associated with human insulator sites

1. Naoki Osato
2. Michiaki Hamada

Reviewed by Review Commons