SpatialSort: a Bayesian model for clustering and cell population annotation of spatial proteomics data.

MOTIVATION: Recent advances in spatial proteomics technologies have enabled the profiling of dozens of proteins in thousands of single cells in situ. This has created the opportunity to move beyond quantifying the composition of cell types in tissue, and instead probe the spatial relationships between cells. However, most current methods for clustering data from these assays only consider the expression values of cells and ignore the spatial context. Furthermore, existing approaches do not account for prior information about the expected cell populations in a sample. RESULTS: To address these shortcomings, we developed SpatialSort, a spatially aware Bayesian clustering approach that allows for the incorporation of prior biological knowledge. Our method is able to account for the affinities of cells of different types to neighbour in space, and by incorporating prior information about expected cell populations, it is able to simultaneously improve clustering accuracy and perform automated annotation of clusters. Using synthetic and real data, we show that by using spatial and prior information SpatialSort improves clustering accuracy. We also demonstrate how SpatialSort can perform label transfer between spatial and nonspatial modalities through the analysis of a real world diffuse large B-cell lymphoma dataset. AVAILABILITY AND IMPLEMENTATION: Source code is available on Github at: https://github.com/Roth-Lab/SpatialSort.

APOL6 predicts immunotherapy efficacy of bladder cancer by ferroptosis.

BACKGROUND: Immune checkpoint inhibitors (ICIs) are rapidly evolving in the management of bladder cancer (BLCA). Nevertheless, effective biomarkers for predicting immunotherapeutic outcomes in BLCA are still insufficient. Ferroptosis, a form of immunogenic cell death, has been found to enhance patient sensitivity to ICIs. However, the underlying mechanisms of ferroptosis in promoting immunotherapy efficacy in BLCA remain obscure. METHODS: Our analysis of The Cancer Genome Atlas (TCGA) mRNA data using single sample Gene Set Enrichment Analysis (ssGSEA) revealed two immunologically distinct subtypes. Based on these subtypes and various other public cohorts, we identified Apolipoprotein L6 (APOL6) as a biomarker predicting the efficacy of ICIs and explored its immunological correlation and predictive value for treatment. Furthermore, the role of APOL6 in promoting ferroptosis and its mechanism in regulating this process were experimentally validated. RESULTS: The results indicate that APOL6 has significant immunological relevance and is indicative of immunologically hot tumors in BLCA and many other cancers. APOL6, interacting with acyl-coenzyme A synthetase long-chain family member 4 (ACSL4), mediates immunotherapy efficacy by ferroptosis. Additionally, APOL6 is regulated by signal transducer and activator of transcription 1 (STAT1). CONCLUSIONS: To conclude, our findings indicate APOL6 has potential as a predictive biomarker for immunotherapy treatment success estimation and reveal the STAT1/APOL6/GPX4 axis as a critical regulatory mechanism in BLCA.

Effect of sludge humic acid-derived nano-biochars on anaerobic degradation of sulfamethoxazole by Shewanella oneidensis MR-1.

Some nano-biochars (nano-BCs) as electron mediators could enter into cells to directly promote intracellular electron transfer and cell activities. However, little information was available on the effect of nano-BCs on SMX degradation. In this study, nano-BCs were prepared using sludge-derived humic acid (SHA) and their effects on SMX degradation by Shewanella oneidensis MR-1 were investigated. Results showed that nano-BCs (Carbon dots, CDs, <10 nm) synthesized using SHA performed a better accelerating effect than that of the nano-BCs with a larger size (10-100 nm), which could be attributed to the better electron transfer abilities of CDs. The degradation rate of 10 mg/L SMX in the presence of 100 mg/L CDs was significantly increased by 84.6% compared to that without CDs. Further analysis showed that CDs could not only be combined with extracellular Fe(III) to accelerate its reduction, but also participate in the reduction of 4-aminobenzenesulphonic acid as an intermediate metabolite of SMX via coupling with extracellular Fe(III) reduction. Meanwhile, CDs could enter cells to directly participate in intracellular electron transfer, resulting in 32.2% and 25.2% increases of electron transfer system activity and ATP level, respectively. Moreover, the activities of SMX-degrading enzymes located in periplasm and cytoplasm were increased by around 2.2-fold in the presence of CDs. These results provide an insight into the accelerating effect of nano-BCs with the size of <10 nm on SMX degradation and an approach for SHA utilization.

Construction of metal interpretable scoring system and identification of tungsten as a novel risk factor in COPD.

