Le Cong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Le Cong has a total of 327 co-authors. Here are the top co-authors by number of shared publications:
- Mengdi Wang
Princeton University, USA
13 shared publications Xiaotong Wang
Department of Pathology, Stanford University School of Medicine, Stanford, USA
10 shared publicationsChengkun Wang
Department of Pathology, Department of Genetics, Stanford University School of Medicine, Stanford, California, United States of America
9 shared publicationsYuanhao Qu
Department of Pathology, Stanford University School of Medicine , Stanford , CA, 94305
9 shared publicationsMengdi Wang
Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA
7 shared publicationsNicholas W. Hughes
Department of Genetics, Stanford University School of Medicine, Stanford, USA
7 shared publications
Latest Publications
- Open Access
- 3 November 2026
- Published by MDPI AG in Preprints.org
Agentic Laboratories of the Future: Towards World Models for Scientific Discovery
Advances in scientific AI have accelerated hypothesis generation, prediction, and experimental design, but translating these capabilities into reliable physical experimentation remains a major bottleneck in scientific discovery. Although automation, high-throughput experimentation, foundation models, and cloud infrastructure have accelerated individual stages of the scientific workflow, they have not unified the discovery process. Scientists must still coordinate between computational models and physical laboratory systems to translate scientific designs into executable experiments and ensure their results are reliable. We argue that the next generation of laboratories will be agentic: environments in which scientists, AI systems, equipment and robotic platforms operate as collaborative discovery partners. We propose an architecture built around two complementary components: an agentic foundation that translates scientific designs into coordinated execution plans, and an evolving laboratory world model that represents physical state, predicts action outcomes, and incorporates experimental feedback. Together, they connect computational reasoning to observable and verifiable physical execution. Multimodal perception, robotics, and human–AI interfaces can make laboratory actions and evolving experimental conditions accessible to these systems, supporting adaptive execution and learning. We further propose an evaluation framework centered on physical grounding, execution fidelity, scientific validity, and adaptive coordination under human oversight, rather than autonomy alone. This Perspective outlines how agentic laboratories could connect scientific reasoning, physical experimentation, and trustworthy evidence within a human-in-the-lead discovery loop.
- 3 November 2026
- Published by MDPI AG in Preprints.org
Open AccessAgentic Laboratories of the Future: Towards World Models for Scientific Discovery
Advances in scientific AI have accelerated hypothesis generation, prediction, and experimental design, but translating these capabilities into reliable physical experimentation remains a major bottleneck in scientific discovery. Although automation, high-throughput experimentation, foundation models, and cloud infrastructure have accelerated individual stages of the scientific workflow, they have not unified the discovery process. Scientists must still coordinate between computational models and physical laboratory systems to translate scientific designs into executable experiments and ensure their results are reliable. We argue that the next generation of laboratories will be agentic: environments in which scientists, AI systems, equipment and robotic platforms operate as collaborative discovery partners. We propose an architecture built around two complementary components: an agentic foundation that translates scientific designs into coordinated execution plans, and an evolving laboratory world model that represents physical state, predicts action outcomes, and incorporates experimental feedback. Together, they connect computational reasoning to observable and verifiable physical execution. Multimodal perception, robotics, and human–AI interfaces can make laboratory actions and evolving experimental conditions accessible to these systems, supporting adaptive execution and learning. We further propose an evaluation framework centered on physical grounding, execution fidelity, scientific validity, and adaptive coordination under human oversight, rather than autonomy alone. This Perspective outlines how agentic laboratories could connect scientific reasoning, physical experimentation, and trustworthy evidence within a human-in-the-lead discovery loop.
- 22 October 2026
- Published by Springer Nature in Nature Reviews Methods Primers
- Vol. 6 (1) , 81
Agentic AI systems for scientific discovery
- 22 October 2026
- Published by Springer Nature in Nature Reviews Methods Primers
- Vol. 6 (1) , 81
Agentic AI systems for scientific discovery
- Top Cited Papers
- 20 August 2026
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 393 (6813) , eadz4351
Autonomous biomedical research with an artificial intelligence agent
Biomedical research is increasingly constrained by repetitive, fragmented workflows that slow discovery. We introduce Biomni, a general-purpose biomedical artificial intelligence agent that autonomously executes diverse research tasks. To map the biomedical action space, Biomni’s action-discovery agent mines tools, databases, and protocols from thousands of publications across 25 domains, building a unified agentic environment. Its general-purpose architecture integrates large language model reasoning with retrieval-augmented planning and code-based execution, dynamically composing workflows without predefined templates. Systematic benchmarking shows strong generalization across heterogeneous tasks—causal gene prioritization, drug repurposing, rare-disease diagnosis, microbiome analysis, and molecular cloning—without task-specific tuning. Real-world case studies demonstrate Biomni interpreting multimodal datasets, optimizing protein stability, orchestrating wet-lab instruments, and generating experimentally testable protocols. Biomni envisions artificial intelligence augmenting human scientists and accelerating discovery.
