Identification of Synthetic Activators of Cancer Cell Migration by Hybrid Deep Learning.

Deep convolutional neural networks (CNNs) are a method of choice for image recognition. Herein a hybrid CNN approach is presented for molecular pattern recognition in drug discovery. Using self-organizing map images of molecular pharmacophores as input, CNN models were trained to identify chemokine receptor CXCR4 modulators with high accuracy. This machine learning classifier identified first-in-class synthetic CXCR4 full agonists. The receptor-activating effects were confirmed by intracellular cAMP response and in a phenotypic spheroid invasion assay of medulloblastoma cell invasion. Additional macromolecular targets of the small molecules were predicted in silico and tested in vitro, revealing modulatory effects on dopamine receptors and CCR1. These results positively advocate the applicability of molecular image recognition by CNNs to ligand-based virtual compound screening, and demonstrate the complementarity of machine intelligence and human expert knowledge.

Intracellular Theileria annulata promote invasive cell motility through kinase regulation of the host actin cytoskeleton.

The intracellular, protozoan Theileria species parasites are the only eukaryotes known to transform another eukaryotic cell. One consequence of this parasite-dependent transformation is the acquisition of motile and invasive properties of parasitized cells in vitro and their metastatic dissemination in the animal, which causes East Coast Fever (T. parva) or Tropical Theileriosis (T. annulata). These motile and invasive properties of infected host cells are enabled by parasite-dependent, poorly understood F-actin dynamics that control host cell membrane protrusions. Herein, we dissected functional and structural alterations that cause acquired motility and invasiveness of T. annulata-infected cells, to understand the molecular basis driving cell dissemination in Tropical Theileriosis. We found that chronic induction of TNFα by the parasite contributes to motility and invasiveness of parasitized host cells. We show that TNFα does so by specifically targeting expression and function of the host proto-oncogenic ser/thr kinase MAP4K4. Blocking either TNFα secretion or MAP4K4 expression dampens the formation of polar, F-actin-rich invasion structures and impairs cell motility in 3D. We identified the F-actin binding ERM family proteins as MAP4K4 downstream effectors in this process because TNFα-induced ERM activation and cell invasiveness are sensitive to MAP4K4 depletion. MAP4K4 expression in infected cells is induced by TNFα-JNK signalling and maintained by the inhibition of translational repression, whereby both effects are parasite dependent. Thus, parasite-induced TNFα promotes invasive motility of infected cells through the activation of MAP4K4, an evolutionary conserved kinase that controls cytoskeleton dynamics and cell motility. Hence, MAP4K4 couples inflammatory signaling to morphodynamic processes and cell motility, a process exploited by the intracellular Theileria parasite to increase its host cell's dissemination capabilities.

MicroRNA signatures as biomarkers and therapeutic target for CNS embryonal tumors: the pros and the cons.

Embryonal tumors of the central nervous system represent a heterogeneous group of childhood cancers with an unknown pathogenesis; diagnosis, on the basis of histological appearance alone, is controversial and patients' response to therapy is difficult to predict. They encompass medulloblastoma, atypical teratoid/rhabdoid tumors and a group of primitive neuroectodermal tumors. All are aggressive tumors with the tendency to disseminate throughout the central nervous system. The large amount of genomic and molecular data generated over the last 5-10 years encourages optimism that new molecular targets will soon improve outcomes. Recent neurobiological studies have uncovered the key role of microRNAs (miRNAs) in embryonal tumors biology and their potential use as biomarkers is increasingly being recognized and investigated. However the successful use of microRNAs as reliable biomarkers for the detection and management of pediatric brain tumors represents a substantial challenge. This review debates the importance of miRNAs in the biology of central nervous systemembryonal tumors focusing on medulloblastoma and atypical teratoid/rhabdoid tumors and highlights the advantages as well as the limitations of their prospective application as biomarkers and candidates for molecular therapeutic targets.

Significance and therapeutic value of miRNAs in embryonal neural tumors.

Embryonal tumors of the nervous system are the leading cause of childhood cancer-related morbidity and mortality. Medulloblastoma, supratentorial primitive neuroectodermal tumors, atypical teratoid/rhabdoid tumor and neuroblastoma account for more than 20% of childhood malignancies and typify the current neural embryonal tumor model in pediatric oncology. Mechanisms driving the formation of these tumors point towards impaired differentiation of neuronal and neuron-associated cells during the development of the nervous system as an important factor. The importance of microRNAs (miRNAs) for proper embryonic cell function has been confirmed and their aberrant expressions have been linked to tumor development. The role of miRNAs in controlling essential regulators of key pathways implicated in tumor development makes their use in diagnostics a powerful tool to be used for early detection of cancer, risk assessment and prognosis, as well as for the design of innovative therapeutic strategies. In this review we focus on the significance of miRNAs involved in the biology of embryonal neural tumors, delineate their clinical significance and discuss their potential as a novel therapeutic target.