Numerous studies have highlighted the correlation between metal intake and deteriorated pulmonary function, emphasizing its pivotal role in the progression of Chronic Obstructive Pulmonary Disease (COPD). However, the efficacy of traditional models is often compromised due to overfitting and high bias in datasets with low-level exposure, rendering them ineffective in delineating the contemporary risk trends associated with pulmonary diseases. To address these limitations, we embarked on developing advanced, interpretable models, crucial for elucidating the intricate mechanisms of metal toxicity and enriching the domain knowledge embedded in toxicity models. In this endeavor, we scrutinized extensive, long-term metal exposure datasets from NHANES to explore the interplay between metal and pulmonary functionality. Employing a variety of machine-learning approaches, we opted for the "Mixer of Experts" model for its proficiency in identifying a myriad of toxicological trends and sensitivities. We conceptualized and illustrated the TSAP (Toxicity Score at Population-level), a metal interpretable scoring system offering performance nearly equivalent to the amalgamation of standard interpretable methods addressing the "black box" conundrum. This streamlined, bifurcated procedural analysis proved instrumental in discerning established risk factors, thereby uncovering Tungsten as a novel contributor to COPD risk. SYNOPSIS: TSAP achieved satisfied performance with transparent interpretability, suggesting tungsten intake need further action for COPD prevention.

Probabilistic cell-type assignment of single-cell RNA-seq for tumor microenvironment profiling.

Single-cell RNA sequencing has enabled the decomposition of complex tissues into functionally distinct cell types. Often, investigators wish to assign cells to cell types through unsupervised clustering followed by manual annotation or via 'mapping' to existing data. However, manual interpretation scales poorly to large datasets, mapping approaches require purified or pre-annotated data and both are prone to batch effects. To overcome these issues, we present CellAssign, a probabilistic model that leverages prior knowledge of cell-type marker genes to annotate single-cell RNA sequencing data into predefined or de novo cell types. CellAssign automates the process of assigning cells in a highly scalable manner across large datasets while controlling for batch and sample effects. We demonstrate the advantages of CellAssign through extensive simulations and analysis of tumor microenvironment composition in high-grade serous ovarian cancer and follicular lymphoma.

Avadomide monotherapy in relapsed/refractory DLBCL: safety, efficacy, and a predictive gene classifier.

Treatment options for relapsed/refractory (R/R) diffuse large B-cell lymphoma (DLBCL) are limited, with no standard of care; prognosis is poor, with 4- to 6-month median survival. Avadomide (CC-122) is a cereblon-modulating agent with immunomodulatory and direct antitumor activities. This phase 1 dose-expansion study assessed safety and clinical activity of avadomide monotherapy in patients with de novo R/R DLBCL and transformed lymphoma. Additionally, a novel gene expression classifier, which identifies tumors with a high immune cell infiltration, was shown to enrich for response to avadomide in R/R DLBCL. Ninety-seven patients with R/R DLBCL, including 12 patients with transformed lymphoma, received 3 to 5 mg avadomide administered on continuous or intermittent schedules until unacceptable toxicity, disease progression, or withdrawal. Eighty-two patients (85%) experienced ≥1 grade 3/4 treatment-emergent adverse events (AEs), most commonly neutropenia (51%), infections (24%), anemia (12%), and febrile neutropenia (10%). Discontinuations because of AEs occurred in 10% of patients. Introduction of an intermittent 5/7-day schedule improved tolerability and reduced frequency and severity of neutropenia, febrile neutropenia, and infections. Among 84 patients with de novo R/R DLBCL, overall response rate (ORR) was 29%, including 11% complete response (CR). Responses were cell-of-origin independent. Classifier-positive DLBCL patients (de novo) had an ORR of 44%, median progression-free survival (mPFS) of 6 months, and 16% CR vs an ORR of 19%, mPFS of 1.5 months, and 5% CR in classifier-negative patients (P = .0096). Avadomide is being evaluated in combination with other antilymphoma agents. This trial was registered at www.clinicaltrials.gov as #NCT01421524.

Single Cell Phenotypic Profiling of 27 DLBCL Cases Reveals Marked Intertumoral and Intratumoral Heterogeneity.

