Bioinformatics

Generative modeling for RNA splicing predictions 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 evidence supporting the authors' claims is convincing, with rigorous analyses demonstrating improved performance relative to existing models, although some aspects of the evaluation would benefit from further clarification. This work will be of particular interest to researchers in computational genomics and RNA biology, as it offers both a refined predictive model and a new tool to designing RNA sequences for targeted splicing outcomes.

Reviewed by eLife

SqueezeCall: nanopore basecalling using a Squeezeformer network

1. Zhongxu Zhu

• Curated by GigaByte

  Editors Assessment:

  The accuracy of basecalling of nanopore sequencing still needs to be improved. With recent advances in deep learning this paper introduces SqueezeCall, a novel end-to-end tool for accurate basecalling. This uses Squeezeformer-achitecture which integrates local context extraction through convolutional layers and long-range dependency modeling via global context acquisition. Testing and peer review demonstrated that SqueezeCall outperformed traditional RNN and Transformer-based basecallers across multiple datasets, indicating its potential to refine genomic assembly and facilitate direct detection of modified bases in future genomic analytics. Future work is ongoing that will focus on training on highly curated datasets, including known modifications, to further increase research value. SqueezeCall is MIT licensed and available from GitHub here: https://github.com/labcbb/SqueezeCall

  This evaluation refers to version 1 of the preprint

Reviewed by GigaByte

Decoding the Molecular Language of Proteins with Evola

1. Xibin Zhou
2. Chenchen Han
3. Yingqi Zhang
4. Jin Su
5. Kai Zhuang
6. Shiyu Jiang
7. Zichen Yuan
8. Wei Zheng
9. Fengyuan Dai
10. Yuyang Zhou
11. Yuyang Tao
12. Dan Wu
13. Fajie Yuan

Reviewed by preLights

Celldetective: an AI-enhanced image analysis tool for unraveling dynamic cell interactions

1. Rémy Torro
2. Beatriz Díaz-Bello
3. Dalia El Arawi
4. Ksenija Dervanova
5. Lorna Ammer
6. Florian Dupuy
7. Patrick Chames
8. Kheya Sengupta
9. Laurent Limozin

• Curated by eLife

  eLife Assessment

  CellDetective is a useful software package for segmentation, tracking, and analysis of time‐lapse microscopy datasets, specifically designed to be accessible to researchers without coding expertise. The authors provide solid evidence of its capabilities through comprehensive validations and well‐executed comparisons across immunological assays. However, the current implementation is limited to 2D widefield imaging and presents technical challenges - including occasional crashes, restricted flexibility in defining multiple cell populations, and some interface issues that hinder the full user experience. Overall, this work will be of significant interest to the bioimaging community, especially those in immunology and cell biology, and promises to evolve into a more robust tool with further development.

Reviewed by eLife

CryoNeRF: reconstruction of homogeneous and heterogeneous cryo-EM structures using neural radiance field

1. Huaizhi Qu
2. Xiao Wang
3. Yuanyuan Zhang
4. Sheng Wang
5. William Stafford Noble
6. Tianlong Chen

Reviewed by PREreview

Discovery of Novel Inhibitors of HMG-CoA Reductase using Bioactive Compounds isolated from Cochlospermum Species through Computational Methods

1. Toba Isaac Olatoye

Reviewed by PREreview

The inflammatory skin disease map (ISD map): an interactive computational resource focused on psoriasis and atopic dermatitis molecular mechanisms

1. Marcio L. Acencio
2. Oxana Lopata
3. Ahmed A. Hemedan
4. Nick Dand
5. Stephan Weidinger
6. Lavinia Paternoster
7. Sara J. Brown
8. Joseph Rastrick
9. Catherine H. Smith
10. Matthias Hübenthal
11. Ravi Ramessur
12. Matladi Ndlovu
13. Soumyabrata Ghosh
14. Xinhui Wang
15. Reinhard Schneider
16. Venkata Satagopam
17. Marek Ostaszewski

Reviewed by Arcadia Science

Exploring the repository of de novo-designed bifunctional antimicrobial peptides through deep learning

1. Ruihan Dong
2. Rongrong Liu
3. Ziyu Liu
4. Yangang Liu
5. Gaomei Zhao
6. Honglei Li
7. Shiyuan Hou
8. Xiaohan Ma
9. Huarui Kang
10. Jing Liu
11. Fei Guo
12. Ping Zhao
13. Junping Wang
14. Cheng Wang
15. Xingan Wu
16. Sheng Ye
17. Cheng Zhu

• Curated by eLife

  eLife Assessment

  This study presents a useful pipeline for de novo design of antimicrobial peptides active both against bacteria and viruses. The method is based on deep learning, using a GAN generator and a regression tasked to predict antimicrobial activity. The experimental evidence supporting the conclusions is solid, with 24 validated peptides, although some additional justifications of the computational strategy would be a plus. This work will be of interest to the community working on machine learning for biomedical applications and specifically on antimicrobial peptides.

Reviewed by eLife

xRead: a coverage-guided approach for scalable construction of read overlapping graph

1. Tangchao Kong
2. Yadong Wang
3. Bo Liu

Reviewed by GigaScience

TransHLA: A Hybrid Transformer Model for HLA-Presented Epitope Detection

1. Tianchi Lu
2. Xueying Wang
3. Wan Nie
4. Miaozhe Huo
5. Shuaicheng Li

Reviewed by GigaScience