Analysis of the impact of a university distance learning course on digitalization in medicine on students and healthcare professionals.

PURPOSE: The public medical universities in Austria (educating 11,000 students) developed a joint public distance learning series in which clinicians discussed current digital lighthouse projects in their specialty. This study aims to examine the changes in attitude and knowledge of the participants before and after the lecture series to gain insights for future curriculum developments. METHOD: The lecture series was announced via various channels at the universities, in health newsletters and in social media. Attitudes toward digitalization in medicine were surveyed before and after the lecture series, together with demographic data. The data were analyzed statistically and descriptively for four groups of interest: female medical students, male medical students, faculty members and members from industry and public agencies. RESULTS: Out of 351 subjects who attended at least 1 lecture, 117 took part in the survey before and 47 after the lectures. Most participants had a positive attitude towards digitalization (85.3%). They improved their self-assessment of their knowledge from 34.4% to 64.7% (p < 0.05). After the lecture series 55.8% of participants considered digital medical applications to be important or very important today and 68.6% in the future. CONCLUSION: The study shows that the presentation and discussion of lighthouse projects improves understanding of digitalization in medicine but does not trigger a strong desire for additional further training.

Neural Network-Based Prediction of Perceived Sleep Quality Through Wearable Device Data.

BACKGROUND: This study focuses on the development of a neural network model to predict perceived sleep quality using data from wearable devices. We collected various physiological metrics from 18 participants over four weeks, including heart rate, physical activity, and both device-measured and self-reported sleep quality. OBJECTIVES: The primary objective was to correlate wearable device data with subjective sleep quality perceptions. METHODS: Our approach used data processing, feature engineering, and optimizing a Multi-Layer Perceptron classifier. RESULTS: Despite comprehensive data analysis and model experimentation, the predictive accuracy for perceived sleep quality was moderate (59%), highlighting the complexities in accurately quantifying subjective sleep experiences through wearable data. Applying a tolerance of 1 grade (on a scale from 1-5), increased accuracy to 92%. DISCUSSION: More in-depth analysis is required to fully comprehend how wearables and artificial intelligence might assist in understanding sleep behavior.

Health data space nodes for privacy-preserving linkage of medical data to support collaborative secondary analyses.

Introduction: The potential for secondary use of health data to improve healthcare is currently not fully exploited. Health data is largely kept in isolated data silos and key infrastructure to aggregate these silos into standardized bodies of knowledge is underdeveloped. We describe the development, implementation, and evaluation of a federated infrastructure to facilitate versatile secondary use of health data based on Health Data Space nodes. Materials and methods: Our proposed nodes are self-contained units that digest data through an extract-transform-load framework that pseudonymizes and links data with privacy-preserving record linkage and harmonizes into a common data model (OMOP CDM). To support collaborative analyses a multi-level feature store is also implemented. A feasibility experiment was conducted to test the infrastructures potential for machine learning operations and deployment of other apps (e.g., visualization). Nodes can be operated in a network at different levels of sharing according to the level of trust within the network. Results: In a proof-of-concept study, a privacy-preserving registry for heart failure patients has been implemented as a real-world showcase for Health Data Space nodes at the highest trust level, linking multiple data sources including (a) electronical medical records from hospitals, (b) patient data from a telemonitoring system, and (c) data from Austria's national register of deaths. The registry is deployed at the tirol kliniken, a hospital carrier in the Austrian state of Tyrol, and currently includes 5,004 patients, with over 2.9 million measurements, over 574,000 observations, more than 63,000 clinical free text notes, and in total over 5.2 million data points. Data curation and harmonization processes are executed semi-automatically at each individual node according to data sharing policies to ensure data sovereignty, scalability, and privacy. As a feasibility test, a natural language processing model for classification of clinical notes was deployed and tested. Discussion: The presented Health Data Space node infrastructure has proven to be practicable in a real-world implementation in a live and productive registry for heart failure. The present work was inspired by the European Health Data Space initiative and its spirit to interconnect health data silos for versatile secondary use of health data.

Actin-mediated plasma membrane plasticity of the intracellular parasite Theileria annulata.

