5arXiv cs.LG (Machine Learning)·
Linear probes on Evo 2 genomic model detect antimicrobial resistance in metagenomic data for biosecurity screening
Researchers trained lightweight linear and attention probes on frozen activations from the Evo 2 genomic foundation model to screen metagenomic data for biosecurity-relevant signals, without fine-tuning the base model. The probes achieve strong discrimination for antimicrobial resistance detection (ROC-AUC up to 0.977 with attention probing) and moderate performance on bacterial virulence, and retain performance on simulated short reads. The work positions embedding-based probes as a fast, low-cost first-pass layer for metagenomic biosurveillance, while also mapping current limits including weak recoverability of AMR labels from Evo 1.5-generated sequences.
Related guides (2)
Related events (8)
EvoStruct: Bridging Evolutionary and Structural Priors for Antibody CDR Design via Protein Language Model Adaptation
EvoStruct addresses vocabulary collapse in GNN-based antibody CDR design by combining a frozen protein language model with an E(3)-equivariant GNN through a cross-attention adapter. The method introduces progressive PLM unfreezing and R-Drop consistency regularization to recover functionally important amino acid diversity. On CHIMERA-Bench, EvoStruct improves sequence recovery by 16%, reduces perplexity by 43%, and achieves 2.3x greater amino acid diversity compared to the best GNN baselines.
AlphaGenome: DeepMind's Unified DNA Sequence Model for Regulatory Variant-Effect Prediction
DeepMind has introduced AlphaGenome, a new unified DNA sequence model designed to advance regulatory variant-effect prediction and improve understanding of genome function. The model is now available via API, making it accessible to researchers. AlphaGenome represents a significant step in applying large-scale AI to genomics, particularly for interpreting non-coding regulatory regions of the genome.
ABC-Bench: Agentic biosecurity benchmark finds LLM agents surpass median expert humans on dual-use biology tasks
Researchers introduce ABC-Bench, a benchmark evaluating LLM agents on biosecurity-relevant biology tasks including liquid-handling robot programming, DNA fragment design, and evasion of DNA synthesis screening. All tested agents outperformed the median expert human baseline across all three tasks. Wet-lab validation confirmed that OpenAI's o4-mini-high produced scripts that successfully assembled DNA on an OpenTrons robot. The results highlight a meaningful shift in the biosecurity risk landscape as AI agents acquire practical wet-lab-adjacent capabilities.
MetaSyn benchmark reveals critical screening bottleneck in LLM-based meta-analysis pipelines
Researchers introduce MetaSyn, a dataset of 442 expert-curated meta-analyses from Nature Portfolio journals, paired with a 140k-article PubMed retrieval corpus, PI/ECO criteria, verified positives, and hard negatives. Benchmarking twelve pipeline configurations — nine RAG variants and a protocol-driven agent — shows that despite 90.9% retrieval recall at K=200, no system recovers more than 52.7% of ground-truth included studies. The core failure is LLMs' inability to reliably distinguish eligible studies from topically similar but criteria-failing distractors. The paper argues that end-to-end scores obscure where pipelines break down and proposes stage-attributed metrics.
Measuring AI's capability to accelerate biological research
OpenAI introduces a real-world evaluation framework designed to measure how AI systems can accelerate biological research in wet lab settings. The work uses GPT-5 to optimize a molecular cloning protocol as a concrete demonstration case. The framework explicitly addresses both the potential benefits and biosecurity risks of AI-assisted experimentation, positioning this as a dual-use capability assessment.
Google's AlphaGenome Interprets Non-Coding DNA That Regulates Genetic Expression
Google has released AlphaGenome, an open-weights model that interprets the ~98% of human and mouse genomes that regulate gene expression rather than coding for proteins. The model takes up to 1 million DNA base pairs as input and outputs roughly 6,000 human and 1,000 mouse gene properties, using a CNN-transformer-CNN architecture trained via ensemble distillation from 64 pretrained models. Across 50 evaluations, AlphaGenome matched or exceeded prior models in 47 cases, and correctly predicted expression changes associated with T-cell acute lymphoblastic leukemia. Weights, API, and inference code are freely available for noncommercial use.
LLM-guided MAP-Elites evolution improves medical decision pipelines at inference time
Researchers propose using LLM-guided MAP-Elites evolutionary search as an inference-time alternative to fine-tuning for adapting LLMs to clinical workflows, formulating triage, consultation, and image classification as evolutionary searches over executable artifacts. Across three medical settings, evolved programs substantially outperform manually designed baselines: triage accuracy improves from 77.3% to 87.1% and emergency recall from 0.60 to 0.97, with gains also shown on MIMIC-ESI, iCRAFTMD, and PneumoniaMNIST. The approach works across Llama-3, Qwen-3.5, and Gemma-4 backbones and produces interpretable program-level mechanisms rather than superficial prompt changes.
Finding the molecular switches behind new infectious diseases
DeepMind's Co-Scientist AI tool is being used by researcher Clare Bryant to identify genetic triggers in emerging infectious diseases. The application demonstrates Co-Scientist's utility in accelerating biological discovery, specifically in understanding molecular mechanisms underlying new pathogens. This represents a concrete scientific use case for AI-assisted research in infectious disease biology.