Thursday, July 24: ISMB/ECCB Day 5 Highlights and Recap

Today was the final day of ISMB/ECCB 2025 and it was a fantastic ending to a great conference!

ISCB and the ISMB/ECCB 2025 Steering Committee wish to thank every attendee for being part of the world's largest conference on bioinformatics and computational biology. We hope you enjoyed your time in Liverpool and the five days of science, networking, and discussion!

Fireside Chat with David Baker

Before our final keynote, ISCB hosted a special fireside chat with 2024 Nobel Laureate David Baker, moderated by Christine Orengo. The conversation highlighted the creative journey behind Baker’s pioneering work in protein design, starting with his early skepticism about computation to developing generative design tools with wide-ranging applications in medicine, sustainability, and technology.

Baker spoke about the power of collaboration—both within his lab and through global partnerships—and shared advice for early-career researchers on building strong, interdisciplinary teams. He emphasized the importance of high-quality data, community-driven infrastructure, and staying grounded in experimental feedback. When asked about the future, Baker expressed optimism about the evolving role of scientists in an increasingly AI-driven landscape, encouraging researchers to stay curious, collaborative, and adaptable.

Keynote Address

In his keynote, “Decoding cellular systems: From observational atlases to generative interventions,” Fabian Theis—the 2025 ISCB Innovator Award winner—traced the evolution of computational cell biology, from mapping cellular identities to modeling and predicting how cells behave, interact, and respond to interventions.

He began with early efforts to build single-cell atlases, sharing how tools like Scanpy, Squidpy, and SpatialData helped unify transcriptomic and spatial data at scale. These frameworks paved the way for deep learning models that could represent cellular states in biologically meaningful latent spaces. Theis emphasized that engineering and data quality remain critical, as do community efforts like scverse that support reproducible, scalable single-cell analysis.

Moving toward virtual cells, Theis introduced foundation models trained across diverse datasets and modalities. His group’s Nicheformer, a transformer-based model, captures spatial and transcriptional relationships across millions of cells and multiple species, enabling tasks like cell-type prediction and niche composition analysis. It outperforms other embeddings and shows promise for generalizable spatial inference.

The keynote culminated with recent work on modeling cellular perturbations using generative AI. Theis presented CellFlow, a flow-matching model for predicting how cells respond to interventions such as gene edits or drug treatments. Together with tools like moscot, which maps unpaired control and perturbed cells using optimal transport, these advances support lab-in-the-loop experimental design—offering a path toward virtual experimentation at scale.

Theis closed by noting that while challenges remain in scaling, evaluation, and computational cost, foundation models offer an unprecedented opportunity to not just observe biology, but to actively shape it.

Session Recaps

Bioinfo-Core

Wednesday, July 23

The bioinfo-core COSI brings together managers and staff working in bioinformatics core facilities around the world. In our session we had a well-rounded and interesting mix of presentations, panel discussions, and breakout groups.

Talks:

Damian Dalle Nogare - Bioimage analysis in the age of AI: lessons and a path forward from a core facility perspective. A thought-provoking keynote regarding some history of the computational imaging field and its journey into a fully AI mode. We can learn a lot from the things they have gone through, and we should work together.

Kübra Narcı - Benchmarking Variant-Calling Workflows: The nf-core/variantbenchmarking Pipeline within the GHGA Framework: Variant callers do all sorts of different things and comparing structural variants is non-trivial. This is an nf-core pipeline to handle this type of comparison that was developed for the GHGA and shared with the world.

Thomas Roder - Assembly Curator: rapid and interactive consensus assembly generation for bacterial genomes – A microbial assembly benchmarking paper (Wick and Holt) basically found no assembler worked well on all assemblies. Tricycler from Ryan Wick is good, but time consuming. The goal of this was to get 80% of the quality of Tricycler in 5% of the time. On github at https://github.com/MrTomRod/assembly-curator

Adam Giess - Long Read Sequencing at Genomics England: They’ve done 12,000 Nanopore Promethion flowcells and shared some of the details of their setup and approach.

Anil S. Thanki - Autonomous Single Cell Transcriptomics Analysis in Persist-seq: Multi-institutional effort to study early tumor environment. Diverse toolset included Kubernetes, Jenkins, Galaxy (workflow executer command line), AWS, and Slack.

Iris Diana Yu - Advancing the Expression Atlas Resources: A Scalable Single-Cell Transcriptomics Pipeline to Facilitate Scientific Discoveries: Expression Atlas and single cell expression atlas – ingest, annotate, curate, and serve data!

Ayushi Agrawal - Mixed effects models applied to single nucleus RNA-seq data identify cell types associated with animal level pathological trait of Alzheimer’s disease: LODopt model applied to single nucleus RNA-seq data. https://github.com/gladstone-institutes/LODopt

Natalie Gill - Optimizing Clustering Resolution for Multi-subject Single Cell Studies: Method of optimizing clustering by splitting PCs into odd and even. https://github.com/gladstone-institutes/clustOpt

Hubert Rehrauer - GEO Uploader: Simplifying the data deposition in the GEO repository: A tool to make it easier for researchers to upload their data to GEO: https://github.com/fgcz/geo-uploader

Carlos Prieto - Enhancing Bioinformatics Workflows with Analytical Visualization Tools: a series of impressive interactive tools and data visualizations – rjsplot, D3GB, looking4clusters, Rvisdiff, RD3plot. https://github.com/BioinfoUSAL

Patricia Carvajal-López - Competency framework profiles to reflect career progression within bioinformatics core facility scientists: A collaboration and community effort led by EBI to develop more robust career definitions and stages for people in core facilities. Publication coming soon in Bioinformatics Advances.

Panels:

The rise of computational imaging

• Panelists: Damian Dalle Nogare, Jamie Soul, Syed Murtuza Baker, Emily Johnson
• Imaging groups and bioinformatics groups feel themselves coming together, mainly due to spatial transcriptomics. How can these two groups interact and learn from each other to advance science? We saw issues with the software built-in to some commercial platforms in terms of calling cells correctly and more custom solutions are probably needed. Perhaps some things can be learned by the bioinformatics core community and some things will be a collaboration between the two groups, but we need to be clear who does what and who needs what files from who in order to accomplish things. In some ways imaging has transformed into a fully AI field and we can learn from their growing pains.
• The practical use of AI in cores
  • Panelists: Madelaine Gogol, Ashley Sawle, Mohab Helmy, Ken Brewer
  • We discussed training users in the use of genAI (because we as bioinformaticians might be more experienced). Do we still need to teach coding? I think the consensus was at least some for some people, but it’s not really clear how much. How do we keep up with new tools? We need to be intentional about setting aside time for reading papers, experimenting, taking time to try things. Seqera AI was mentioned as a platform for writing NextFlow code (many of the models are not good at it yet). Multiqc has an argument now to generate an AI summary about the quality in the report. Could be used to take a collection of scripts and make it into a NextFlow pipeline with a little effort. University of Queensland fast AI course was mentioned as a potential source for upskilling. There were discussions of hiring in the age of AI with in-person interviews maybe more required and deep questions to check knowledge. Watch out for slopsquatting or bad prompting generating garbage for collaborators.

