Skip to content
#explainable ai Review Open access

AutoScreen: AI Co-Scientist System for Target Discovery in Functional Genomics

Sep 2026 · bioRxiv · 0 citations · 32 references
Biology

TL;DR

This work introduces AutoScreen, an AI co-scientist system supporting target discovery through both Pre-screen Design, which constructs perturbation libraries de novo from free-text research descriptions, and Post-screen Analysis, which re-ranks experimental screen hits by integrating statistical scores with biological context.

Abstract

Target discovery in functional genomics remains largely manual and time-consuming, lacking systematic tools for efficient and reproducible gene-level hypothesis generation. We introduce AutoScreen, an AI co-scientist system supporting target discovery through both Pre-screen Design, which constructs perturbation libraries de novo from free-text research descriptions, and Post-screen Analysis, which re-ranks experimental screen hits by integrating statistical scores with biological context. AutoScreen leverages the complementary strengths of multiple specialist agents that perform deep research into multi-modal evidence, information restructuring, parallel searches across >26 biomedical databases, evidence synthesis, and target review to provide transparent, explainable gene prioritization with pipeline provenance. Across 320 genome-scale CRISPR screens as expert-curated benchmarks, AutoScreen achieved a ∼19% increase in validated-hit recovery among its top 100 predictions, relative to the strongest agent baseline, and required a 1.2-fold smaller library to recover the same number of hits at the top-500 reference point. AutoScreen reached mean average precision more than two orders-of-magnitude above random baseline. Further, we validated AutoScreen in cancer immune-evasion case studies focusing on natural killer (NK) and T-cell therapeutics. AutoScreen recovered NK-resistance genes that were initially lower-ranked in a leukemia screen, moving MUC1, PDPN, and LRRC15 from raw ranks of 118, 81, 1384 to 5, 44, 659, respectively. In follow-up tumor killing assay with primary human NK cells, individual perturbation validated all three hits successfully. Next, in prospective benchmarking across two cytotoxic T-cell-killing screens, AutoScreen recovered 77.1% of ground-truth hits called by the consensus of two gold-standard analysis pipelines (FDR<0.1), achieving 8% improvement over the strongest general-purpose LLM agent baseline. Finally, we re-analyzed >500 public datasets to construct the AutoScreen Resource Hub, a growing knowledge base of pre-computed, annotated reports for CRISPR screens, RNA-seq differential expression, and gene-level UK Biobank genome-wide association studies. This agentic AI approach enables real-time genomics benchmark construction that are continuously updated, expanded, for evaluating frontier AI co-scientists. Overall, AutoScreen enables AI-powered target discovery to be more auditable, scalable, extensible, and reproducible.

Read PDF

Similar papers

Open access Aug 2026

Perturb-ME: Scalable mechanism discovery from phenotype-enriched genome-wide screens

Perturb-ME, along with agentic interpretation, provide a scalable framework for comprehensive functional discovery from phenotype-enriched genetic screens and combines genome-scale CRISPR screening, phenotype-based enrichment and multimodal single-cell profiling.

Han-Chen Wang, Jiacheng Gu, Chris J. Frangieh et al. · 0 citations
Open access Sep 2026

Iterative Gene Enrichment Analysis: interpretable networks for human and AI-assisted biological insights

Background Over-representation analysis (ORA) is widely used to interpret gene lists from high-throughput biological experiments. However, ORA often produces long and fragmented lists of enriched terms that are difficult to translate into coherent, testable biological hypotheses. This challenge is amplified by the rapi...

Maxim V. Kuleshov, Yair Benita · 0 citations
Open access Sep 2026

TigerAI: An AI-powered genetic evidence platform to support clinical development

A novel domain-grounded instruction framework is developed to systematically evaluate GPT-5 for producing genetic evidence relevant to clinical trial success and introduces TigerAI, a dual-purpose platform for AI-powered genetic evidence that benchmarks emerging state-of-the-art LLMs and provides an accessible service...

Zi-Chen Zhang, Wan-Heng Zhang, Xiao-Chen Yang et al. · 0 citations
Review Open access Sep 2026

Pathway-driven target prioritisation in drug discovery.

Genome-scale association studies and functional screens routinely implicate hundreds of candidate genes per disease, yet only a few will be clinically validated as drug targets. Choosing which to pursue is a central drug-discovery decision that depends on interpreting each candidate in its biological context. Curated p...

Polina Rusina, D. Ochoa, Franck Rapaport et al. · 0 citations
Open access Sep 2026

scBaseCount: An AI agent-curated, standardized, auto-updated single-cell data repository.

Single-cell RNA sequencing has transformed cell biology by enabling precise transcriptomic measurements of individual cells. The Sequence Read Archive (SRA) is the largest public repository of sequencing reads, yet much of it remains underutilized due to unstandardized metadata. Here, we introduce scBaseCount, a databa...

Nicholas D. Youngblut, Christopher Carpenter, Arshia Nayebnazar et al. · 7 citations
Open access Sep 2026

A scalable, high-throughput glue perturbation screening platform for molecular glue discovery

Summary The discovery of molecular glue degraders (MGDs) is undergoing a paradigm shift from serendipitous discovery toward empirical design. However, efficiently prioritizing active leads from synthetic libraries while simultaneously confirming their E3 dependency remains a formidable challenge. In this study, we intr...

Di-Yun Huang, Ze-Yu Shuang, Lu Chen et al. · 0 citations

Related blog posts

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

GPT-Lab Nov 13, 2026

TenderIntell at ICSOB 2026: Three Days in Gothenburg

At ICSOB 2026 in Gothenburg, we presented TenderIntell, our work on multi-agent support for tendering. This post looks back at the conference, the idea behind a panel of three AI reviewers who score each proposal independently, and why evaluating agents reliably is the question we keep coming back to. The post TenderIntell at ICSOB 2026: Three Days in Gothenburg appeared first on GPT-Lab.

MIT News · Artificial Intelligence Nov 13, 2026

Helping robots fit into the human workplace

Founded by Anthony Jules ’92, SM ’92 and Professor Emeritus Rodney Brooks, Robust AI’s robots are designed to collaborate with humans in factories and warehouses.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.