Biology subjects

Johnson, M. R.

Publications and source records attributed to Johnson, M. R..

At least 19 recordsLinked to original sources

bioRxiv2026

Extravillous trophoblast model shows generation of bioequivalent N-glycans can maintain immunological protection against natural killer cell cytotoxicity

Extravillous trophoblasts (EVTs) are a trophoblast subpopulation critical for feto-maternal tolerance during early pregnancy, primarily using HLA-G to exert immunomodulatory effect, and possessing N-glycomic profiles distinct from other trophoblast subpopulations. However, whether the N-glycosylation confers distinct immunological properties to EVTs remains poorly understood. To investigate this, we employed JEG-3, a human choriocarcinoma cell line having the capacity to produce pregnancy-related hormones and expressing both HLA-C and HLA-G resembling placental EVTs, as an in vitro EVT model, alongside cell line JAR which exhibits villous trophoblast phenotypes distinct from JEG-3. Both cell lines were treated with kifunensine or swainsonine, inhibitors of -mannosidases, to remodel their N-glycosylation patterns. This led to significant remodelling of their N-glycomic profiles, with JEG-3 cells showing an increased level of polylactosamine chains and decreased levels of -2,6-sialylation and core -1,6-fucosylation. Western blot analysis showed that inhibiting -mannosidases altered only the composition of N-glycans on cell-surface HLA-G, without affecting the overall abundance of cell-surface HLA-G. In kifunensine-treated JEG-3 cells that predominantly express oligomannose type N-glycans, an intracellular accumulation of unfolded HLA-G fragments, increased hCG secretion, and down-regulations of EVT markers GATA3 and KRT7 were observed compared to untreated control, while swainsonine treatment did not impact N-glycan expression. Cytotoxicity assays using NK-92 as effector cells showed that the de-sialylation of JEG-3 by neuraminidase treatment led to increased NK-92 mediated killing. JEG-3 cell sustained its EVT immunological properties through generating bioequivalent N-glycans, exemplified by NK-92 cells pre-conditioned with used culture media of kifunensine-treated JEG-3 cells displaying reduced cytotoxicity toward NK-sensitive lymphoblast cell line K562, an effect not observed with swainsonine-treated JEG-3 cells. This model suggests that EVTs immunological properties are dependent on specific N-glycomic profiles that are maintained by unique N-glycosylation homeostasis, and overall improves our understanding of how EVTs maintain their immunomodulatory effect at the maternal-fetal interface.

immunology↗

bioRxiv2026

Cell-surface N-linked glycans manipulation of K562 cells for augmented susceptibility to natural killer cell killing

Glycosylation of proteins is arguably the most diverse post-translational modification that is altered in almost all cancer types, which has been demonstrated to play a crucial role in creating an immunosuppressive microenvironment that promotes immune tolerance and evasion. However, the biosynthesis of N-linked glycan is mediated by a series of enzymatic reactions catalysed by glycosyltransferases and glycosidases in a template-independent manner, hindering our understanding of specific structure-function relationships and roles of specific glycans on specific proteins. Here we use HLA class I-negative cell line K562, a known reference target for NK-mediated cytolysis, to establish a model investigating how cell surface glycan dynamics influence its susceptibility to cytolysis mediated by NK-92 cells. Treatment of K562 cells with kifunensine, swainsonine, 2F-peracetyl-fucose, or 3Fax-peracetyl Neu5Ac, inhibitors of N-linked glycan processing, resulted in drastic alterations in cell surface carbohydrate phenotype, as could be shown by flow cytometric analysis of the lectiNbinding properties of the cells. Despite these clear changes in carbohydrate phenotype, only K562 cells treated with either kifunensine or 3Fax-peracetyl Neu5Ac exhibited higher susceptibility to the cytolysis medidated by NK-92 cells accompanied with an increased CD107a expression by NK-92 cells. Although K562 cells overexpressing gene MGAT3 exhibited a decreased NK-susceptibility, we further found that this decrease was not exclusively determined by the overexpression of gene MGAT3 product bisecting {beta}1,4-GlcNAc, because the treatment of 3Fax-peracetyl Neu5Ac reversed the resistance of K562 cell against NK-92 cell in despite of expressing higher levels of bisecting {beta}1,4-GlcNAc. Expressing HLA-G on cell surface as extravillous trophoblast did not change the NK-susceptibility of K562 cells, despite evidence that HLA-G molecules expressed by K562 cells can bind to inhibitory receptor ILT2 expressed on NK-92 cell surface. These findings suggest that the level of terminal sialylation, outweighing other components in N-linked glycan, determines the NK-susceptibility of K562 cell, offering a new strategy to weaken the resistance of cancer cells so that the immune system can maximise the elimination.