Breakout groups:

We broke into four breakout groups based on what the people in the room were interested in discussing.

• Spatial / Imaging – Imaging and Bioinformatics groups can stay separate but improve communication and make sure it’s clear who does what. Bioinformaticians need to learn to perform common and easy image-based tasks, and to ask for help with the hard ones. We have a lot to learn from imaging groups so short trainings could help us be able to leverage some things for spatial transcriptomics.
• AI – When users ask for AI, we need to find out if it’s the right tool and then guide them, otherwise they may pursue other less reputable sources. Upskilling our users in the use of AI could work better with free food. Assigning a few people in the team as AI experts could help the team learn and support users better.
• Project Management and tools – Jira and Agile might help manage projects and time. Getting involved early can help avoid bad data. Some teams like strict scoping, others feel it’s not collaborative. Being able to say no is essential, and so is maintaining good relationships.
• Reporting / communicating results – Quarto was mentioned as a great solution for updating reports and presentations when something changes. Containers and NextFlow are important for reproducibility, and clinical environments may be more resistant to changes.

CAMDA

Wednesday, July 23

The first day of CAMDA 2025 opened with a striking keynote by Thomas Rattei (University of Vienna), exploring the computational prediction of microbial phenotypic traits using neural networks trained on protein families from large-scale metagenomic datasets, linking microbiome diversity to human health.

The following session on the AMR Prediction Challenge featured diverse approaches to predicting antimicrobial resistance. Leonid Chindelevitch (Imperial College London) discussed the construction of the challenge based on the CABBAGE project compiling a unique curated genotype-phenotype database. Anton Pashkov (UNAM) compared a range of ML strategies integrating taxonomic and functional features. Jack Vaska (Stony Brook University) demonstrated the good performance of ~85% accuracy from DNABERT2 language models with DBGWAS-informed features. Alper Yurtseven (Helmholtz Institute) applied scalable models across the more than 5,000 bacterial strains. Owen Visser (University of Florida) presented an ensemble model, through which he also identified key resistance genes. David Danko (Biotia Inc.) showcased their BIOTIA-DX pipeline, achieving an F1 score of 84%, developing a clinically validated metagenomic workflow.

The second session of the day on the Gut Microbiota Challenge was introduced by Kinga Zielińska (Jagiellonian University), introducing new microbiome health indices that integrate taxonomy and function under the Theatre of Activity concept. Rafael Pérez Estrada (UNAM) developed an ensemble approach combining taxonomic and functional profiles, outperforming existing indices, and presenting a web-based health calculator. Khartik Uppalapati (RareGen) built RDMHI, a rare-disease-specific index for Phenylketonuria, integrating EHR simulations and genetic data for a 91% AUROC . Vincent Mel (University of Florida) introduced an ensemble index combining 61 species and 21 pathways, achieving 72% balanced accuracy. Doroteya Staykova (Multicore Dynamics) used topological data analysis to identify subgroups within healthy microbiomes, offering a stratified framework for gut health assessment.

Together, the first day of CAMDA 2025 highlighted how curated benchmarking data, advanced ML, and innovative integration strategies are driving new advances and insights in AMR prediction and microbiome-based health measures.

Join us tomorrow for a leading keynote by Spiros Denaxas (UCL) discussing the value hidden in electronic health records, as well as contributed talks and a panel discussion on

- The Health Privacy Challenge, presenting an interactive platform for achieving trust and robustness in the generation of privacy-preserving synthetic gene expression datasets

- The Synthetic Clinical Health Records Challenge, providing a rich set of highly realistic Electronic Health Records (EHRs) tracing the diagnosis trajectories, distilling information from 1.2 million real diabetic patients

Find our programme at http://www.camda.info/.

Thursday, July 24

The second day of CAMDA 2025 began with a keynote by Spiros Denaxas (University College London), who explored how electronic health records (EHRs) are reshaping biomedical research, enabling the simultaneous analysis of thousands of conditions while highlighting
the challenges of data sensitivity and privacy.

 The Synthetic EHR Challenge followed, with Carlos Loucera (FPS)
describing the generation of synthetic EHRs for one million diabetic
patients using VAEs and GANs. Daniel Voskergian (Al-Quds University)
leveraged these data to predict diabetic complications
using a Grouping–Scoring–Modeling framework, achieving AUCs up to 84%.

The Health Privacy Challenge, part of the ELSA initiative, was
introduced by Antti Honkela (University of Helsinki) and Hakime Öztürk
(EMBL), outlining a Blue Team vs Red Team format focused on
privacy-preserving synthetic data. A panel featuring Honkela, Denaxas,
David Kreil, Wenzhong Xiao, and Joaquin Dopazo debated regulatory and technical aspects of privacy in AI and health data.

Blue Team participants presented a variety of approaches: Andrew Wicks (DKFZ) used NMF with differential privacy for synthetic genomics; Steven Golob (UW Tacoma) assessed SDG performance on RNA-seq; Patrick McKeever (UW) evaluated scRNA-seq generators, finding scDesign2 most effective; and Jules Kreuer (Tübingen) introduced NoisyDiffusion, a privacy-preserving diffusion model with strong predictive accuracy and MIA resilience.

Serghei Mangul (Sage Bionetworks / Univ. of Suceava) gave two talks: one analyzing 6M+ publications to reveal underuse of RNA-seq data in
secondary analyses, and another uncovering fragmented pre-publication data sharing practices, showing that early release
improves citations. Finally, Yuexi Gu (Xi’an Jiaotong Univ.) presented
HI-MGSyn, a multi-granularity hypergraph model for drug synergy
prediction, successfully identifying novel combinations supported by
literature.

These sessions showcased the convergence of synthetic data generation, privacy-preserving AI, and open science to drive innovation in health research.

CAMDA 2025 concluded with the CAMDA Trophy ceremony, where the First Prize was awarded to Anton Pashkov (ENES Morelia, UNAM, Mexico). The Second Prize went to Rafael Pérez-Estrada (Centro de Ciencias Matemáticas, UNAM, Mexico), and the Third Prize to Owen Visser (University of Florida, U.S.A.). An Honourable Mention for
Sustainability was awarded to Serghei Mangul (University of Suceava,
Romania).

Stay tuned for the CAMDA 2026 challenges—visit our website at
www.camda.info and sign up for the low-volume CAMDA COSI announcements mailing list.

HiTSeq

What a day 2 at #HitSeq! The topics were so vast and quite original! First, we began the day with our final keynote speaker, Tobias Marschall from Heinrich Heine University Düsseldorf, who discussed pangenome-based analysis of structural variation. In this talk, he addressed the current limitations of draft pangenomes, including existing gaps and small sample sizes that hinder the detection of rare alleles, and discussed approaches to overcome them. Good news: HGSVC3 is in progress to complete the assembly of 65 new genomes!

Then, our second fabulous sponsor, Oxford Nanopore, gave a promotional talk with Mike Vella, Senior Director of Machine Learning at Oxford Nanopore Technologies, as the designated speaker. According to Mike, base calling is one of the most critical challenges for long-read sequencing data. He introduced us to duplex basecalling and how machine learning is enabling us to solve several issues that were previously almost intractable without machine learning implementation for base calling.

