Allosteric Activation Dictates PRC2 Activity Independent of Its Recruitment to Chromatin.

PRC2 is a therapeutic target for several types of cancers currently undergoing clinical trials. Its activity is regulated by a positive feedback loop whereby its terminal enzymatic product, H3K27me3, is specifically recognized and bound by an aromatic cage present in its EED subunit. The ensuing allosteric activation of the complex stimulates H3K27me3 deposition on chromatin. Here we report a stepwise feedback mechanism entailing key residues within distinctive interfacing motifs of EZH2 or EED that are found to be mutated in cancers and/or Weaver syndrome. PRC2 harboring these EZH2 or EED mutants manifested little activity in vivo but, unexpectedly, exhibited similar chromatin association as wild-type PRC2, indicating an uncoupling of PRC2 activity and recruitment. With genetic and chemical tools, we demonstrated that targeting allosteric activation overrode the gain-of-function effect of EZH2Y646X oncogenic mutations. These results revealed critical implications for the regulation and biology of PRC2 and a vulnerability in tackling PRC2-addicted cancers.

Analysis of super-enhancer using machine learning and its application to medical biology.

The analysis of super-enhancers (SEs) has recently attracted attention in elucidating the molecular mechanisms of cancer and other diseases. SEs are genomic structures that strongly induce gene expression and have been reported to contribute to the overexpression of oncogenes. Because the analysis of SEs and integrated analysis with other data are performed using large amounts of genome-wide data, artificial intelligence technology, with machine learning at its core, has recently begun to be utilized. In promoting precision medicine, it is important to consider information from SEs in addition to genomic data; therefore, machine learning technology is expected to be introduced appropriately in terms of building a robust analysis platform with a high generalization performance. In this review, we explain the history and principles of SE, and the results of SE analysis using state-of-the-art machine learning and integrated analysis with other data are presented to provide a comprehensive understanding of the current status of SE analysis in the field of medical biology. Additionally, we compared the accuracy between existing machine learning methods on the benchmark dataset and attempted to explore the kind of data preprocessing and integration work needed to make the existing algorithms work on the benchmark dataset. Furthermore, we discuss the issues and future directions of current SE analysis.

Mechanism of ERBB2 gene overexpression by the formation of super-enhancer with genomic structural abnormalities in lung adenocarcinoma without clinically actionable genetic alterations.

BACKGROUND: In an extensive genomic analysis of lung adenocarcinomas (LUADs), driver mutations have been recognized as potential targets for molecular therapy. However, there remain cases where target genes are not identified. Super-enhancers and structural variants are frequently identified in several hundred loci per case. Despite this, most cancer research has approached the analysis of these data sets separately, without merging and comparing the data, and there are no examples of integrated analysis in LUAD. METHODS: We performed an integrated analysis of super-enhancers and structural variants in a cohort of 174 LUAD cases that lacked clinically actionable genetic alterations. To achieve this, we conducted both WGS and H3K27Ac ChIP-seq analyses using samples with driver gene mutations and those without, allowing for a comprehensive investigation of the potential roles of super-enhancer in LUAD cases. RESULTS: We demonstrate that most genes situated in these overlapped regions were associated with known and previously unknown driver genes and aberrant expression resulting from the formation of super-enhancers accompanied by genomic structural abnormalities. Hi-C and long-read sequencing data further corroborated this insight. When we employed CRISPR-Cas9 to induce structural abnormalities that mimicked cases with outlier ERBB2 gene expression, we observed an elevation in ERBB2 expression. These abnormalities are associated with a higher risk of recurrence after surgery, irrespective of the presence or absence of driver mutations. CONCLUSIONS: Our findings suggest that aberrant gene expression linked to structural polymorphisms can significantly impact personalized cancer treatment by facilitating the identification of driver mutations and prognostic factors, contributing to a more comprehensive understanding of LUAD pathogenesis.

Application of non-negative matrix factorization in oncology: one approach for establishing precision medicine.