- 20 August 2026
- Published by American Association for the Advancement of Science (AAAS) in Science
- Vol. 393 (6813) , eadz4351
Top Cited PapersAutonomous biomedical research with an artificial intelligence agent
Biomedical research is increasingly constrained by repetitive, fragmented workflows that slow discovery. We introduce Biomni, a general-purpose biomedical artificial intelligence agent that autonomously executes diverse research tasks. To map the biomedical action space, Biomni’s action-discovery agent mines tools, databases, and protocols from thousands of publications across 25 domains, building a unified agentic environment. Its general-purpose architecture integrates large language model reasoning with retrieval-augmented planning and code-based execution, dynamically composing workflows without predefined templates. Systematic benchmarking shows strong generalization across heterogeneous tasks—causal gene prioritization, drug repurposing, rare-disease diagnosis, microbiome analysis, and molecular cloning—without task-specific tuning. Real-world case studies demonstrate Biomni interpreting multimodal datasets, optimizing protein stability, orchestrating wet-lab instruments, and generating experimentally testable protocols. Biomni envisions artificial intelligence augmenting human scientists and accelerating discovery.
- Open Access
- 6 August 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1) , 9442
Surfaceome CRISPR activation screening uncovers ligands regulating tumor sensitivity to NK cell killing
Natural killer (NK) cell-based immunotherapies are promising for cancer treatment due to their ability to eliminate cancer cells independently of antigen presentation and “off-the-shelf” utility. However, molecular determinants governing tumor susceptibility to NK cytotoxicity remain incompletely understood. Here we employ CRISPR activation (CRISPRa) screening to identify cancer cell surface regulators of NK killing. Using a surfaceome-focused library, we screen human and murine cancer cell lines co-cultured with NK cells, identifying known and novel ligands modulating NK cytotoxicity. Screens reveal established factors including CD43 and previously uncharacterized regulators CD44, PDPN, and Siglec-1/CD169. Validation with orthogonal approaches confirm that disruption of these factors alters NK killing susceptibility in vitro and in humanized mouse models. Mechanistically, we find that CD43-mediated NK resistance operates independently of its proposed interaction with Siglec-7, and that targeting CD43 on NK cells or CAR T cells substantially enhances cytotoxic activity against leukemia. These results establish gain-of-function surfaceome screening as a powerful tool for identifying therapeutic targets for NK cell-based immunotherapy.
- 6 August 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1) , 9442
Open AccessSurfaceome CRISPR activation screening uncovers ligands regulating tumor sensitivity to NK cell killing
Natural killer (NK) cell-based immunotherapies are promising for cancer treatment due to their ability to eliminate cancer cells independently of antigen presentation and “off-the-shelf” utility. However, molecular determinants governing tumor susceptibility to NK cytotoxicity remain incompletely understood. Here we employ CRISPR activation (CRISPRa) screening to identify cancer cell surface regulators of NK killing. Using a surfaceome-focused library, we screen human and murine cancer cell lines co-cultured with NK cells, identifying known and novel ligands modulating NK cytotoxicity. Screens reveal established factors including CD43 and previously uncharacterized regulators CD44, PDPN, and Siglec-1/CD169. Validation with orthogonal approaches confirm that disruption of these factors alters NK killing susceptibility in vitro and in humanized mouse models. Mechanistically, we find that CD43-mediated NK resistance operates independently of its proposed interaction with Siglec-7, and that targeting CD43 on NK cells or CAR T cells substantially enhances cytotoxic activity against leukemia. These results establish gain-of-function surfaceome screening as a powerful tool for identifying therapeutic targets for NK cell-based immunotherapy.