Then we proceeded with our amazing, carefully selected proceedings and abstracts, chosen to showcase at the final session of the HitSeq COSI track. Refreshing presentations included the creation algorithms (ALICE) to accelerate genome assembly, to capture uncertainty in single-cell copy-number calling, to perform assessment of long read data using SQANTI-reads (Netanya Keil, Winner for Oral presentation!), and even a new algorithm to detect Copy Number Variants (CNVs) in ancient genomes (LYCEUM!).

Thank you for attending and listening to the excellent presentation at HitSeq! The HitSeq aims to leverage the latest advances in high-throughput sequencing algorithms. We look forward to seeing you next year! Don’t forget to subscribe to our social media for more updates!

Twitter (X) @HiTSeq, BlueSky @hitseq.bsky.social

iRNA

The first day of the iRNA COSI started with a great keynote by Steven West from Exeter University discussing transcription attrition and why the decision between productive elongation and premature termination involves two complexes, the Integrator and the Restrictor, each monitoring different stages of transcription and providing a sequential verification mechanism. We had several talks from abstracts on methods for the identification, regulation and function of diverse noncoding RNAs including circular RNAs, miRNAs, snoRNAs, tRNAs and lncRNAs. These were followed by talks on approaches for the design of different flavours of CRISPR/Cas systems, RNA editing detection and mRNA design as well as our second keynote given by Roser Vento-Tormo from the Wellcome Sanger Institute showing beautiful work using single cell sequencing and highlighting the importance of spatial data for the study and comparison of the female reproductive tract throughout development and adulthood. The day ended with the iRNA dinner within the ISMB networking event at Punch Tarmey’s and the traditional iRNA quiz which was won ex aequo by ChatGPT and a team of dedicated students.

The second day covered diverse topics including predicting and characterizing split open reading frames, RBP binding, intron retention, RNA-DNA interactions, pseudouridine levels, isoform quantification and cryptic exons. We had a special session on ‘Building the future of RNA tools’ with a keynote talk by Blake Sweeney from the EMBL/EBI and talks from abstracts on current tools for the characterization of RNA biology, finishing with a thought-provoking panel discussion with Ana Conesa (University of Valencia), Jan Gorodkin (University of Copenhagen), Lina Ma (Beijing Institute of Genomics) and Yaron Orenstein (Bar-Ilan University). Through numerous questions from the audience, the panel highlighted the importance of generating more quality data to study different RNA characteristics and most particularly RNA structure, better covering the whole RNA space. Our last keynote talk of the day was given by Yiliang Ding from John Innes Centre discussing tools and approaches her group has built to study and characterize functional and dynamic RNA structures including G-quadruplexes which her group found serving as dynamic cold sensors.

JPI

ISCB Junior PI Community Grows at ISMB

Junior PIs met at ISMB to network and discuss upcoming activities. The meetup was exciting, welcoming new members and ideas for the community. Leading a research group or projects as an independent researcher? Join our Slack workspace: https://tinyurl.com/jpislack

If you have questions, let us know: [email protected]

How to Receive Your Certificate of Participation/Presentation

As with each year's conference, you will be able to receive a certificate of participation/presentation for ISMB/ECCB 2025. The certificate will be accessible upon completion of the conference survey which was sent out this evening after the last keynote. The email subject line is "ISMB/ECCB 2025 Conference Survey - Your feedback requested".

A Gentle Reminder

To help us protect the integrity of the conference certificates and to prevent potential misuse, we kindly ask that you do not share images of your certificate on any social media platform.

ISMB/ECCB 2025 On-Demand

Remember that sessions have been recorded (with author permissions) and will be part of the ISMB/ECCB 2025 On-Demand library on Nucleus.

After the conference, we will work to edit the live session recordings into individual videos. All registered participants of ISMB/ECCB will have exclusive access to the conference content and will be able to log in at any time to view recordings of any talks you’d like see again!

Wednesday, July 23: ISMB/ECCB Day 4 Highlights and Recap

On day 4 or ISMB/ECCB 2025, we had a full day with 9 COSI tracks, CollaborationFest, and the industry and ELIXIR/NIH-ODSS special sessions. 

Before the ACC was full of attendees, however, another morning started off with the Serene Stretch Symposium. 

The ISCB Town Hall was held, allowing attendees to learn about the latest programs and initiatives from ISCB, as well as upcoming conferences. This meeting provided the opportunity for members to provide feedback and suggestions to help shape the future of the society!

Another great highlight of the day was the presentation of the 2025 Outstanding Contribution to ISCB Award to this year's winner, Lucia Peixoto. Lucia was recognized for her leadership, service,
and dedication to building an inclusive scientific community. 

**Please make sure to read the “Important Notes” section below.**

Keynote Address: Charlotte Deane

In her keynote address, “Building the future of AI-driven structure-based drug discovery,” Professor Charlotte Deane explored how artificial intelligence is reshaping the development of therapeutics while offering a candid look at both its potential and its pitfalls.

Drug development remains an extraordinarily costly and time-consuming process, with high failure rates and limited incentives to pursue treatments for diseases that disproportionately affect underserved populations. Deane made a compelling case for why democratizing drug discovery is critical, discussing how AI might help.

She shared a series of projects from her lab that demonstrate the capabilities and constraints of AI tools in this space. Among them was Paragraph, an antibody paratope prediction model that uses experimental and modeled structures to train an Equivariant Graph Neural Network. She also introduced AbLang, a language model for antibody sequences that revealed how skewed training data can bias model predictions toward germline residues, highlighting the importance of diverse and representative datasets.

For flexible protein modeling, Deane presented ITsFlexible, a method for predicting conformational flexibility in antibody CDR3 loops. This tool goes beyond static structure prediction, enabling more nuanced representations of protein dynamics.

Deane also examined AI tools for small molecule drug discovery, including structure-based docking and binding affinity prediction. She’s found that traditional docking methods often outperform newer AI-based models, especially when evaluated on physically realistic or out-of-distribution test sets. Benchmarks such as CASF-2016 were shown to have significant data overlap with training sets, raising questions about how well current AI models generalize. Her group proposed a zero-ligand bias benchmark as a more rigorous alternative.

Ultimately, Deane emphasized that while AI will undoubtedly continue to play a critical role in structure-based drug discovery, it is not a cure-all. Its success depends on thoughtful model design, realistic evaluation metrics, and—most importantly—robust, well-curated data.

Session Recaps

CSi

Wednesday, July 22: 

2025 marks the first year of Computational and Systems Immunology, CSI for short, COSI. We were excited to start the day with a packed room for Dr. Julio-Saez Rodriguez's Keynote talk on use of multiomic and spatial data alongside biological knowledge to model gene regulatory and signalling networks. This was followed by a talk from founder and former chair of the Computational Biology Department at Carnegie Mellon, Dr. Robert F. Murphy, on their vision transformer based cell annotation method for highly multiplexed tissue images. The morning session continued with talks on protein expression imputation from spatial transcriptomics data and spatial and single-cell study of the human thymus to understand how it becomes dysfunctional as we age.