Pathogen-host interactions are modulated at multiple levels by both the pathogen and the host cell. Modulation of host cell functions is particularly intriguing in the case of the intracellular Theileria parasite, which resides as a multinucleated schizont free in the cytosol of the host cell. Direct contact between the schizont plasma membrane and the cytoplasm enables the parasite to affect the function of host cell proteins through direct interaction or through the secretion of regulators. Structure and dynamics of the schizont plasma membrane are poorly understood and whether schizont membrane dynamics contribute to parasite propagation is not known. Here we show that the intracellular Theileria schizont can dynamically change its shape by actively extending filamentous membrane protrusions. We found that isolated schizonts bound monomeric tubulin and in vitro polymerized microtubules, and monomeric tubulin polymerized into dense assemblies at the parasite surface. However, we established that isolated Theileria schizonts free of host cell microtubules maintained a lobular morphology and extended filamentous protrusions, demonstrating that host microtubules are dispensable both forthe maintenance of lobular schizont morphology and for the generation of membrane protrusions. These protrusions resemble nanotubes and extend in an actin polymerization-dependent manner; using cryo-electron tomography, we detected thin actin filaments beneath these protrusions, indicating that their extension is driven by schizont actin polymerization. Thus the membrane of the schizont and its underlying actin cytoskeleton possess intrinsic activity for shape control and likely function as a peri-organelle to interact with and manipulate host cell components.

G-quadruplexes as potential therapeutic targets for embryonal tumors.

Embryonal tumors include a heterogeneous group of highly malignant neoplasms that primarily affect infants and children and are characterized by a high rate of mortality and treatment-related morbidity, hence improved therapies are clearly needed. G-quadruplexes are special secondary structures adopted in guanine (G)-rich DNA sequences that are often present in biologically important regions, e.g. at the end of telomeres and in the regulatory regions of oncogenes such as MYC. Owing to the significant roles that both telomeres and MYC play in cancer cell biology, G-quadruplexes have been viewed as emerging therapeutic targets in oncology and as tools for novel anticancer drug design. Several compounds that target these structures have shown promising anticancer activity in tumor xenograft models and some of them have entered Phase II clinical trials. In this review we examine approaches to DNA targeted cancer therapy, summarize the recent developments of G-quadruplex ligands as anticancer drugs and speculate on the future direction of such structures as a potential novel therapeutic strategy for embryonal tumors of the nervous system.

Introduction and Comparison of Novel Decentral Learning Schemes with Multiple Data Pools for Privacy-Preserving ECG Classification.

Artificial intelligence and machine learning have led to prominent and spectacular innovations in various scenarios. Application in medicine, however, can be challenging due to privacy concerns and strict legal regulations. Methods that centralize knowledge instead of data could address this issue. In this work, 6 different decentralized machine learning algorithms are applied to 12-lead ECG classification and compared to conventional, centralized machine learning. The results show that state-of-the-art federated learning leads to reasonable losses of classification performance compared to a standard, central model (-0.054 AUROC) while providing a significantly higher level of privacy. A proposed weighted variant of federated learning (-0.049 AUROC) and an ensemble (-0.035 AUROC) outperformed the standard federated learning algorithm. Overall, considering multiple metrics, the novel batch-wise sequential learning scheme performed best (-0.036 AUROC to baseline). Although, the technical aspects of implementing them in a real-world application are to be carefully considered, the described algorithms constitute a way forward towards preserving-preserving AI in medicine.

Leveraging molecular structure and bioactivity with chemical language models for de novo drug design.

Generative chemical language models (CLMs) can be used for de novo molecular structure generation by learning from a textual representation of molecules. Here, we show that hybrid CLMs can additionally leverage the bioactivity information available for the training compounds. To computationally design ligands of phosphoinositide 3-kinase gamma (PI3Kγ), a collection of virtual molecules was created with a generative CLM. This virtual compound library was refined using a CLM-based classifier for bioactivity prediction. This second hybrid CLM was pretrained with patented molecular structures and fine-tuned with known PI3Kγ ligands. Several of the computer-generated molecular designs were commercially available, enabling fast prescreening and preliminary experimental validation. A new PI3Kγ ligand with sub-micromolar activity was identified, highlighting the method's scaffold-hopping potential. Chemical synthesis and biochemical testing of two of the top-ranked de novo designed molecules and their derivatives corroborated the model's ability to generate PI3Kγ ligands with medium to low nanomolar activity for hit-to-lead expansion. The most potent compounds led to pronounced inhibition of PI3K-dependent Akt phosphorylation in a medulloblastoma cell model, demonstrating efficacy of PI3Kγ ligands in PI3K/Akt pathway repression in human tumor cells. The results positively advocate hybrid CLMs for virtual compound screening and activity-focused molecular design.

