Explore the vast range of titles available.

Recently, imputation techniques have been adapted to predict activity values among sparse bioactivity matrices, showing improvements in predictive performance over traditional QSAR models. These models are able to use experimental activity values for auxiliary assays when predicting the activity of a test compound on a specific assay. In this study, we tested three different multi-task imputation techniques on three classification-based toxicity datasets: two of small scale (12 assays each) and one large scale with 417 assays. Moreover, we analyzed in detail the improvements shown by the imputation models. We found that test compounds that were dissimilar to training compounds, as well as test compounds with a large number of experimental values for other assays, showed the largest improvements. We also investigated the impact of sparsity on the improvements seen as well as the relatedness of the assays being considered. Our results show that even a small amount of additional information can provide imputation methods with a strong boost in predictive performance over traditional single task and multi-task predictive models.

Background Combining different sources of knowledge to build improved structure activity relationship models is not easy owing to the variety of knowledge formats and the absence of a common framework to interoperate between learning techniques. Most of the current approaches address this problem by using consensus models that operate at the prediction level. We explore the possibility to directly combine these sources at the knowledge level, with the aim to harvest potentially increased synergy at an earlier stage. Our goal is to design a general methodology to facilitate knowledge discovery and produce accurate and interpretable models. Results To combine models at the knowledge level, we propose to decouple the learning phase from the knowledge application phase using a pivot representation (lingua franca) based on the concept of hypothesis. A hypothesis is a simple and interpretable knowledge unit. Regardless of its origin, knowledge is broken down into a collection of hypotheses. These hypotheses are subsequently organised into hierarchical network. This unification permits to combine different sources of knowledge into a common formalised framework. The approach allows us to create a synergistic system between different forms of knowledge and new algorithms can be applied to leverage this unified model. This first article focuses on the general principle of the Self Organising Hypothesis Network (SOHN) approach in the context of binary classification problems along with an illustrative application to the prediction of mutagenicity. Conclusion It is possible to represent knowledge in the unified form of a hypothesis network allowing interpretable predictions with performances comparable to mainstream machine learning techniques. This new approach offers the potential to combine knowledge from different sources into a common framework in which high level reasoning and meta-learning can be applied; these latter perspectives will be explored in future work.

Background A new algorithm has been developed to enable the interpretation of black box models. The developed algorithm is agnostic to learning algorithm and open to all structural based descriptors such as fragments, keys and hashed fingerprints. The algorithm has provided meaningful interpretation of Ames mutagenicity predictions from both random forest and support vector machine models built on a variety of structural fingerprints. A fragmentation algorithm is utilised to investigate the model’s behaviour on specific substructures present in the query. An output is formulated summarising causes of activation and deactivation. The algorithm is able to identify multiple causes of activation or deactivation in addition to identifying localised deactivations where the prediction for the query is active overall. No loss in performance is seen as there is no change in the prediction; the interpretation is produced directly on the model’s behaviour for the specific query. Results Models have been built using multiple learning algorithms including support vector machine and random forest. The models were built on public Ames mutagenicity data and a variety of fingerprint descriptors were used. These models produced a good performance in both internal and external validation with accuracies around 82%. The models were used to evaluate the interpretation algorithm. Interpretation was revealed that links closely with understood mechanisms for Ames mutagenicity. Conclusion This methodology allows for a greater utilisation of the predictions made by black box models and can expedite further study based on the output for a (quantitative) structure activity model. Additionally the algorithm could be utilised for chemical dataset investigation and knowledge extraction/human SAR development.

Structure Activity Relationship (SAR) modelling capitalises on techniques developed within the computer science community, particularly in the fields of machine learning and data mining. These machine learning approaches are often developed for the optimisation of model accuracy which can come at the expense of the interpretation of the prediction. Highly predictive models should be the goal of any modeller, however, the intended users of the model and all factors relating to usage of the model should be considered. One such aspect is the clarity, understanding and explanation for the prediction. In some cases black box models which do not provide an interpretation can be disregarded regardless of their predictive accuracy. In this thesis the problem of model interpretation has been tackled in the context of models to predict toxicity of drug like molecules. Firstly a novel algorithm has been developed for the interpretation of binary classification models where the endpoint meets defined criteria: activity is caused by the presence of a feature and inactivity by the lack of an activating feature or the deactivation of all such activating features. This algorithm has been shown to provide a meaningful interpretation of the model’s cause(s) of both active and inactive predictions for two toxicological endpoints: mutagenicity and skin irritation. The algorithm shows benefits over other interpretation algorithms in its ability to not only identify the causes of activity mapped to fragments and physicochemical descriptors but also in its ability to account for combinatorial effects of the descriptors. The interpretation is presented to the user in the form of the impact of features and can be visualised as a concise summary or in a hierarchical network detailing the full elucidation of the models behaviour for a particular query compound. The interpretation output has been capitalised on and incorporated into a knowledge mining strategy. The knowledge mining is able to extract the learned structure activity relationship trends from a model such as a Random Forest, decision tree, k Nearest Neighbour or support vector machine. These trends can be presented to the user focused around the feature responsible for the assessment such as ACTIVATING or DEACTIVATING. Supporting examples are provided along with an estimation of the models predictive performance for a given SAR trend. Both the interpretation and knowledge mining has been applied to models built for the prediction of Ames mutagenicity and skin irritation. The performance of the developed models is strong and comparable to both academic and commercial predictors for these two toxicological activities.