- 24 April 2026
- Published by Springer Nature in Nature Machine Intelligence
- Vol. 8 (4) , 559-574
Programmable RNA translation through deep learning-driven IRES discovery and de novo generation
- 24 April 2026
- Published by Springer Nature in Nature Machine Intelligence
- Vol. 8 (4) , 559-574
Programmable RNA translation through deep learning-driven IRES discovery and de novo generation
- Open Access
MedOS: AI-XR-Cobot World Model for Clinical Perception and Action
Medicine historically separates abstract clinical reasoning from physical intervention. We bridge this divide with MedOS, a general-purpose embodied world model. Mimicking human cognition via a dual-system architecture, MedOS demonstrates superior reasoning on biomedical benchmarks and autonomously executes complex clinical research. To extend this intelligence physically, the system simulates medical procedures as a physics-aware model to foresee adverse events. Generating and validating on the MedSuperVision benchmark, MedOS exhibits spatial intelligence for reasoning and action. Crucially, we demonstrate that this platform democratizes clinical expertise and narrows the performance gap between junior and senior physicians. MedOS transforms clinical intervention towards a collaborative discipline where human intuition and machine intelligence co-evolve.
Open AccessMedOS: AI-XR-Cobot World Model for Clinical Perception and Action
Medicine historically separates abstract clinical reasoning from physical intervention. We bridge this divide with MedOS, a general-purpose embodied world model. Mimicking human cognition via a dual-system architecture, MedOS demonstrates superior reasoning on biomedical benchmarks and autonomously executes complex clinical research. To extend this intelligence physically, the system simulates medical procedures as a physics-aware model to foresee adverse events. Generating and validating on the MedSuperVision benchmark, MedOS exhibits spatial intelligence for reasoning and action. Crucially, we demonstrate that this platform democratizes clinical expertise and narrows the performance gap between junior and senior physicians. MedOS transforms clinical intervention towards a collaborative discipline where human intuition and machine intelligence co-evolve.
- Open Access
- 14 January 2026
- Published by Oxford University Press (OUP) in Nucleic Acids Research
- Vol. 54 (2)
Compact bacterial recombination complexes drive efficient kilobase-scale knock-in in mammalian cells
Efficient homologous recombination, homology-directed repair (HDR), remains a major hurdle for precise genome editing in mammalian cells, particularly for kilobase-scale insertions. Bacterial recombineering proteins, such as RecE and RecT, offer potential solutions, but their activity in eukaryotic systems has been largely uncharacterized. Here, we identify Escherichia coli RecE (EcRecE) as a potent enhancer of HDR in mammalian cells. Targeted recruitment of EcRecE via CRISPR/Cas9 significantly increased HDR efficiency at multiple genomic loci across different cellular contexts, including human embryonic stem cells, achieving a 3–6-fold enhancement in the integration efficiency of kilobase-scale sequences. Furthermore, in combination with RecT and a catalytically inactive Cas9 (dCas9), applying functional domain engineering, we developed a dCas9-miniRecTE editor that enhances large-fragment integration without introducing double-strand breaks in human cells and primary mouse neurons, achieving ∼20% kilobase-scale knock-in efficiency. These results establish EcRecE as a versatile tool for improving precision genome engineering, with potential applications in therapeutic gene editing.
- 14 January 2026
- Published by Oxford University Press (OUP) in Nucleic Acids Research
- Vol. 54 (2)
Open AccessCompact bacterial recombination complexes drive efficient kilobase-scale knock-in in mammalian cells
Efficient homologous recombination, homology-directed repair (HDR), remains a major hurdle for precise genome editing in mammalian cells, particularly for kilobase-scale insertions. Bacterial recombineering proteins, such as RecE and RecT, offer potential solutions, but their activity in eukaryotic systems has been largely uncharacterized. Here, we identify Escherichia coli RecE (EcRecE) as a potent enhancer of HDR in mammalian cells. Targeted recruitment of EcRecE via CRISPR/Cas9 significantly increased HDR efficiency at multiple genomic loci across different cellular contexts, including human embryonic stem cells, achieving a 3–6-fold enhancement in the integration efficiency of kilobase-scale sequences. Furthermore, in combination with RecT and a catalytically inactive Cas9 (dCas9), applying functional domain engineering, we developed a dCas9-miniRecTE editor that enhances large-fragment integration without introducing double-strand breaks in human cells and primary mouse neurons, achieving ∼20% kilobase-scale knock-in efficiency. These results establish EcRecE as a versatile tool for improving precision genome engineering, with potential applications in therapeutic gene editing.
