Next, Johanna von Wachsmann
@johannavw.bsky.social presented Gemsparcl—Rapid and consistent genome clustering for navigating bacterial diversity with millions of genomes" #GI2025

Jim Shaw @jimshaw.bsky.social presented "High-resolution metagenome assembly for modern long reads
with myloasm"
This efficient tool uses SNPmers and leverages high quality ONT and PacBio reads for metagenome assembly.
myloasm: doi.org/10.1101/2025.09.05.674543

Anshul Kundaje @anshulkundaje.bsky.social presented "Deep learning models of regulatory DNA—A comparison of model
design choices" #GI2025 He focused more on task-specific models & showed multi-task models lack causal interpretability.
ChromBPNet: doi.org/10.1101/2024.12.25.630221
encodeproject.org

Today is the last day of Genome Informatics #GI2025. The first talk was presented by Genrietta Yagudayeva on "A reproducible RNA-seq pipeline for mitogenomics and barcoding phylogenetics in neglected biodiversity"

Yana Safonova (Penn State) delivered the keynote "Enabling biomedical discoveries through immunogenomics
approaches"

Mammalian Immune Luci: doi.org/10.1093/molbev/msaf152
PatchWorkPlot: doi.org/10.1093/bioinformatics/btaf504

Ryan Moreno from @sroyyors.bsky.social Lab presented "Integrating single-cell omics data across species using matrix factorization regularized by gene-level phylogenies"

A very cool application of gene orthology across species for single-cell expression analysis! #orthology #GI2025 #singlecell

Li Song @mourisl.bsky.social presented "Quality control of single-cell ATAC-seq data without peak calling using Chromap"

Chromap-QC: biorxiv.org/content/10.1101/2025.07.15.664951
Chromap: nature.com/articles/s41467-021-26865-w #GI2025

The session 5 is on Single cell and spatial omics, chaired by Saurabh Sinha and Cong Ma @congma.bsky.social.

Cong Ma gave a great talk on "COMPOSITION—Efficient modeling of cell type and spatial organization for high resolution spatial transcriptomics"

Wui Wang Lui presented "SpliSync—Genomic-language-model-driven splice site correction of long RNA sequencing reads"
It uses sequence embeddings from HyenaDNA in addition to feed-forward NN form alignment pileup for splice detection, which is very cool!

Thomas Pierrot introduces the third version of Nucleotide Transformer in his talk!
NTv2 nature.com/articles/s41592-024-02523-z
They post-train the model (pre-trained on open genome dataset) with different genomic annotations and tracks. Preprint will be out soon!

Hanchen Wang presented "Biomni—A general-purpose biomedical AI agent" #GI2025
doi.org/10.1101/2025.05.30.656746

Matthew Nguyen delivered a great talk on "Refining Kraken2 long-read taxonomic classifications using convolutional neural networks"

Next, Jacob H. Wynne presented "Integrating targeted experiments with deep learning to resolve biogeochemical mechanisms in an antarctic microbiome" #GI2025

Yijie Kang (CSHL, Stony Brook) from @pkoo562.bsky.social Lab presented "Decoding the sequence basis of Pol II elongation with deep learning"

We are all sad that we didn’t have the opportunity to hear Adam Phillippy @aphillippy.bsky.social speak at the Genome Informatics #GI2025 due to the current circumstances. It would have been fascinating to learn about his work on the evolution of human acrocentric chromosomes.

Second's day concluded by fantastic talk by Cristina Martin Linares on "Minimal reconstruction of SpliceAI using distilled matryoshka sparse autoencoders"

They showed that matryoshka SAEs arxiv.org/abs/2503.17547 improves upon openSpliceAI elifesciences.org/reviewed-preprints/107454. #GI2025