The increase in the expectations of artificial intelligence (AI) technology has led to machine learning technology being actively used in the medical field. Non-negative matrix factorization (NMF) is a machine learning technique used for image analysis, speech recognition, and language processing; recently, it is being applied to medical research. Precision medicine, wherein important information is extracted from large-scale medical data to provide optimal medical care for every individual, is considered important in medical policies globally, and the application of machine learning techniques to this end is being handled in several ways. NMF is also introduced differently because of the characteristics of its algorithms. In this review, the importance of NMF in the field of medicine, with a focus on the field of oncology, is described by explaining the mathematical science of NMF and the characteristics of the algorithm, providing examples of how NMF can be used to establish precision medicine, and presenting the challenges of NMF. Finally, the direction regarding the effective use of NMF in the field of oncology is also discussed.

Interactions between JARID2 and noncoding RNAs regulate PRC2 recruitment to chromatin.

JARID2 is an accessory component of Polycomb repressive complex-2 (PRC2) required for the differentiation of embryonic stem cells (ESCs). A role for JARID2 in the recruitment of PRC2 to target genes silenced during differentiation has been put forward, but the molecular details remain unclear. We identified a 30-amino-acid region of JARID2 that mediates interactions with long noncoding RNAs (lncRNAs) and found that the presence of lncRNAs stimulated JARID2-EZH2 interactions in vitro and JARID2-mediated recruitment of PRC2 to chromatin in vivo. Native and crosslinked RNA immunoprecipitations of JARID2 revealed that Meg3 and other lncRNAs from the imprinted Dlk1-Dio3 locus, an important regulator of development, interacted with PRC2 via JARID2. Lack of MEG3 expression in human induced pluripotent cells altered the chromatin distribution of JARID2, PRC2, and H3K27me3. Our findings show that lncRNAs facilitate JARID2-PRC2 interactions on chromatin and suggest a mechanism by which lncRNAs contribute to PRC2 recruitment.

Jarid2 Is Implicated in the Initial Xist-Induced Targeting of PRC2 to the Inactive X Chromosome.

During X chromosome inactivation (XCI), the Polycomb Repressive Complex 2 (PRC2) is thought to participate in the early maintenance of the inactive state. Although Xist RNA is essential for the recruitment of PRC2 to the X chromosome, the precise mechanism remains unclear. Here, we demonstrate that the PRC2 cofactor Jarid2 is an important mediator of Xist-induced PRC2 targeting. The region containing the conserved B and F repeats of Xist is critical for Jarid2 recruitment via its unique N-terminal domain. Xist-induced Jarid2 recruitment occurs chromosome-wide independently of a functional PRC2 complex, unlike at other parts of the genome, such as CG-rich regions, where Jarid2 and PRC2 binding are interdependent. Conversely, we show that Jarid2 loss prevents efficient PRC2 and H3K27me3 enrichment to Xist-coated chromatin. Jarid2 thus represents an important intermediate between PRC2 and Xist RNA for the initial targeting of the PRC2 complex to the X chromosome during onset of XCI.

Nascent RNA interaction keeps PRC2 activity poised and in check.

Polycomb-repressive complex 2 (PRC2) facilitates the maintenance and inheritance of chromatin domains repressive to transcription through catalysis of methylation of histone H3 at Lys27 (H3K27me2/3). However, through its EZH2 subunit, PRC2 also binds to nascent transcripts from active genes that are devoid of H3K27me2/3 in embryonic stem cells. Here, biochemical analyses indicated that RNA interaction inhibits SET domain-containing proteins, such as PRC2, nonspecifically in vitro. However, CRISPR-mediated truncation of a PRC2-interacting nascent RNA rescued PRC2-mediated deposition of H3K27me2/3. That PRC2 activity is inhibited by interactions with nascent transcripts supports a model in which PRC2 can only mark for repression those genes silenced by transcriptional repressors.

Histone methyltransferase SMYD2 selective inhibitor LLY-507 in combination with poly ADP ribose polymerase inhibitor has therapeutic potential against high-grade serous ovarian carcinomas.

