Google says it has begun requiring users to turn on JavaScript, the widely used programming language to make web pages interactive, in order to use Google Search. In an email to TechCrunch, a company spokesperson claimed that the change is intended to “better protect” Google Search against malicious activity, such as bots and spam, and […]
© 2024 TechCrunch. All rights reserved. For personal use only.
When you think of AI’s contributions to science, you probably think of AlphaFold, the Google DeepMind protein-folding program that earned its creator a Nobel Prize last year.
Now OpenAI says it’s getting into the science game too—with a model for engineering proteins.
The company says it has developed a language model that dreams up proteins capable of turning regular cells into stem cells—and that it has handily beat humans at the task.
The work represents OpenAI’s first model focused on biological data and its first public claim that its models can deliver unexpected scientific results. As such, it is a step toward determining whether or not AI can make true discoveries, which some argue is a major test on the pathway to “artificial general intelligence.”
Last week, OpenAI CEO Sam Altman said he was “confident” his company knows how to build an AGI, adding that “superintelligent tools could massively accelerate scientific discovery and innovation well beyond what we are capable of doing on our own.”
The protein engineering project started a year ago when Retro Biosciences, a longevity research company based in San Francisco, approached OpenAI about working together.
That link-up did not happen by chance. Sam Altman, the CEO of OpenAI, personally funded Retro with $180 million, as MIT Technology Review first reported in 2023.
Retro has the goal of extending the normal human lifespan by 10 years. For that, it studies what are called Yamanaka factors. Those are a set of proteins that, when added to a human skin cell, will cause it to morph into a young-seeming stem cell, a type that can produce any other tissue in the body.
It’s a phenomenon that researchers at Retro, and at richly funded companies like Altos Labs, see as the possible starting point for rejuvenating animals, building human organs, or providing supplies of replacement cells.
But such cell “reprogramming” is not very efficient. It takes several weeks, and less than 1% of cells treated in a lab dish will complete the rejuvenation journey.
OpenAI’s new model, called GPT-4b micro, was trained to suggest ways to re-engineer the protein factors to increase their function. According to OpenAI, researchers used the model’s suggestions to change two of the Yamanaka factors to be more than 50 times as effective—at least according to some preliminary measures.
“Just across the board, the proteins seem better than what the scientists were able to produce by themselves,” says John Hallman, an OpenAI researcher.
Hallman and OpenAI’s Aaron Jaech, as well as Rico Meinl from Retro, were the model’s lead developers.
Outside scientists won’t be able to tell if the results are real until they’re published, something the companies say they are planning. Nor is the model available for wider use—it’s still a bespoke demonstration, not an official product launch.
“This project is meant to show that we’re serious about contributing to science,” says Jaech. “But whether those capabilities will come out to the world as a separate model or whether they’ll be rolled into our mainline reasoning models—that’s still to be determined.”
The model does not work the same way as Google’s AlphaFold, which predicts what shape proteins will take. Since the Yamanaka factors are unusually floppy and unstructured proteins, OpenAI said, they called for a different approach, which its large language models were suited to.
The model was trained on examples of protein sequences from many species, as well as information on which proteins tend to interact with one another. While that’s a lot of data, it’s just a fraction of what OpenAI’s flagship chatbots were trained on, making GPT-4b an example of a “small language model” that works with a focused data set.
Once Retro scientists were given the model, they tried to steer it to suggest possible redesigns of the Yamanaka proteins. The prompting tactic used is similar to the “few-shot” method, in which a user queries a chatbot by providing a series of examples with answers, followed by an example for the bot to respond to.
Although genetic engineers have ways to direct evolution of molecules in the lab, they can usually test only so many possibilities. And even a protein of typical length can be changed in nearly infinite ways (since they’re built from hundreds of amino acids, and each acid comes in 20 possible varieties).
OpenAI’s model, however, often spits out suggestions in which a third of the amino acids in the proteins were changed.
“We threw this model into the lab immediately and we got real-world results,” says Retro’s CEO, Joe Betts-Lacroix. He says the model’s ideas were unusually good, leading to improvements over the original Yamanaka factors in a substantial fraction of cases.
Vadim Gladyshev, a Harvard University aging researcher who consults with Retro, says better ways of making stem cells are needed. “For us, it would be extremely useful. [Skin cells] are easy to reprogram, but other cells are not,” he says. “And to do it in a new species—it’s often extremely different, and you don’t get anything.”
