An artificial intelligence-assisted clinical framework to facilitate diagnostics and translational discovery in hematologic neoplasia.

BACKGROUND: The increasing volume and intricacy of sequencing data, along with other clinical and diagnostic data, like drug responses and measurable residual disease, creates challenges for efficient clinical comprehension and interpretation. Using paediatric B-cell precursor acute lymphoblastic leukaemia (BCP-ALL) as a use case, we present an artificial intelligence (AI)-assisted clinical framework clinALL that integrates genomic and clinical data into a user-friendly interface to support routine diagnostics and reveal translational insights for hematologic neoplasia. METHODS: We performed targeted RNA sequencing in 1365 cases with haematological neoplasms, primarily paediatric B-cell precursor acute lymphoblastic leukaemia (BCP-ALL) from the AIEOP-BFM ALL study. We carried out fluorescence in situ hybridization (FISH), karyotyping and arrayCGH as part of the routine diagnostics. The analysis results of these assays as well as additional clinical information were integrated into an interactive web interface using Bokeh, where the main graph is based on Uniform Manifold Approximation and Projection (UMAP) analysis of the gene expression data. At the backend of the clinALL, we built both shallow machine learning models and a deep neural network using Scikit-learn and PyTorch respectively. FINDINGS: By applying clinALL, 78% of undetermined patients under the current diagnostic protocol were stratified, and ambiguous cases were investigated. Translational insights were discovered, including IKZF1plus status dependent subpopulations of BCR::ABL1 positive patients, and a subpopulation within ETV6::RUNX1 positive patients that has a high relapse frequency. Our best machine learning models, LDA and PASNET-like neural network models, achieve F1 scores above 97% in predicting patients' subgroups. INTERPRETATION: An AI-assisted clinical framework that integrates both genomic and clinical data can take full advantage of the available data, improve point-of-care decision-making and reveal clinically relevant insights promptly. Such a lightweight and easily transferable framework works for both whole transcriptome data as well as the cost-effective targeted RNA-seq, enabling efficient and equitable delivery of personalized medicine in small clinics in developing countries. FUNDING: German Ministry of Education and Research (BMBF), German Research Foundation (DFG) and Foundation for Polish Science.

The IL-7R antagonist Lusvertikimab reduces leukemic burden in xenograft-ALL via antibody-dependent cellular phagocytosis.

Acute lymphoblastic leukemia (ALL) arises from the uncontrolled proliferation of precursor B or T cells (BCP- or T-ALL). Current treatment protocols obtain high cure rates in children but are based on toxic polychemotherapy. Novel therapies are urgently needed, especially in relapsed/refractory (r/r) disease, high-risk leukemias and T-ALL, where immunotherapy approaches remain scarce. While the Interleukin-7 receptor (IL-7R) plays a pivotal role in ALL development, no IL-7R-targeting immunotherapy has yet reached clinical application in ALL. The IL-7Rα chain (CD127)-targeting IgG4 antibody Lusvertikimab (formerly OSE-127) is a full antagonist of the IL-7R pathway showing a good safety profile in healthy volunteers. Here, we show that ~85% of ALL cases express surface CD127. We demonstrate significant in vivo efficacy of Lusvertikimab immunotherapy in a heterogeneous cohort of BCP- and T-ALL patient-derived xenografts (PDX) in minimal residual disease (MRD) and overt leukemia models, including r/r and high-risk leukemias. Importantly, Lusvertikimab was particularly effective when combined with polychemotherapy in a phase 2-like PDX study with CD127high samples leading to MRD-negativity in >50% of mice treated with combination therapy. Mechanistically, Lusvertikimab targeted ALL cells via a dual mode of action comprising direct IL-7R antagonistic activity and induction of macrophage-mediated antibody-dependent cellular phagocytosis (ADCP). Lusvertikimab-mediated in vitro ADCP levels significantly correlated with CD127 expression levels and the reduction of leukemia burden upon treatment of PDX animals in vivo. Altogether, through its dual mode of action and good safety profile, Lusvertikimab may represent a novel immunotherapy option for any CD127-positive ALL, particularly in combination with standard-of-care polychemotherapy.

