AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents

• URL: http://arxiv.org/abs/2605.10876v1
• Date: Mon, 11 May 2026 17:27:16 GMT
• Title: AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents
• Abstract summary: We present AssayBench, a benchmark for phenotypic screen prediction built from 1,920 publicly available CRISPR screens.<n>We formulate the screen prediction task as a gene rank prediction for each screen and introduce the adjusted nDCG, a continuous metric for comparing performance.<n>Our evaluation shows that existing methods remain far from empirically estimated performance ceilings.
• Score: 45.98505638696823
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in machine learning and large-scale biological data collections have revived the prospect of building a virtual cell, a computational model of cellular behavior that could accelerate biological discovery. One of the most compelling promises of this vision is the ability to perform in silico phenotypic screens, in which a model predicts the effects of cellular perturbations in unseen biological contexts. This task combines heterogeneous textual inputs with diverse phenotypic outputs, making it particularly well-suited to LLMs and agentic systems. Yet, no standard benchmark currently exists for this task, as existing efforts focus on narrower molecular readouts that are only indirectly aligned with the phenotypic endpoints driving many real-world drug discovery workflows. In this work, we present AssayBench, a benchmark for phenotypic screen prediction, built from 1,920 publicly available CRISPR screens spanning five broad classes of cellular phenotypes. We formulate the screen prediction task as a gene rank prediction for each screen and introduce the adjusted nDCG, a continuous metric for comparing performance across heterogeneous assays. Our extensive evaluation shows that existing methods remain far from empirically estimated performance ceilings and zero-shot generalist LLMs outperform biology-specific LLMs and trainable baselines. Optimization techniques such as fine-tuning, ensembling, and prompt optimization can further improve LLM performance on this task. Overall, AssayBench offers a practical testbed for measuring progress toward in silico phenotypic screening and, more broadly, virtual cell models.

Related papers

• MMBU: A Massive Multi-modal Biomedical Understanding Benchmark to Probe the Perception Capabilities of Vision-Language Models [83.50100003741628]
  Vision and language models (VLMs) hold immense promise to transform biomedical imaging.<n>We introduce the Massive Multimodal Biomedical Understanding (MMBU) benchmark.<n>It is the largest vision and language benchmark to date, covering 35 submodalities with rich structured metadata.
  arXiv  Detail & Related papers  (2026-06-04T20:24:47Z)
• Influence-Guided Symbolic Regression: Scientific Discovery via LLM-Driven Equation Search with Granular Feedback [56.69850045068714]
  We introduce textitInfluence-Guided Regression (IGSR), a method that frames equation discovery as an iterative two-step process.<n>We demonstrate IGSRs effectiveness on a diverse suite of benchmarks, including LLM-SRBench, pharmacological PKPD models, an epidemiological simulation, and real-world genomic data.
  arXiv  Detail & Related papers  (2026-05-27T23:48:01Z)
• ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding [56.94419746470799]
  Large Language Models (LLMs) have revolutionized scientific text processing, but exhibit a significant capability gap when interpreting chemical reaction diagrams.<n>We propose the Chemical Visual Activation (ChemVA) framework, which employs a Visual Anchor mechanism to ground functional groups.<n>We evaluate our approach on OCRD-Bench, a newly constructed dataset featuring dense visual-semantic contexts.
  arXiv  Detail & Related papers  (2026-05-17T01:12:50Z)
• Lessons Learned from Deploying Adaptive Machine Learning Agents with Limited Data for Real-time Cell Culture Process Monitoring [4.920530441985874]
  This study explores the deployment of three machine learning (ML) approaches for real-time prediction of glucose, lactate, and ammonium concentrations in cell culture processes.<n>The research addresses challenges associated with limited data availability and process variability.<n>Two industrial case studies are presented to evaluate the impact of varying bioprocess conditions on model performance.
  arXiv  Detail & Related papers  (2025-08-29T22:26:13Z)
• CellVerse: Do Large Language Models Really Understand Cell Biology? [74.34984441715517]
  We introduce CellVerse, a unified language-centric question-answering benchmark that integrates four types of single-cell multi-omics data.<n>We systematically evaluate the performance across 14 open-source and closed-source LLMs ranging from 160M to 671B on CellVerse.
  arXiv  Detail & Related papers  (2025-05-09T06:47:23Z)
• Predicting gene essentiality and drug response from perturbation screens in preclinical cancer models with LEAP: Layered Ensemble of Autoencoders and Predictors [4.882734501598445]
  Existing predictive models suffer from limited, generalisability and interpretability.<n>We introduce a framework of Layered Ensemble of Autoencoders and Predictors (LEAP)<n>LEAP consistently improves prediction performances in unscreened cell lines across modelling strategies.
  arXiv  Detail & Related papers  (2025-02-21T18:12:36Z)
• GENERator: A Long-Context Generative Genomic Foundation Model [66.46537421135996]
  We present GENERator, a generative genomic foundation model featuring a context length of 98k base pairs (bp) and 1.2B parameters.<n>Trained on an expansive dataset comprising 386B bp of DNA, the GENERator demonstrates state-of-the-art performance across both established and newly proposed benchmarks.<n>It also shows significant promise in sequence optimization, particularly through the prompt-responsive generation of enhancer sequences with specific activity profiles.
  arXiv  Detail & Related papers  (2025-02-11T05:39:49Z)
• scReader: Prompting Large Language Models to Interpret scRNA-seq Data [12.767105992391555]
  We propose an innovative hybrid approach that integrates the general knowledge capabilities of large language models with domain-specific representation models for single-cell omics data interpretation.<n>By inputting single-cell gene-level expression data with prompts, we effectively model cellular representations based on the differential expression levels of genes across various species and cell types.
  arXiv  Detail & Related papers  (2024-12-24T04:28:42Z)
• Efficient Fine-Tuning of Single-Cell Foundation Models Enables Zero-Shot Molecular Perturbation Prediction [0.9433990107181004]
  In this study, we leverage single-cell foundation models (FMs) pre-trained on tens of millions of single cells.<n>We introduce a drug-conditional adapter that allows efficient fine-tuning by training less than 1% of the original foundation model.
  arXiv  Detail & Related papers  (2024-12-18T03:42:20Z)
• Weakly Supervised Set-Consistency Learning Improves Morphological Profiling of Single-Cell Images [0.6491172192043603]
  We propose a set-level consistency learning algorithm, Set-DINO, to improve learned representations of perturbation effects in single-cell images. We conduct experiments on a large-scale Optical Pooled Screening dataset with more than 5000 genetic perturbations.
  arXiv  Detail & Related papers  (2024-06-08T00:53:30Z)
• Benchmarking Machine Learning Robustness in Covid-19 Genome Sequence Classification [109.81283748940696]
  We introduce several ways to perturb SARS-CoV-2 genome sequences to mimic the error profiles of common sequencing platforms such as Illumina and PacBio. We show that some simulation-based approaches are more robust (and accurate) than others for specific embedding methods to certain adversarial attacks to the input sequences.
  arXiv  Detail & Related papers  (2022-07-18T19:16:56Z)
• Towards an Automatic Analysis of CHO-K1 Suspension Growth in Microfluidic Single-cell Cultivation [63.94623495501023]
  We propose a novel Machine Learning architecture, which allows us to infuse a neural deep network with human-powered abstraction on the level of data. Specifically, we train a generative model simultaneously on natural and synthetic data, so that it learns a shared representation, from which a target variable, such as the cell count, can be reliably estimated.
  arXiv  Detail & Related papers  (2020-10-20T08:36:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.