Bioinformatics

OmniNA: A foundation model for nucleotide sequences

1. Xilin Shen
2. Xiangchun Li

Reviewed by Arcadia Science

A Multi-omics Data Analysis Workflow Packaged as a FAIR Digital Object

1. Anna Niehues
2. Casper de Visser
3. Fiona A. Hagenbeek
4. Purva Kulkarni
5. Rene Pool
6. Naama Karu
7. Alida S. D. Kindt
8. Gurnoor Singh
9. Robert R. J. M. Vermeiren
10. Dorret I. Boomsma
11. Jenny van Dongen
12. Peter A. C. 't Hoen
13. Alain J. van Gool

Reviewed by GigaScience

Machine Learning Made Easy (MLme): a comprehensive toolkit for machine learning–driven data analysis

1. Akshay Akshay
2. Mitali Katoch
3. Navid Shekarchizadeh
4. Masoud Abedi
5. Ankush Sharma
6. Fiona C Burkhard
7. Rosalyn M Adam
8. Katia Monastyrskaya
9. Ali Hashemi Gheinani

Reviewed by GigaScience

Vulture: cloud-enabled scalable mining of microbial reads in public scRNA-seq data

1. Junyi Chen
2. Danqing Yin
3. Harris Y H Wong
4. Xin Duan
5. Ken H O Yu
6. Joshua W K Ho

Reviewed by GigaScience

Predicting metabolic modules in incomplete bacterial genomes with MetaPathPredict

1. David Geller-McGrath
2. Kishori M Konwar
3. Virginia P Edgcomb
4. Maria Pachiadaki
5. Jack W Roddy
6. Travis J Wheeler
7. Jason E McDermott

• Curated by eLife

  eLife assessment

  This landmark study presents MetaPathPredict, a method that uses a stacked ensemble of neural networks to predict the presence or absence of KEGG modules based on annotated features in the genome. The evidence supporting the conclusions is compelling, with a tool that allows for prediction of KEGG modules in sparse gene sequence datasets.

Reviewed by eLife

AutoPeptideML: a study on how to build more trustworthy peptide bioactivity predictors

1. Raúl Fernández-Díaz
2. Rodrigo Cossio-Pérez
3. Clement Agoni
4. Hoang Thanh Lam
5. Vanessa Lopez
6. Denis C Shields

Reviewed by Arcadia Science

LazyAF, a pipeline for accessible medium-scale in silico prediction of protein-protein interactions

1. Thomas C. McLean

Reviewed by Arcadia Science

Transformer-based spatial–temporal detection of apoptotic cell death in live-cell imaging

1. Alain Pulfer
2. Diego Ulisse Pizzagalli
3. Paolo Armando Gagliardi
4. Lucien Hinderling
5. Paul Lopez
6. Romaniya Zayats
7. Pau Carrillo-Barberà
8. Paola Antonello
9. Miguel Palomino-Segura
10. Benjamin Grädel
11. Mariaclaudia Nicolai
12. Alessandro Giusti
13. Marcus Thelen
14. Luca Maria Gambardella
15. Thomas T Murooka
16. Olivier Pertz
17. Rolf Krause
18. Santiago Fernandez Gonzalez

• Curated by eLife

  eLife assessment

  This valuable study advances our understanding of spatial-temporal cell dynamics both in vivo and in vitro. The authors provide solid evidence for their innovative deep learning-based apoptosis detection system, ADeS, which utilizes the principle of activity recognition. This work will be of broad interest to cell biologists and neuroscientists.

Reviewed by eLife

Enhancing TCR specificity predictions by combined pan- and peptide-specific training, loss-scaling, and sequence similarity integration

1. Mathias Fynbo Jensen
2. Morten Nielsen

• Curated by eLife

  eLife assessment

  This study presents a useful tool for predicting TCR specificity with compelling evidence for improvements over prior art. This work/tool will be broadly relevant to computational biologists and immunologists.

Reviewed by eLife

A concerted increase in readthrough and intron retention drives transposon expression during aging and senescence

1. Kamil Pabis
2. Diogo Barardo
3. Olga Sirbu
4. Kumar Selvarajoo
5. Jan Gruber
6. Brian K Kennedy

• Curated by eLife

  eLife assessment

  This study presents fundamental findings on the role of transcription readout and intron retention in transposon expression during aging in mammals. The evidence supporting the claims of the authors is compelling, strongly supporting the authors' claims. The work will be of interest to scientists studying aging, transcription regulation, and epigenetics.

Reviewed by eLife