Classification of Clinical Notes from a Heart Failure Telehealth Network.

Heart failure is a common chronic disease which is associated with high re-hospitalization and mortality rates. Within the telemedicine-assisted transitional care disease management program HerzMobil, monitoring data such as daily measured vital parameters and various other heart failure related data are collected in a structured way. Additionally, involved healthcare professionals communicate with one another via the system using free-text clinical notes. Since manual annotation of such notes is too time-consuming for routine care applications, an automated analysis process is needed. In the present study, we established a ground truth classification of 636 randomly selected clinical notes from HerzMobil based on annotations of 9 experts with different professional background (2 physicians, 4 nurses, and 3 engineers). We analyzed the influence of the professional background on the inter annotator reliability and compared the results with the accuracy of an automated classification algorithm. We found significant differences depending on the profession and on the category. These results indicate that different professional backgrounds should be considered when selecting annotators in such scenarios.

Discovery of a small molecule ligand of FRS2 that inhibits invasion and tumor growth.

PURPOSE: Aberrant activation of the fibroblast growth factor receptor (FGFR) family of receptor tyrosine kinases drives oncogenic signaling through its proximal adaptor protein FRS2. Precise disruption of this disease-causing signal transmission in metastatic cancers could stall tumor growth and progression. The purpose of this study was to identify a small molecule ligand of FRS2 to interrupt oncogenic signal transmission from activated FGFRs. METHODS: We used pharmacophore-based computational screening to identify potential small molecule ligands of the PTB domain of FRS2, which couples FRS2 to FGFRs. We confirmed PTB domain binding of molecules identified with biophysical binding assays and validated compound activity in cell-based functional assays in vitro and in an ovarian cancer model in vivo. We used thermal proteome profiling to identify potential off-targets of the lead compound. RESULTS: We describe a small molecule ligand of the PTB domain of FRS2 that prevents FRS2 activation and interrupts FGFR signaling. This PTB-domain ligand displays on-target activity in cells and stalls FGFR-dependent matrix invasion in various cancer models. The small molecule ligand is detectable in the serum of mice at the effective concentration for prolonged time and reduces growth of the ovarian cancer model in vivo. Using thermal proteome profiling, we furthermore identified potential off-targets of the lead compound that will guide further compound refinement and drug development. CONCLUSIONS: Our results illustrate a phenotype-guided drug discovery strategy that identified a novel mechanism to repress FGFR-driven invasiveness and growth in human cancers. The here identified bioactive leads targeting FGF signaling and cell dissemination provide a novel structural basis for further development as a tumor agnostic strategy to repress FGFR- and FRS2-driven tumors.

Towards a Verification Approach of a Smart Registry for Chronic Heart Failure Patients.

BACKGROUND: The daily increasing amount of health data from different sources like electronic medical records and telehealth systems go hand in hand with the ongoing development of novel digital and data-driven analytics. Unifying this in a privacy-preserving data aggregation infrastructure can enable services for clinical decision support in personalized patient therapy. OBJECTIVES: The goal of this work was to consider such an infrastructure, implemented in a smart registry for heart failure, as a comparative method for the analysis of health data. METHODS: We analyzed to what extent the dataset of a study on the telehealth program HerzMobil Tirol (HMT) can be reproduced with the data from the smart registry. RESULTS: A table with 96 variables for 251 patients of the HMT publication could theoretically be replicated from the smart registry for 248 patients with 80 variables. The smart registry contained the tables to reproduce a large part of the information, especially the core statements of the HMT publication. CONCLUSION: Our results show how such an infrastructure can enable efficient analysis of health data, and thus take a further step towards personalized health care.

TGF-b2 induction regulates invasiveness of Theileria-transformed leukocytes and disease susceptibility.