How exactly the GPT-4b arrives at its guesses is still not clear—as is often the case with AI models. “It’s like when AlphaGo crushed the best human at Go, but it took a long time to find out why,” says Betts-Lacroix. “We are still figuring out what it does, and we think the way we apply this is only scratching the surface.”
OpenAI says no money changed hands in the collaboration. But because the work could benefit Retro—whose biggest investor is Altman—the announcement may add to questions swirling around the OpenAI CEO’s side projects.
Last year, the Wall Street Journal said Altman’s wide-ranging investments in private tech startups amount to an “opaque investment empire” that is “creating a mounting list of potential conflicts,” since some of these companies also do business with OpenAI.
In Retro’s case, simply being associated with Altman, OpenAI, and the race toward AGI could boost its profile and increase its ability to hire staff and raise funds. Betts-Lacroix did not answer questions about whether the early-stage company is currently in fundraising mode.
OpenAI says Altman was not directly involved in the work and that it never makes decisions based on Altman’s other investments.
Nature Biotechnology, Published online: 17 January 2025; doi:10.1038/s41587-024-02541-4
Therapeutic T cells with synthetic gene circuits act locally
Oncogene, Published online: 17 January 2025; doi:10.1038/s41388-024-03270-3
Evidence of DNA methylation heterogeneity and epipolymorphism in kidney cancer tissue samples
Nature, Published online: 15 January 2025; doi:10.1038/d41586-025-00134-y
Proteins made using machine learning successfully bind snake toxins — plus, Earth’s temperature breaks a significant climate threshold for the first time.
Nature, Published online: 15 January 2025; doi:10.1038/d41586-025-00045-y
Machine-learning system can process words spoken in 101 languages, spitting out voice-synthesized translations in 36 target languages.
Nature, Published online: 15 January 2025; doi:10.1038/d41586-025-00052-z
The incoming US president is expected to gut support for research on the environment and infectious diseases, but could buoy work in artificial intelligence, quantum research and space exploration.
Am J Hum Genet. 2025 Jan 6:S0002-9297(24)00456-7. doi: 10.1016/j.ajhg.2024.12.014. Online ahead of print.
ABSTRACT
Mosaic loss of Y (mLOY) is the most common somatic chromosomal alteration detected in human blood. The presence of mLOY is associated with altered blood cell counts and increased risk of Alzheimer disease, solid tumors, and other age-related diseases. We sought to gain a better understanding of genetic drivers and associated phenotypes of mLOY through analyses of whole-genome sequencing (WGS) of a large set of genetically diverse males from the Trans-Omics for Precision Medicine (TOPMed) program. We show that haplotype-based calling methods can be used with WGS data to successfully identify mLOY events. This approach enabled us to identify differences in mLOY frequencies across populations defined by genetic similarity, revealing a higher frequency of mLOY in the European (EUR) ancestry group compared to other ancestries. We identify multiple loci associated with mLOY susceptibility and show that subsets of human hematopoietic stem cells are enriched for the activity of mLOY susceptibility variants. Finally, we found that certain alleles on chromosome Y are more likely to be lost than others in detectable mLOY clones.
PMID:39809269 | DOI:10.1016/j.ajhg.2024.12.014
Cancer Lett. 2025 Jan 12;612:217462. doi: 10.1016/j.canlet.2025.217462. Online ahead of print.
ABSTRACT
A user-friendly integrated database, RMethyMD (http://www.tmliang.cn/rnamethy), was developed to provide a comprehensive analysis of methylation regulators aimed at facilitating the exploration of molecular features in tumorigenesis and clinical implications in cancer diagnosis and treatment via a multiomics approach. Subsequently, molecular landscapes and a robust constructed m6A-based prognostic model using coxBoost + RSF algorithms in lung cancer highlighted m6A as a suitable marker to guide therapeutic strategy. RMethyMD provides a comprehensive resource and multiomics analysis to explore m6A-based prognostic and clinical values, thereby contributing to aiding personalized cancer therapy.
PMID:39809358 | DOI:10.1016/j.canlet.2025.217462
Radiother Oncol. 2025 Jan 10;204:110715. doi: 10.1016/j.radonc.2025.110715. Online ahead of print.
ABSTRACT
BACKGROUND AND PURPOSE: Quantifying tumor heterogeneity from various dimensions is crucial for precise treatment. This study aimed to develop and validate multi-omics models based on the computed tomography images, pathological images, dose and clinical information to predict treatment response and overall survival of non-small cell lung cancer (NSCLC) patients undergoing chemotherapy and radiotherapy.