immunology↗

bioRxiv2026

IL1 blockade attenuates E. coli induced intrauterine inflammation and preterm labor in Rhesus macaques

Intrauterine infection and inflammation are major causes of preterm labor, yet antibiotics alone often fail to prevent preterm birth despite achieving microbial clearance. Interleukin1 (IL1) is a key mediator of intra-amniotic inflammation and functional progesterone withdrawal, processes linked to labor initiation. We tested whether IL1 blockade with the clinically approved IL1 receptor antagonist, anakinra, could reduce inflammation and preterm labor in a Rhesus macaque model of intra-amniotic Escherichia coli infection followed by delayed antibiotic treatment. Here we show that anakinra reduced the incidence of preterm labor by 40% (p=0.07), attenuated inflammation in the fetal membranes and cervix, and preserved progesterone receptor-B abundance in the fetal membranes. These effects were most pronounced in animals protected from preterm labor. Our findings in a relevant model support the translational potential of combining IL1 blockade with antibiotics for infection-associated preterm labor. One sentence summaryRecombinant human IL1 receptor antagonist (anakinra) decreased E. coli infection induced preterm labor and partially decreased intrauterine inflammation in a non-human primate model of inflammation mediated preterm labor.

immunology↗

bioRxiv2025

CompBio and MIRaS : A Multi-omic Analysis Platform Built on a Memory-Based Intelligence Engine

As molecular and cellular technologies have advanced, the need to analyze and interpret the resulting, often vast and multi-modal, data into actionable intelligence has become a rate-limiting factor in scientific advancement. While traditional knowledgebase-pathway tools and LLM-based AI tools both provide a degree of support in data interpretation, both exhibit limitations. Presented here is the CompBio multi-omic analysis platform built upon a novel memory-based intelligence engine, MIRaS. The system is not dependent on human-curated pathway knowledgebases, can perform statistical significance analysis, does not suffer from hallucination, and produces traceable results. Furthermore, substantial effort has been placed in the computer-human knowledge transfer components of the system to enable efficient interaction, interpretation, and learning. The system has undergone years of extensive testing, validation, and evolution in omics-based research with dozens of associated publications verifying its effectiveness. A systematic assessment of CompBio and a detailed description of the MIRaS method are provided.

bioinformatics↗

bioRxiv2025

Molecular detection of a cryptic salamander: Development of an eDNA assay for the detection of the mud salamander (Pseudotriton montanus).

The mud salamander (Pseudotriton montanus) is a notoriously cryptic semi-aquatic Plethodontid found throughout much of the eastern United States, reports of decades passing between observations of this species in areas of known occurrence are common. Although it is listed as imperiled or in need of conservation throughout much of its range, with extirpation suspected in many areas, relatively little is known of its current distribution due to its secretive nature. We developed a species-specific qPCR assay for use in eDNA detection of Pseudotriton montanus. Primers and probe were designed based on cytochrome b sequences obtained from specimens collected in central and eastern KY, compared to published sequences throughout the species range, and screened in silico (twenty-seven species) and in vitro (seventeen species) for specificity against sympatric salamander species. The developed assay was field tested via the collection of water samples at sites known or suspected to contain P. montanus in Kentucky, Ohio, and Tennessee. Of the 68 samples collected, P. montanus eDNA was detected in eight, including all sites (six) in which P. montanus larvae were observed in the field. Sequencing of each environmentally-obtained amplicon confirmed detection of P. montanus diastictus. This work provides thoroughly vetted tools that should prove useful for future monitoring and range delineation of this threatened and cryptic species.