The afternoon session started with a remote talk from Dr. Harinder Singh on deciphering transcriptional regulatory code of immune cells using an expanded DNA motif lexicon (such as composite TF motifs). Following talks by trainees looked at transcriptional regulators of Tfh differentiation, double negative B cells in cancer and prediction of pairing of heavy and light immunoglobulin chains. These were followed by talks on incorporation of phylogeny information for B cell epitope prediction, improvements for TCR-epitope binding prediction models and prediction of neoantigen immunogenicity in cancer. The last full talk of the afternoon introduced SHISMA, a novel tool to infer significant cell type-specific regulatory patterns with strong statistical guarantees. The day and the COSI session for this year was concluded with 5-minute short talks selected from submitted abstracts. See you next year in Washington DC to hear the latest and most exciting research directions in computational and systems immunology. Stay tuned for more CSI COSI activity including an online seminar series in the meantime!

Education

The Education COSI hosted a vibrant program covering a range of current issues in computational biology education. The session led off with an exciting keynote from Gabriela Rustici of AstraZeneca to share her experiences with bioinformatics training, emphasizing partnerships between industry and academia training and some of the challenges and opportunities that entails. This session also provides a bridge to the next day’s Workshop on Education in Bioinformatics (WEB), which will follow up on the theme of industry’s role in bioinformatics in education.

The program featured two proceedings talks by Alistair Kilpatrick and Pavlin G. Poličar and eight contributed abstract talks by Allissa Dillman, Ajay Mishra, Dusanka Nikolic, Aparna Nathan, Inimary Toby-Ogundeji, Amanda Saravia-Butler, Nadiia Kasianchuk, Nicola Mulder, and Alina Frolova. Collectively, these talks covered a wide range of ongoing and emerging topics in bioinformatics education, including computational and quantitative education of experimental biologists and public health workers, new pedagogy models and use cases, meeting challenges of content delivery in resource-limited environments, and the use of large language models (LLMs) to facilitate bioinformatics education.

Wrapping up the program was our closing keynote speaker, Patricia Carvajal-López of EMBL/EBI, sharing her work in developing and maintaining communities of practice in bioinformatics education and highlighting the recent success of the Bioinformatics Education Summit she co-organized in Mexico City this past May.

We thank the community for another great year in Bioinformatics Education and encourage participation in the WEB, visiting the Education posters, and contributing to community educational activities throughout the year.

HiTSeq

Today our amazing Hitseq track kicked off with cutting-edge advancements in algorithms for analyzing diverse types of high-throughput sequencing data.

We had two fantastic keynote speakers:

• Valentina Boeva – “Learning variant effects on chromatin accessibility and 3D structure without matched Hi-C data”, and
• Jonathan Goke – “Quantifying RNA Expression and Modifications using Long Read RNA-Seq”.

Our proceedings presentations featured:

• A benchmark of deconvolution tools to estimate cell fractions in spatial transcriptomic data using ATAC- or RNA-based references, presented by Laura Mortens,
• Oarfish – improving accuracy in long-read transcriptome quantification, presented by Zahra Zare,
• Alevin-fry-atac – enabling frugal mapping of single-cell ATAC-seq data through virtual colors for precise genomic pseudoalignment, presented by Noor Pratap.

We also had exciting algorithm introductions including:

• Icona – identifying structure-defining chromatic contacts, and
• SplitSync – leveraging deep learning to improve splice site accuracy.

Finally, our sponsor PacBio presented “Bioinformatics analysis for long-read RNA sequencing: challenges and promises” by Elizabeth Tseng.

Follow us on our social media for more updates!

X @HiTSeq BlueSky @hitseq.bsky.social

NetBio

We wrapped up another engaging and well-attended half-day at the NetBio COSI, continuing the momentum from Day 1 with a packed room and lively discussion throughout the sessions. Today's program showcased a range of innovative work at the intersection of network
biology and translational medicine.

The morning opened with a proceedings talk by Dongmin Bang on
MixingDTA, a novel approach for improving drug-target affinity
prediction by extending Mixup with guilt-by-association principles. This
was followed by compelling presentations from Nicoleta Siminea,
Terence Egbelo, Johannes Kersting, and Samuele Firmani. These talks highlighted diverse computational strategies for supporting personalized therapies, addressing target-adverse event associations, building robust disease modules, and identifying antiviral
targets using message-passing neural networks.

After the lunch break, Piotr Sliwa presented a multilayer network
approach for identifying clinically relevant patient endotypes in
COVID-19 and sepsis, offering new insights into patient stratification.
We then turned our attention to visualization, with Chad Myers presenting the winners of the Cytoscape Visualization Competition - thank you to all who submitted their figures and voted! Congratulations to the winners Alejandra Paulina Perez Gonzalez, Michael Costanzo and Jong Chan Lim! Check out their submissions below!

The day concluded with a shared keynote talk with the Microbiome COSI by Fiona Brinkman, who walked us through the complexity of microbiome data and metadata management.

Many thanks to all NetBio speakers, poster presenters, moderators and organizers for their fantastic contributions!

If you haven't checked out the 45 NetBio posters yet, tomorrow's your last chance! Don't miss them!

SysMod

Wednesday, July 22

The 10th Annual SysMod Meeting was hoster by Matteo Barberis and Chiara Damiani, and it has been such a rich, dynamic, and truly international event. Whether through a talk, a poster presentation, joining the session, or simply listening and engaging in the discussions, the highly attendance of participants contributed to what felt like a very special milestone for the Systems Biology and Modelling community.

Three were the sessions covered in the 2025 edition of the meeting, with many highlights and takeways:

- Metabolic Modeling: New Variational Perspectives: The meeting opened with a session focused on metabolic modeling — a natural framework for bridging data-driven and mechanistic approaches. Ronan Fleming (University of Galway) shared his long-term vision to reformulate reaction kinetics using a variational framework, addressing a key limitation of genome-scale models: the lack of metabolite concentration dynamics. Talks by Lisa Corbeij, Garhima Arora, and Sultana Al Zubaidi explored new directions in dynamic and single-cell metabolic modeling.

- Multiscale Systems Biology and Control: Here we saw how computational models are being used to make sense of biological complexity across scales. Jasmin Fisher (UCL) delivered a powerful keynote on multiscale modeling in oncology, showing how intra- and inter-cellular signaling models can support data-driven and personalized medicine. Other talks featured reinforcement learning for optimizing JAK/STAT interventions (Nhung Duong), logic-based models for drug discovery (Bi-Rong Wang), and benchmarking of agent-based simulations (Arnau Montagud). The generative framework ARTEMIS (Sayali Alatkar) stood out for integrating autoencoders with Schrödinger Bridges to model gene expression dynamics from time-series single-cell data.

- Single-Cell Dynamics and Inference: The final session zoomed in on single-cell and spatial data. We saw high-resolution modeling of bacterial dynamics in microfluidic traps (Ati Ahmadi), metabolic atlas construction across organs (Erick Armingol), and deep learning approaches to spatiotemporal tissue dynamics (Koichiro Majima).