SNUPN deficiency causes a recessive muscular dystrophy due to RNA mis-splicing and ECM dysregulation.

SNURPORTIN-1, encoded by SNUPN, plays a central role in the nuclear import of spliceosomal small nuclear ribonucleoproteins. However, its physiological function remains unexplored. In this study, we investigate 18 children from 15 unrelated families who present with atypical muscular dystrophy and neurological defects. Nine hypomorphic SNUPN biallelic variants, predominantly clustered in the last coding exon, are ascertained to segregate with the disease. We demonstrate that mutant SPN1 failed to oligomerize leading to cytoplasmic aggregation in patients' primary fibroblasts and CRISPR/Cas9-mediated mutant cell lines. Additionally, mutant nuclei exhibit defective spliceosomal maturation and breakdown of Cajal bodies. Transcriptome analyses reveal splicing and mRNA expression dysregulation, particularly in sarcolemmal components, causing disruption of cytoskeletal organization in mutant cells and patient muscle tissues. Our findings establish SNUPN deficiency as the genetic etiology of a previously unrecognized subtype of muscular dystrophy and provide robust evidence of the role of SPN1 for muscle homeostasis.

Further delineation of the rare GDACCF (global developmental delay, absent or hypoplastic corpus callosum, dysmorphic facies syndrome): genotype and phenotype of 22 patients with ZNF148 mutations.

BACKGROUND: Pathogenic variants in the zinc finger protein coding genes are rare causes of intellectual disability and congenital malformations. Mutations in the ZNF148 gene causing GDACCF syndrome (global developmental delay, absent or hypoplastic corpus callosum, dysmorphic facies; MIM #617260) have been reported in five individuals so far. METHODS: As a result of an international collaboration using GeneMatcher Phenome Central Repository and personal communications, here we describe the clinical and molecular genetic characteristics of 22 previously unreported individuals. RESULTS: The core clinical phenotype is characterised by developmental delay particularly in the domain of speech development, postnatal growth retardation, microcephaly and facial dysmorphism. Corpus callosum abnormalities appear less frequently than suggested by previous observations. The identified mutations concerned nonsense or frameshift variants that were mainly located in the last exon of the ZNF148 gene. Heterozygous deletion including the entire ZNF148 gene was found in only one case. Most mutations occurred de novo, but were inherited from an affected parent in two families. CONCLUSION: The GDACCF syndrome is clinically diverse, and a genotype-first approach, that is, exome sequencing is recommended for establishing a genetic diagnosis rather than a phenotype-first approach. However, the syndrome may be suspected based on some recurrent, recognisable features. Corpus callosum anomalies were not as constant as previously suggested, we therefore recommend to replace the term 'GDACCF syndrome' with 'ZNF148-related neurodevelopmental disorder'.

The Gene Expression Classifier ALLCatchR Identifies B-cell Precursor ALL Subtypes and Underlying Developmental Trajectories Across Age.