ecology↗

bioRxiv2024

Dynamic roles of ILC3 in endometrial repair and regeneration

Innate lymphoid cells (ILC) are prominent in the human uterine mucosa and play physiological roles in pregnancy. ILC3 are the second-most common ILC subset in the uterine mucosa, but their role remains unclear. Here we define two subsets of lineage-negative CD56+ CD117+ CRTH2-uterine ILC3, distinguished by their expression of CD127. The CD127-subset is most numerous and active during menstruation and immediately after parturition, suggesting a role in repair of the uterine mucosa (called endometrium outside of pregnancy); the CD127+ subset is most numerous and active immediately after menstruation, as the endometrium regenerates. In healthy endometrium, ILC3 are spatially associated with glandular epithelial and endothelial cells, which both express receptors for the ILC3-derived cytokines, IL-22 and IL-8. In the eutopic endometrium of people with endometriosis, ILC3 are located further from glandular epithelial and endothelial cells suggesting that these cells may be less exposed to ILC3 products, potentially with negative consequences for endometrial regeneration. Our findings highlight the dynamic nature of ILC3 in the uterine mucosa and suggest their primary role is in repair and regeneration. An improved understanding of uterine ILC3 will inform future research on endometrial health and disease.

immunology↗

bioRxiv2024

Computationally designed mRNA-launched protein nanoparticle vaccines

Both protein nanoparticle and mRNA vaccines were clinically de-risked during the COVID-19 pandemic1-6. These vaccine modalities have complementary strengths: antigen display on protein nanoparticles can enhance the magnitude, quality, and durability of antibody responses7-10, while mRNA vaccines can be rapidly manufactured11 and elicit antigen-specific CD4 and CD8 T cells12,13. Here we leverage a computationally designed icosahedral protein nanoparticle that was redesigned for optimal secretion from eukaryotic cells14 to develop an mRNA-launched nanoparticle vaccine for SARS-CoV-2. The nanoparticle, which displays 60 copies of a stabilized variant of the Wuhan-Hu-1 Spike receptor binding domain (RBD)15, formed monodisperse, antigenically intact assemblies upon secretion from transfected cells. An mRNA vaccine encoding the secreted RBD nanoparticle elicited 5- to 28-fold higher levels of neutralizing antibodies than an mRNA vaccine encoding membrane-anchored Spike, induced higher levels of CD8 T cells than the same immunogen when delivered as an adjuvanted protein nanoparticle, and protected mice from vaccine-matched and -mismatched SARS-CoV-2 challenge. Our data establish that delivering protein nanoparticle immunogens via mRNA vaccines can combine the benefits of each modality and, more broadly, highlight the utility of computational protein design in genetic immunization strategies.

immunology↗

bioRxiv2023

De novo design of highly selective miniprotein inhibitors of integrins αvβ6 and αvβ8

The RGD (Arg-Gly-Asp)-binding integrins v{beta}6 and v{beta}8 are clinically validated cancer and fibrosis targets of considerable therapeutic importance. Compounds that can discriminate between the two closely related integrin proteins and other RGD integrins, stabilize specific conformational states, and have sufficient stability enabling tissue restricted administration could have considerable therapeutic utility. Existing small molecules and antibody inhibitors do not have all of these properties, and hence there is a need for new approaches. Here we describe a method for computationally designing hyperstable RGD-containing miniproteins that are highly selective for a single RGD integrin heterodimer and conformational state, and use this strategy to design inhibitors of v{beta}6 and v{beta}8 with high selectivity. The v{beta}6 and v{beta}8 inhibitors have picomolar affinities for their targets, and >1000-fold selectivity over other RGD integrins. CryoEM structures are within 0.6-0.7[A] root-mean-square deviation (RMSD) to the computational design models; the designed v{beta}6 inhibitor and native ligand stabilize the open conformation in contrast to the therapeutic anti-v{beta}6 antibody BG00011 that stabilizes the bent-closed conformation and caused on-target toxicity in patients with lung fibrosis, and the v{beta}8 inhibitor maintains the constitutively fixed extended-closed v{beta}8 conformation. In a mouse model of bleomycin-induced lung fibrosis, the v{beta}6 inhibitor potently reduced fibrotic burden and improved overall lung mechanics when delivered via oropharyngeal administration mimicking inhalation, demonstrating the therapeutic potential of de novo designed integrin binding proteins with high selectivity.