In addition to the three sessions, thre fast-paced talks added diversity and depth to the program: Jiachen Li (TFvelo: RNA velocity without splicing), Bingxin Lu (DNA repair and structural variation from cell-cycle modeling), and Marek Kimmel (Modeling telomere reconstruction).

Finally, so much energy and talent was spread in the poster session, with the poster prized being awarded to: Yanjun Liu (1st place), Rupinder Kaur (2nd place), and Sebastian Huß (3rd place). . Many Congratulations to the awardees! And many thanks to all the presenters for their valuable contributions.

🧭Career Compass Featured Job🧭

Postdoctoral Researcher (m/f/d) in Computational Oncology

University of Tübingen, Institute for Bioinformatics and Medical Informatics

Tübingen, Germany

KohlbacherLab.org

Job description:

The chair for Applied Bioinformatics at the University of Tübingen, Germany (Prof. Oliver Kohlbacher) is looking for a Postdoctoral Researcher position in Computational Oncology.
Position Details
Start Date: negotiable, available immediately
Duration: 3 years (initially)
Working Hours: Full-time (100%)
Salary: According to German salary scale TV-L E13

Description

The successful candidate will join an interdisciplinary team focused on applying bioinformatics to personalized oncology. The primary objective is to unravel molecular pathways of cancer by analyzing and integrating multi-omics and clinical data.

Key Responsibilities

• Analyze and interpret multi-omics datasets, including genomic, transcriptomic, and clinical data from over 7,000 cases treated in molecular tumor boards.

• Develop and implement bioinformatics pipelines to identify biomarkers and therapeutic targets.

• Collaborate with clinicians and researchers to translate computational findings into clinical applications.

• Publish research findings in peer-reviewed journals and present at international conferences.

• Mentor junior researchers and contribute to the academic environment of the institute.
  
  

Opportunities

• Access to a unique and comprehensive dataset combining genomic and clinical information from a large cohort of cancer patients.

• Potential to establish an independent research group for candidates with a strong publication record and leadership potential.

• Engagement with the University of Tübingen’s vibrant research community and participation in collaborative projects within the Clusters of Excellence ‘Machine Learning for Science’ and ‘Image-Guided and Functionally Instructed Tumor Therapies (iFIT)’.
  
  

Qualifications

Requirements

• PhD in Bioinformatics, Computational Biology, or a related field.

• Demonstrated expertise in analyzing high-throughput sequencing data and developing bioinformatics tools.

• Proficiency in programming languages such as Python or R, and experience with relevant bioinformatics software.

• Strong understanding of cancer biology and molecular oncology is advantageous.

• Excellent communication skills and the ability to work collaboratively in a multidisciplinary team 

• Previous experience in using machine learning methods will be beneficial

ISCB Values and EDI Initiatives

Have you seen the posters at the ISCB booth? We had two new ones created for the conference this year to share a reminder of the ISCB values, as well as the EDI Strategic Plan from 2025 to 2030. The EDI Strategic Plan highlights recent progress and outlines future goals to build a more inclusive, representative, and connected computational biology community. 

Check out a sneak peak of the posters below or visit the booth tomorrow!

❗Important Notes❗

POSTERS

All posters must be taken down by 4pm tomorrow, Thursday, July 24.

LUGGAGE AND COAT CHECK 

If you’re leaving right after the conference and your hotel is nearby, please ask the staff at the front desk of your hotel if they can hold your luggage for you. If your hotel isn’t nearby, you will be able to drop off your luggage at the cloakroom on the main floor of the ACC Galleria. 

NOTE: The cloakroom will close at 6:30pm on Thursday, July 24. If you do not collect your luggage by this time, anything left will be moved to the registration desk or given to lost and found.

**Neither ISCB event staff nor the ACC staff will be responsible for your luggage.

LOST ITEMS

If you’ve lost something while attending sessions during the conference, please visit the ISMB/ECCB registration desk as many lost items have been dropped off there. If your item isn't at the registration desk, please ask for any lost and found items at the ACC's Guest Relations desk.

TRANSPORTATION TO THE AIRPORT

Bus:If you're hoping to travel by bus, there are two main buses that service the Liverpool City Region:Arriva and Stagecoach. You can check the respective websites to find the correct bus line for you. Remember that the Liverpool ONE Bus Station is the closest service point for long distance coaches and the Liverpool ONE bus station is only a 5 minute walk from the ACC Liverpool.

Train: If you need to find a train to reach the city you're flying out from, Avanti West Coast has several cities they travel to or you can look at train options on Trainline.

Ride Share: If you want to travel by Uber to the airport, consider the ‘Share’ option to lower travel expenses, or connect with other conference attendees and split the fare for an Uber or taxi.

You can also try reviewing travel options on the Merseytravel website.

Coming Up Tomorrow, Thursday, July 24

• 7:30am – Serene Stretch Symposium
• Sessions starting at 8:40am:
  • BioVis
  • CAMDA
  • CollaborationFest
  • GenCompBio
  • HitSeq
  • iRNA
  • MICROBIOME
  • RegSys
  • Stewardship of Critical Infrastructure
  • Text Mining
  • WEB
• 10:00am – Caffeinate and Connect with Posters and Exhibitors
• 1:00pm – Lunch with Posters
• 4:00pm – Grab and go coffee break
• 4:20pm – Fireside chat with David Baker
• 4:45pm – Day 5 Keynote: Fabian Theis (ISCB 2025 Innovator Award winner), and closing ceremonies

Tuesday, July 22: ISMB/ECCB Day 3 Highlights and Recap

Day 3 started with another fantastic keynote address and continued with science during the day and reinvented networking at the Success Circles event in the evening!

Before we get to the keynote summary, we wanted to take a moment to share some sustainability information with you about the venue. In case you've not had a chance to read the information, here are some important slides from the slideshow that's been running on several of the screens:

In short, Liverpool is a zero waste community! The packaging of lunch items is compostable, and everything is sorted to the appropriate bins for correct disposal. 

A quick note: Paper bags are available to help carry your lunch items, but they are completely optional. If you don’t need one, feel free to leave it behind or reuse the bag!

If you want more information about the ACC's sustainability efforts, click here. 

Keynote Address: James Zou

To kick off day 3 of ISMB/ECCB, the 2025 Overton Prize Award winner James Zou explored how large language model–based agents are transforming the field in his keynote address “Computational biology in the age of AI agents.”

Zou introduced the Virtual Lab, a team of AI “scientists” capable of brainstorming, designing, and refining research ideas with minimal human input. Drawing from real examples, including the successful design of nanobodies against emerging SARS-CoV-2 variants, he showed how these agents debate, critique, and improve each other’s suggestions in collaborative meetings, with little need for human intervention.

He also discussed CellVoyager, an AI data scientist designed to reanalyze complex genomics datasets and uncover novel insights, showing that even previously published data can yield fresh discoveries when AI explores beyond the limits of standard analysis pipelines.

Finally, Zou shared InterPLM, an agent that helps interpret the inner workings of large protein language models. By translating abstract model behavior into human-understandable biological concepts, InterPLM has begun revealing not only how these models function, but also where they might be identifying under-annotated or missing protein features.