Current classifications (World Health Organization-HAEM5/ICC) define up to 26 molecular B-cell precursor acute lymphoblastic leukemia (BCP-ALL) disease subtypes by genomic driver aberrations and corresponding gene expression signatures. Identification of driver aberrations by transcriptome sequencing (RNA-Seq) is well established, while systematic approaches for gene expression analysis are less advanced. Therefore, we developed ALLCatchR, a machine learning-based classifier using RNA-Seq gene expression data to allocate BCP-ALL samples to all 21 gene expression-defined molecular subtypes. Trained on n = 1869 transcriptome profiles with established subtype definitions (4 cohorts; 55% pediatric / 45% adult), ALLCatchR allowed subtype allocation in 3 independent hold-out cohorts (n = 1018; 75% pediatric / 25% adult) with 95.7% accuracy (averaged sensitivity across subtypes: 91.1% / specificity: 99.8%). High-confidence predictions were achieved in 83.7% of samples with 98.9% accuracy. Only 1.2% of samples remained unclassified. ALLCatchR outperformed existing tools and identified novel driver candidates in previously unassigned samples. Additional modules provided predictions of samples blast counts, patient's sex, and immunophenotype, allowing the imputation in cases where these information are missing. We established a novel RNA-Seq reference of human B-lymphopoiesis using 7 FACS-sorted progenitor stages from healthy bone marrow donors. Implementation in ALLCatchR enabled projection of BCP-ALL samples to this trajectory. This identified shared proximity patterns of BCP-ALL subtypes to normal lymphopoiesis stages, extending immunophenotypic classifications with a novel framework for developmental comparisons of BCP-ALL. ALLCatchR enables RNA-Seq routine application for BCP-ALL diagnostics with systematic gene expression analysis for accurate subtype allocation and novel insights into underlying developmental trajectories.

Variants in FGF10 cause early onset of severe childhood interstitial lung disease: A detailed description of four affected children.

INTRODUCTION: Fibroblast growth factor 10 (FGF10) is a signaling molecule with a well-established role for lung branching morphogenesis. Rare heterozygous, deleterious variants in the FGF10 gene are known causes of the lacrimo-auriculo-dento-digital (LADD) syndrome and aplasia of lacrimal and salivary glands. Previous studies indicate that pathogenic variants in FGF10 can cause childhood Interstitial Lung Disease (chILD) due to severe diffuse developmental disorders of the lung, but detailed reports on clinical presentation and follow-up of affected children are lacking. METHODS: We describe four children with postnatal onset of chILD and heterozygous variants in FGF10, each detected by exome or whole genome sequencing. RESULTS: All children presented with postnatal respiratory failure. Two children died within the first 2 days of life, one patient died at age of 12 years due to right heart failure related to severe pulmonary hypertension (PH) and one patient is alive at age of 6 years, but still symptomatic. Histopathological analysis of lung biopsies from the two children with early postpartum demise revealed diffuse developmental disorder representing acinar dysplasia and interstitial fibrosis. Sequential biopsies of the child with survival until the age of 12 years revealed alveolar simplification and progressive interstitial fibrosis. DISCUSSION: Our report extends the phenotype of FGF10-related disorders to early onset chILD with progressive interstitial lung fibrosis and PH. Therefore, FGF10-related disorder should be considered even without previously described syndromic stigmata in children with postnatal respiratory distress, not only when leading to death in the neonatal period but also in case of persistent respiratory complaints and PH.

Parallel deletion and duplication at 7q11.23 in a silent carrier for two reciprocal syndromic disorders.

Partial deletions at chromosome 7q11.23 are causative for the autosomal-dominant Williams-Beuren syndrome (WBS), whereas the partial duplication of this region leads to the 7q11.23 duplication syndrome. Both syndromes are highly penetrant and occur with a frequency of 1:7500-10,000 (WBS) and 1:13,000-20,000 (7q11.23 duplication syndrome). They are associated with multiple organ defects, intellectual disability, and typical facial dysmorphisms showing broad phenotypic variability. The 7q11.23 region is susceptible to chromosomal rearrangements due to flanking segmental duplications and regions of long repetitive DNA segments. Here, we report on a family with two children affected by WBS and clinically unaffected parents. Interestingly, metaphase fluorescence in situ hybridization (FISH) revealed a deletion on 7q11.23 in the father. Intensive genetic testing, using interphase FISH, whole genome sequencing and optical genome mapping led to the confirmation of a 1.5 Mb deletion at one 7q11.23 allele and the identification of a reciprocal 1.8 Mb duplication at the other allele. This finding is highly important regarding genetic counseling in this family. The father is a silent carrier for two syndromic disorders, thus his risk to transmit a disease-causing allele is 100%. To the best of our knowledge we, here, report on the first case in which the phenotype of a microdeletion/microduplication syndrome was compensated by its reciprocal counterpart.