biochemistry↗

bioRxiv2023

Trial Averaging for Deep EEG Classification

Many signals, particularly of biological origin, suffer from a signal-to-noise ratio sufficiently low that it can be difficult to classify individual examples reliably, even with relatively sophisticated machine-learning techniques such as deep learning. In some cases, the noise can be high enough that it is even difficult to achieve convergence during training. We considered this problem for one data type that often suffers from such difficulties, namely electroencephalography (EEG) data from cognitive neuroscience studies in humans. One solution to increase signal-to-noise is, of course, to perform averaging among trials, which has been employed before in other studies of human neuroscience but not, to our knowledge, investigated rigorously, particularly not in deep learning. Here, we parametrically studied the effects of different amounts of trial averaging during training and/or testing in a human EEG dataset, and compared the results to that of a related algorithm, Mixup. Broadly, we found that even a small amount of averaging could significantly improve classification, particularly when both training and testing data were subjected to averaging. Simple averaging clearly outperformed Mixup, although the benefits of averaging differed across classification categories. Overall, our results confirm the value of averaging during training and testing when single-trial classification is not strictly necessary for the application in question. HighlightsO_LIAveraging trials can dramatically improve performance in classification of EEG data C_LIO_LIThe benefits can be seen when averaging on both training and test datasets C_LIO_LISimple trial averaging outperformed a popular related algorithm, Mixup C_LIO_LIHowever, effects of averaging differed across different stimulus categories C_LI

neuroscience↗

bioRxiv2022

Sfrp2 is a multifunctional regulator of rodent color patterns

Animal pigment patterns are excellent models to elucidate mechanisms of biological organization. Although theoretical simulations, such as Turing reaction-diffusion systems, recapitulate many animal patterns, they are insufficient to account for those showing a high degree of spatial organization and reproducibility. Here, we compare the coats of the African striped mouse (Rhabdomys pumilio) and the laboratory mouse (Mus musculus) to study the molecular mechanisms controlling stripe pattern formation. By combining transcriptomics, mathematical modeling, and mouse transgenics, we show that Sfrp2 regulates the distribution of hair follicles and establishes an embryonic prepattern that foreshadows pigment stripes. Moreover, by developing and employing in vivo gene editing experiments in striped mice, we find that Sfrp2 knockout is sufficient to alter the stripe pattern. Strikingly, mutants also exhibit changes in coat color, revealing an additional function of Sfrp2 in regulating hair color. Thus, a single factor controls coat pattern formation by acting both as an orienting signaling mechanism and a modulator of pigmentation. By uncovering a multifunctional regulator of stripe formation, our work provides insights into the mechanisms by which spatial patterns are established in developing embryos and the molecular basis of phenotypic novelty.

developmental biology↗

bioRxiv2022

Single-cell Mendelian randomisation identifies cell-type specific genetic effects on human brain disease and behaviour

Translating genome-wide association loci to therapies requires knowledge of the causal genes, their directionality of effect and the cell-types in which they act. To infer these relationships in the human brain, we implemented Mendelian randomisation using single cell-type expression quantitative trait loci (eQTLs) as genetic anchors. Expression QTLs were mapped across 8 major cell-types in brain tissue exclusively ascertained from donors with no history of brain disease. We report evidence for a causal association between the change in expression of 118 genes and one or more of 16 brain phenotypes, revealing candidate targets for risk mitigation and opportunities for shared preventative therapeutic strategies. We highlight key causal genes for neurodegenerative and neuropsychiatric disease and for each, we report its cellular context and the therapeutic directionality required for risk mitigation. Our use of control samples establishes a new resource for the causal interpretation of GWAS risk alleles for human brain phenotypes.

neuroscience↗

bioRxiv2022

Uterine NK cells underexpress receptors recognizing HLA-C2 and HLA-G in reproductive failure

A significant proportion of recurrent miscarriage, recurrent implantation failure and infertility are unexplained, and these conditions have been proposed to have an etiology of immunological dysfunction at the maternal-fetal interface. Uterine Natural Killer cells (uNK) comprise three subsets and are the most numerous immune cells found in the uterine mucosa at the time of implantation. They are thought to play an important role in successful pregnancy by regulation of extravillous trophoblast (EVT) invasion and spiral artery remodelling. Here, we examine the frequency, phenotype and function of uNK1-3 from the uterine mucosa of 16 women with unexplained reproductive failure compared to 11 controls with no reproductive problems, during the window of implantation. We report that KIR2DL1/S1 and LILRB1 expression is lower in the reproductive failure group for both uNK (total uNK, uNK 2 and 3) and pNK. We also show that degranulation activity is significantly reduced in total uNK, and that TNF- production is lower in all uNK subsets in the reproductive failure group. Taken together, our findings suggest that reproductive failure may be caused by global reduction in expression of uNK receptors important for interaction with HLA-C and HLA-G on EVT during early pregnancy, leading to reduced uNK activation. This is the first study to examine uNK subsets during the window of implantation in women with reproductive failure and will serve as a platform to focus on particular aspects of phenotype and function of uNK subsets in future studies. Further understanding of uNK dysregulation is important to establish potential diagnostic and therapeutic targets in the population of women with unexplained reproductive failure.