Diffuse large B-cell lymphoma (DLBCL) is the most common histologic subtype of non-Hodgkin lymphoma and is notorious for its clinical heterogeneity. Patient outcomes can be predicted by cell-of-origin (COO) classification, demonstrating that the underlying transcriptional signature of malignant B-cells informs biological behavior in the context of standard combination chemotherapy regimens. In the current study, we used mass cytometry (CyTOF) to examine tumor phenotypes at the protein level with single cell resolution in a collection of 27 diagnostic DLBCL biopsy specimens from treatment naïve patients. We found that malignant B-cells from each patient occupied unique regions in 37-dimensional phenotypic space with no apparent clustering of samples into discrete subtypes. Interestingly, variable MHC class II expression was found to be the greatest contributor to phenotypic diversity. Within individual tumors, a subset of cases showed multiple phenotypic subpopulations, and in one case, we were able to demonstrate direct correspondence between protein-level phenotypic subsets and DNA mutation-defined subclones. In summary, CyTOF analysis can resolve both intertumoral and intratumoral heterogeneity among primary samples and reveals that each case of DLBCL is unique and may be comprised of multiple, genetically distinct subclones. © 2019 International Society for Advancement of Cytometry.

The Long Noncoding RNA TUG1 Promotes Laryngeal Cancer Proliferation and Migration.

BACKGROUND/AIMS: Researchers have shown that long noncoding RNAs are closely associated with the pathogenesis of laryngeal squamous cell carcinoma (LSCC). However, the role of the long noncoding RNA taurine-upregulated gene 1 (TUG1) in the pathogenesis of LSCC remains unclear, although it is recognized as an oncogenic regulator for several types of squamous cell carcinoma. METHODS: qRT-PCR was performed to measure the expression of TUG1 in LSCC tissues and cell lines. 3-(4,5-dimethyl-2-thiazolyl)-2,5-diphenyl-2-H-tetrazolium bromide (MTT) was used to measure the effect of TUG1 on cell proliferation. Transwell assay and flow cytometry were employed to determine the effect of TUG1 on cell migration and invasion. Western-blot were performed to explore the relation of TUG1 and p53 mRNA. RESULTS: Higher TUG1 expression in LSCC than in paired normal tumor-adjacent tissue specimens (N = 64) was observed using quantitative real-time polymerase chain reaction. Also, high TUG1 expression was positively associated with advanced T category, worse lymph node metastasis and late clinical stage. Furthermore, in vitro experiments demonstrated that silencing of TUG1 markedly inhibited proliferation, cell-cycle progression, migration, and invasion of LSCC cells, whereas depletion of TUG1 led to increased apoptosis. CONCLUSION: These findings demonstrated that upregulated TUG1 expression exerted oncogenic effects by promoting proliferation, migration, and invasion, and inhibiting apoptosis in LSCC cells.

YM155 decreases radiation-induced invasion and reverses epithelial-mesenchymal transition by targeting STAT3 in glioblastoma.

BACKGROUND: Radiotherapy constitutes a standard arm of therapy in the multimodal treatment of patients with glioblastoma (GBM). Ironically, studies have recently revealed that radiation can augment malignant progression, by promoting migration and invasion, which make the disease especially difficult to cure. Here, we investigated the anticancer effects of YM155, a purported radiosensitizer, in GBM cell lines. METHODS: GBM cell lines U251 and U87 were treated with YM155 to assess cytotoxicity and activity of the molecule in vitro. Nude mice were implanted with cells to generate orthotopic xenografts for in vivo studies. Response of cells to treatment was examined using cell viability, immunofluorescence, wound healing, and the Transwell invasion assay. Molecules potentially mediating response were examined through western blot analysis, phospho-kinase arrays, and qPCR. Cells were transfected with siRNA knockdown and gene expression constructs to identify molecular mediators of response. RESULTS: YM155 reduced viability of U251 and U87 cells and enhanced radiosensitivity through inhibition of homologous recombination. Besides, YM155 decreased invasion caused by radiation and led to expression changes in molecular markers associated with EMT. STAT3 was one of 10 molecules identified on a phosphokinase array exhibiting significant change in phosphorylation under YM155 treatment. Transfection with STAT3 siRNAs or expression constructs demonstrated that EMT changes were achieved by inhibiting the phosphorylation of STAT3 and were survivin-independent. Finally, combining YM155 and radiation in orthotopic xenografts reduced growth and prolonged overall survival of animals. CONCLUSIONS: YM155 decreased radiation-induced invasion in GBM cell lines in vitro and in vivo through inhibition of STAT3.

Integrated TCGA analysis implicates lncRNA CTB-193M12.5 as a prognostic factor in lung adenocarcinoma.