MATERIALS AND METHODS: This retrospective study included 220 NSCLC patients from three centers. Following feature extraction and selection, single-omics and multi-omics models were built for treatment response and overall survival prediction. The performance of treatment response models was evaluated using the area under the curve (AUC) and box plots. For overall survival analysis, the model's evaluation included AUC, concordance index (C-index), Kaplan-Meier curves, and calibration curves. Shapley values were used to assess the contribution of different features to multi-omics models.
RESULTS: Multi-omics models consistently exhibited superior discriminative ability compared to single-omics models in predicting both treatment response and overall survival. For treatment response, the three all-modality models achieved AUC values of 0.87, 0.91, and 0.82 in the external validation set, respectively. In overall survival analysis, the three all-modality models demonstrated AUC values and C-index of 0.73/0.72, 0.80/0.77, 0.79/0.78 in the external validation set, respectively.
CONCLUSION: Multi-omics prediction models demonstrated superior predictive ability with robustness and interpretability. By predicting treatment response and overall survival in NSCLC patients, these models have the potential to assist clinician optimizing treatment plans, supporting individualized treatment strategies, improving the tumor control probability and prolonging the patients' survival.
PMID:39800269 | DOI:10.1016/j.radonc.2025.110715
Global Spine J. 2025 Jan;15(1_suppl):16S-28S. doi: 10.1177/21925682231222012.
ABSTRACT
STUDY DESIGN: Narrative review.
OBJECTIVES: This article aims to provide a narrative review of the current state of research for liquid biopsy in spinal tumors and to discuss the potential application of liquid biopsy in the clinical management of patients with spinal tumors.
METHODS: A comprehensive review of the literature was performed using PubMed, Google Scholar, Medline, Embase and Cochrane databases, and the review was limited to articles of English language. All the relevant articles which were identified to be related to liquid biomarker study in spinal tumors, were studied in full text.
RESULTS: Liquid biopsy has revolutionized the field of precision medicine by guiding personalized clinical management of cancer patients based on the liquid biomarker status. In recent years, more research has been done to investigate its potential utilization in patients with tumors from the spine. Herein, we review the liquid biomarkers that have been proposed in different spine malignancies including chordoma, chondrosarcoma, Ewing sarcoma, osteosarcoma, astrocytoma and ependymoma. We also discuss the wide window of opportunity to utilize these liquid biomarkers in diagnosis, treatment response, monitoring, and detection of minimal residual disease in patients with spinal tumors.
CONCLUSIONS: Liquid biomarkers, especially blood-derived circulating tumor DNA, has a promising clinical utility as they are disease-specific, minimally invasive, and the procedure is repeatable. Prospective studies with larger populations are needed to fully establish its use in the setting of spinal tumors.
PMID:39801114 | PMC:PMC11726521 | DOI:10.1177/21925682231222012
Nature, Published online: 14 January 2025; doi:10.1038/d41586-025-00110-6
Experimental model’s record-breaking performance on science and maths tests wows researchers.
Nature, Published online: 14 January 2025; doi:10.1038/d41586-025-00123-1
Fresh approach to diagnosing the condition looks at how excess body fat affects the body.
Respir Res. 2025 Jan 10;26(1):10. doi: 10.1186/s12931-024-03088-3.
ABSTRACT
BACKGROUND: In COPD, the balance between matrix metalloproteinases (MMPs) and their natural inhibitors [tissue inhibitors of metalloproteinases (TIMPs)] is shifted towards excessive degradation, reflected in bronchoalveolar lavage (BAL) as increased MMP concentrations. Because of their critical role in lung homeostasis, MMP activity is tightly regulated, but to what extent this regulation occurs through epigenetic mechanisms remains unknown.
METHODS: To explore the interplay between MMPs, TIMPs, and DNA methylation (DNAm) we (1) analysed MMP-9, -12, and TIMP-1 concentrations in BAL fluid, and profiled DNAm in BAL cells from 18 COPD and 30 control subjects, (2) estimated protein-COPD relationships using multivariable regression, (3) identified protein quantitative trait methylation loci (pQTMs) with COPD as a potential modifier in a separate interaction model, and (4) integrated significant interactions with a previous COPD GWAS meta-analysis.
RESULTS: COPD was associated with higher levels of BAL MMP-12 (p = 0.016) but not with MMP-9 or TIMP-1. Further examination of MMP-12 identified association with DNAm at 34 loci (pQTMs), with TGFBR2 (p = 2.25 × 10-10) and THBS4 (p = 1.11 × 10-9) among the top ten pQTM genes. The interaction model identified 66 sites where the DNAm-MMP-12 association was significantly different in COPD compared to controls. Of these, one was colocalized with SNPs previously associated with COPD.