Dysfunction of histone methylation is known to be related to cancer progression. The histone methyltransferase SMYD2 methylates histone protein H3 and non-histone proteins, including poly ADP ribose polymerase 1 (PARP1). There have been reports of SMYD2 overexpression in several types of cancers. However, there are no reports regarding its role in high-grade serous ovarian carcinomas (HGSOCs). Therefore, we investigated the expression profile and conducted functional analysis on SMYD2 in HGSOC cells. In addition, we verified whether SMYD2 inhibition increases the susceptibility of HGSOC cells to PARP inhibitors. We analyzed the expression of histone methyltransferase SMYD2 by quantitative real-time polymerase chain reaction and immunohistochemistry using HGSOC clinical tissues (n = 35). We performed functional analyses, including cell proliferation assay, cell cycle analysis, and immunoblotting, after treatment with SMYD2 siRNAs and SMYD2 selective inhibitor LLY-507 in HGSOC cells. We also performed colony-formation assay after combination treatment with LLY-507 and PARP inhibitor olaparib in HGSOC cells. The expression profiles of SMYD2 showed significant overexpression of SMYD2 in HGSOC clinical tissues. The knockdown or inhibition of SMYD2 by siRNAs or LLY-507, respectively, suppressed cell growth by increasing the proportion of apoptotic cells. LLY-507 showed additive effect with olaparib in the colony-formation assay. These findings suggest that LLY-507 can be used alone or in combination with a PARP inhibitor for the treatment of patients with HGSOC.

The histone methyltransferase WHSC1 is regulated by EZH2 and is important for ovarian clear cell carcinoma cell proliferation.

BACKGROUND: Wolf-Hirschhorn syndrome candidate gene-1 (WHSC1), a histone methyltransferase, has been found to be upregulated and its expression to be correlated with expression of enhancer of zeste homolog 2 (EZH2) in several cancers. In this study, we evaluated the role of WHSC1 and its therapeutic significance in ovarian clear cell carcinoma (OCCC). METHODS: First, we analyzed WHSC1 expression by quantitative PCR and immunohistochemistry using 23 clinical OCCC specimens. Second, the involvement of WHSC1 in OCCC cell proliferation was evaluated by MTT assays after siRNA-mediated WHSC1 knockdown. We also performed flow cytometry (FACS) to address the effect of WHSC1 on cell cycle. To examine the functional relationship between EZH2 and WHSC1, we knocked down EZH2 using siRNAs and checked the expression levels of WHSC1 and its histone mark H3K36m2 in OCCC cell lines. Finally, we checked WHSC1 expression after treatment with the selective inhibitor, GSK126. RESULTS: Both quantitative PCR and immunohistochemical analysis revealed that WHSC1 was significantly overexpressed in OCCC tissues compared with that in normal ovarian tissues. MTT assay revealed that knockdown of WHSC1 suppressed cell proliferation, and H3K36me2 levels were found to be decreased in immunoblotting. FACS revealed that WHSC1 knockdown affected the cell cycle. We also confirmed that WHSC1 expression was suppressed by EZH2 knockdown or inhibition, indicating that EZH2 is upstream of WHSC1 in OCCC cells. CONCLUSIONS: WHSC1 overexpression induced cell growth and its expression is, at least in part, regulated by EZH2. Further functional analysis will reveal whether WHSC1 is a promising therapeutic target for OCCC.

Phosphorylation of the PRC2 component Ezh2 is cell cycle-regulated and up-regulates its binding to ncRNA.

Ezh2 functions as a histone H3 Lys 27 (H3K27) methyltransferase when comprising the Polycomb-Repressive Complex 2 (PRC2). Trimethylation of H3K27 (H3K27me3) correlates with transcriptionally repressed chromatin. The means by which PRC2 targets specific chromatin regions is currently unclear, but noncoding RNAs (ncRNAs) have been shown to interact with PRC2 and may facilitate its recruitment to some target genes. Here we show that Ezh2 interacts with HOTAIR and Xist. Ezh2 is phosphorylated by cyclin-dependent kinase 1 (CDK1) at threonine residues 345 and 487 in a cell cycle-dependent manner. A phospho-mimic at residue 345 increased HOTAIR ncRNA binding to Ezh2, while the phospho-mimic at residue 487 was ineffectual. An Ezh2 domain comprising T345 was found to be important for binding to HOTAIR and the 5' end of Xist.

Advances in cancer DNA methylation analysis with methPLIER: use of non-negative matrix factorization and knowledge-based constraints to enhance biological interpretability.

