Distinct metabolic requirements regulate B cell activation and germinal center responses.

Following infection or vaccination, activated B cells at extrafollicular sites or within germinal centers (GCs) undergo vigorous clonal proliferation. Proliferating lymphocytes have been shown to undertake lactate dehydrogenase A (LDHA)-dependent aerobic glycolysis; however, the specific role of this metabolic pathway in a B cell transitioning from a naïve to a highly proliferative, activated state remains poorly defined. Here, we deleted LDHA in a stage-specific and cell-specific manner. We find that ablation of LDHA in a naïve B cell did not profoundly affect its ability to undergo a bacterial lipopolysaccharide-induced extrafollicular B cell response. On the other hand, LDHA-deleted naïve B cells had a severe defect in their capacities to form GCs and mount GC-dependent antibody responses. In addition, loss of LDHA in T cells severely compromised B cell-dependent immune responses. Strikingly, when LDHA was deleted in activated, as opposed to naïve, B cells, there were only minimal effects on the GC reaction and in the generation of high-affinity antibodies. These findings strongly suggest that naïve and activated B cells have distinct metabolic requirements that are further regulated by niche and cellular interactions.

Conserved transcriptional connectivity of regulatory T cells in the tumor microenvironment informs new combination cancer therapy strategies.

While regulatory T (Treg) cells are traditionally viewed as professional suppressors of antigen presenting cells and effector T cells in both autoimmunity and cancer, recent findings of distinct Treg cell functions in tissue maintenance suggest that their regulatory purview extends to a wider range of cells and is broader than previously assumed. To elucidate tumoral Treg cell 'connectivity' to diverse tumor-supporting accessory cell types, we explored immediate early changes in their single-cell transcriptomes upon punctual Treg cell depletion in experimental lung cancer and injury-induced inflammation. Before any notable T cell activation and inflammation, fibroblasts, endothelial and myeloid cells exhibited pronounced changes in their gene expression in both cancer and injury settings. Factor analysis revealed shared Treg cell-dependent gene programs, foremost, prominent upregulation of VEGF and CCR2 signaling-related genes upon Treg cell deprivation in either setting, as well as in Treg cell-poor versus Treg cell-rich human lung adenocarcinomas. Accordingly, punctual Treg cell depletion combined with short-term VEGF blockade showed markedly improved control of PD-1 blockade-resistant lung adenocarcinoma progression in mice compared to the corresponding monotherapies, highlighting a promising factor-based querying approach to elucidating new rational combination treatments of solid organ cancers.

Regulatory T cells function in established systemic inflammation and reverse fatal autoimmunity.

The immunosuppressive function of regulatory T (Treg) cells is dependent on continuous expression of the transcription factor Foxp3. Foxp3 loss of function or induced ablation of Treg cells results in a fatal autoimmune disease featuring all known types of inflammatory responses with every manifestation stemming from Treg cell paucity, highlighting a vital function of Treg cells in preventing fatal autoimmune inflammation. However, a major question remains whether Treg cells can persist and effectively exert their function in a disease state, where a broad spectrum of inflammatory mediators can either inactivate Treg cells or render innate and adaptive pro-inflammatory effector cells insensitive to suppression. By reinstating Foxp3 protein expression and suppressor function in cells expressing a reversible Foxp3 null allele in severely diseased mice, we found that the resulting single pool of rescued Treg cells normalized immune activation, quelled severe tissue inflammation, reversed fatal autoimmune disease and provided long-term protection against them. Thus, Treg cells are functional in settings of established broad-spectrum systemic inflammation and are capable of affording sustained reset of immune homeostasis.

Genetic tracing reveals transcription factor Foxp3-dependent and Foxp3-independent functionality of peripherally induced Treg cells.

Regulatory T (Treg) cells expressing the transcription factor Foxp3 are an essential suppressive T cell lineage of dual origin: Foxp3 induction in thymocytes and mature CD4+ T cells gives rise to thymic (tTreg) and peripheral (pTreg) Treg cells, respectively. While tTreg cells suppress autoimmunity, pTreg cells enforce tolerance to food and commensal microbiota. However, the role of Foxp3 in pTreg cells and the mechanisms supporting their differentiation remain poorly understood. Here, we used genetic tracing to identify microbiota-induced pTreg cells and found that many of their distinguishing features were Foxp3 independent. Lineage-committed, microbiota-dependent pTreg-like cells persisted in the colon in the absence of Foxp3. While Foxp3 was critical for the suppression of a Th17 cell program, colitis, and mastocytosis, pTreg cells suppressed colonic effector T cell expansion in a Foxp3-independent manner. Thus, Foxp3 and the tolerogenic signals that precede and promote its expression independently confer distinct facets of pTreg functionality.