Theileria parasites invade and transform bovine leukocytes causing either East Coast fever (T. parva), or tropical theileriosis (T. annulata). Susceptible animals usually die within weeks of infection, but indigenous infected cattle show markedly reduced pathology, suggesting that host genetic factors may cause disease susceptibility. Attenuated live vaccines are widely used to control tropical theileriosis and attenuation is associated with reduced invasiveness of infected macrophages in vitro. Disease pathogenesis is therefore linked to aggressive invasiveness, rather than uncontrolled proliferation of Theileria-infected leukocytes. We show that the invasive potential of Theileria-transformed leukocytes involves TGF-b signalling. Attenuated live vaccine lines express reduced TGF-b2 and their invasiveness can be rescued with exogenous TGF-b. Importantly, infected macrophages from disease susceptible Holstein-Friesian (HF) cows express more TGF-b2 and traverse Matrigel with great efficiency compared to those from disease-resistant Sahiwal cattle. Thus, TGF-b2 levels correlate with disease susceptibility. Using fluorescence and time-lapse video microscopy we show that Theileria-infected, disease-susceptible HF macrophages exhibit increased actin dynamics in their lamellipodia and podosomal adhesion structures and develop more membrane blebs. TGF-b2-associated invasiveness in HF macrophages has a transcription-independent element that relies on cytoskeleton remodelling via activation of Rho kinase (ROCK). We propose that a TGF-b autocrine loop confers an amoeboid-like motility on Theileria-infected leukocytes, which combines with MMP-dependent motility to drive invasiveness and virulence.

Theileria annulata promotes Src kinase-dependent host cell polarization by manipulating actin dynamics in podosomes and lamellipodia.

Theileria annulata is an intracellular protozoan parasite that infects B cells and macrophages of ruminants. Macrophages infected with T. annulata are de-differentiated and display tumour cell properties and a metastatic behaviour. How parasitized cells adapt their morphology, motility and invasive behaviour has not yet been addressed in detail. In this study, I investigated the regulation of host cell actin dynamics in T. annulata-transformed macrophages and how this affects host cell morphology and motility. T. annulata was found to promote the formation of filamentous-actin-rich podosome-type adhesions (PTAs) and lamellipodia, and to establish a polarized morphology of the infected cell. Characteristic for parasite-dependent host cell polarization is that infected cells display a single, persistent lamellipodium. Src kinases--in particular Hck--are required for the polar extension of this lamellipodium. Hck does so by promoting the clustered assembly of PTAs and accumulation of proteins of the Ezrin, Radixin, Moesin (ERM) family in lamellipodia. Polar accumulation of PTAs and ERM proteins correlates with focal matrix degradation underneath lamellipodia. These findings suggest that T. annulata equips its host cell with properties to adhere and invade. These properties are likely to promote the motile behaviour required for dissemination of infected cells in vivo.

Pathological stage distribution in patients treated with radical prostatectomy reflecting the need for protocol-based active surveillance: results from a contemporary European patient cohort.

UNLABELLED: Study Type - Therapy (case series). Level of Evidence 4. What's known on the subject? and What does the study add? Low-risk prostate cancer is frequently diagnosed in the context of PSA screening or during a routine check-up. For those patients, to avoid possible overtreatment AS is an increasingly chosen treatment option. However, the concept of AS could possibly misclassify potentially dangerous PCa as a low-risk disease resulting in inferior cancer control outcomes. In the present study, we could demonstrate that the histopathological results of patients treated by RP in course of AS are significantly better if the selection criteria for AS are entirely fulfilled. Our findings underline the importance of a strict and precise admittance procedure for patients with early prostate cancer who are willing to undergo an AS programme. OBJECTIVE: • To compare the histopathological outcomes of patients treated with radical prostatectomy (RP) after an initial active surveillance (AS) for localized, low-risk prostate cancers (PCa) among men who fulfilled the Epstein criteria at diagnosis with those who did not. PATIENTS AND METHODS: • In all, 283 patients with localized PCa were initially managed at our institution with AS. • In all, ≈ 50% originated from the European Randomized Study of Screening for Prostate Cancer (ERSPC) participants from Switzerland: 75 (26.5%) patients underwent treatment during follow-up and 61 were treated with RP (21.6%). • These patients were stratified into those who did (n= 39) vs those who did not (n= 22) entirely fulfil AS inclusion criteria according to Epstein et al. at PCa diagnosis. RESULTS: • Patients who did completely fulfil the AS inclusion criteria had significantly lower prostate-specific antigen (PSA)-values (4.9 vs 7.8 ng/mL; P= 0.02), a significantly lower PSA density at diagnosis (0.09 vs 0.2 ng/mL/ccm; P= 0.007) and at RP, a higher proportion of organ-confined cancers (89.7% vs 59.1%, P= 0.02) and fewer positive surgical margins (25.6% vs 40.9%). • However, the rate of favourable histopathological outcome, defined as organ-confined disease with negative surgical margins, was statistically significantly higher in the group fulfilling AS criteria (69.2% vs 40.9%; P= 0.03). CONCLUSIONS: • In our AS series, 26.5% of the patients underwent definitive therapy. • Most patients treated with RP had organ-confined disease in the majority of cases, especially when the Epstein criteria were rigorously fulfilled at PCa diagnosis. • This underlines the importance of a strict and precise per protocol AS for patients with early PCa, otherwise there is a risk of missing more significant disease.

