Addressing 6 challenges in generative AI for digital health: A scoping review.

Generative artificial intelligence (AI) can exhibit biases, compromise data privacy, misinterpret prompts that are adversarial attacks, and produce hallucinations. Despite the potential of generative AI for many applications in digital health, practitioners must understand these tools and their limitations. This scoping review pays particular attention to the challenges with generative AI technologies in medical settings and surveys potential solutions. Using PubMed, we identified a total of 120 articles published by March 2024, which reference and evaluate generative AI in medicine, from which we synthesized themes and suggestions for future work. After first discussing general background on generative AI, we focus on collecting and presenting 6 challenges key for digital health practitioners and specific measures that can be taken to mitigate these challenges. Overall, bias, privacy, hallucination, and regulatory compliance were frequently considered, while other concerns around generative AI, such as overreliance on text models, adversarial misprompting, and jailbreaking, are not commonly evaluated in the current literature.

EZH2-driven immune evasion defines high-risk pediatric AML with t(16;21) FUS::ERG gene fusion.

Minimal improvement in outcomes for high-risk pediatric acute myeloid leukemia (pAML) patients has been made in the past decades. Nowhere is this more evident than in patients carrying a t(16;21)(p11;q22) FUS::ERG translocation; quick time to relapse and universal failure of hematopoietic stem cell transplant contribute to one of the lowest survival rates in childhood leukemia. Here, we have identified a unique, defining immune-evasion phenotype in FUS::ERG pAML driven by EZH2 and characterized by loss of MHC class I and II molecules and immune co-stimulatory receptors. This loss of immune engagement, present at diagnosis, allows pervasiveness of blasts that prove resistant to standard treatment. We demonstrate that treatment with the FDA-approved EZH2 inhibitor tazemetostat, in combination with IFN-γ, reverses the phenotype, re-expresses MHC receptor expression, and reduces blast viability. EZH2 inhibitors provide a novel therapeutic option for this high-risk population and may prove a beneficial supplemental treatment for FUS::ERG pAML.

Designing Oligonucleotide-Based FISH Probe Sets with PaintSHOP.

Fluorescent in situ hybridization (FISH) enables the visualization of the position and abundance of nucleic acid molecules in fixed cell and tissue samples. Many FISH-based methods employ sets of synthetic, computationally designed DNA oligonucleotide (oligo) FISH probes, including massively multiplexed imaging spatial transcriptomics and spatial genomics technologies. Oligo probes can either be designed de novo or accessed from an existing database of pre-discovered probe sequences. This chapter describes the use of PaintSHOP, a user-friendly, web-based platform for the design of sets of oligo-based FISH probes. PaintSHOP hosts large collections of pre-discovered probes from many model organisms and also provides collections of functional sequences such as primers and readout domains and interactive tools to add these functional sequences to selected probes. Detailed examples are provided for three common experimental scenarios.

Rapid-kinetics degron benchmarking reveals off-target activities and mixed agonism-antagonism of MYB inhibitors.

Attenuating aberrant transcriptional circuits holds great promise for the treatment of numerous diseases, including cancer. However, development of transcriptional inhibitors is hampered by the lack of a generally accepted functional cellular readout to characterize their target specificity and on-target activity. We benchmarked the direct gene-regulatory signatures of six agents reported as inhibitors of the oncogenic transcription factor MYB against targeted MYB degradation in a nascent transcriptomics assay. The inhibitors demonstrated partial specificity for MYB target genes but displayed significant off-target activity. Unexpectedly, the inhibitors displayed bimodal on-target effects, acting as mixed agonists-antagonists. Our data uncover unforeseen agonist effects of small molecules originally developed as TF inhibitors and argue that rapid-kinetics benchmarking against degron models should be used for functional characterization of transcriptional modulators.

Leukemia core transcriptional circuitry is a sparsely interconnected hierarchy stabilized by incoherent feed-forward loops.

Lineage-defining transcription factors form densely interconnected circuits in chromatin occupancy assays, but the functional significance of these networks remains underexplored. We reconstructed the functional topology of a leukemia cell transcription network from the direct gene-regulatory programs of eight core transcriptional regulators established in pre-steady state assays coupling targeted protein degradation with nascent transcriptomics. The core regulators displayed narrow, largely non-overlapping direct transcriptional programs, forming a sparsely interconnected functional hierarchy stabilized by incoherent feed-forward loops. BET bromodomain and CDK7 inhibitors disrupted the core regulators' direct programs, acting as mixed agonists/antagonists. The network is predictive of dynamic gene expression behaviors in time-resolved assays and clinically relevant pathway activity in patient populations.