A distal Foxp3 enhancer enables interleukin-2 dependent thymic Treg cell lineage commitment for robust immune tolerance.

Activation of the STAT5 transcription factor downstream of the Interleukin-2 receptor (IL-2R) induces expression of Foxp3, a critical step in the differentiation of regulatory T (Treg) cells. Due to the pleiotropic effects of IL-2R signaling, it is unclear how STAT5 acts directly on the Foxp3 locus to promote its expression. Here, we report that IL-2 - STAT5 signaling converged on an enhancer (CNS0) during Foxp3 induction. CNS0 facilitated the IL-2 dependent CD25+Foxp3- precursor to Treg cell transition in the thymus. Its deficiency resulted in impaired Treg cell generation in neonates, which was partially mitigated with age. While the thymic Treg cell paucity caused by CNS0 deficiency did not result in autoimmunity on its own, it exacerbated autoimmune manifestations caused by disruption of the Aire gene. Thus, CNS0 enhancer activity ensures robust Treg cell differentiation early in postnatal life and cooperatively with other tolerance mechanisms minimizes autoimmunity.

The Transcription Factor Foxp3 Shapes Regulatory T Cell Identity by Tuning the Activity of trans-Acting Intermediaries.

Regulatory T (Treg) cell identity is defined by the lineage-specifying transcription factor (TF) Foxp3. Here we examined mechanisms of Foxp3 function by leveraging naturally occurring genetic variation in wild-derived inbred mice, which enables the identification of DNA sequence motifs driving epigenetic features. Chromatin accessibility, TF binding, and gene expression patterns in resting and activated subsets of Treg cells, conventional CD4 T cells, and cells expressing a Foxp3 reporter null allele revealed that the majority of Foxp3-dependent changes occurred at sites not bound by Foxp3. Chromatin accessibility of these indirect Foxp3 targets depended on the presence of DNA binding motifs for other TFs, including TCF1. Foxp3 expression correlated with decreased TCF1 and reduced accessibility of TCF1-bound chromatin regions. Deleting one copy of the Tcf7 gene recapitulated Foxp3-dependent negative regulation of chromatin accessibility. Thus, Foxp3 defines Treg cell identity in a largely indirect manner by fine-tuning the activity of other major chromatin remodeling TFs such as TCF1.

Novel antigen-presenting cell imparts Treg-dependent tolerance to gut microbiota.

Establishing and maintaining tolerance to self-antigens or innocuous foreign antigens is vital for the preservation of organismal health. Within the thymus, medullary thymic epithelial cells (mTECs) expressing autoimmune regulator (AIRE) have a critical role in self-tolerance through deletion of autoreactive T cells and promotion of thymic regulatory T (Treg) cell development1-4. Within weeks of birth, a separate wave of Treg cell differentiation occurs in the periphery upon exposure to antigens derived from the diet and commensal microbiota5-8, yet the cell types responsible for the generation of peripheral Treg (pTreg) cells have not been identified. Here we describe the identification of a class of RORγt+ antigen-presenting cells called Thetis cells, with transcriptional features of both mTECs and dendritic cells, comprising four major sub-groups (TC I-TC IV). We uncover a developmental wave of Thetis cells within intestinal lymph nodes during a critical window in early life, coinciding with the wave of pTreg cell differentiation. Whereas TC I and TC III expressed the signature mTEC nuclear factor AIRE, TC IV lacked AIRE expression and was enriched for molecules required for pTreg generation, including the TGF-ß-activating integrin αvß8. Loss of either major histocompatibility complex class II (MHCII) or ITGB8 by Thetis cells led to a profound impairment in intestinal pTreg differentiation, with ensuing colitis. By contrast, MHCII expression by RORγt+ group 3 innate lymphoid cells (ILC3) and classical dendritic cells was neither sufficient nor required for pTreg generation, further implicating TC IV as the tolerogenic RORγt+ antigen-presenting cell with an essential function in early life. Our studies reveal parallel pathways for the establishment of tolerance to self and foreign antigens in the thymus and periphery, respectively, marked by the involvement of shared cellular and transcriptional programmes.

BLNK negatively regulates innate antifungal immunity through inhibiting c-Cbl-mediated macrophage migration.

