rtificial intelligence (AI) methods have the potential to revolutionize the domain of medicine, as witnessed, for example, in medical imaging, where the application of computer vision techniques, traditional machine learning 1,2 and-more recently-deep neural networks have achieved remarkable successes. This progress can be ascribed to the release of large, curated corpora of images (ImageNet 3 perhaps being the best known), giving rise to performant pre-trained algorithms that facilitate transfer learning and led to increasing publications both in oncology-with applications in tumour detection 4,5 , genomic characterization 6,7 , tumour subtyping 8,9 , grading prediction 10 , outcome risk assessment 11 or risk of relapse quantification 12 -and non-oncologic applications, such as chest X-ray analysis 13 and retinal fundus imaging 14 .To allow medical imaging AI applications to offer clinical decision support suitable for precision medicine implementations, even larger amounts of imaging and clinical data will be required. Large cross-sectional population studies based solely on volunteer participation, such as the UK Biobank 15 , cannot fill this gap. Even the largest current imaging studies in the field 4,5 , demonstrating better-than-human performance in their respective tasks, include considerably less data than, for example, ImageNet 3 , or the amount of data used to train algorithmic agents in the games of Go or StarCraft 16,17 , or autonomous vehicles 18 . Furthermore, such datasets often stem from relatively few institutions, geographic regions or patient demographics, and might therefore contain unquantifiable bias due to their incompleteness with respect to co-variables such as comorbidities, ethnicity, gender and so on 19 .However, considering that the sum of the world's patient databases probably contains enough data to answer many significant questions, it becomes clear that the inability to access and leverage this data poses a significant barrier to AI applications in this field.The lack of standardized, electronic patient records is one reason. Electronic patient data management is expensive 20 , and hospitals in underprivileged regions might be unable to afford participation in studies requiring it, potentially perpetuating the aforementioned issues of bias and fairness. In the medical imaging field, electronic data management is the standard: Digital Imaging and Communications in Medicine (DICOM) 21 is the universally adopted imaging data format, and electronic file storage is the near-global standard of care. Even where non-digital formats are still in use, the archival nature of, for instance, film radiography allows post hoc digitization, seen, for example, in the CBIS-DDSM dataset 22 , consisting of digitized film breast radiographs. Digital imaging data, easily shareable, permanently storable and remotely accessible in the cloud has driven the aforementioned successes of medical imaging AI.The second issue representing a stark deterrent from multi-institutional/multi-national AI trials 23 is ...

Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal human cancers and shows resistance to any therapeutic strategy used. Here we tested small-molecule inhibitors targeting chromatin regulators as possible therapeutic agents in PDAC. We show that JQ1, an inhibitor of the bromodomain and extraterminal (BET) family of proteins, suppresses PDAC development in mice by inhibiting both MYC activity and inflammatory signals. The histone deacetylase (HDAC) inhibitor SAHA synergizes with JQ1 to augment cell death and more potently suppress advanced PDAC. Finally, using a CRISPR-Cas9–based method for gene editing directly in the mouse adult pancreas, we show that de-repression of p57 (also known as KIP2 or CDKN1C) upon combined BET and HDAC inhibition is required for the induction of combination therapy–induced cell death in PDAC. SAHA is approved for human use, and molecules similar to JQ1 are being tested in clinical trials. Thus, these studies identify a promising epigenetic-based therapeutic strategy that may be rapidly implemented in fatal human tumors.

Morphogenesis of a vascular network requires dynamic vessel growth and regression. To investigate the cellular mechanism underlying this process, we deleted focal adhesion kinase (FAK), a key signaling mediator, in endothelial cells (ECs) using Tie2-Cre mice. Targeted FAK depletion occurred efficiently early in development, where mutants exhibited a distinctive and irregular vasculature, resulting in hemorrhage and lethality between embryonic day (e) 10.5 and 11.5. Capillaries and intercapillary spaces in yolk sacs were dilated before any other detectable abnormalities at e9.5, and explants demonstrate that the defects resulted from the loss of FAK and not from organ failure. Time-lapse microscopy monitoring EC behavior during vascular formation in explants revealed no apparent decrease in proliferation or migration but revealed increases in cell retraction and death leading to reduced vessel growth and increased vessel regression. Consistent with this phenotype, ECs derived from mutant embryos exhibited aberrant lamellipodial extensions, altered actin cytoskeleton, and nonpolarized cell movement. This study reveals that FAK is crucial for vascular morphogenesis and the regulation of EC survival and morphology.

Here, we show CRISPR/Cas9-based targeted somatic multiplexmutagenesis and its application for high-throughput analysis of gene function in mice. Using hepatic single guide RNA (sgRNA) delivery, we targeted large gene sets to induce hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC). We observed Darwinian selection of target genes, which suppress tumorigenesis in the respective cellular/tissue context, such as Pten or Cdkn2a, and conversely found low frequency of Brca1/2 alterations, explaining mutational spectra in human ICC/HCC. Our studies show that multiplexed CRISPR/Cas9 can be used for recessive genetic screening or high-throughput cancer gene validation in mice. The analysis of CRISPR/Cas9-induced tumors provided support for a major role of chromatin modifiers in hepatobiliary tumorigenesis, including that of ARID family proteins, which have recently been reported to be mutated in ICC/HCC. We have also comprehensively characterized the frequency and size of chromosomal alterations induced by combinatorial sgRNA delivery and describe related limitations of CRISPR/Cas9 multiplexing, as well as opportunities for chromosome engineering in the context of hepatobiliary tumorigenesis. Our study describes novel approaches to model and study cancer in a high-throughput multiplexed format that will facilitate the functional annotation of cancer genomes.in vivo CRISPR/Cas9 | somatic multiplex-mutagenesis | hepatocellular carcinoma | intrahepatic cholangiocarcinoma | chromosome engineering F or decades, a major bottleneck in cancer research has been our limited ability to identify genetic alterations in cancer. The revolution in array-based and sequencing technologies and the recent development of insertional mutagenesis tools in animal models enable the discovery of cancer-associated genetic alterations on a genome-wide scale in a high-throughput manner. Nextgeneration sequencing (NGS) of cancer genomes and transposonbased genetic screening in mice, for example, are currently creating large catalogs of putative cancer genes for principally all cancer types (1-3). A challenge for the next decades will be to validate the causative cancer relevance of these large gene sets (to distinguish drivers from passengers) and to understand their biological function. Moreover, pinpointing downstream targets of mutated cancer genes or drivers among the thousands of transcriptionally or epigenetically dysregulated genes within individual cancers is complex and limited by the lack of tools for high-throughput functional cancer genomic analyses.The development of technologies for targeted manipulation of the mouse germ line has opened tremendous opportunities to study gene function (4, 5). Mouse models recapitulate the extensive biological complexity of human cancer and have given insights into many fundamental aspects of the disease that can be studied only at an organismal level (6). However, the speed and efficiency of such studies is limited by the long time frames needed to genetically engineer, intercross,...