BACKGROUND: Lung cancer is a malignant tumor with the highest incidence and mortality around the world. Recent advances in RNA sequencing technology have enabled insights into long non-coding RNAs (lncRNAs), a previously largely overlooked species in dissecting lung cancer pathology. METHODS: In this study, we used a comprehensive bioinformatics analysis strategy to identify lncRNAs closely associated with lung adenocarcinoma, using the RNA sequencing datasets collected from more than 500 lung adenocarcinoma patients and deposited at The Cancer Genome Atlas (TCGA) database. RESULTS: Differential expression analysis highlighted lncRNAs CTD-2510F5.4 and CTB-193M12.5, both of which were significantly upregulated in cancerous specimens. Moreover, network analyses showed highly correlated expression levels of both lncRNAs with those of differentially expressed protein-coding genes, and suggested central regulatory roles of both lncRNAs in the gene co-expression network. Importantly, expression of CTB-193M12.5 showed strong negative correlation with patient survival. CONCLUSIONS: Our study mined existing TCGA datasets for novel factors associated with lung adenocarcinoma, and identified a largely unknown lncRNA as a potential prognostic factor. Further investigation is warranted to characterize the roles and significance of CTB-193M12.5 in lung adenocarcinoma biology.

Leukemia stem cells in T-ALL require active Hif1α and Wnt signaling.

The Wnt signaling pathway has been shown to play important roles in normal hematopoietic stem cell biology and in the development of both acute and chronic myelogenous leukemia. Its role in maintaining established leukemia stem cells, which are more directly relevant to patients with disease, however, is less clear. To address what role Wnt signaling may play in T-cell acute lymphoblastic leukemia (T-ALL), we used a stably integrated fluorescent Wnt reporter construct to interrogate endogenous Wnt signaling activity in vivo. In this study, we report that active Wnt signaling is restricted to minor subpopulations within bulk tumors, that these Wnt-active subsets are highly enriched for leukemia-initiating cells (LICs), and that genetic inactivation of ß-catenin severely reduces LIC frequency. We show further that ß-catenin transcription is upregulated by hypoxia through hypoxia-inducible factor 1α (Hif1α) stabilization, and that deletion of Hif1α also severely reduces LIC frequency. Of note, the deletion of ß-catenin or Hif1α did not impair the growth or viability of bulk tumor cells, suggesting that elements of the Wnt and Hif pathways specifically support leukemia stem cells. We also confirm the relevance of these findings to human disease using cell lines and patient-derived xenografts, suggesting that targeting these pathways could benefit patients with T-ALL.

EphrinB1 and EphrinB2 regulate T cell chemotaxis and migration in experimental autoimmune encephalomyelitis and multiple sclerosis.

T cells are believed to be key effector cells in multiple sclerosis (MS). In this study, we examined the roles of T cell ephrinB1 (EFNB1) and ephrinB2 (EFNB2) in the pathogenesis of experimental autoimmune encephalomyelitis (EAE) and MS. We provide evidence that animals with T cell specific double deletion of EFNB1 and EFNB2 (dKO) have reduced proliferation in response to MOG35-55, defective Th1 and Th17 differentiations and significantly lower scores of MOG-induced EAE. We further demonstrate that dKO T cells are compromised in their ability to migrate into the CNS of EAE animals in vivo and towards multiple chemokines in vitro. Using deletion mutations, we identified a critical 11-aa EFNB1 intracellular domain segment that controls T cell chemotaxis towards CCL21. In humans, EFNB1 and EFNB2 are highly expressed in Th1 and Th17 cells and EFNB1- and EFNB2-expressing T cells are found among immune cell infiltrates in MS lesions. Reverse signaling through EFNB1 and EFNB2 in human Th17 cells enhances their migration through a monolayer of blood brain barrier endothelial cells. Our study demonstrates that expression of EFNB1 and EFNB2 is implicated in Th cell differentiation and migration to inflammatory sites in both EAE and MS.

TNF-like ligand 1A (TL1A) gene knockout leads to ameliorated collagen-induced arthritis in mice: implication of TL1A in humoral immune responses.