B cell linker protein (BLNK) is crucial for orchestrating B cell receptor-associated spleen tyrosine kinase (Syk) signaling. However, the role of BLNK in Syk-coupled C-type lectin receptor (CLR) signaling in macrophages remains unclear. Here, we delineate that CLRs govern the Syk-mediated activation of BLNK, thereby impeding macrophage migration by disrupting podosome ring formation upon stimulation with fungal ß-glucans or α-mannans. Mechanistically, BLNK instigates its association with casitas B-lineage lymphoma (c-Cbl), competitively impeding the interaction between c-Cbl and Src-family kinase Fyn. This interference disrupts Fyn-mediated phosphorylation of c-Cbl and subsequent c-Cbl-associated F-actin assembly. Consequently, BLNK deficiency intensifies CLR-mediated recruitment of the c-Cbl/phosphatidylinositol 3-kinase complex to the F-actin cytoskeleton, thereby enhancing macrophage migration. Notably, mice with monocyte-specific BLNK deficiency exhibit heightened resistance to infection with Candida albicans, a prominent human fungal pathogen. This resistance is attributed to the increased infiltration of Ly6C+ macrophages into renal tissue. These findings unveil a previously unrecognized role of BLNK for the negative regulation of macrophage migration through inhibiting CLR-mediated podosome ring formation during fungal infections.

Comprehensive whole-genome analyses of the UK Biobank reveal significant sex differences in both genotype missingness and allele frequency on the X chromosome.

The UK Biobank is the most used dataset for genome-wide association studies (GWAS). GWAS of sex, essentially sex differences in minor allele frequencies (sdMAF), has identified autosomal SNPs with significant sdMAF, including in the UK Biobank, but the X chromosome was excluded. Our recent report identified multiple regions on the X chromosome with significant sdMAF, using short-read sequencing of other datasets. We performed a whole genome sdMAF analysis, with ~410 k white British individuals from the UK Biobank, using array genotyped, imputed or exome sequencing data. We observed marked sdMAF on the X chromosome, particularly at the boundaries between the pseudo-autosomal regions (PAR) and the non-PAR (NPR), as well as throughout the NPR, consistent with our earlier report. A small fraction of autosomal SNPs also showed significant sdMAF. Using the centrally imputed data, which relied mostly on low-coverage whole genome sequence, resulted in 2.1% of NPR SNPs with significant sdMAF. The whole exome sequencing also displays sdMAF on the X chromosome, including some NPR SNPs with heterozygous genotype calls in males. Genotyping, sequencing and imputation of X chromosomal SNPs requires further attention to ensure the integrity for downstream association analysis.

eXclusionarY: 10 years later, where are the sex chromosomes in GWASs?

10 years ago, a detailed analysis showed that only 33% of genome-wide association study (GWAS) results included the X chromosome. Multiple recommendations were made to combat such exclusion. Here, we re-surveyed the research landscape to determine whether these earlier recommendations had been translated. Unfortunately, among the genome-wide summary statistics reported in 2021 in the NHGRI-EBI GWAS Catalog, only 25% provided results for the X chromosome and 3% for the Y chromosome, suggesting that the exclusion phenomenon not only persists but has also expanded into an exclusionary problem. Normalizing by physical length of the chromosome, the average number of studies published through November 2022 with genome-wide-significant findings on the X chromosome is ∼1 study/Mb. By contrast, it ranges from ∼6 to ∼16 studies/Mb for chromosomes 4 and 19, respectively. Compared with the autosomal growth rate of ∼0.086 studies/Mb/year over the last decade, studies of the X chromosome grew at less than one-seventh that rate, only ∼0.012 studies/Mb/year. Among the studies that reported significant associations on the X chromosome, we noted extreme heterogeneities in data analysis and reporting of results, suggesting the need for clear guidelines. Unsurprisingly, among the 430 scores sampled from the PolyGenic Score Catalog, 0% contained weights for sex chromosomal SNPs. To overcome the dearth of sex chromosome analyses, we provide five sets of recommendations and future directions. Finally, until the sex chromosomes are included in a whole-genome study, instead of GWASs, we propose such studies would more properly be referred to as "AWASs," meaning "autosome-wide scans."

dHICA: a deep transformer-based model enables accurate histone imputation from chromatin accessibility.

