Blind prediction of HIV integrase binding from the SAMPL4 challenge.

Here, we give an overview of the protein-ligand binding portion of the Statistical Assessment of Modeling of Proteins and Ligands 4 (SAMPL4) challenge, which focused on predicting binding of HIV integrase inhibitors in the catalytic core domain. The challenge encompassed three components--a small "virtual screening" challenge, a binding mode prediction component, and a small affinity prediction component. Here, we give summary results and statistics concerning the performance of all submissions at each of these challenges. Virtual screening was particularly challenging here in part because, in contrast to more typical virtual screening test sets, the inactive compounds were tested because they were thought to be likely binders, so only the very top predictions performed significantly better than random. Pose prediction was also quite challenging, in part because inhibitors in the set bind to three different sites, so even identifying the correct binding site was challenging. Still, the best methods managed low root mean squared deviation predictions in many cases. Here, we give an overview of results, highlight some features of methods which worked particularly well, and refer the interested reader to papers in this issue which describe specific submissions for additional details.

Knowledge abstraction and filtering based federated learning over heterogeneous data views in healthcare.

Robust data privacy regulations hinder the exchange of healthcare data among institutions, crucial for global insights and developing generalised clinical models. Federated learning (FL) is ideal for training global models using datasets from different institutions without compromising privacy. However, disparities in electronic healthcare records (EHRs) lead to inconsistencies in ML-ready data views, making FL challenging without extensive preprocessing and information loss. These differences arise from variations in services, care standards, and record-keeping practices. This paper addresses data view heterogeneity by introducing a knowledge abstraction and filtering-based FL framework that allows FL over heterogeneous data views without manual alignment or information loss. The knowledge abstraction and filtering mechanism maps raw input representations to a unified, semantically rich shared space for effective global model training. Experiments on three healthcare datasets demonstrate the framework's effectiveness in overcoming data view heterogeneity and facilitating information sharing in a federated setup.

Cancer drug sensitivity prediction from routine histology images.

Drug sensitivity prediction models can aid in personalising cancer therapy, biomarker discovery, and drug design. Such models require survival data from randomised controlled trials which can be time consuming and expensive. In this proof-of-concept study, we demonstrate for the first time that deep learning can link histological patterns in whole slide images (WSIs) of Haematoxylin & Eosin (H&E) stained breast cancer sections with drug sensitivities inferred from cell lines. We employ patient-wise drug sensitivities imputed from gene expression-based mapping of drug effects on cancer cell lines to train a deep learning model that predicts patients' sensitivity to multiple drugs from WSIs. We show that it is possible to use routine WSIs to predict the drug sensitivity profile of a cancer patient for a number of approved and experimental drugs. We also show that the proposed approach can identify cellular and histological patterns associated with drug sensitivity profiles of cancer patients.

Cross-linking breast tumor transcriptomic states and tissue histology.

Identification of the gene expression state of a cancer patient from routine pathology imaging and characterization of its phenotypic effects have significant clinical and therapeutic implications. However, prediction of expression of individual genes from whole slide images (WSIs) is challenging due to co-dependent or correlated expression of multiple genes. Here, we use a purely data-driven approach to first identify groups of genes with co-dependent expression and then predict their status from WSIs using a bespoke graph neural network. These gene groups allow us to capture the gene expression state of a patient with a small number of binary variables that are biologically meaningful and carry histopathological insights for clinical and therapeutic use cases. Prediction of gene expression state based on these gene groups allows associating histological phenotypes (cellular composition, mitotic counts, grading, etc.) with underlying gene expression patterns and opens avenues for gaining biological insights from routine pathology imaging directly.

mRNA codon optimization with quantum computers.

Reverse translation of polypeptide sequences to expressible mRNA constructs is a NP-hard combinatorial optimization problem. Each amino acid in the protein sequence can be represented by as many as six codons, and the process of selecting the combination that maximizes probability of expression is termed codon optimization. This work investigates the potential impact of leveraging quantum computing technology for codon optimization. A Quantum Annealer (QA) is compared to a standard genetic algorithm (GA) programmed with the same objective function. The QA is found to be competitive in identifying optimal solutions. The utility of gate-based systems is also evaluated using a simulator resulting in the finding that while current generations of devices lack the hardware requirements, in terms of both qubit count and connectivity, to solve realistic problems, future generation devices may be highly efficient.