TNF-like ligand 1A (TL1A), also known as TNFSF15, is a member of the TNF superfamily. Its known receptor is death receptor 3 (DR3). In humans, TL1A also binds to a secreted TNF family member called decoy receptor 3, which interferes with the interaction between TL1A and DR3. TL1A/DR3 signal has been implicated in several autoimmune diseases in animal models as well as in clinical conditions. We generated TL1A gene knockout (KO) mice to assess its role in collagen-induced arthritis (CIA), a mouse model of human rheumatoid arthritis. The KO mice were fertile and had no visible anomalies. Their lymphoid organ size and cellularity, T and B cell subpopulations, Th cell and regulatory T cell development in vivo and in vitro, and antiviral immune responses were comparable to those of wild-type mice. However, the KO mice presented ameliorated CIA in terms of clinical scores, disease incidence, and pathological scores. The KO mice had reduced titers of pathogenic anti-collagen Abs in the sera. No apparent defect was found in the function of follicular Th cells. We revealed that plasma cells but not B cells expressed high levels of DR3 and were direct targets of TL1A. In the presence of TL1A, they survived better and produced more pathogenic Ab. This study presented novel knowledge about the role of TL1A in humoral immune responses and its mechanism of action in CIA pathogenesis.

Efficient In/SSZ-39 catalysts for the selective catalytic reduction of NO with CH4.

The M/SSZ-39 catalysts (M = In, Co, Cu, Fe) with different metal species and metal loadings were synthesized using the wet impregnation method on a small-pore SSZ-39 molecular sieve. X-ray diffraction (XRD), transmission electron microscopy (TEM), nitrogen adsorption-dehydrogenation and hydrogen temperature program reduction (H2-TPR) were employed to characterize the effects of various metal components and metal loadings on the performance of CH4 selective catalytic reduction of NO reaction (CH4-SCR). The characterization results showed that the In/SSZ-39 catalyst exhibited significantly higher catalytic activity compared to the Cu-, Co-, and Fe/SSZ-39 catalysts, suggesting that indium (In) is a more suitable active ingredient for the CH4-SCR reaction. The xIn/SSZ-39 (x = 1, 2, 3, x represents the In loadings of 1.0 wt%, 2.0 wt% and 3.0 wt%) catalysts, with different In loadings, all present excellent CH4-SCR performance. By varying the In loadings, the type of In species present in the catalyst can be regulated, thus enhancing DeNOx activity and CH4 selectivity in the CH4-SCR reaction. At a low temperature of 400 °C and a low CH4/NO feed ratio (CH4/NO = 1), the 3In/SSZ-39 catalyst, featuring highly active InOx clusters, achieves the best low-temperature CH4-SCR performance, with a high NO conversion rate of up to 90% and a CH4 selectivity of up to 74.2%.

Long-term in situ straw returning increased soil aggregation and aggregate associated organic carbon fractions in a paddy soil.

Despite the well-documentation of the effects of straw returning on soil structural stability and fertility, its long-term in situ impacts on profile aggregate size composition and organic carbon (OC) fractions remain poorly investigated. To address this research gap, the present nine-year field trial explored the co-effects of straw returning and chemical fertilization on soil total OC (TOC), dissolved OC (DOC), resistant OC (ROC), easily oxidative OC (EOC), as well as soil aggregate size composition of different soil depths (0-15, 15-30, and 30-50 cm) in a paddy field, East China. To do so, four different treatments were set up, including no straw returning plus no fertilization (CK), conventional fertilization (F), straw returning plus conventional fertilization (SF), and straw returning plus 80 % conventional fertilization (SDF). Our findings revealed that the >2 mm aggregates were dominant in all treatments, particularly in SF and SDF 0-30 cm soil layers ranging from 62 to 70 % (P < 0.05). The highest TOC contents happened in SF topsoil 0.25-2 mm aggregates (0-30 cm; 21.4 g/kg), 44.4 and 21.1 % higher than the CK and F treatments, respectively (P < 0.05). Regardless of soil depth, the highest EOC contents occurred in SDF 0.25-2 mm aggregates varying from 2.36 ± 0.1 to 7.7 ± 0.57 g/kg (P < 0.05). Further, the highest ROC and DOC contents took place in SF 0.25-2 mm and SF > 2 mm aggregates, respectively, differing from 3.86 to 15.8 g/kg and 250-413 mg/kg, respectively (P < 0.05). It is also worth noting that SF had the highest crop productivity with the seasonal yields of 3.51 and 13.5 t ha-1 for rapeseed and rice, respectively (P < 0.05). Altogether, our findings suggested that long-term straw returning coupled with conventional (SF) or 80 % conventional (SDF) fertilization are the most efficient schemes for the formation/stability of soil aggregates, as well as for the accumulation of different soil OC fractions and crop productivity in the Chaohu Lake agricultural soils of East China.

Bifunctional sludge-derived redox carbon dots with photoelectron storage and delivery properties for ammonia production by photosensitized Shewanella oneidensis MR-1.

