Bioinformatics

The role of induced polarization in drug discovery applications

1. Ashraf Mohamed
2. Bernard R. Brooks
3. Muhamed Amin

Reviewed by PREreview

Have protein-ligand cofolding methods moved beyond memorisation?

1. Peter Škrinjar
2. Jérôme Eberhardt
3. Gerardo Tauriello
4. Torsten Schwede
5. Janani Durairaj

Reviewed by PREreview, Arcadia Science

AI-guided discovery and optimization of antimicrobial peptides through species-aware language model

1. Daehun Bae
2. Minsang Kim
3. Jiwon Seo
4. Hojung Nam

Reviewed by Arcadia Science

From Likelihood to Fitness: Improving Variant Effect Prediction in Protein and Genome Language Models

1. Charles W. J. Pugh
2. Paulina G. Nuñez-Valencia
3. Mafalda Dias
4. Jonathan Frazer

Reviewed by Arcadia Science

External validation of machine learning models—registered models and adaptive sample splitting

1. Giuseppe Gallitto
2. Robert Englert
3. Balint Kincses
4. Raviteja Kotikalapudi
5. Jialin Li
6. Kevin Hoffschlag
7. Ulrike Bingel
8. Tamas Spisak

Reviewed by GigaScience

Spatial Integration of Multi-Omics Data using the novel Multi-Omics Imaging Integration Toolset

1. Maximillian Wess
2. Maria K. Andersen
3. Elise Midtbust
4. Juan Carlos Cabellos Guillem
5. Trond Viset
6. Øystein Størkersen
7. Sebastian Krossa
8. Morten Beck Rye
9. May-Britt Tessem

Reviewed by GigaScience

Integrative Analysis of Neuroimaging and Microbiome Data Predicts Cognitive Decline in Parkinson’s Disease

1. Büşranur Delice
2. Özkan Ufuk Nalbantoğlu
3. Süleyman Yıldırım

Reviewed by PREreview

Predicting the effect of CRISPR-Cas9-based epigenome editing

1. Sanjit Singh Batra
2. Alan Cabrera
3. Jeffrey P Spence
4. Jacob Goell
5. Selvalakshmi S Anand
6. Isaac B Hilton
7. Yun S Song

• Curated by eLife

  eLife Assessment

  This study presents an advance in efforts to use histone post-translational modification (PTM) data to model gene expression and to predict epigenetic editing activity. Such models are broadly useful to the research community, especially ones that can model and predict epigenetic editing activity, which is novel; additionally, the authors have nicely integrated datasets across cell types into their model. The work is mostly solid, but it would be strengthened by performing further comparisons to existing methods that predict gene expression from PTM data and from more comprehensive functional validation of model-predicted epigenome editing outcomes beyond dCas9-p300 based perturbations. This work will be of interest to the epigenetics and computational modeling communities.

Reviewed by eLife

Biophysics-based protein language models for protein engineering

1. Sam Gelman
2. Bryce Johnson
3. Chase R. Freschlin
4. Arnav Sharma
5. Sameer D’Costa
6. John Peters
7. Anthony Gitter
8. Philip A. Romero

Reviewed by Arcadia Science

Unsupervised reference-free inference reveals unrecognized regulated transcriptomic complexity in human single cells

1. Roozbeh Dehghannasiri
2. George Henderson
3. Rob Bierman
4. Tavor Baharav
5. Kaitlin Chaung
6. Peter Wang
7. Julia Salzman

• Curated by eLife

  eLife Assessment

  This study presents a valuable advance for the analysis of gene expression variation at the level of individual cells by introducing a novel reference-free framework that can detect splicing, fusion, editing, immune-receptor diversity and repeated elements in sequencing data. The evidence supporting these claims is solid, with rigorous validation on simulated datasets and extensive analysis of full-length single-cell sequencing data demonstrating improved performance over existing methods. This work will be of particular interest to researchers developing methods for high-resolution transcriptome analysis and to those studying cellular heterogeneity in health and disease.

Reviewed by eLife, Arcadia Science