DNA methylation is an epigenetic modification that results in dynamic changes during ontogenesis and cell differentiation. DNA methylation patterns regulate gene expression and have been widely researched. While tools for DNA methylation analysis have been developed, most of them have focused on intergroup comparative analysis within a dataset; therefore, it is difficult to conduct cross-dataset studies, such as rare disease studies or cross-institutional studies. This study describes a novel method for DNA methylation analysis, namely, methPLIER, which enables interdataset comparative analyses. methPLIER combines Pathway Level Information Extractor (PLIER), which is a non-negative matrix factorization (NMF) method, with regularization by a knowledge matrix and transfer learning. methPLIER can be used to perform intersample and interdataset comparative analysis based on latent feature matrices, which are obtained via matrix factorization of large-scale data, and factor-loading matrices, which are obtained through matrix factorization of the data to be analyzed. We used methPLIER to analyze a lung cancer dataset and confirmed that the data decomposition reflected sample characteristics for recurrence-free survival. Moreover, methPLIER can analyze data obtained via different preprocessing methods, thereby reducing distributional bias among datasets due to preprocessing. Furthermore, methPLIER can be employed for comparative analyses of methylation data obtained from different platforms, thereby reducing bias in data distribution due to platform differences. methPLIER is expected to facilitate cross-sectional DNA methylation data analysis and enhance DNA methylation data resources.

PROX1 induction by autolysosomal activity stabilizes persister-like state of colon cancer via feedback repression of the NOX1-mTORC1 pathway.

Cancer chemoresistance is often attributed to slow-cycling persister populations with cancer stem cell (CSC)-like features. However, how persister populations emerge and prevail in cancer remains obscure. We previously demonstrated that while the NOX1-mTORC1 pathway is responsible for proliferation of a fast-cycling CSC population, PROX1 expression is required for chemoresistant persisters in colon cancer. Here, we show that enhanced autolysosomal activity mediated by mTORC1 inhibition induces PROX1 expression and that PROX1 induction in turn inhibits NOX1-mTORC1 activation. CDX2, identified as a transcriptional activator of NOX1, mediates PROX1-dependent NOX1 inhibition. PROX1-positive and CDX2-positive cells are present in distinct populations, and mTOR inhibition triggers conversion of the CDX2-positive population to the PROX1-positive population. Inhibition of autophagy synergizes with mTOR inhibition to block cancer proliferation. Thus, mTORC1 inhibition-mediated induction of PROX1 stabilizes a persister-like state with high autolysosomal activity via a feedback regulation that involves a key cascade of proliferating CSCs.

Integrative analysis reveals early epigenetic alterations in high-grade serous ovarian carcinomas.

High-grade serous ovarian carcinoma (HGSOC) is the most lethal gynecological malignancy. To date, the profiles of gene mutations and copy number alterations in HGSOC have been well characterized. However, the patterns of epigenetic alterations and transcription factor dysregulation in HGSOC have not yet been fully elucidated. In this study, we performed integrative omics analyses of a series of stepwise HGSOC model cells originating from human fallopian tube secretory epithelial cells (HFTSECs) to investigate early epigenetic alterations in HGSOC tumorigenesis. Assay for transposase-accessible chromatin using sequencing (ATAC-seq), chromatin immunoprecipitation sequencing (ChIP-seq), and RNA sequencing (RNA-seq) methods were used to analyze HGSOC samples. Additionally, protein expression changes in target genes were confirmed using normal HFTSECs, serous tubal intraepithelial carcinomas (STICs), and HGSOC tissues. Transcription factor motif analysis revealed that the DNA-binding activity of the AP-1 complex and GATA family proteins was dysregulated during early tumorigenesis. The protein expression levels of JUN and FOSL2 were increased, and those of GATA6 and DAB2 were decreased in STIC lesions, which were associated with epithelial-mesenchymal transition (EMT) and proteasome downregulation. The genomic region around the FRA16D site, containing a cadherin cluster region, was epigenetically suppressed by oncogenic signaling. Proteasome inhibition caused the upregulation of chemokine genes, which may facilitate immune evasion during HGSOC tumorigenesis. Importantly, MEK inhibitor treatment reversed these oncogenic alterations, indicating its clinical effectiveness in a subgroup of patients with HGSOC. This result suggests that MEK inhibitor therapy may be an effective treatment option for chemotherapy-resistant HGSOC.

Polyadenylation factor CPSF-73 is the pre-mRNA 3'-end-processing endonuclease.