- Open Access
- 8 December 2025
- Published by Springer Nature in Nature Biomedical Engineering
- Vol. 10 (2) , 405
Publisher Correction: CRISPR-GPT for agentic automation of gene-editing experiments
- 8 December 2025
- Published by Springer Nature in Nature Biomedical Engineering
- Vol. 10 (2) , 405
Open AccessPublisher Correction: CRISPR-GPT for agentic automation of gene-editing experiments
- Open Access
- 26 November 2025
- Published by Springer Nature in Research Square
LabOS: The AI-XR Co-Scientist That Sees and Works With Humans
Modern science advances fastest when thought meets action. LabOS represents the first AI co-scientist that unites computational reasoning with physical experimentation through multimodal perception, self-evolving agents, and XR-enabled, embodied human-AI collaboration. To empower agentic AI with embodied intelligence, we built LabSuperVision, the first vision–language-model (VLM) benchmark spanning biomedical and materials science laboratories, designed to evaluate scientific perception and reasoning. This endowed LabOS with visual reasoning capabilities that surpass those of general-purpose models on laboratory-specific tasks. By connecting multi-model AI agents, smart glasses, and human-AI-robot collaboration, LabOS allows AI to see what scientists see, understand experimental context, and participate in real-time execution through immersive XR interaction and robotic autonomation. Across applications—from cancer immunotherapy target discovery to stem cell engineering—LabOS shows that AI can move beyond computational design to participation, turning the laboratory into an intelligent, collaborative environment where human and machine discovery evolve together.
- 26 November 2025
- Published by Springer Nature in Research Square
Open AccessLabOS: The AI-XR Co-Scientist That Sees and Works With Humans
Modern science advances fastest when thought meets action. LabOS represents the first AI co-scientist that unites computational reasoning with physical experimentation through multimodal perception, self-evolving agents, and XR-enabled, embodied human-AI collaboration. To empower agentic AI with embodied intelligence, we built LabSuperVision, the first vision–language-model (VLM) benchmark spanning biomedical and materials science laboratories, designed to evaluate scientific perception and reasoning. This endowed LabOS with visual reasoning capabilities that surpass those of general-purpose models on laboratory-specific tasks. By connecting multi-model AI agents, smart glasses, and human-AI-robot collaboration, LabOS allows AI to see what scientists see, understand experimental context, and participate in real-time execution through immersive XR interaction and robotic autonomation. Across applications—from cancer immunotherapy target discovery to stem cell engineering—LabOS shows that AI can move beyond computational design to participation, turning the laboratory into an intelligent, collaborative environment where human and machine discovery evolve together.
- Open Access
Securing the Language of Life: Inheritable Watermarks from DNA Language Models to Proteins
DNA language models have revolutionized our ability to understand and design DNA sequences--the fundamental language of life--with unprecedented precision, enabling transformative applications in therapeutics, synthetic biology, and gene editing. However, this capability also poses substantial dual-use risks, including the potential for creating pathogens, viruses, and even bioweapons. To address these biosecurity challenges, we introduce two innovative watermarking techniques to reliably track the designed DNA: DNAMark and CentralMark. DNAMark employs synonymous codon substitutions to embed watermarks in DNA sequences while preserving the original function. CentralMark further advances this by creating inheritable watermarks that transfer from DNA to translated proteins, leveraging protein embeddings to ensure detection across the central dogma. Both methods utilize semantic embeddings to generate watermark logits, enhancing robustness against natural mutations, synthesis errors, and adversarial attacks. Evaluated on our therapeutic DNA benchmark, DNAMark and CentralMark achieve F1 detection scores above 0.85 under various conditions, while maintaining over 60% sequence similarity to ground truth and degeneracy scores below 15%. A case study on the CRISPR-Cas9 system underscores CentralMark's utility in real-world settings. This work establishes a vital framework for securing DNA language models, balancing innovation with accountability to mitigate biosecurity risks.
Open AccessSecuring the Language of Life: Inheritable Watermarks from DNA Language Models to Proteins
DNA language models have revolutionized our ability to understand and design DNA sequences--the fundamental language of life--with unprecedented precision, enabling transformative applications in therapeutics, synthetic biology, and gene editing. However, this capability also poses substantial dual-use risks, including the potential for creating pathogens, viruses, and even bioweapons. To address these biosecurity challenges, we introduce two innovative watermarking techniques to reliably track the designed DNA: DNAMark and CentralMark. DNAMark employs synonymous codon substitutions to embed watermarks in DNA sequences while preserving the original function. CentralMark further advances this by creating inheritable watermarks that transfer from DNA to translated proteins, leveraging protein embeddings to ensure detection across the central dogma. Both methods utilize semantic embeddings to generate watermark logits, enhancing robustness against natural mutations, synthesis errors, and adversarial attacks. Evaluated on our therapeutic DNA benchmark, DNAMark and CentralMark achieve F1 detection scores above 0.85 under various conditions, while maintaining over 60% sequence similarity to ground truth and degeneracy scores below 15%. A case study on the CRISPR-Cas9 system underscores CentralMark's utility in real-world settings. This work establishes a vital framework for securing DNA language models, balancing innovation with accountability to mitigate biosecurity risks.