Discovery of inhibitors of lupin diadenosine 5',5'''-P(1),P(4)-tetraphosphate hydrolase by virtual screening.

Novel inhibitors of lupin diadenosine 5',5'''-P(1),P(4)-tetraphosphate (Ap(4)A) hydrolase have been identified by in silico screening of a large virtual chemical library. Compounds were ranked on the basis of a consensus from six scoring functions. From the top 100 ranked compounds six were selected and initially screened for inhibitory activity using a single concentration isothermal titration calorimetry assay. Two of these compounds that showed excellent solubility properties were further analyzed, but only one [NSC51531; 2-((8-hydroxy-4-(4-methyl-2-sulfoanilino)-9,10-dioxo-9,10-dihydro-1-anthracenyl)amino)-5-methylbenzenesulfonic acid] exhibited competitive inhibition with a K(i) of 1 microM. A structural analogue of this compound also exhibited competitive inhibition with a comparable K(i) of 2.9 microM. (1)H, (15)N NMR spectroscopy was used to map the binding site of NSC51531 on lupin Ap(4)A hydrolase and demonstrated that the compound bound specifically in the substrate-binding site, consistent with the competitive inhibition results. Binding of NSC51531 to the human form of Ap(4)A hydrolase is nonspecific, suggesting that this compound may represent a useful lead in the design of specific inhibitors of the plant-like form of Ap(4)A hydrolases.

Bayesian analysis of isothermal titration calorimetry for binding thermodynamics.

Isothermal titration calorimetry (ITC) is the only technique able to determine both the enthalpy and entropy of noncovalent association in a single experiment. The standard data analysis method based on nonlinear regression, however, provides unrealistically small uncertainty estimates due to its neglect of dominant sources of error. Here, we present a Bayesian framework for sampling from the posterior distribution of all thermodynamic parameters and other quantities of interest from one or more ITC experiments, allowing uncertainties and correlations to be quantitatively assessed. For a series of ITC measurements on metal:chelator and protein:ligand systems, the Bayesian approach yields uncertainties which represent the variability from experiment to experiment more accurately than the standard data analysis. In some datasets, the median enthalpy of binding is shifted by as much as 1.5 kcal/mol. A Python implementation suitable for analysis of data generated by MicroCal instruments (and adaptable to other calorimeters) is freely available online.

A Web-Based Tool for Patient Triage in Emergency Department Settings: Validation Using the Emergency Severity Index.

BACKGROUND: We evaluated the concordance between triage scores generated by a novel Internet clinical decision support tool, Clinical GPS (cGPS) (Lumiata Inc, San Mateo, CA), and the Emergency Severity Index (ESI), a well-established and clinically validated patient severity scale in use today. Although the ESI and cGPS use different underlying algorithms to calculate patient severity, both utilize a five-point integer scale with level 1 representing the highest severity. OBJECTIVE: The objective of this study was to compare cGPS results with an established gold standard in emergency triage. METHODS: We conducted a blinded trial comparing triage scores from the ESI: A Triage Tool for Emergency Department Care, Version 4, Implementation Handbook to those generated by cGPS from the text of 73 sample case vignettes. A weighted, quadratic kappa statistic was used to assess agreement between cGPS derived severity scores and those published in the ESI handbook for all 73 cases. Weighted kappa concordance was defined a priori as almost perfect (kappa > 0.8), substantial (0.6 < kappa < 0.8), moderate (0.4 < kappa < 0.6), fair (0.2 < kappa< 0.4), or slight (kappa < 0.2). RESULTS: Of the 73 case vignettes, the cGPS severity score matched the ESI handbook score in 95% of cases (69/73 cases), in addition, the weighted, quadratic kappa statistic showed almost perfect agreement (kappa = 0.93, 95% CI 0.854-0.996). In the subanalysis of 41 case vignettes assigned ESI scores of level 1 or 2, the cGPS and ESI severity scores matched in 95% of cases (39/41 cases). CONCLUSIONS: These results indicate that the cGPS is a reliable indicator of triage severity, based on its comparison to a standardized index, the ESI. Future studies are needed to determine whether the cGPS can accurately assess the triage of patients in real clinical environments.

