Bioinformatics

Inferring protein from mRNA concentrations using convolutional neural networks

1. Patrick Maximilian Schwehn
2. Pascal Falter-Braun

Reviewed by preLights

In Silico Toxicity Assessment of Organophosphates: A DFT and Molecular Docking Study on Their Interaction with Human Serum Albumin (HSA)

1. Tanya Singh
2. Nisha Shankhwar
3. Neeta Raj Sharma
4. Anil Kumar
5. Awadhesh Kumar Verma

Reviewed by PREreview

On estimating phenomenological model states for epileptic seizure prediction

1. A I Bhatti

Reviewed by PREreview

Benchmarking Long-read Sequencing Tools for Chromosome End-specific Telomere Analysis

1. Jake Reed
2. Mark Oelkuct
3. Kevin Coombes

Reviewed by PREreview

Identification of Potential Hub Genes and Therapeutic Targets in Colorectal Cancer Using Integrated Bioinformatics Approaches

1. Kamalakannan D
2. Manivannan R
3. Suresh Gopal Kumar
4. Dilip Kumar

Reviewed by PREreview

CompactTree: a lightweight header-only C++ library and Python wrapper for ultra-large phylogenetics

1. Niema Moshiri

• Curated by GigaByte

  Editors Assessment:

  As volumes of viral and bacterial sequence data grow exponentially, the field of computational phylogenetics now demands resources to manage the burgeoning scale of this input data. This study introduces CompactTree, a C++ library designed for ultra-large phylogenetic trees with millions of tips. To address these scalability issues while maintaining ease of incorporation into external code bases, CompactTree is a header-only library with enhanced performance utilizing minimal dependencies, optimized node representation, and memory-efficient tree structure schemes. Resulting in significantly reduced memory footprints and improved processing times. Peer review requested some more detail on the functionality and some real-world examples, demonstrating the current utility of the tool. Although primarily supporting the (text-based) Newick format, the increased and extensibility scalability holds promise for multiple biological and epidemiological applications supporting more complex formats such as Nexus and NeXML. The tool is open source (GPLv3 licensed) and available in GitHub: https://niema.net/CompactTree

  This evaluation refers to version 1 of the preprint

Reviewed by GigaByte

Pathway activation model for personalized prediction of drug synergy

1. Quang Thinh Trac
2. Yue Huang
3. Tom Erkers
4. Päivi Östling
5. Anna Bohlin
6. Albin Österroos
7. Mattias Vesterlund
8. Rozbeh Jafari
9. Ioannis Siavelis
10. Helena Bäckvall
11. Santeri Kiviluoto
12. Lukas M. Orre
13. Mattias Rantalainen
14. Janne Lehtiö
15. Sören Lehmann
16. Olli Kallioniemi
17. Yudi Pawitan
18. Trung Nghia Vu

• Curated by eLife

  eLife Assessment

  This valuable study presents a deep learning framework for predicting synergistic drug combinations for cancer treatment in the AstraZeneca-Sanger (AZS) DREAM Challenge dataset. However, the evidence on the generalizability of the model is incomplete, as part of the validation seems to be flawed by overfitting, and only a modest correlation between predictions and observations was observed in the second, more independent test set. The reported tool, DIPx, could be of use for personalized drug synergy prediction and exploring the activated pathways related to the effects of drug combinations.

Reviewed by eLife

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

MerQuaCo: a computational tool for quality control in image-based spatial transcriptomics

1. Naomi Martin
2. Paul Olsen
3. Jacob Quon
4. Jazmin Campos
5. Nasmil Valera Cuevas
6. Josh Nagra
7. Marshall VanNess
8. Zoe Maltzer
9. Emily C Gelfand
10. Alana Oyama
11. Amanda Gary
12. Yimin Wang
13. Angela Alaya
14. Augustin Ruiz
15. Cade Reynoldson
16. Cameron Bielstein
17. Christina Alice Pom
18. Cindy Huang
19. Cliff Slaughterbeck
20. Elizabeth Liang
21. Jason Alexander
22. Jeanelle Ariza
23. Jocelin Malone
24. Jose Melchor
25. Kaity Colbert
26. Krissy Brouner
27. Lyudmila Shulga
28. Melissa Reding
29. Patrick Latimer
30. Raymond Sanchez
31. Stuard Barta
32. Tom Egdorf
33. Zachary Madigan
34. Chelsea M Pagan
35. Jennie L Close
36. Brian Long
37. Michael Kunst
38. Ed S Lein
39. Hongkui Zeng
40. Delissa McMillen
41. Jack Waters

• Curated by eLife

  eLife Assessment

  This valuable study describes MerQuaCo, a computational and automatic quality control tool for spatial transcriptomics datasets. The authors have collected a remarkable number of tissues to construct the main algorithm. The exceptional strength of the evidence is demonstrated through a combination of empirical observations, automated computational approaches, and validation against existing software packages. MerQuaCo will interest researchers who routinely perform spatial transcriptomic imaging (especially MERSCOPE), as it provides an imperfection detector and quality control measures for reliable and reproducible downstream analysis.

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