Necroptotic cell death is mediated by the most terminal known effector of the pathway, MLKL. Precisely how phosphorylation of the MLKL pseudokinase domain activation loop by the upstream kinase, RIPK3, induces unmasking of the N-terminal executioner four-helix bundle (4HB) domain of MLKL, higher-order assemblies, and permeabilization of plasma membranes remains poorly understood. Here, we reveal the existence of a basal monomeric MLKL conformer present in human cells prior to exposure to a necroptotic stimulus. Following activation, toggling within the MLKL pseudokinase domain promotes 4HB domain disengagement from the pseudokinase domain αC helix and pseudocatalytic loop, to enable formation of a necroptosis-inducing tetramer. In contrast to mouse MLKL, substitution of RIPK3 substrate sites in the human MLKL pseudokinase domain completely abrogated necroptotic signaling. Therefore, while the pseudokinase domains of mouse and human MLKL function as molecular switches to control MLKL activation, the underlying mechanism differs between species. RIPK3-mediated phosphorylation of the mixed lineage kinase domain-like (MLKL) pseudokinase is thought to be the trigger for MLKL activation during necroptotic signaling. Here the authors provide evidence that the transition of human MLKL from a monomeric state to a tetramer is essential for necroptosis signalling.

Among nonhospitalized patients with Covid-19–related symptoms that began less than a week previously, a 3-day course of remdesivir resulted in an 87% lower risk of hospitalization or death than placebo. Adverse effects in the remdesivir group were similar to those in the placebo group.

Significance The four-helix bundle (4HB) domain of Mixed Lineage Kinase Domain-Like (MLKL) bears two clusters of residues that are required for cell death by necroptosis. Mutations within a cluster centered on the α4 helix of the 4HB domain of MLKL prevented its membrane translocation, oligomerization, and ability to induce necroptosis. This cluster is composed principally of acidic residues and therefore challenges the idea that the 4HB domain engages negatively charged phospholipid membranes via a conventional positively charged interaction surface. The importance of membrane translocation to MLKL-mediated death is supported by our identification of a small molecule that binds the MLKL pseudokinase domain and retards membrane translocation to inhibit necroptotic signaling. Necroptosis is considered to be complementary to the classical caspase-dependent programmed cell death pathway, apoptosis. The pseudokinase Mixed Lineage Kinase Domain-Like (MLKL) is an essential effector protein in the necroptotic cell death pathway downstream of the protein kinase Receptor Interacting Protein Kinase-3 (RIPK3). How MLKL causes cell death is unclear, however RIPK3–mediated phosphorylation of the activation loop in MLKL trips a molecular switch to induce necroptotic cell death. Here, we show that the MLKL pseudokinase domain acts as a latch to restrain the N-terminal four-helix bundle (4HB) domain and that unleashing this domain results in formation of a high-molecular-weight, membrane-localized complex and cell death. Using alanine-scanning mutagenesis, we identified two clusters of residues on opposing faces of the 4HB domain that were required for the 4HB domain to kill cells. The integrity of one cluster was essential for membrane localization, whereas MLKL mutations in the other cluster did not prevent membrane translocation but prevented killing; this demonstrates that membrane localization is necessary, but insufficient, to induce cell death. Finally, we identified a small molecule that binds the nucleotide binding site within the MLKL pseudokinase domain and retards MLKL translocation to membranes, thereby preventing necroptosis. This inhibitor provides a novel tool to investigate necroptosis and demonstrates the feasibility of using small molecules to target the nucleotide binding site of pseudokinases to modulate signal transduction.