Systematic genetic analysis of pediatric patients with autoinflammatory diseases.

Monogenic autoinflammatory diseases (AID) encompass a growing group of inborn errors of the innate immune system causing unprovoked or exaggerated systemic inflammation. Diagnosis of monogenic AID requires an accurate description of the patients' phenotype, and the identification of highly penetrant genetic variants in single genes is pivotal. We performed whole exome sequencing (WES) of 125 pediatric patients with suspected monogenic AID in a routine genetic diagnostic setting. Datasets were analyzed in a step-wise approach to identify the most feasible diagnostic strategy. First, we analyzed a virtual gene panel including 13 genes associated with known AID and, if no genetic diagnosis was established, we then analyzed a virtual panel including 542 genes published by the International Union of Immunological Societies associated including all known inborn error of immunity (IEI). Subsequently, WES data was analyzed without pre-filtering for known AID/IEI genes. Analyzing 13 genes yielded a definite diagnosis in 16.0% (n = 20). The diagnostic yield was increased by analyzing 542 genes to 20.8% (n = 26). Importantly, expanding the analysis to WES data did not increase the diagnostic yield in our cohort, neither in single WES analysis, nor in trio-WES analysis. The study highlights that the cost- and time-saving analysis of virtual gene panels is sufficient to rapidly confirm the differential diagnosis in pediatric patients with AID. WES data or trio-WES data analysis as a first-tier diagnostic analysis in patients with suspected monogenic AID is of limited benefit.

Graph4Med: a web application and a graph database for visualizing and analyzing medical databases.

BACKGROUND: Medical databases normally contain large amounts of data in a variety of forms. Although they grant significant insights into diagnosis and treatment, implementing data exploration into current medical databases is challenging since these are often based on a relational schema and cannot be used to easily extract information for cohort analysis and visualization. As a consequence, valuable information regarding cohort distribution or patient similarity may be missed. With the rapid advancement of biomedical technologies, new forms of data from methods such as Next Generation Sequencing (NGS) or chromosome microarray (array CGH) are constantly being generated; hence it can be expected that the amount and complexity of medical data will rise and bring relational database systems to a limit. DESCRIPTION: We present Graph4Med, a web application that relies on a graph database obtained by transforming a relational database. Graph4Med provides a straightforward visualization and analysis of a selected patient cohort. Our use case is a database of pediatric Acute Lymphoblastic Leukemia (ALL). Along routine patients' health records it also contains results of latest technologies such as NGS data. We developed a suitable graph data schema to convert the relational data into a graph data structure and store it in Neo4j. We used NeoDash to build a dashboard for querying and displaying patients' cohort analysis. This way our tool (1) quickly displays the overview of patients' cohort information such as distributions of gender, age, mutations (fusions), diagnosis; (2) provides mutation (fusion) based similarity search and display in a maneuverable graph; (3) generates an interactive graph of any selected patient and facilitates the identification of interesting patterns among patients. CONCLUSION: We demonstrate the feasibility and advantages of a graph database for storing and querying medical databases. Our dashboard allows a fast and interactive analysis and visualization of complex medical data. It is especially useful for patients similarity search based on mutations (fusions), of which vast amounts of data have been generated by NGS in recent years. It can discover relationships and patterns in patients cohorts that are normally hard to grasp. Expanding Graph4Med to more medical databases will bring novel insights into diagnostic and research.

OnkoRiskNET: a multicenter, interdisciplinary, telemedicine-based model to improve care for patients with a genetic tumor risk syndrome.

