Bioinformatics

Interpreting the Effects of DNA Polymerase Variants at the Structural Level

1. Matteo Arnaudi
2. Karolina Krzesińska
3. Ludovica Beltrame
4. Matteo Tiberti
5. Mef Nilbert
6. Anna Rohlin
7. Elena Papaleo

Reviewed by Review Commons

A genotype-phenotype transformer to assess and explain polygenic risk

1. Ingoo Lee
2. Zachary S. Wallace
3. Yuqi Wang
4. Sungjoon Park
5. Hojung Nam
6. Amit R. Majithia
7. Trey Ideker

Reviewed by Review Commons

Comparative evaluation of computational methods for reconstruction of human viral genomes

1. Maria J. P. Sousa
2. Mari Toppinen
3. Lari Pyöriä
4. Klaus Hedman
5. Antti Sajantila
6. Maria F. Perdomo
7. Diogo Pratas

Reviewed by GigaScience

An Integrative Multi-Omics Random Forest Framework for Robust Biomarker Discovery

1. Wei Zhang
2. Hanchen Huang
3. Lily Wang
4. Brian D. Lehmann
5. Steven X. Chen

Reviewed by GigaScience

Investigating the native functions of [NiFe]-carbon monoxide dehydrogenases through genomic context analysis

1. Maximilian Böhm
2. Henrik Land

• Curated by eLife

  eLife Assessment

  This study presents a valuable analysis of a large dataset of [NiFe]-CODHs, integrating genomic context, operon organization, and clade-specific gene neighborhoods to discern patterns of functional diversification and adaptation. Carefully looking at the CODH genomic context, e.g., CODH-HCP co-occurrence, the authors gain insight into enzymatic activity, biotechnological potential, and differential functional roles. The approach aligns with current standards in genomic enzymology to characterize newly identified enzymes. With solid support, this work provides a broadly informative contribution to the field.

Reviewed by eLife

Squidly: Enzyme Catalytic Residue Prediction Harnessing a Biology-Informed Contrastive Learning Framework

1. William JF Rieger
2. Mikael Boden
3. Frances Arnold
4. Ariane Mora

• Curated by eLife

  eLife Assessment

  This important contribution to enzyme annotation offers a deep learning framework for catalytic site prediction. Integrating biochemical knowledge with large language models, the authors demonstrate how to extract meaningful information from sequence alone. They introduce Squidly, a freely available new ML modeling framework, that outperforms existing tools on standard benchmarks, including the CataloDB dataset. The evidence is convincing, with an extensively and carefully addressed narrative upon revision.

Reviewed by eLife

Generative modeling for RNA splicing prediction and design

1. Di Wu
2. Natalie Maus
3. Anupama Jha
4. Kevin Yang
5. Benjamin D Wales-McGrath
6. San Jewell
7. Anna Tangiyan
8. Peter Choi
9. Jacob R Gardner
10. Yoseph Barash

• Curated by eLife

  eLife Assessment

  TrASPr is an important contribution that leverages transformer models focused on regulatory regions to enhance predictions of tissue-specific splicing events. The revisions strengthen the manuscript by clarifying methodology and expanding analyses across exon and intron sizes, and the evidence supporting TrASPr's predictive performance is compelling. This work will be of interest to researchers in computational genomics and RNA biology, offering an improved model for splicing prediction and a promising approach to RNA sequence design.

Reviewed by eLife

Label-free biochemical imaging and timepoint analysis of neural organoids via deep learning-enhanced Raman microspectroscopy

1. Dimitar Georgiev
2. Ruoxiao Xie
3. Daniel Reumann
4. Xiaoyu Zhao
5. Álvaro Fernández-Galiana
6. Mauricio Barahona
7. Molly M. Stevens

Reviewed by Arcadia Science

Beyond P-values: A Multi-Metric Framework for Robust Feature Selection and Predictive Modeling

1. Raelynn Chen
2. Attri Ghosh
3. Jie Hu
4. Yong Chen
5. Jason H. Moore
6. Ruowang Li

Reviewed by Arcadia Science

Weakly supervised learning uncovers phenotypic signatures in single-cell data

1. Anastasia Litinetskaya
2. Soroor Hediyeh-zadeh
3. Amir Ali Moinfar
4. Mohammad Lotfollahi
5. Fabian J. Theis

Reviewed by Arcadia Science