Bioinformatics

MuLan-Methyl - Multiple Transformer-based Language Models for Accurate DNA Methylation Prediction

1. Wenhuan Zeng
2. Anupam Gautam
3. Daniel H. Huson

Reviewed by GigaScience

Structure-based learning to model complex protein-DNA interactions and transcription-factor co-operativity in cis -regulatory elements

1. O Fornes
2. A Meseguer
3. J Aguirre-Plans
4. P Gohl
5. PM Bota
6. R Molina-Fernández
7. J Bonet
8. AC Hernandez
9. F Pegenaute
10. O Gallego
11. N Fernandez-Fuentes
12. B Oliva

• Curated by eLife

  eLife assessment

  This valuable study describes the development of a new structure-based learning approach to predict transcription binding specificity and its application in the modeling of regulatory complexes in cis-regulatory modules. The authors developed a structure-based learning approach to predict TF binding features and model the regulatory complex(es) in cis-regulatory modules, integrating experimental knowledge of structures of TF-DNA complexes and high-throughput TF-DNA interactions. The validation presented by the authors is currently incomplete, with a large variability in the performance of the method on the different TF families tested.

Reviewed by eLife

Similarity metric learning on perturbational datasets improves functional identification of perturbations

1. Ian Smith
2. Petr Smirnov
3. Benjamin Haibe-Kains

Reviewed by preLights

Inter-species association mapping links splice site evolution to METTL16 and SNRNP27K

1. Matthew T Parker
2. Sebastian M Fica
3. Geoffrey J Barton
4. Gordon G Simpson

Reviewed by Review Commons

The evolutionary history of class I aminoacyl-tRNA synthetases indicates early statistical translation

1. Jagoda Jabłońska
2. Yao Chun-Chen
3. Liam M. Longo
4. Dan S. Tawfik
5. Ita Gruic-Sovulj

Reviewed by PREreview

Predicting Relative Populations of Protein Conformations without a Physics Engine Using AlphaFold2

1. Gabriel Monteiro da Silva
2. Jennifer Y Cui
3. David C Dalgarno
4. George P Lisi
5. Brenda M Rubenstein

Reviewed by PREreview

Spatial transformation of multi-omics data unlocks novel insights into cancer biology

1. Mateo Sokač
2. Asbjørn Kjær
3. Lars Dyrskjøt
4. Benjamin Haibe-Kains
5. Hugo JWL Aerts
6. Nicolai J Birkbak

• Curated by eLife

  eLife assessment

  This valuable manuscript presents a new approach to transform multi-omics datasets into images and to exploit Deep Learning methods for image analysis of the transformed datasets. As an example, the method is applied to multi-omics datasets on different cancers. While the evidence in this specific case is solid, whether the method is working as advertised in other settings is not yet known.

Reviewed by eLife

Surface-guided computing to quantify dynamic interactions between cell morphology and molecular signals in 3D

1. Felix Y. Zhou
2. Virangika K. Wimalasena
3. Qiongjing Zou
4. Andrew Weems
5. Gabriel M. Gihana
6. Edward Jenkins
7. Bingying Chen
8. Bo-Jui Chang
9. Meghan Driscoll
10. Andrew J. Ewald
11. Gaudenz Danuser

Reviewed by Arcadia Science

AlphaPulldown—a python package for protein–protein interaction screens using AlphaFold-Multimer

1. Dingquan Yu
2. Grzegorz Chojnowski
3. Maria Rosenthal
4. Jan Kosinski

Reviewed by Arcadia Science

MuDoGeR: Multi-Domain Genome Recovery from metagenomes made easy

1. Ulisses Nunes da Rocha
2. Jonas Coelho Kasmanas
3. René Kallies
4. Joao Pedro Saraiva
5. Rodolfo Brizola Toscan
6. Polonca Štefanič
7. Marcos Fleming Bicalho
8. Felipe Borim Correa
9. Merve Nida Baştürk
10. Efthymios Fousekis
11. Luiz Miguel Viana Barbosa
12. Julia Plewka
13. Alexander Probst
14. Petr Baldrian
15. Peter Stadler
16. CLUE-TERRA consortium

Reviewed by Arcadia Science