v311: Proceedings of MLCB 2025

2026-06-04 · Source: Proceedings of Machine Learning Research · Field: Science & Research — Life Sciences & Biology, Mathematics & Computational Sciences, Artificial Intelligence & Machine Learning · Depth: Expert, short

Summary

Volume 311 of the Proceedings of the 20th Machine Learning in Computational Biology meeting, held on 10-11 September 2025 in New York, NY, USA, presents 23 research papers exploring diverse applications of machine learning in biological contexts. Key contributions include GeST, a Generative Pretrained Transformer for cellular spatial context learning, and TCR-ECHO, which uses evolutionary cross-attention for TCR-peptide binding prediction. Other papers introduce PerTurboAgent, an LLM-based agent for designing Perturb-Seq experiments, and GOLF, a generative AI framework for pathogenicity prediction of Myocilin OLF variants. The volume also covers topics such as unsupervised evolutionary cell type matching, genomic language models for promoter indel effects, context-dependent genetic modifiers of Huntington's Disease, and AI-based histopathology phenotyping for breast cancer morphology. Further research addresses challenges in single-cell microscopy, automated seizure detection, and personalized combination drug screening.

Key takeaway

For research scientists and ML engineers in computational biology, staying current with these diverse advancements is crucial. You should explore integrating generative AI, such as Transformers and LLMs, into your projects for tasks like cellular spatial context learning, experimental design, and genomic prediction. Consider how foundation models can accelerate cross-species analyses. Evaluating new methods like evolutionary cross-attention for binding prediction or variational graph auto-encoders for denoising single-cell data can enhance your research capabilities.

Key insights

Machine learning, particularly generative AI, is rapidly advancing computational biology applications.

Principles

• Generative models offer new ways to learn biological context.
• AI agents can streamline complex experimental design.
• Foundation models enable cross-species genomic predictions.

In practice

• Investigate Transformers for cellular spatial context.
• Employ LLMs for automated biological experiment design.
• Leverage genomic language models for zero-shot predictions.

Topics

• Computational Biology
• Generative AI
• Genomic Language Models
• Single-Cell Analysis
• Disease Modeling
• Protein Binding Prediction

Best for: AI Scientist, Research Scientist, Machine Learning Engineer

Related on AIssential

• Generative AI analyzes medical data faster than human research teams — Generative AI can accelerate medical data analysis, potentially outperforming human teams in speed and accuracy.
• Artificial intelligence and biology: AI’s potential for launching a novel era for health and medicine — AI is transforming biology by enabling large-scale analysis of complex interactions, moving towards causal understanding.
• The scientist using AI to hunt for antibiotics just about everywhere — AI-driven peptide discovery from diverse biological sources offers a novel approach to combat antimicrobial resistance.
• Is AI Drug Discovery Becoming a Data Infrastructure Race? — AI drug discovery's primary bottleneck is the availability of diverse, relevant biological training data, not model architecture or compute.
• 🗞️ Techie uses ChatGPT and AlphaFold to build DIY mRNA cancer vaccine, saves dog — AI tools empower individuals without specialized training to conduct complex scientific research and develop novel solutions.
• Accelerating discovery of liver disease mechanisms — AI-driven literature analysis can uncover novel biological hypotheses and candidate therapies for complex diseases.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Proceedings of Machine Learning Research.