CONCLUSIONS: Our findings indicate that airway MMP-12 may partially be regulated by epigenetic mechanisms and that this regulation is disrupted in COPD. Furthermore, integration with COPD GWAS data suggests that this dysregulation is influenced by a combination of environmental factors, disease processes, and genetics, with the latter potentially playing a lesser role.
PMID:39794761 | PMC:PMC11724436 | DOI:10.1186/s12931-024-03088-3
Clin Transl Med. 2025 Jan;15(1):e70160. doi: 10.1002/ctm2.70160.
ABSTRACT
BACKGROUND: Plasma protein has gained prominence in the non-invasive predicting of lung cancer. We utilised Zeolite Zotero NaY-based plasma proteomics to investigate its potential for multiple event predicting, including lung cancer diagnosis (task #1), lymph node metastasis detection (task #2) and tumour‒node‒metastasis (TNM) staging (task #3).
METHODS: A total of 4703 plasma proteins were quantified from 241 participants based on a prospective cohort of 2757 participants. An additional 46 participants from external prospective cohort of 735 participants were used for validation. Feature selection was performed using differential expressed protein analysis, area under curve (AUC) evaluation and least absolute shrinkage and selection operator (LASSO) regression. Random forest was used for multitask model construction based on the key proteins. Feature importance was interpreted using Shapley additive explanations (SHAP) algorithm.
RESULTS: For task #1, 10 proteins panel showed an AUC of .87 (.77‒.97) in the external validation. After integrating clinical factors, a significant increase diagnostic accuracy was observed with AUC of .91 (.85‒.98). For task #2, nine proteins panel achieved an AUC of .88 (.80‒.96), integration model showed an increase diagnostic accuracy with AUC of .90 (.85‒.97). For task #3, 10 proteins panel showed an AUC of .88 (.74‒.96) for stage I, .92 (.84‒.97) for stage II, .88 (.76‒.96) for stage III and .99 (.98‒.99) for stage IV in the integration model.
CONCLUSIONS: This study comprehensively profiled the NaY-based plasma proteome biomarker, laying the foundation for a high-performance blood test for predicting multiple events in lung cancer.
KEY POINTS: Our study developed an innovative nanomaterial, Zeolite NaY, which addressed the masking effect and improved the depth of the proteome. The performance of NaY-based plasma proteomics as a preclinical diagnostic tool was validated through both internal and external cohort. Furthermore, we explored the different patterns of plasma protein changes during the progression of lung cancer and used the explanations method to elucidate the roles of proteins in the multitask predictive model.
PMID:39783847 | PMC:PMC11714244 | DOI:10.1002/ctm2.70160
Int J Med Sci. 2025 Jan 1;22(2):341-356. doi: 10.7150/ijms.104437. eCollection 2025.
ABSTRACT
Background: Gastric cancer (GC) remains a significant global health challenge. This study aimed to comprehensively analyze GC epidemiology and risk factors to inform prevention and intervention strategies. Methods: We analyzed the Global Burden of Disease Study 2021 data, conducted 16 different machine learning (ML) models of NHANES data, performed Mendelian randomization (MR) studies on disease phenotypes, dietary preferences, microbiome, blood-based markers, and integrated differential gene expression and expression quantitative trait loci (eQTL) data from multiple cohorts to identify factors associated with GC risk. Results: Global age-standardized disability-adjusted life year rates (ASDR) for GC declined from 886.24 to 358.42 per 100,000 population between 1990 and 2030, with significant regional disparities. Despite this decline, total disability-adjusted life years show a concerning upward trend from 2015, rising from approximately 22.9 million to a projected 24.3 million by 2030. The slope index of inequality shifted from 87 in 1990 to -184 in 2021, indicating a reversal in GC burden distribution, with higher ASDR now associated with lower socio-demographic index countries. The ML models analysis identified higher levels of clinical characteristics such as phosphorus, calcium, eosinophils percent, and triglycerides, as well as lower levels of iron and monocyte percent, may be associated with an increased risk of GC. MR analyses revealed causal associations between GC risk and disease phenotypes such as Helicobacter pylori infection, chronic gastritis, obesity, depression, and dietary preferences such as dairy and processed meats. Gut microbiome analysis showed associations with microbiome such as Phascolarctobacterium and Ruminococcaceae species. Blood-based markers analysis identified protective and risk effects for cortisol, glutamate, nicotinamide, Natural Killer %lymphocyte, CD4-CD8- T cell Absolute Count, Phosphatidylcholine (16:0_18:1), and Interleukin-1-alpha. Integrated genomic analysis identified 10 genes significantly associated with GC risk, with strong evidence for colocalization in genes such as CCR6 and PILRB. Conclusions: This systematic analysis reveals complex global trends in GC burden and identifies novel clinical, disease phenotypes, dietary preferences, microbial, blood-based, and genetic risk factors. These findings provide potential targets for improved risk stratification, prevention, and intervention strategies to reduce the global burden of GC.