Histone modifications (HMs) are pivotal in various biological processes, including transcription, replication, and DNA repair, significantly impacting chromatin structure. These modifications underpin the molecular mechanisms of cell-type-specific gene expression and complex diseases. However, annotating HMs across different cell types solely using experimental approaches is impractical due to cost and time constraints. Herein, we present dHICA (deep histone imputation using chromatin accessibility), a novel deep learning framework that integrates DNA sequences and chromatin accessibility data to predict multiple HM tracks. Employing the transformer architecture alongside dilated convolutions, dHICA boasts an extensive receptive field and captures more cell-type-specific information. dHICA outperforms state-of-the-art baselines and achieves superior performance in cell-type-specific loci and gene elements, aligning with biological expectations. Furthermore, dHICA's imputations hold significant potential for downstream applications, including chromatin state segmentation and elucidating the functional implications of SNPs (Single Nucleotide Polymorphisms). In conclusion, dHICA serves as a valuable tool for advancing the understanding of chromatin dynamics, offering enhanced predictive capabilities and interpretability.

A droplet-based electricity generator with high instantaneous power density.

Extensive efforts have been made to harvest energy from water in the form of raindrops1-6, river and ocean waves7,8, tides9 and others10-17. However, achieving a high density of electrical power generation is challenging. Traditional hydraulic power generation mainly uses electromagnetic generators that are heavy, bulky, and become inefficient with low water supply. An alternative, the water-droplet/solid-based triboelectric nanogenerator, has so far generated peak power densities of less than one watt per square metre, owing to the limitations imposed by interfacial effects-as seen in characterizations of the charge generation and transfer that occur at solid-liquid1-4 or liquid-liquid5,18 interfaces. Here we develop a device to harvest energy from impinging water droplets by using an architecture that comprises a polytetrafluoroethylene film on an indium tin oxide substrate plus an aluminium electrode. We show that spreading of an impinged water droplet on the device bridges the originally disconnected components into a closed-loop electrical system, transforming the conventional interfacial effect into a bulk effect, and so enhancing the instantaneous power density by several orders of magnitude over equivalent devices that are limited by interfacial effects.

Transcriptome and translatome co-evolution in mammals.

Gene-expression programs define shared and species-specific phenotypes, but their evolution remains largely uncharacterized beyond the transcriptome layer1. Here we report an analysis of the co-evolution of translatomes and transcriptomes using ribosome-profiling and matched RNA-sequencing data for three organs (brain, liver and testis) in five mammals (human, macaque, mouse, opossum and platypus) and a bird (chicken). Our within-species analyses reveal that translational regulation is widespread in the different organs, in particular across the spermatogenic cell types of the testis. The between-species divergence in gene expression is around 20% lower at the translatome layer than at the transcriptome layer owing to extensive buffering between the expression layers, which especially preserved old, essential and housekeeping genes. Translational upregulation specifically counterbalanced global dosage reductions during the evolution of sex chromosomes and the effects of meiotic sex-chromosome inactivation during spermatogenesis. Despite the overall prevalence of buffering, some genes evolved faster at the translatome layer-potentially indicating adaptive changes in expression; testis tissue shows the highest fraction of such genes. Further analyses incorporating mass spectrometry proteomics data establish that the co-evolution of transcriptomes and translatomes is reflected at the proteome layer. Together, our work uncovers co-evolutionary patterns and associated selective forces across the expression layers, and provides a resource for understanding their interplay in mammalian organs.

Size-dependent charge transfer between water microdroplets.

Contact electrification (CE) in water has attracted much attention, owing to its potential impacts on the chemical reactions, such as the recent discovery of spontaneous generation of hydrogen peroxide (H2O2) in water microdroplets. However, current studies focus on the CE of bulk water, the measurement of CE between micrometer-size water droplets is a challenge and its mechanism still remains ambiguous. Here, a method for quantifying the amount of charge carried by the water microdroplets produced by ultrasonic atomization is proposed. In the method, the motions of water microdroplets in a uniform electric field are observed and the electrostatic forces on the microdroplets are calculated based on the moving speed of the microdroplets. It is revealed that the charge transfer between water microdroplets is size-dependent. The large microdroplets tend to be positively charged while the small microdroplets tend to receive negative charges, implying that the negative charges transfer from large microdroplets to the small microdroplets during ultrasonic atomization. Further, a theoretical model for microdroplets charging is proposed, in which the curvature-induced surface potential/energy difference is suggested to be responsible for the charge transfer between microdroplets. The findings show that the electric field strength between two microdroplets with opposite charges during separation is strong enough to convert OH‒ to OH*, providing evidence for the CE-induced spontaneous generation of H2O2 in water microdroplets.

Direct mapping of bending and torsional dynamics in individual nanostructures.