Most eukaryotic messenger RNA precursors (pre-mRNAs) undergo extensive maturational processing, including cleavage and polyadenylation at the 3'-end. Despite the characterization of many proteins that are required for the cleavage reaction, the identity of the endonuclease is not known. Recent analyses indicated that the 73-kDa subunit of cleavage and polyadenylation specificity factor (CPSF-73) might be the endonuclease for this and related reactions, although no direct data confirmed this. Here we report the crystal structures of human CPSF-73 at 2.1 A resolution, complexed with zinc ions and a sulphate that might mimic the phosphate group of the substrate, and the related yeast protein CPSF-100 (Ydh1) at 2.5 A resolution. Both CPSF-73 and CPSF-100 contain two domains, a metallo-beta-lactamase domain and a novel beta-CASP (named for metallo-beta-lactamase, CPSF, Artemis, Snm1, Pso2) domain. The active site of CPSF-73, with two zinc ions, is located at the interface of the two domains. Purified recombinant CPSF-73 possesses RNA endonuclease activity, and mutations that disrupt zinc binding in the active site abolish this activity. Our studies provide the first direct experimental evidence that CPSF-73 is the pre-mRNA 3'-end-processing endonuclease.

The tumor suppressor Cdc73 functionally associates with CPSF and CstF 3' mRNA processing factors.

The CDC73 tumor suppressor gene is mutationally inactivated in hereditary and sporadic parathyroid tumors. Its product, the Cdc73 protein, is a component of the RNA polymerase II and chromatin-associated human Paf1 complex (Paf1C). Here, we show that Cdc73 physically associates with the cleavage and polyadenylation specificity factor (CPSF) and cleavage stimulation factor (CstF) complexes that are required for the maturation of mRNA 3' ends in the cell nucleus. Immunodepletion experiments indicate that the Cdc73-CPSF-CstF complex is necessary for 3' mRNA processing in vitro. Microarray analysis of CDC73 siRNA-treated cells revealed INTS6, a gene encoding a subunit of the Integrator complex, as an in vivo Cdc73 target. Cdc73 depletion by siRNA resulted in decreased INTS6 mRNA abundance, and decreased association of CPSF and CstF subunits with the INTS6 locus. Our results suggest that Cdc73 facilitates association of 3' mRNA processing factors with actively-transcribed chromatin and support the importance of links between tumor suppression and mRNA maturation.

Downregulation of METTL6 mitigates cell progression, migration, invasion and adhesion in hepatocellular carcinoma by inhibiting cell adhesion molecules.

RNA modifications have attracted increasing interest in recent years because they have been frequently implicated in various human diseases, including cancer, highlighting the importance of dynamic post­transcriptional modifications. Methyltransferase­like 6 (METTL6) is a member of the RNA methyltransferase family that has been identified in many cancers; however, little is known about its specific role or mechanism of action. In the present study, we aimed to study the expression levels and functional role of METTL6 in hepatocellular carcinoma (HCC), and further investigate the relevant pathways. To this end, we systematically conducted bioinformatics analysis of METTL6 in HCC using gene expression data and clinical information from a publicly available dataset. The mRNA expression levels of METTL6 were significantly upregulated in HCC tumor tissues compared to that in adjacent non­tumor tissues and strongly associated with poorer survival outcomes in patients with HCC. CRISPR/Cas9­mediated knockout of METTL6 in HCC cell lines remarkably inhibited colony formation, cell proliferation, cell migration, cell invasion and cell attachment ability. RNA sequencing analysis demonstrated that knockout of METTL6 significantly suppressed the expression of cell adhesion­related genes. However, chromatin immunoprecipitation sequencing results revealed no significant differences in enhancer activities between cells, which suggests that METTL6 may regulate genes of interest post­transcriptionally. In addition, it was demonstrated for the first time that METTL6 was localized in the cytosol as detected by immunofluorescence analysis, which indicates the plausible location of RNA modification mediated by METTL6. Our findings provide further insight into the function of RNA modifications in cancer and suggest a possible role of METTL6 as a therapeutic target in HCC.

Automated Endocardial Border Detection and Left Ventricular Functional Assessment in Echocardiography Using Deep Learning.