Combining the light-harvesting capabilities of photosensitizers with microbial catalysis shows great potential in solar-driven biomanufacturing. However, little information is available about the effects of photosensitizers on the photoelectron transport during the dissimilatory nitrate reduction to ammonium (DNRA) process. Herein, redox carbon dots (CDs-500) were prepared from sludge via the pyrolysis-Fenton reaction and then used to construct a photosynthetic system with Shewanella oneidensis MR-1. The MR-1/CDs-500 photosynthetic system showed a 5.9-fold increase in ammonia production (4.9 mmol(NH3)·g-1(protein)·h-1) with a high selectivity of 94.0 %. The photoelectrons were found to be stored in CDs-500 and transferred into the cells. During the inward electron transport, the intracellular CDs-500 could be used as the direct photoelectron transfer stations between outer membrane cytochrome c and DNRA-related enzymes without the involvement of CymA and MtrA. This work provides a new method for converting waste into functional catalysts and increases solar-driven NH3 production to a greater extent.

Electron transferring with oxygen defects on Ni-promoted Pd/Al2O3 catalysts for low-temperature lean methane combustion.

Methane (CH4) is the second most consequential greenhouse gas after CO2, with a substantial global warming potential. The CH4 catalytic combustion offers an efficient method for the elimination of CH4. However, improving the catalytic performance of Pd-based materials for low-temperature CH4 combustion remains a big challenge. In this study, we synthesized an enhanced Pd/5NiAlOx catalyst that demonstrated superior catalytic activity and improved water resistance compared to the Pd/Al2O3 catalyst. Specifically, the T90 was decreased by over 100 °C under both dry and wet conditions. Introducing Ni resulted in an enormously enhanced number of oxygen defects on the obtained 5NiAlOx support. This defect-rich support facilitates the anchoring of PdO through increased electron transfer, thereby inhibiting the production of high-valence Pd(2+δ)+ and stimulating the generation of unsaturated Pd sites. Pd0 can effectively activate surface oxygen and PdO plays a significant role in activating CH4, resulting in high activity for Pd/5NiAlOx. On the other hand, the increased water resistance of Pd/5NiAlOx was mainly due to the generation of *OOH species and the lower accumulation of surface -OH species during the reaction process.

TRBC1 in flow cytometry: Assay development, validation, and reporting considerations.

The assessment of T-cell clonality by flow cytometry has long been suboptimal, relying on aberrant marker expression and/or intensity. The introduction of TRBC1 shows much promise for improving the diagnosis of T-cell neoplasms in the clinical flow laboratory. Most laboratories considering this marker already have existing panels designed for T-cell workups and will be determining how best to incorporate TRBC1. We present this comprehensive summary of TRBC1 and supplemental case examples to familiarize the flow cytometry community with its potential for routine application, provide examples of how to incorporate it into T-cell panels, and signal caution in interpreting the results in certain diagnostic scenarios where appropriate.

MAGIC-DR: An interpretable machine-learning guided approach for acute myeloid leukemia measurable residual disease analysis.

Multiparameter flow cytometry is widely used for acute myeloid leukemia minimal residual disease testing (AML MRD) but is time consuming and demands substantial expertise. Machine learning offers potential advancements in accuracy and efficiency, but has yet to be widely adopted for this application. To explore this, we trained single cell XGBoost classifiers from 98 diagnostic AML cell populations and 30 MRD negative samples. Performance was assessed by cross-validation. Predictions were integrated with UMAP as a heatmap parameter for an augmented/interactive AML MRD analysis framework, which was benchmarked against traditional MRD analysis for 25 test cases. The results showed that XGBoost achieved a median AUC of 0.97, effectively distinguishing diverse AML cell populations from normal cells. When integrated with UMAP, the classifiers highlighted MRD populations against the background of normal events. Our pipeline, MAGIC-DR, incorporated classifier predictions and UMAP into flow cytometry standard (FCS) files. This enabled a human-in-the-loop machine learning guided MRD workflow. Validation against conventional analysis for 25 MRD samples showed 100% concordance in myeloid blast detection, with MAGIC-DR also identifying several immature monocytic populations not readily found by conventional analysis. In conclusion, Integrating a supervised classifier with unsupervised dimension reduction offers a robust method for AML MRD analysis that can be seamlessly integrated into conventional workflows. Our approach can support and augment human analysis by highlighting abnormal populations that can be gated on for quantification and further assessment. This has the potential to speed up MRD analysis, and potentially improve detection sensitivity for certain AML immunophenotypes.