Investigating coherent acoustic vibrations in nanostructured materials provides fundamental insights into optomechanical responses and microscopic energy flow. Extensive measurements of vibrational dynamics have been performed for a wide variety of nanoparticles and nanoparticle assemblies. However, virtually all of them show that only the dilation modes are launched after laser excitations, and the acoustic bending and torsional motions, which are commonly observed in photoexcited chemical bonds, are absent. Unambiguous identification and refined characterization of these "missing" modes have been a long-standing issue. In this report, we investigated the acoustic vibrational dynamics of individual Au nanoprisms on free-standing graphene substrates using an ultrafast high-sensitivity dark-field imaging approach in four-dimensional transmission electron microscopy. Following optical excitations, we observed low-frequency multiple-mode oscillations and higher superposition amplitudes at nanoprism corners and edges on the subnanoparticle level. In combination with finite-element simulations, we determined that these vibrational modes correspond to out-of-plane bending and torsional motions, superimposed by an overall tilting effect of the nanoprisms. The launch and relaxation processes of these modes are highly pertinent to substrate effects and nanoparticle geometries. These findings contribute to the fundamental understanding about acoustic dynamics of individual nanostructures and their interaction with substrates.

NtMYB27 acts downstream of NtBES1 to modulate flavonoids accumulation in response to UV-B radiation in tobacco.

UV-B radiation can induce the accumulation of many secondary metabolites, including flavonoids, in plants to protect them from oxidative damage. BRI1-EMS-SUPPRESSOR1 (BES1) has been shown to mediate the biosynthesis of flavonoids in response to UV-B. However, the detailed mechanism by which it acts still needs to be further elucidated. Here, we revealed that UV-B significantly inhibited the transcription of multiple transcription factor genes in tobacco, including NtMYB27, which was subsequently shown to be a repressor of flavonoids synthesis in tobacco. We further demonstrated that NtBES1 directly binds to the E-box motifs present in the promoter of NtMYB27 to mediate its transcriptional repression upon UV-B exposure. The UV-B-repressed NtMYB27 could bind to the ACCT-containing element (ACE) in the promoters of Nt4CL and NtCHS and served as a modulator that promoted the biosynthesis of lignin and chlorogenic acid (CGA) but inhibited the accumulation of flavonoids in tobacco. The expression of NtMYB27 was also significantly repressed by heat stress, suggesting its putative roles in regulating heat-induced flavonoids accumulation. Taken together, our results revealed the role of NtBES1 and NtMYB27 in regulating the synthesis of flavonoids during the plant response to UV-B radiation in tobacco.

Genomic Anatomy of Homozygous XX Females and YY Males Reveals Early Evolutionary Trajectory of Sex-determining Gene and Sex Chromosomes in Silurus Fishes.

Sex chromosomes display remarkable diversity and variability among vertebrates. Compared with research on the X/Y and Z/W chromosomes, which have long evolutionary histories in mammals and birds, studies on the sex chromosomes at early evolutionary stages are limited. Here, we precisely assembled the genomes of homozygous XX female and YY male Lanzhou catfish (Silurus lanzhouensis) derived from an artificial gynogenetic family and a self-fertilized family, respectively. Chromosome 24 (Chr24) was identified as the sex chromosome based on resequencing data. Comparative analysis of the X and Y chromosomes showed an approximate 320 kb Y-specific region with a Y-specific duplicate of anti-Mullerian hormone type II receptor (amhr2y), which is consistent with findings in 2 other Silurus species but on different chromosomes (Chr24 of Silurus meridionalis and Chr5 of Silurus asotus). Deficiency of amhr2y resulted in male-to-female sex reversal, indicating that amhr2y plays a male-determining role in S. lanzhouensis. Phylogenetic analysis and comparative genomics revealed that the common sex-determining gene amhr2y was initially translocated to Chr24 of the Silurus ancestor along with the expansion of transposable elements. Chr24 was maintained as the sex chromosome in S. meridionalis and S. lanzhouensis, whereas a sex-determining region transition triggered sex chromosome turnover from Chr24 to Chr5 in S. asotus. Additionally, gene duplication, translocation, and degeneration were observed in the Y-specific regions of Silurus species. These findings present a clear case for the early evolutionary trajectory of sex chromosomes, including sex-determining gene origin, repeat sequence expansion, gene gathering and degeneration in sex-determining region, and sex chromosome turnover.

TCMFP: a novel herbal formula prediction method based on network target's score integrated with semi-supervised learning genetic algorithms.