immunology↗

bioRxiv2022

Drosophila embryos spatially sort their nutrient stores to facilitate their utilization

Animal embryos are provisioned by their mothers with a diverse nutrient supply critical for development. In Drosophila, the three most abundant nutrients (triglycerides, proteins, and glycogen) are sequestered in distinct storage structures, lipid droplets (LDs), yolk vesicles (YVs) and glycogen granules (GGs). Using transmission electron microscopy as well as live and fixed-sample fluorescence imaging, we find that all three storage structures are dispersed throughout the egg but are then spatially allocated to distinct tissues by gastrulation: LDs largely to the peripheral epithelium, YVs and GGs to the central yolk cell. To confound the embryos ability to sort its nutrients, we employ mutants in Jabba and Mauve to generate LD:GG or LD:YV compound structures. In these mutants, LDs are missorted to the yolk cell and their turnover is delayed. Our observations demonstrate dramatic spatial nutrient sorting in early embryos and provide the first evidence for its functional importance.

developmental biology↗

bioRxiv2022

Dynamic changes in uterine NK cell subset frequency and function over the menstrual cycle and pregnancy

Uterine Natural Killer cells (uNK) play an important role in promoting successful pregnancy by regulating trophoblast invasion and spiral artery remodelling in the first trimester. Recently, single cell RNA sequencing (scRNAseq) on first trimester decidua showed that uNKs can be divided into three subsets, which may have different roles in pregnancy. Here we present an integration of previously published scRNAseq datasets, together with novel flow cytometry data to interrogate the frequency, phenotype and function of uNK1-3 in seven stages of the reproductive cycle (menstrual, proliferative, secretory phases; first, second, third trimester; and postpartum). We found that uNK1 and -2 peak in the first trimester, but by the third trimester the majority of uNK are uNK3. All three subsets are most able to degranulate and produce cytokines during the secretory phase of the menstrual cycle and express KIR2D molecules, which allow them to interact with HLA-C expressed by placental extravillous trophoblast cells, at the highest frequency during the first trimester. Taken together, our findings suggest that uNK are particularly active and able to interact with placental cells at the time of implantation, and that uNK1 and 2 may be particularly involved in these processes. Our findings are the first to establish how uNK frequency and function changes dynamically across the healthy reproductive cycle. This serves as a platform from which the relationship between uNK function and impaired implantation and placentation can be investigated. This will have important implications for the study of subfertility, recurrent miscarriage, pre-eclampsia and pre-term labour.

immunology↗

bioRxiv2021

Lipid droplets regulate actin remodeling via prostaglandin signaling during Drosophila oogenesis

A key factor controlling oocyte quality and fertility is lipids. Even though lipid droplets (LDs) are crucial regulators of lipid metabolism, their roles in fertility are poorly understood. During Drosophila oogenesis, LD accumulation in nurse cells coincides with dynamic actin remodeling necessary for late-stage follicle morphogenesis and fertility. Loss of the LD-associated Adipose Triglyceride Lipase (ATGL) disrupts both actin bundle formation and cortical actin integrity, an unusual phenotype also seen when Pxt, the enzyme responsible for prostaglandin (PG) synthesis, is missing. Dominant genetic interactions and PG treatment of follicles in vitro reveal that ATGL and Pxt act in the same pathway to regulate actin remodeling, with ATGL upstream of Pxt. Further, lipidomic analysis detects arachidonic acid (AA) containing triglycerides in ovaries. Because AA is the substrate for Pxt, we propose that ATGL releases AA from LDs to drive PG synthesis necessary for follicle development. We also find that exogenous AA is toxic to follicles in vitro, and LDs modulate this toxicity. This leads to the model that LDs both sequester AA to limit toxicity, and release AA via ATGL to drive PG production. We speculate that the same pathways are conserved across organisms to regulate oocyte development and promote fertility.

cell biology↗

bioRxiv2021

Tracing the evolution of human gene regulation and its association with shifts in environment