The necroptosis cell death pathway has been implicated in host defense and in the pathology of inflammatory diseases. While phosphorylation of the necroptotic effector pseudokinase Mixed Lineage Kinase Domain-Like (MLKL) by the upstream protein kinase RIPK3 is a hallmark of pathway activation, the precise checkpoints in necroptosis signaling are still unclear. Here we have developed monobodies, synthetic binding proteins, that bind the N-terminal four-helix bundle (4HB) “killer” domain and neighboring first brace helix of human MLKL with nanomolar affinity. When expressed as genetically encoded reagents in cells, these monobodies potently block necroptotic cell death. However, they did not prevent MLKL recruitment to the “necrosome” and phosphorylation by RIPK3, nor the assembly of MLKL into oligomers, but did block MLKL translocation tomembranes where activatedMLKL normally disrupts membranes to kill cells. An X-ray crystal structure revealed a monobodybinding site centered on the α4 helix of the MLKL 4HB domain, which mutational analyses showed was crucial for reconstitution of necroptosis signaling. These data implicate the α4 helix of its 4HB domain as a crucial site for recruitment of adaptor proteins that mediatemembrane translocation, distinct from known phospholipid binding sites.

Phosphorylation of the MLKL pseudokinase by the RIPK3 kinase leads to MLKL oligomerization, translocation to, and permeabilization of, the plasma membrane to induce necroptotic cell death. The precise choreography of MLKL activation remains incompletely understood. Here, we report Monobodies, synthetic binding proteins, that bind the pseudokinase domain of MLKL within human cells and their crystal structures in complex with the human MLKL pseudokinase domain. While Monobody-32 constitutively binds the MLKL hinge region, Monobody-27 binds MLKL via an epitope that overlaps the RIPK3 binding site and is only exposed after phosphorylated MLKL disengages from RIPK3 following necroptotic stimulation. The crystal structures identified two distinct conformations of the MLKL pseudokinase domain, supporting the idea that a conformational transition accompanies MLKL disengagement from RIPK3. These studies provide further evidence that MLKL undergoes a large conformational change upon activation, and identify MLKL disengagement from RIPK3 as a key regulatory step in the necroptosis pathway. Mixed Lineage Kinase Domain-Like (MLKL) pseudokinase is phosphorylated by RIPK3 kinase prior to cell death by necroptosis. Here, the authors use monobodies that bind to the MLKL pseudokinase domain as tools, which allowed them to determine the crystal structures of the MLKL pseudokinase domain in two distinct conformations. By combining their structural data with cell signalling assays and MD simulations they provide evidence that endogenous MLKL preassociates with its upstream regulator RIPK3, and that MLKL disengages from RIPK3 following the induction of necroptosis.

Accurate methods of identifying patients with COVID-19 who are at high risk of poor outcomes has become especially important with the advent of limited-availability therapies such as monoclonal antibodies. Here we describe development and validation of a simple but accurate scoring tool to classify risk of hospitalization and mortality. All consecutive patients testing positive for SARS-CoV-2 from March 25-October 1, 2020 within the Intermountain Healthcare system were included. The cohort was randomly divided into 70% derivation and 30% validation cohorts. A multivariable logistic regression model was fitted for 14-day hospitalization. The optimal model was then adapted to a simple, probabilistic score and applied to the validation cohort and evaluated for prediction of hospitalization and 28-day mortality. 22,816 patients were included; mean age was 40 years, 50.1% were female and 44% identified as non-white race or Hispanic/Latinx ethnicity. 6.2% required hospitalization and 0.4% died. Criteria in the simple model included: age (0.5 points per decade); high-risk comorbidities (2 points each): diabetes mellitus, severe immunocompromised status and obesity (body mass index≥30); non-white race/Hispanic or Latinx ethnicity (2 points), and 1 point each for: male sex, dyspnea, hypertension, coronary artery disease, cardiac arrythmia, congestive heart failure, chronic kidney disease, chronic pulmonary disease, chronic liver disease, cerebrovascular disease, and chronic neurologic disease. In the derivation cohort (n = 16,030) area under the receiver-operator characteristic curve (AUROC) was 0.82 (95% CI 0.81-0.84) for hospitalization and 0.91 (0.83-0.94) for 28-day mortality; in the validation cohort (n = 6,786) AUROC for hospitalization was 0.8 (CI 0.78-0.82) and for mortality 0.8 (CI 0.69-0.9). A prediction score based on widely available patient attributes accurately risk stratifies patients with COVID-19 at the time of testing. Applications include patient selection for therapies targeted at preventing disease progression in non-hospitalized patients, including monoclonal antibodies. External validation in independent healthcare environments is needed.