Integration of Python Modules in a MATLAB-Based Predictive Analytics Toolset for Healthcare.

BACKGROUND: Python and MATLAB both are common tools used for predictive modelling applications, not only in healthcare. In our predictive modelling group, both tools are widely used. None of the two tools is optimal for all tasks along the value chain of predictive modelling in healthcare. OBJECTIVES: The aim of this study was to explore different ways to extend our MATLAB-based toolset with Python functions. METHODS: Pre-existing interfaces between MATLAB and Python have been evaluated and more comprehensive interfaces have been designed to exchange even complex data formats such as MATLAB tables. RESULTS: The interfaces have successfully been implemented and they were validated in a Natural Language Processing scenario based on free-text notes from a telehealth services for heart failure patients. CONCLUSION: Integration of Python modules in our MATLAB toolset is possible. Further improvements especially in terms of performance, are required if large datasets need to be exchanged. A big advantage of our concept is that tabular data can be exchanged between MATLAB and Python without loss and the Python functions are called dynamically via the interface.

Digital health understanding and preparedness of medical students: a cross-sectional study.

Digitalisation is changing all areas of our daily life. This changing environment requires new competences from physicians in all specialities. This study systematically surveyed the knowledge, attitude, and interests of medical students. These results will help further develop the medical curriculum, as well as increase our understanding of future physicians by other healthcare market players. A web-based survey consisting of four sections was developed: Section one queried demographic data, section two assessed the current digital health knowledge of medical students, section three queried their attitudes about the future impact of digital health in medicine and section four assessed the recommendations medical students have for the medical curriculum in terms of digital health. This survey was distributed to all (11,978) student at all public Austrian medical schools. A total of 8.4% of the medical student population started the survey. At the knowledge self-assessment section, the medical students reached mean of 11.74 points (SD 4.42) out of a possible maximum of 32 (female mean 10.66/ SD 3.87, male mean 13.34/SD 4.50). The attitude section showed that students see digitalisation as a threat, especially with respect to the patient-physician relationship. The curriculum recommendation section showed a high interest for topics related to AI, a per study year increasing interest in impact of digital health in communication, as well as a decreasing interest in robotic related topics. The attitude towards digital health can be described as sceptical. To ensure that future physicians keep pace with this development and fulfil their responsibility towards the society, medical schools need to be more proactive to foster the understanding of medical students that digital health will persistently alter the medical practice.

The molecular basis of the dichotomous functionality of MAP4K4 in proliferation and cell motility control in cancer.

The finely tuned integration of intra- and extracellular cues by components of the mitogen-activated protein kinase (MAPK) signaling pathways controls the mutually exclusive phenotypic manifestations of uncontrolled growth and tumor cell dissemination. The Ser/Thr kinase MAP4K4 is an upstream integrator of extracellular cues involved in both proliferation and cell motility control. Initially identified as an activator of the c-Jun N-terminal kinase (JNK), the discovery of diverse functions and additional effectors of MAP4K4 beyond JNK signaling has considerably broadened our understanding of this complex kinase. The implication of MAP4K4 in the regulation of cytoskeleton dynamics and cell motility provided essential insights into its role as a pro-metastatic kinase in cancer. However, the more recently revealed role of MAP4K4 as an activator of the Hippo tumor suppressor pathway has complicated the understanding of MAP4K4 as an oncogenic driver kinase. To develop a better understanding of the diverse functions of MAP4K4 and their potential significance in oncogenesis and tumor progression, we have collected and assessed the current evidence of MAP4K4 implication in molecular mechanisms that control proliferation and promote cell motility. A better understanding of these mechanisms is particularly relevant in the brain, where MAP4K4 is highly expressed and under pathological conditions either drives neuronal cell death in neurodegenerative diseases or cell dissemination in malignant tumors. We review established effectors and present novel interactors of MAP4K4, which offer mechanistic insights into MAP4K4 function and may inspire novel intervention strategies. We discuss possible implications of novel interactors in tumor growth and dissemination and evaluate potential therapeutic strategies to selectively repress pro-oncogenic functions of MAP4K4.