Zou closed by acknowledging the limitations of AI agents and emphasized the power of human-AI collaboration. In this emerging era, he argued, agents offer scale and speed, while humans provide creativity, critical thinking, and experimental grounding.

Session Recaps

BOSC

Today, the BOSC and BOKR COSIs joined forces. The joint session was kicked off by keynote speaker Chris Mungall, who wove together his work on agentic AI, ontologies and knowledge bases to describe a “future of bioinformatics” that is in fact happening right now. While we have heard a great deal on the limits of LLMs, some of Chris’ latest work examines the potential of agentic AI as an important aid for biocuration. As the number of tools grows, an under-recognized challenge will be evaluating and benchmarking the utility and reproducibility of these tools. One strategy for examining AI agent work benefits from the long history of provenance around curator maintenance of ontologies. Dating back to pre-GitHub times—circa 2002—this evidence trail allows evaluation work to directly compare how AI decisions are compared with the work of human curators. The talk ended with his reflections on AI ethics, particularly circumstances where an AI might be tasked with conflicting policy directives.

Next up was a session on Artificial Intelligence / Machine Learning, with an emphasis on open approaches. After lunch, speakers delved into topics around ontologies and knowledge representation (with, again, a heavy dose of AI). A short talk on the global biodata infrastructure by Guy Cochrane led directly into the closing panel on Data Sustainability, with panelists Scott Edmunds, Varsha Khodiyar, Tony Burdett, Nicky Mulder, and Chris Mungall. The thought-provoking panel discussion touched on FAIR and CARE principles, ecological sustainability, funding, “handoffs” between data providers and data users, the importance of trust and governance, and much more.

We hope to see you at BOSC 2026!

EvolCompGen

 Today, EvolCompGen and Function started with a joint session. Keynote speaker Marc Robinson-Rechavi presented the current state of the debate on the ortholog conjecture. He made a compelling case for best practices and infrastructure supporting rigorous assessment of functional conservation among related genes. These themes were echoed throughout session, which nicely melded topics in both evolution and function. One observation from this joint session is that it is a great way to connect two COSIs!

The second EvolCompGen session had a focus on viral and bacterial genomes. We learned about which non-pharmaceutical interventions were most important for reduction of covid spread in Germany, how to cleverly represent viral genomes, and interesting properties of genomes found in Antarctica and the Dead sea. The third session had a wide range of topics, but a focus population genomics. We should highlight the proceedings talk on how to improve inference of ancestral genome segments.

The day ended with a panel discussion of current and future directions in Evolution and Comparative Genomics. Good natured bickering about the impact of AI methods in evolutionary studies, or rather the lack of impact, ensued. Both for "classic" phylogeny and cell-trajectory studies, typically cancer related, AI methods have not been the same driving force as in some other areas. Why is that?

NetBio

We had a fantastic and well-attended day at the NetBio COSI track at ISMB/ECCB2025, with a full room, people sitting on the stairs, and even an overflow room needed for parts of the program - great energy from the network biology community.

The morning session featured an all-female speaker lineup, highlighting the outstanding contributions of women in the field. Throughout the day, we were thrilled to see so many junior researchers presenting innovative work.

The session opened with a keynote by Laura Cantini on multi-modal learning for single-cell data integration, followed by talks from Mayra Luisa Ruiz Tejada Segura, Saniya Khullar, and Giulia Cesaro, covering diverse approaches to modeling cellular communication, regulation, and signaling.

The afternoon included proceedings presentations by Sindhura Kommu and Lucas Gillenwater, alongside selected talks from Ibrahim Alsaggaf, Kivilcim Ozturk, Erik Sonnhammer, Dewei Hu, Beatriz Urda-García, and Aritra Bose, covering topics ranging from gene regulation and structural basis of protein interactions to cancer biology. The speakers utilized a broad range of approaches, including graph machine learning, quantum computing, and discrete algorithms to address problems in these domains. We closed the day with a dynamic keynote by Jan Baumbach on the potential of quantum computing in network medicine.

🙌 A huge thank you to all speakers, attendees, and organizers!

📣 Don’t forget to vote in the Cytoscape Visualization Contest - voting is still open until tomorrow lunchtime! https://woobox.com/b9poce

Tomorrow another exciting half-day of NetBio is waiting for you! We also have 45 posters to visit on Wednesday and Thursday. We’ll announce our best talk and poster prizes during the ISMB award session on Thursday!

TransMed

The TransMed COSI celebrated its 10th anniversary today at ISMB/ECCB 2025. The program began with welcome remarks by co-chair Venkata Satagopam, reflecting on a decade of progress at the interface of clinical research, multi-omics, and digital health. The session show how translational bioinformatics has evolved from proof-of-concept studies to real-world clinical integration.

The day opened with the keynote speaker Melanie Schirmer, who introduced a gene-centric metagenomic framework to identify disease-associated microbial genes and operon structures across 9,000+ microbiome samples, offering novel insights into IBD and colorectal cancer. The day featured a rich series of contributed talks showcasing a forward-looking agenda focused on translational bioinformatics, integrative multi-omic, and AI-powered approaches for improving diagnostics, patient stratification, and therapeutic development. It closed with Jonathan Carlson who delivered an inspiring invited talk on the rise of general AI in biomedicine, emphasizing how generative models are beginning to reason over proteins, images, and molecular systems—heralding a transformative shift in biomedical discovery.

TransMed’s anniversary celebration not only honored its past but also signaled a future driven by integrative, interpretable, and clinically actionable biomedical data science.

VarI

This year marked the 15th anniversary of the VarI COSI session at ISMB, showcasing cutting-edge advances in variant interpretation. The session received 57 abstract submissions (34 for talks, 23 for posters), with 13 selected talks and 3 keynote presentations.

The morning keynote featured Dr. Alexander Sasse from Heidelberg University, who explored how multi-task convolutional neural networks decode genomic regulatory patterns while addressing their limitations in predicting directional effects of genetic variants on gene expression - crucial for understanding disease mechanisms. The session continued with five talks on protein language models for missense variant effect prediction.

Dr. Ellen McDonagh delivered the second keynote, presenting OpenTargets' latest developments in multi-omics integration, AI-driven target prioritization, and collaborative tools for therapeutic discovery.

The final keynote by Dr. Andrew Lawson highlighted research on somatic mutations in normal tissues, introducing NanoSeq - an ultra-accurate duplex sequencing method that revealed extensive clonal selection patterns in human tissues, offering new insights into cancer development and aging.

The afternoon session featured eight talks showcasing major advances in genetic disease research. Presenters revealed novel insights into neurodevelopmental disorders, identifying unexpected cellular mechanisms beyond neurons. New computational tools improved predictions of splicing defects and cancer drug resistance using single-cell data, while cardiovascular studies uncovered hundreds of CAD-associated genes including non-coding RNAs. Breakthroughs in polygenic scoring addressed ethnic disparities and gender-related genetic factors, and cancer research uncovered protective gene effects and recessive inheritance patterns. Together, these studies demonstrated how multi-omics approaches and single-cell technologies are revolutionizing our understanding of disease genetics.