Endocardial border detection is a key step in assessing left ventricular systolic function in echocardiography. However, this process is still not sufficiently accurate, and manual retracing is often required, causing time-consuming and intra-/inter-observer variability in clinical practice. To address these clinical issues, more accurate and normalized automatic endocardial border detection would be valuable. Here, we develop a deep learning-based method for automated endocardial border detection and left ventricular functional assessment in two-dimensional echocardiographic videos. First, segmentation of the left ventricular cavity was performed in the six representative projections for a cardiac cycle. We employed four segmentation methods: U-Net, UNet++, UNet3+, and Deep Residual U-Net. UNet++ and UNet3+ showed a sufficiently high performance in the mean value of intersection over union and Dice coefficient. The accuracy of the four segmentation methods was then evaluated by calculating the mean value for the estimation error of the echocardiographic indexes. UNet++ was superior to the other segmentation methods, with the acceptable mean estimation error of the left ventricular ejection fraction of 10.8%, global longitudinal strain of 8.5%, and global circumferential strain of 5.8%, respectively. Our method using UNet++ demonstrated the best performance. This method may potentially support examiners and improve the workflow in echocardiography.

The metabolic stress-activated checkpoint LKB1-MARK3 axis acts as a tumor suppressor in high-grade serous ovarian carcinoma.

High-grade serous ovarian carcinoma (HGSOC) is the most aggressive gynecological malignancy, resulting in approximately 70% of ovarian cancer deaths. However, it is still unclear how genetic dysregulations and biological processes generate the malignant subtype of HGSOC. Here we show that expression levels of microtubule affinity-regulating kinase 3 (MARK3) are downregulated in HGSOC, and that its downregulation significantly correlates with poor prognosis in HGSOC patients. MARK3 overexpression suppresses cell proliferation and angiogenesis of ovarian cancer cells. The LKB1-MARK3 axis is activated by metabolic stress, which leads to the phosphorylation of CDC25B and CDC25C, followed by induction of G2/M phase arrest. RNA-seq and ATAC-seq analyses indicate that MARK3 attenuates cell cycle progression and angiogenesis partly through downregulation of AP-1 and Hippo signaling target genes. The synthetic lethal therapy using metabolic stress inducers may be a promising therapeutic choice to treat the LKB1-MARK3 axis-dysregulated HGSOCs.

Tumor Suppressive Role of the PRELP Gene in Ovarian Clear Cell Carcinoma.

Ovarian clear cell carcinoma (OCCC) has a poor prognosis, and its therapeutic strategy has not been established. PRELP is a leucine-rich repeat protein in the extracellular matrix of connective tissues. Although PRELP anchors the basement membrane to the connective tissue and is absent in most epithelial cancers, much remains unknown regarding its function as a regulator of ligand-mediated signaling pathways. Here, we obtained sets of differentially expressed genes by PRELP expression using OCCC cell lines. We found that more than 1000 genes were significantly altered by PRELP expression, particularly affecting the expression of a group of genes involved in the PI3K-AKT signaling pathway. Furthermore, we revealed the loss of active histone marks on the loci of the PRELP gene in patients with OCCC and how its forced expression inhibited cell proliferation. These findings suggest that PRELP is not only a molecule anchored in connective tissues but is also a signaling molecule acting in a tumor-suppressive manner. It can serve as the basis for early detection and novel therapeutic approaches for OCCC toward precision medicine.

Introducing AI to the molecular tumor board: one direction toward the establishment of precision medicine using large-scale cancer clinical and biological information.

Since U.S. President Barack Obama announced the Precision Medicine Initiative in his New Year's State of the Union address in 2015, the establishment of a precision medicine system has been emphasized worldwide, particularly in the field of oncology. With the advent of next-generation sequencers specifically, genome analysis technology has made remarkable progress, and there are active efforts to apply genome information to diagnosis and treatment. Generally, in the process of feeding back the results of next-generation sequencing analysis to patients, a molecular tumor board (MTB), consisting of experts in clinical oncology, genetic medicine, etc., is established to discuss the results. On the other hand, an MTB currently involves a large amount of work, with humans searching through vast databases and literature, selecting the best drug candidates, and manually confirming the status of available clinical trials. In addition, as personalized medicine advances, the burden on MTB members is expected to increase in the future. Under these circumstances, introducing cutting-edge artificial intelligence (AI) technology and information and communication technology to MTBs while reducing the burden on MTB members and building a platform that enables more accurate and personalized medical care would be of great benefit to patients. In this review, we introduced the latest status of elemental technologies that have potential for AI utilization in MTB, and discussed issues that may arise in the future as we progress with AI implementation.