BACKGROUND: Genetic tumor risk syndromes are responsible for at least five to ten percent of the 4 million cases of cancer diagnosed in Europe every year. Currently, the care of oncological patients suffers from a lack of specialists in medical genetics and also a lack of access to genetic care in rural areas and structured care pathways between oncologists and medical geneticists. As a result, genetic tumor risk syndromes are underdiagnosed with potentially fatal consequences for patients and their families. METHODS: The OnkoRiskNET study is supported by a grant from the Federal Joint Committee of the Federal Republic of Germany. The study will include 2,000 oncological index patients from oncology practices in Lower Saxony and Saxony after the start of the study in July 2021. Randomization is carried out by means of a stepped wedge design at the level of the practices. Patients either go through routine care or the new form of care with structured cooperation between medical geneticists and oncologists, case management and the use of telemedical genetic counseling. Using a mixed-methods approach, the following parameters will be evaluated in the control and intervention group: (1) Conducted genetic counseling sessions by patients with suspected tumor risk syndrome and their first degree relatives; (2) Patient satisfaction and psychological distress after genetic counseling and testing; (3) Factors influencing the acceptance and experience of telemedical genetic counseling; (4) Satisfaction of oncologists and medical genetics with the structured pathway; (5) Cost efficiency of the new form of care. DISCUSSION: OnkoRiskNET aims to close the gap in care through the formation of a cooperation network between practicing oncologists and specialists in medical genetics and the use of telemedical genetic counseling, thereby, increasing the diagnostic rate in genetic tumor risk syndromes and serving as a model for future genetic care in Germany. TRIAL REGISTRATION: Trial was registered on 01.12.2021 in the German Clinical Trial Register ( https://trialsearch.who.int/ ) with the DRKS-ID:  DRKS00026679 . TITLE: Cooperation network for the provision of local care for patients and families with a genetic tumour risk syndrome. Trial acronym: OnkoRiskNET. Protocol version 1.1.

The Clinical Utility of Optical Genome Mapping for the Assessment of Genomic Aberrations in Acute Lymphoblastic Leukemia.

Acute lymphoblastic leukemia (ALL) is the most prevalent type of cancer occurring in children. ALL is characterized by structural and numeric genomic aberrations that strongly correlate with prognosis and clinical outcome. Usually, a combination of cyto- and molecular genetic methods (karyotyping, array-CGH, FISH, RT-PCR, RNA-Seq) is needed to identify all aberrations relevant for risk stratification. We investigated the feasibility of optical genome mapping (OGM), a DNA-based method, to detect these aberrations in an all-in-one approach. As proof of principle, twelve pediatric ALL samples were analyzed by OGM, and results were validated by comparing OGM data to results obtained from routine diagnostics. All genomic aberrations including translocations (e.g., dic(9;12)), aneuploidies (e.g., high hyperdiploidy) and copy number variations (e.g., IKZF1, PAX5) known from other techniques were also detected by OGM. Moreover, OGM was superior to well-established techniques for resolution of the more complex structure of a translocation t(12;21) and had a higher sensitivity for detection of copy number alterations. Importantly, a new and unknown gene fusion of JAK2 and NPAT due to a translocation t(9;11) was detected. We demonstrate the feasibility of OGM to detect well-established as well as new putative prognostic markers in an all-in-one approach in ALL. We hope that these limited results will be confirmed with testing of more samples in the future.

Increased prostaglandin-D2 in male STAT3-deficient hearts shifts cardiac progenitor cells from endothelial to white adipocyte differentiation.

