Papers for

computational biology engineers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Biosynthetic gene cluster benchmark compares multi-scale models and tasks

Data-Scarce, Multi-Granular, Multimodal: Benchmark Design for Biosynthetic Gene Clusters

Abstract: Biosynthetic gene clusters (BGCs) are co-located genes that encode the biosynthesis of specialized metabolites, an important source of antibiotics, anticancer agents, immunosuppressants, and agricultural bioactives. Deep learning, particularly self-supervised foundation models, has spurred interest in BGC sequence modeling, but evaluation has lagged behind: existing benchmarks often rely on coarse classification over small curated datasets, providing limited discrimination among models and insight into downstream utility. We propose a benchmark-design framework in which an informative benchmark should be discriminative, separating models with statistical confidence, and applicable, spanning scientifically meaningful tasks under different levels of generalization. We instantiate this framework as BGC-Bench, which derives five tasks from MIBiG, ranging from A-domain substrate prediction to BGC-molecule retrieval, evaluates them under genotype- and phenotype-shift splits, includes an active-learning setting for label-scarce discovery, and is easily extensible to new tasks and encoders. BGCs further provide a shared testbed across granularities and modalities: BGC-Bench compares twelve encoders on nucleotide, amino-acid, or Pfam-domain sequences, including compositional baselines for each input type, and combines BGC and chemical encoders for cross-modal retrieval. No single representation dominates: the best granularity depends on the biological scale of the task, and pretrained encoders do not consistently outperform other representations across tasks and splits. Active-learning experiments show that most tasks remain data-limited, encoder rankings change with labeling budget, and acquisition strategies yield modest gains. These results show that BGC model evaluation requires task-diverse, shift-aware benchmarks, and the framework can be generalized to benchmark design beyond BGCs.

Sun 1 NovArtificial Intelligence
The gist
Biosynthetic gene clusters (BGCs) are groups of genes that work together to produce useful molecules like antibiotics. The authors created a new testing system called BGC-Bench to better evaluate computer models that predict BGC functions and related molecules. This system uses various tasks that reflect real scientific challenges and compares different ways of representing BGC data, like DNA or protein patterns. Their findings show no single best way to model BGCs for all tasks, and that many tasks still need more data for better model training. This benchmark helps guide future improvements in using AI to understand and discover important natural products.
Open → 2611.02275v1

Cell Painting predictions improve by weighing and reasoning on evidence

From Retrieval to Reasoning: Agentic Mechanism Prediction from Cell Painting Profiles

Abstract: Cell Painting is a high-content morphological profiling assay widely used for phenotype-based biological inference, with mechanism of action (MOA) prediction as a central application. Existing approaches largely formulate Cell Painting-based inference as representation matching, assigning predictions from nearby reference perturbations in morphological feature space. However, retrieved neighbors are often noisy and partially misleading evidence due to batch effects, non-specific cytotoxicity, phenotypic convergence, and source-dependent variability. We reformulate Cell Painting-based MOA prediction as a calibrated evidence reasoning problem, where retrieved neighbors are treated as uncertain observations that must be evaluated, compared, and sometimes rejected before supporting a mechanistic conclusion. We propose PhenoAIR, a reliability-aware multi-agent framework that maintains a candidate-centric evidence memory and performs controller-guided refinement over phenotype- and mechanism-side evidence. PhenoAIR uses offline reference-set calibration to weight evidence by source reliability, phenotype stability, and mechanism-level confusion. We evaluate PhenoAIR on a benchmark constructed from JUMP Cell Painting profiles and annotations, covering controlled, realistic, and discovery-oriented open-world MOA prediction settings. PhenoAIR outperforms representation-matching and LLM-based baselines across all settings.

Tue 29 SeptArtificial Intelligence
The gist
Predicting how drugs work using cell images can be tricky because similar-looking cells don’t always mean the same drug effect. The authors show that instead of just matching similar profiles, it’s better to carefully consider and weigh different pieces of evidence before deciding. They built a system called PhenoAIR that judges how reliable each piece of evidence is and uses that to make better predictions. This approach worked better than methods that only compare cell profiles or use language models.
Open → 2609.36406v1