Traditional Chinese medicine (TCM) has accumulated thousands years of knowledge in herbal therapy, but the use of herbal formulas is still characterized by reliance on personal experience. Due to the complex mechanism of herbal actions, it is challenging to discover effective herbal formulas for diseases by integrating the traditional experiences and modern pharmacological mechanisms of multi-target interactions. In this study, we propose a herbal formula prediction approach (TCMFP) combined therapy experience of TCM, artificial intelligence and network science algorithms to screen optimal herbal formula for diseases efficiently, which integrates a herb score (Hscore) based on the importance of network targets, a pair score (Pscore) based on empirical learning and herbal formula predictive score (FmapScore) based on intelligent optimization and genetic algorithm. The validity of Hscore, Pscore and FmapScore was verified by functional similarity and network topological evaluation. Moreover, TCMFP was used successfully to generate herbal formulae for three diseases, i.e. the Alzheimer's disease, asthma and atherosclerosis. Functional enrichment and network analysis indicates the efficacy of targets for the predicted optimal herbal formula. The proposed TCMFP may provides a new strategy for the optimization of herbal formula, TCM herbs therapy and drug development.

DRONet: effectiveness-driven drug repositioning framework using network embedding and ranking learning.

As one of the most vital methods in drug development, drug repositioning emphasizes further analysis and research of approved drugs based on the existing large amount of clinical and experimental data to identify new indications of drugs. However, the existing drug repositioning methods didn't achieve enough prediction performance, and these methods do not consider the effectiveness information of drugs, which make it difficult to obtain reliable and valuable results. In this study, we proposed a drug repositioning framework termed DRONet, which make full use of effectiveness comparative relationships (ECR) among drugs as prior information by combining network embedding and ranking learning. We utilized network embedding methods to learn the deep features of drugs from a heterogeneous drug-disease network, and constructed a high-quality drug-indication data set including effectiveness-based drug contrast relationships. The embedding features and ECR of drugs are combined effectively through a designed ranking learning model to prioritize candidate drugs. Comprehensive experiments show that DRONet has higher prediction accuracy (improving 87.4% on Hit@1 and 37.9% on mean reciprocal rank) than state of the art. The case analysis also demonstrates high reliability of predicted results, which has potential to guide clinical drug development.

Multiparametric Characterization of Focal Cortical Dysplasia Using 3D MR Fingerprinting.

OBJECTIVE: To develop a multiparametric machine-learning (ML) framework using high-resolution 3 dimensional (3D) magnetic resonance (MR) fingerprinting (MRF) data for quantitative characterization of focal cortical dysplasia (FCD). MATERIALS: We included 119 subjects, 33 patients with focal epilepsy and histopathologically confirmed FCD, 60 age- and gender-matched healthy controls (HCs), and 26 disease controls (DCs). Subjects underwent whole-brain 3 Tesla MRF acquisition, the reconstruction of which generated T1 and T2 relaxometry maps. A 3D region of interest was manually created for each lesion, and z-score normalization using HC data was performed. We conducted 2D classification with ensemble models using MRF T1 and T2 mean and standard deviation from gray matter and white matter for FCD versus controls. Subtype classification additionally incorporated entropy and uniformity of MRF metrics, as well as morphometric features from the morphometric analysis program (MAP). We translated 2D results to individual probabilities using the percentage of slices above an adaptive threshold. These probabilities and clinical variables were input into a support vector machine for individual-level classification. Fivefold cross-validation was performed and performance metrics were reported using receiver-operating-characteristic-curve analyses. RESULTS: FCD versus HC classification yielded mean sensitivity, specificity, and accuracy of 0.945, 0.980, and 0.962, respectively; FCD versus DC classification achieved 0.918, 0.965, and 0.939. In comparison, visual review of the clinical magnetic resonance imaging (MRI) detected 48% (16/33) of the lesions by official radiology report. In the subgroup where both clinical MRI and MAP were negative, the MRF-ML models correctly distinguished FCD patients from HCs and DCs in 98.3% of cross-validation trials. Type II versus non-type-II classification exhibited mean sensitivity, specificity, and accuracy of 0.835, 0.823, and 0.83, respectively; type IIa versus IIb classification showed 0.85, 0.9, and 0.87. In comparison, the transmantle sign was present in 58% (7/12) of the IIb cases. INTERPRETATION: The MRF-ML framework presented in this study demonstrated strong efficacy in noninvasively classifying FCD from normal cortex and distinguishing FCD subtypes. ANN NEUROL 2024;96:944-957.