Cardiac levels of the signal transducer and activator of transcription factor-3 (STAT3) decline with age, and male but not female mice with a cardiomyocyte-specific STAT3 deficiency conditional knockout (CKO) display premature age-related heart failure associated with reduced cardiac capillary density. In the present study, isolated male and female CKO-cardiomyocytes exhibit increased prostaglandin (PG)-generating cyclooxygenase-2 (COX-2) expression. The PG-degrading hydroxyprostaglandin-dehydrogenase-15 (HPGD) expression is only reduced in male cardiomyocytes, which is associated with increased prostaglandin D2 (PGD2) secretion from isolated male but not female CKO-cardiomyocytes. Reduced HPGD expression in male cardiomyocytes derive from impaired androgen receptor (AR)-signaling due to loss of its cofactor STAT3. Elevated PGD2 secretion in males is associated with increased white adipocyte accumulation in aged male but not female hearts. Adipocyte differentiation is enhanced in isolated stem cell antigen-1 (SCA-1)+ cardiac progenitor cells (CPC) from young male CKO-mice compared with the adipocyte differentiation of male wild-type (WT)-CPC and CPC isolated from female mice. Epigenetic analysis in freshly isolated male CKO-CPC display hypermethylation in pro-angiogenic genes (Fgfr2, Epas1) and hypomethylation in the white adipocyte differentiation gene Zfp423 associated with up-regulated ZFP423 expression and a shift from endothelial to white adipocyte differentiation compared with WT-CPC. The expression of the histone-methyltransferase EZH2 is reduced in male CKO-CPC compared with male WT-CPC, whereas no differences in the EZH2 expression in female CPC were observed. Clonally expanded CPC can differentiate into endothelial cells or into adipocytes depending on the differentiation conditions. ZFP423 overexpression is sufficient to induce white adipocyte differentiation of clonal CPC. In isolated WT-CPC, PGD2 stimulation reduces the expression of EZH2, thereby up-regulating ZFP423 expression and promoting white adipocyte differentiation. The treatment of young male CKO mice with the COX inhibitor Ibuprofen or the PGD2 receptor (DP)2 receptor antagonist BAY-u 3405 in vivo increased EZH2 expression and reduced ZFP423 expression and adipocyte differentiation in CKO-CPC. Thus, cardiomyocyte STAT3 deficiency leads to age-related and sex-specific cardiac remodeling and failure in part due to sex-specific alterations in PGD2 secretion and subsequent epigenetic impairment of the differentiation potential of CPC. Causally involved is the impaired AR signaling in absence of STAT3, which reduces the expression of the PG-degrading enzyme HPGD.

Implementation of RNA sequencing and array CGH in the diagnostic workflow of the AIEOP-BFM ALL 2017 trial on acute lymphoblastic leukemia.

Risk-adapted therapy has significantly contributed to improved survival rates in pediatric acute lymphoblastic leukemia (ALL) and reliable detection of chromosomal aberrations is mandatory for risk group stratification. This study evaluated the applicability of panel-based RNA sequencing and array CGH within the diagnostic workflow of the German study group of the international AIEOP-BFM ALL 2017 trial. In a consecutive cohort of 117 children with B cell precursor (BCP) ALL, array analysis identified twelve cases with an IKZF1plus profile of gene deletions and one case of masked hypodiploidy. Genetic markers BCR-ABL1 (n = 1), ETV6-RUNX1 (n = 25), and rearrangements involving KMT2A (n = 3) or TCF3 (n = 3) were assessed by established conventional techniques such as karyotyping, FISH, and RT-PCR. Comparison of these results with RNA sequencing analysis revealed overall consistency in n=115/117 cases, albeit with one undetected AFF1-KMT2A fusion in RNA sequencing and one undetected ETV6-RUNX1 fusion in conventional analyses. The combined application of RNA sequencing, FISH, and CGH+SNP array reliably detected all genetic markers necessary for risk stratification and will be used as the diagnostic standard workflow for BCP-ALL patients enrolled in the AIEOP-BFM ALL 2017 study. Prospectively, consistent collection of genome-wide CGH+SNP array as well as RNA sequencing data will be a valuable source to elucidate new prognostic lesions beyond established markers of pediatric ALL. In this respect, RNA sequencing identified various gene fusions in up to half of the IKZF1plus (n = 6/12) and B-other (n = 19/36) cases but not in cases with hyperdiploid karyotypes (n = 35). Among these fusions, this study reports several previously undescribed in frame PAX5 fusions, including PAX5-MYO1G and PAX5-NCOA6.