With 213 registered delegates, the session fostered active discussion. The VarI poster session will continue tomorrow (July 22, 10:00-16:40 BST), and attendees can vote for best talks/posters at: https://bit.ly/vari-nominations.

Success Circles

The Success Circle event this year featured 6 focused discussion tables which included:

• Integrating the sex and gender dimension in research
• Balancing AI use for computational biology versus climate impact
• Discussing the worth of high-profile and (vs.) author-centric journals
• Making Connections: Networking as Introverted Researchers
• PhD to PI: Cultivating Leadership in Science
• Bridging the Gap between Academic and Industry Careers

The event offered a valuable opportunity for attendees to share experiences, explore challenges, and expand their networks in an engaging, conversational setting. Big ideas and even bigger conversations made the night a success!

Coming Up Tomorrow Wednesday, July 23

• 7:30am – Serene Stretch Symposium
• 8:40am – Welcome and Day 4 Distinguished Keynote: Charlotte Deane
• 10:00am and 4:00pm – Caffeinate and Connect with Posters and Exhibitors
• 1:00pm – Lunch / ISCB Town Hall 
• Sessions starting at 11:20am:
  • BioInfo-Core
  • BOKR
  • CAMDA
  • CollaborationFest
  • Education
  • Elixir/NIH-ODSS
  • HitSeq
  • Industry's Role in Bioinformatics
  • iRNA
  • MICROBIOME
  • NetBio
  • RegSys
• 6:00pm – JPI Meet-Up

Monday, July 21: ISMB/ECCB Day 2 Highlights and Recap

Day 2 of ISMB/ECCB 2025 started off with a celebration of the ISCB 2025 Class of Fellows where they were presented with the Fellows Awards. Congratulations once again to the 2025 Class of Fellows!

Following the Fellows presentation and the keynote address from Dr. Amos Bairoch (read more below) we had a full day of COSI tracks and special sessions, including Bioinformatics in the UK. 

Read on for the highlights of the second day of the conference!

Keynote Address: Amos Bairoch

Dr. Amos Bairoch, our 2025 Accomplishments by a Senior Scientist Award winner, spoke to our attendees this morning, giving his keynote address, “Plus ça change, plus c’est la même chose: From Swiss-Prot to Cellosaurus, 45 years of biocuration.”

The talk offered a richly contextual reflection on the evolution of biocuration. With more than four decades of experience in the field, Bairoch outlined how foundational and forward-looking his work has been across generations of bioinformatics resources.

He traced the early days of biocuration back to 1980, when he manually typed in protein sequences for a software package that would become PC/Gene. By 1986, he had led the first release of Swiss-Prot, an effort that eventually involved more than 200 annotators, now recognized as biocurators. He continued to shape the field with the development of PROSITE and ENZYME in 1988, neXtProt in 2010, and the launch of Cellosaurus in 2012, a resource he continues to lead and expand.

While technical progress has been remarkable, Bairoch emphasized that many of the core challenges in biocuration remain unchanged. From underfunding and undervaluation to persistent misconceptions about the replaceability of expert curation, the field continues to face pressures from evolving technologies and shifting expectations. He offered a brief history of how funders and users have viewed biocuration over the decades, highlighting the ongoing disconnect between its recognized importance and its consistent underfunding.

Through humor, historical perspective, and insights—including hard-earned lessons about licensing, funding structures, and institutional pressures—Bairoch made a compelling case for recognizing the enduring value of human expertise. He closed by celebrating Cellosaurus, a curated knowledge resource encompassing over 166,000 cell lines, underscoring how such efforts remain essential infrastructure for the life sciences.

If you missed the keynote or would like to revisit it, it will be available in the ISMB/ECCB On-Demand Library within 24 hours.

Session Recaps

BOSC

The Bioinformatics Open Source Conference, BOSC (open-bio.org/events/bosc), is one of the oldest COSIs; this year it celebrates its 26th birthday! Today’s program began with a welcome from chair Nomi Harris, followed by an overview of BOSC’s parent organization, the Open Bioinformatics Foundation, by OBF President Peter Cock. The opening session also included a tribute to Peter Amstutz, a co-founder of the Common Workflow Language and very active member of the bioinformatics open-source community who passed away recently. Peter contributed his energy and vision to many BOSCs and CollaborationFests.

The first BOSC keynote talk was delivered by Dr. Christine Orengo: “Working together to develop, promote and protect our data resources: Lessons learnt developing CATH and TED.” Dr. Orengo is the Vice President of the ISCB and was previously the ISCB’s first female President. Dr. Orengo’s talk covered the history of CATH (which is celebrating its 30th anniversary) and the insights CATH and TED provided about protein structure and function, while also providing a model of how to bring the community together to sustain a resource. Interestingly, this also involved working together with competitors to improve each other's approaches.

BOSC’s packed first-day schedule included sessions focusing on topics in open science and open-source bioinformatics, including analytic tools, pipelines, and platforms. Day 1 closed with a session on open data which highlighted the need for AI-readiness and interoperability.

Be sure to join us tomorrow, when we partner with the Bio-Ontologies and Knowledge Representation (BOKR) COSI, and don’t miss our closing panel on Data Sustainability!

EvolCompGen

Presentations in today's EvolCompGen track treated several synergistic themes. The first theme focused on fast reconstruction of tumor cell evolution, including efficient selection of molecular features in various data types and identification structural variants. It was striking that presentations explored the variety of molecular data that can be used for tracking cancer progression.

The second main theme approached similar evolutionary questions on a very different time scale. These included phylogeny- and orthology-related studies, covering issues important for function prediction, and phylogenetic sequence and tree based methods for investigating protein family evolution, with particular attention to scalability in the face of the data deluge. Presentations in the session used a refreshing variety of computational techniques, ranging from machine learning, Bayesian statistics, algorithm theory to combinatorial optimization.

🎉Youth Bioinformatics Symposium Winner

Congratulations to Zeyu Peter Yao from AlphaMind Club, Singapore, for winning the 2025 YBS Student challenge with their submission "Explainable Subcellular Localization Predictor"!

Important Lunch Reminders

Food Reminder:
To make sure there’s enough for everyone, attendees are reminded to take only one sandwich, one bag of crisps, one piece of fruit, and one drink. With a full house each day, your cooperation helps ensure all participants are fed and cared for. Thank you for respecting these limits.

Allergen Station:
If you're looking for ingredient details, visit the dedicated allergen station in Hall 2 (immediately to the right as you enter). The catering staff are ready to help, and this setup is designed to reduce wait times for all.