Transcriptional Plasticity Drives Leukemia Immune Escape.

Relapse of acute myeloid leukemia (AML) after allogeneic bone marrow transplantation has been linked to immune evasion due to reduced expression of major histocompatibility complex class II (MHCII) genes through unknown mechanisms. In this work, we developed CORENODE, a computational algorithm for genome-wide transcription network decomposition that identified a transcription factor (TF) tetrad consisting of IRF8, MYB, MEF2C, and MEIS1, regulating MHCII expression in AML cells. We show that reduced MHCII expression at relapse is transcriptionally driven by combinatorial changes in the expression of these TFs, where MYB and IRF8 play major opposing roles, acting independently of the IFNγ/CIITA pathway. Beyond the MHCII genes, MYB and IRF8 antagonistically regulate a broad genetic program responsible for cytokine signaling and T-cell stimulation that displays reduced expression at relapse. A small number of cells with altered TF abundance and silenced MHCII expression are present at the time of initial leukemia diagnosis, likely contributing to eventual relapse. SIGNIFICANCE: Our findings point to an adaptive transcriptional mechanism of AML evolution after allogeneic transplantation whereby combinatorial fluctuations of TF expression under immune pressure result in the selection of cells with a silenced T-cell stimulation program. This article is highlighted in the In This Issue feature, p. 369.

A distinct core regulatory module enforces oncogene expression in KMT2A-rearranged leukemia.

Acute myeloid leukemia with KMT2A (MLL) rearrangements is characterized by specific patterns of gene expression and enhancer architecture, implying unique core transcriptional regulatory circuitry. Here, we identified the transcription factors MEF2D and IRF8 as selective transcriptional dependencies of KMT2A-rearranged AML, where MEF2D displays partially redundant functions with its paralog, MEF2C. Rapid transcription factor degradation followed by measurements of genome-wide transcription rates and superresolution microscopy revealed that MEF2D and IRF8 form a distinct core regulatory module with a narrow direct transcriptional program that includes activation of the key oncogenes MYC, HOXA9, and BCL2. Our study illustrates a mechanism of context-specific transcriptional addiction whereby a specific AML subclass depends on a highly specialized core regulatory module to directly enforce expression of common leukemia oncogenes.

An oncogenic enhancer encodes selective selenium dependency in AML.

Deregulation of transcription is a hallmark of acute myeloid leukemia (AML) that drives oncogenic expression programs and presents opportunities for therapeutic targeting. By integrating comprehensive pan-cancer enhancer landscapes with genetic dependency mapping, we find that AML-enriched enhancers encode for more selective tumor dependencies. We hypothesized that this approach could identify actionable dependencies downstream of oncogenic driver events and discovered a MYB-regulated AML-enriched enhancer regulating SEPHS2, a key component of the selenoprotein production pathway. Using a combination of patient samples and mouse models, we show that this enhancer upregulates SEPHS2, promoting selenoprotein production and antioxidant function required for AML survival. SEPHS2 and other selenoprotein pathway genes are required for AML growth in vitro. SEPHS2 knockout and selenium dietary restriction significantly delay leukemogenesis in vivo with little effect on normal hematopoiesis. These data validate the utility of enhancer mapping in target identification and suggest that selenoprotein production is an actionable target in AML.

Defining the transcriptional control of pediatric AML highlights RARA as a superenhancer-regulated druggable dependency.

Somatic mutations are rare in pediatric acute myeloid leukemia (pAML), indicating that alternate strategies are needed to identify targetable dependencies. We performed the first enhancer mapping of pAML in 22 patient samples. Generally, pAML samples were distinct from adult AML samples, and MLL (KMT2A)-rearranged samples were also distinct from non-KMT2A-rearranged samples. Focusing specifically on superenhancers (SEs), we identified SEs associated with many known leukemia regulators. The retinoic acid receptor alpha (RARA) gene was differentially regulated in our cohort, and a RARA-associated SE was detected in 64% of the study cohort across all cytogenetic and molecular subtypes tested. RARA SE+ pAML cell lines and samples exhibited high RARA messenger RNA levels. These samples were specifically sensitive to the synthetic RARA agonist tamibarotene in vitro, with slowed proliferation, apoptosis induction, differentiation, and upregulated retinoid target gene expression, compared with RARA SE- samples. Tamibarotene prolonged survival and suppressed the leukemia burden of an RARA SE+ pAML patient-derived xenograft mouse model compared with a RARA SE- patient-derived xenograft. Our work shows that examining chromatin regulation can identify new, druggable dependencies in pAML and provides a rationale for a pediatric tamibarotene trial in children with RARA-high AML.