PMID:39781526 | PMC:PMC11704698 | DOI:10.7150/ijms.104437
Cancers (Basel). 2024 Dec 12;16(24):4145. doi: 10.3390/cancers16244145.
ABSTRACT
Lung cancer is a deadly disease with the highest rates of mortality. Over recent decades, a better understanding of the biological mechanisms implicated in its pathogenesis has led to the development of targeted therapies and immunotherapy, resulting in improvements in patient outcomes. To better understand lung cancer tumor biology and advance towards precision oncology, a comprehensive tumor profile is necessary. In recent years, novel in situ spatial multiomics approaches have emerged offering a more detailed view of the spatial location of tumor and tumor microenvironment cells, identifying their unique composition and functional status. In this sense, novel multiomics platforms have been developed to evaluate tumor heterogeneity, gene expression, metabolic reprogramming, signaling pathway activation, cell-cell interactions, and immune cell programs. In lung cancer research, several studies have used these spatial technologies to locate cells and associated them with histological features that are relevant to the pathogenesis of lung adenocarcinoma. These advancements may unveil further molecular and immune mechanisms in tumor biology that will lead to the discovery of biomarkers for treatment prediction and prognosis. In this review, we provide an overview of more widely used and emerging pathology-based approaches for spatial immune profiling in lung cancer and how they enhance our understanding of tumor biology and immune response.
PMID:39766047 | PMC:PMC11674389 | DOI:10.3390/cancers16244145
Nat Commun. 2025 Jan 8;16(1):430. doi: 10.1038/s41467-024-55428-y.
ABSTRACT
The analysis of circulating tumour DNA (ctDNA) through minimally invasive liquid biopsies is promising for early multi-cancer detection and monitoring minimal residual disease. Most existing methods focus on targeted deep sequencing, but few integrate multiple data modalities. Here, we develop a methodology for ctDNA detection using deep (80x) whole-genome TET-Assisted Pyridine Borane Sequencing (TAPS), a less destructive approach than bisulphite sequencing, which permits the simultaneous analysis of genomic and methylomic data. We conduct a diagnostic accuracy study across multiple cancer types in symptomatic patients, achieving 94.9% sensitivity and 88.8% specificity. Matched tumour biopsies are used for validation, not for guiding the analysis, imitating an early detection scenario. Furthermore, in silico validation demonstrates strong discrimination (86% AUC) at ctDNA fractions as low as 0.7%. Additionally, we successfully track tumour burden and ctDNA shedding from precancerous lesions post-treatment without requiring matched tumour biopsies. This pipeline is ready for further clinical evaluation to extend cancer screening and improve patient triage and monitoring.
PMID:39779727 | PMC:PMC11711490 | DOI:10.1038/s41467-024-55428-y
Int J Mol Sci. 2024 Dec 20;25(24):13669. doi: 10.3390/ijms252413669.
ABSTRACT
Liquid biopsy (LB) involves the analysis of circulating tumour-derived DNA (ctDNA), providing a minimally invasive method for gathering both quantitative and qualitative information. Genomic analysis of ctDNA through next-generation sequencing (NGS) enables comprehensive genetic profiling of tumours, including non-driver alterations that offer prognostic insights. LB can be applied in both early-stage disease settings, for the diagnosis and monitoring of minimal residual disease (MRD), and advanced disease settings, for monitoring treatment response and understanding the mechanisms behind disease progression and tumour heterogeneity. Currently, LB has limited use in clinical practice, primarily due to its significant costs, limited diagnostic yield, and uncertain prognostic role. The application of artificial intelligence (AI) in the medical field is a promising approach to processing extensive information and applying it to individual cases to enhance therapeutic decision-making and refine risk assessment.
PMID:39769431 | PMC:PMC11727717 | DOI:10.3390/ijms252413669
Login