Quick Reminders

• Talk and poster presenters: Please review the details found on the Presenter Information Page.
• Having trouble accessing the virtual platform?
  • Make sure you’re logged in using the correct email address. Remember: You must use the email you used to register for the conference in order to access the virtual platform.
  • Refresh your browser! Clear your cache/cookies and try again. 
  • Try a different browser. Chrome works best.
  • If you're still experiencing issues, please reach out to [email protected]

Coming Up Tomorrow, Tuesday, July 22

• 7:30am – Serene Stretch Symposium
• 8:40am – Welcome and Day 3 Distinguished Keynote: James Zou (ISCB 2025 Overton Prize Award winner)
• 10:00am and 4:00pm – Caffeinate and Connect with Posters and Exhibitors
• 1:00pm – Lunch / LGBTQI+ Meet-Up
• Sessions starting at 11:20am:
  • 3DSIG
  • BOSC
  • BOKR
  • CompMS
  • CSI
  • EvolCompGen
  • Function
  • MLCSB
  • NetBio
  • SysMod
  • Tech Track
  • TransMed
• 6:00pm – Success Circles

Sunday, July 20: ISMB/ECCB Day 1 Highlights and Recap

Welcome back to ISMB/ECCB! After a great opening keynote and fantastic networking reception, we hope you're looking forward to several more days of science.

Day 1 of the ISMB/ECCB 2025 conference started on a high note with 8 in-person tutorials, the Student Council Symposium, the Youth Bioinformatics Symposium, and the Career Fair!

Keynote Address: John Jumper

In his keynote, “Predicting the universe of biomolecular interactions with artificial intelligence,” Dr. John Jumper walked attendees through the evolution of the AlphaFold project.

Jumper shared insights into the technical and conceptual milestones behind each generation of AlphaFold, including innovations like rawMSA masked language models, Evoformer modules, and the importance of self-distillation. He emphasized that no single breakthrough carried the project; instead, AlphaFold’s success came from a steady accumulation of improvements and a methodology rooted in biological intuition and empirical iteration. AlphaFold 3 now aims to extend the success of its predecessors, building on the insights gained from earlier versions.

If you missed it—or just want to watch it again—the full keynote will be available in the ISMB/ECCB On-Demand Library within 24 hours.

Quick Reminders

• The PDF of the conference programme can be found here. 
• Talk and poster presenters: Please review the details found on the Presenter Information Page.
• WiFi Access: The WiFi info can be found on the back of your badge, but just in case:
  • Network: ISMBECCB2025
  • Password: 2025ISMBECCB
• Having trouble accessing the virtual platform?
  • Make sure you’re logged in using the correct email address. Remember: You must use the email you registered for the conference with in order to access the virtual platform.
  • Refresh your browser! Clear your cache/cookies and try again.
  • Try a different browser.
  • If you're still experiencing issues, please reach out to [email protected]

Navigating the Virtual Platform

ISMB/ECCB 2025 is powered by JUNO. While it works on all browsers, JUNO works best on a Chrome browser. To have the best experience, viewing virtually or participating on-site using the platform feature, be sure your device is operating the latest version of Chrome.

Missed a Session?

Sessions (with author permissions) have been recorded and will be part of the on-demand library. You can view the available sessions at https://iscb.junolive.co/ISMB/On-Demand 24 hours AFTER the session has been completed.

After the conference, we will work to edit the live session recording into individual videos. All registered participants of this event will have exclusive access to the conference content and will be able to log in at any time to view a recording!

Coming Up Tomorrow, Monday, July 21

• 7:30am – Serene Stretch Symposium
• 8:40am – Welcome and Day 2 Distinguished Keynote Amos Bairoch (2025 ISCB Accomplishments by a Senior Scientist Award winner)
• 10:00am and 4:00pm – Caffeinate and Connect with Posters and Exhibitors
• 1:00pm – Lunch / Bioinfo4Women Meet-Up
• Sessions starting at 11:20am:
  
  • 3DSIG
  • Bioinformatics in the UK
  • BOSC
  • DREAM Challenges
  • EvolCompGen
  • Fellows Presentation
  • GenCompBio
  • ISCB-China Workshop
  • MLCSB
  • NIH Track on GenAI, Cyberinfrastructure, Digital Twins, and Quantum Computing
  • Publication—Navigating Journal Submissions (ends at 1:00pm)
  • Tech Track
  • VarI
  • Wikipedia Edit-a-thon
• 6:00pm – Bioinformatics in the UK Reception (ticketed event)

Calling all computational biologists: are you ready to dive into the future of discovery?

10x Genomics is thrilled to be heading to Liverpool for ISMB / ECCB 2025, with an inspiring program and a team of 10x-perts. We look forward to exploring the future of discovery together!

We invite all computational biologists to learn how cutting-edge single cell and spatial technologies are unlocking unprecedented biological insights. Swing by Booth #31 to connect with our team of scientists, meet data experts, and see demos. Learn how we're advancing the frontiers of biology with scalable, high-resolution tools that speak your language: data and impact.

See the full program below:

10x Genomics at ISMB / ECCB 2025

Booth #31

July 21 | 3:20 PM | Room 11BC

Tech Track talk "Revving up insights in single cell and spatial exploration", by Stephen Williams (10x Genomics) and Severin Dicks (NVIDIA). Join and get inspired by the latest innovations powering the next wave of discovery.

July 21 | Booth #31

Demo sessions

Visit our booth for expert tips and tricks on data analysis, led by our Applied Bioinformatics Scientist, Roman Laddach. Don’t miss this chance to sharpen your skills - and pick up a complimentary pair of 10x-branded headphones!

Schedule

• 10:15 - 11:00 AM - Xenium In Situ

• 1:15 - 1:45 PM - Chromium Single Cell

• 4:15 - 4:30 PM - Visium Spatial

July 24 | 10:00-11:20 AM and 1:00-2:00 PM | Poster session D, number D-136
"Accelerating scRNA-seq Analysis: Automated cell type annotation using representation learning and vector search."

Stephen R. Williams, Fedor Grab, Govinda Kamath, Yerdos Ordabayev, Jeff Mellen, Patrick Roelli, Kristian Cibulskis, Erik Lehnert, Fen Xie, Miguel Covarrubias, Nur-Taz Rahman, Timothy Tickle, Emre Erhan, Nicolas Malfroy-Camine, Kevin Lydon, Mehrtash Babadi, Nigel Delaney

We’d love to hear about your experience with single cell and spatial data analysis and/or 10x technologies. Fill out a quick survey and have a chance to win a prize at our exhibition booth!

Fill out the survey now!

Can’t make it to Liverpool this year? We are happy to chat online in our virtual booth. Join the virtual booth.

We look forward to meeting you at ISMB / ECCB 2025,

10x Genomics EMEA Team

Help shape the future of ISCB

The polls are open! Help shape the future of our Society by casting your ballot for ISCB President and ISCB Vice President. 

Voting is open through July 27, 2025.

To vote, sign in to your MyISCB account and click the red Vote Now button.

Your participation is vital to the continued success and leadership of ISCB. Thank you for taking the time to make your voice heard!

We’re pleased to share that the ISMB/ECCB 2025 Conference Programme is now available!

Inside, you’ll find:

• A message from the ISCB President

• Highlights of 2025 ISCB award recipients

• A welcome from this year's conference chairs

• Abstracts from our Distinguished Keynotes

• Detailed schedules for COSI tracks and special sessions

Plus: The programme includes a clickable Table of Contents to help you easily navigate the PDF.

We look forward to welcoming you to Liverpool and to another engaging and inspiring ISMB/ECCB meeting!