As humans spread throughout the world, they adapted to variation in many environmental factors, including climate, diet, and pathogens. Because many of these adaptations were likely mediated by multiple non-coding variants with small effects on gene regulation, it has been difficult to link genomic signals of selection to specific genes, and to describe the regulatory response to selection. To overcome this challenge, we adapted PrediXcan, a machine learning method for imputing gene regulation from genotype data, to analyze low-coverage ancient human DNA (aDNA). First, we used simulated genomes to benchmark strategies for adapting gene regulatory prediction to increase robustness to incomplete aDNA data. Applying the resulting models to 490 ancient Eurasians, we found that genes with the strongest divergent regulation among ancient populations with hunter-gatherer, pastoralist, and agricultural lifestyles are enriched for metabolic and immune functions. Next, we explored the contribution of divergent gene regulation to two traits with strong evidence of recent adaptation: dietary metabolism and skin pigmentation. We found enrichment for divergent regulation among genes previously proposed to be involved in diet-related local adaptation, and in many cases, the predicted effects on regulation provide explanations for previously observed signals of selection, e.g., at FADS1, GPX1, and LEPR. For skin pigmentation, we applied new models trained in melanocytes to a time series of 2999 ancient Europeans spanning ~38,000 years BP. In contrast to diet, skin pigmentation genes show little regulatory change over time, suggesting that adaptation mainly involved large-effect coding variants. This work demonstrates how aDNA can be combined with present-day genomes to shed light on the biological differences among ancient populations, the role of gene regulation in adaptation, and the relationship between ancient genetic diversity and the present-day distribution of complex traits.

genomics↗

bioRxiv2021

Cross-platform transcriptional profiling identifies common and distinct molecular pathologies in Lewy Body diseases

Parkinsons disease (PD), Parkinsons disease with dementia (PDD) and dementia with Lewy bodies (DLB) are three clinically, genetically and neuropathologically overlapping neurodegenerative diseases collectively known as the Lewy body diseases (LBDs). A variety of molecular mechanisms have been implicated in PD pathogenesis, but the mechanisms underlying PDD and DLB remain largely unknown, a knowledge gap that presents an impediment to the discovery of disease-modifying therapies. Transcriptomic profiling can contribute to addressing this gap, but remains limited in the LBDs. Here, we applied paired bulk-tissue and single-nucleus RNA-sequencing to anterior cingulate cortex samples derived from 28 individuals, including healthy controls, PD, PDD and DLB cases (n = 7 per group), to transcriptomically profile the LBDs. Using this approach, we (i) found transcriptional alterations in multiple cell types across the LBDs; (ii) discovered evidence for widespread dysregulation of RNA splicing, particularly in PDD and DLB; (iii) identified potential splicing factors, with links to other dementia-related neurodegenerative diseases, coordinating this dysregulation; and (iv) identified transcriptomic commonalities and distinctions between the LBDs that inform understanding of the relationships between these three clinical disorders. Together, these findings have important implications for the design of RNA-targeted therapies for these diseases and highlight a potential molecular "window" of therapeutic opportunity between the initial onset of PD and subsequent development of Lewy body dementia.

neuroscience↗

bioRxiv2020

Deep-Learning-Based Multivariate Pattern Analysis (dMVPA): A Tutorial and a Toolbox

In recent years, multivariate pattern analysis (MVPA) has been hugely beneficial for cognitive neuroscience by making new experiment designs possible and by increasing the inferential power of functional magnetic resonance imaging (fMRI), electroencephalography (EEG), and other neuroimaging methodologies. In a similar time frame, "deep learning" (a term for the use of artificial neural networks with convolutional, recurrent, or similarly sophisticated architectures) has produced a parallel revolution in the field of machine learning and has been employed across a wide variety of applications. Traditional MVPA also uses a form of machine learning, but most commonly with much simpler techniques based on linear calculations; a number of studies have applied deep learning techniques to neuroimaging data, but we believe that those have barely scratched the surface of the potential deep learning holds for the field. In this paper, we provide a brief introduction to deep learning for those new to the technique, explore the logistical pros and cons of using deep learning to analyze neuroimaging data - which we term "deep MVPA," or dMVPA - and introduce a new software toolbox (the "Deep Learning In Neuroimaging: Exploration, Analysis, Tools, and Education" package, DeLINEATE for short) intended to facilitate dMVPA for neuroscientists (and indeed, scientists more broadly) everywhere.

neuroscience↗