Weekly AI/ML & Biotech Digest — Sep 21 to Sep 27, 2026

Curated weekly digest of notable AI/ML and biotech developments. Flagged items are manually selected; remaining items are the week's most recent.

🧬 Biotech

• ★ SurfGraphPro: Integrating Protein Language Models with Geometric Deep Learning On Coarse Protein Surfaces for Binding Site Prediction — This work from my team introduced a new protein representation algorithm that bridges proteins structure model and language model. Our algorithm does not compute amino acid features computationally. Instead, it utilizes PLM embeddings plus protien surface contour coarse-grained graph model to replace the feature engineering. In test application focusing on protein binding interface prediction, we achieved state-of-the-art performance at a much faster (~18x-28x) speed.
• ★ GitHub - PacesaLab/BindCraft2: Easy to use suite for designing a wide range of protein binder modalities. — Easy to use suite for designing a wide range of protein binder modalities.
• ★ The Virtual Biotech: A multi-agent AI framework for therapeutic discovery and development — Drug development requires evidence integration across biological scales and modalities, but relevant tools are fragmented.
• ★ Deep-learning-based gene perturbation effect prediction does not yet outperform simple linear baselines — Recent research in deep-learning-based foundation models promises to learn representations of single-cell data that enable prediction of the effects of genetic perturbations.
• ★ Benchmarking biomedical foundation models — A transparent evaluation and proof of reproducibility, generalization and replicability of algorithms are the bedrock of method development in computational biology.
• ★ A theoretical separation between quantum computers & LLMs — Recent research further demonstrates the theoretical abilities of quantum computing
• ★ Artificial intelligence and machine learning in nanoparticle drug delivery systems
• ★ A consensus-based guideline for personalized bacteriophage therapy — This is a consensus from the Association of the Scientific Medical Societies in Germany proposing a guideline for personalized bacteriophage therapy. With the increasing cases of AMR bacteria pathogens, bacteriaphage is evovlving as an alternative to conventional anti infection therapeutics. This consensus reflects the accelerating marching order on this front.
• ★ This team combined single cell lipidomics and use GNN models to connnect most nearest neighbors in lipidomics profiling results to differentiate healthy and cancer cells from peritoneal metastasis. They developed a classifer that could potentially work as a diagnostic tool.
• ★ The next big questions in immunology