Identification and specificity studies of small-molecule ligands for SH3 protein domains.

The Src Homology 3 (SH3) domains are small protein-protein interaction domains that bind proline-rich sequences and mediate a wide range of cell-signaling and other important biological processes. Since deregulated signaling pathways form the basis of many human diseases, the SH3 domains have been attractive targets for novel therapeutics. High-affinity ligands for SH3 domains have been designed; however, these have all been peptide-based and no examples of entirely nonpeptide SH3 ligands have previously been reported. Using the mouse Tec Kinase SH3 domain as a model system for structure-based ligand design, we have identified several simple heterocyclic compounds that selectively bind to the Tec SH3 domain. Using a combination of nuclear magnetic resonance chemical shift perturbation, structure-activity relationships, and site-directed mutagenesis, the binding of these compounds at the proline-rich peptide-binding site has been characterized. The most potent of these, 2-aminoquinoline, bound with Kd = 125 microM and was able to compete for binding with a proline-rich peptide. Synthesis of 6-substituted-2-aminoquinolines resulted in ligands with up to 6-fold improved affinity over 2-aminoquinoline and enhanced specificity for the Tec SH3 domain. Therefore, 2-aminoquinolines may potentially be useful for the development of high affinity small molecule ligands for SH3 domains.

Design of ß-amyloid aggregation inhibitors from a predicted structural motif.

Drug design studies targeting one of the primary toxic agents in Alzheimer's disease, soluble oligomers of amyloid ß-protein (Aß), have been complicated by the rapid, heterogeneous aggregation of Aß and the resulting difficulty to structurally characterize the peptide. To address this, we have developed [Nle(35), D-Pro(37)]Aß(42), a substituted peptide inspired from molecular dynamics simulations which forms structures stable enough to be analyzed by NMR. We report herein that [Nle(35), D-Pro(37)]Aß(42) stabilizes the trimer and prevents mature fibril and ß-sheet formation. Further, [Nle(35), D-Pro(37)]Aß(42) interacts with WT Aß(42) and reduces aggregation levels and fibril formation in mixtures. Using ligand-based drug design based on [Nle(35), D-Pro(37)]Aß(42), a lead compound was identified with effects on inhibition similar to the peptide. The ability of [Nle(35), D-Pro(37)]Aß(42) and the compound to inhibit the aggregation of Aß(42) provides a novel tool to study the structure of Aß oligomers. More broadly, our data demonstrate how molecular dynamics simulation can guide experiment for further research into AD.

Alchemical free energy methods for drug discovery: progress and challenges.

Improved rational drug design methods are needed to lower the cost and increase the success rate of drug discovery and development. Alchemical binding free energy calculations, one potential tool for rational design, have progressed rapidly over the past decade, but still fall short of providing robust tools for pharmaceutical engineering. Recent studies, especially on model receptor systems, have clarified many of the challenges that must be overcome for robust predictions of binding affinity to be useful in rational design. In this review, inspired by a recent joint academic/industry meeting organized by the authors, we discuss these challenges and suggest a number of promising approaches for overcoming them.

Practical aspects of the SAMPL challenge: providing an extensive experimental data set for the modeling community.

To provide an experimental basis for a comprehensive molecular modeling evaluation study, 500 fragments from the Maybridge fragment library were soaked into crystals of bovine pancreatic trypsin and the structures determined by X-ray crystallography. The soaking experiments were performed in both single and pooled aliquots to determine if combination of fragments is an appropriate strategy. A further set of data was obtained from co-crystallizing the pooled fragments with the protein. X-ray diffraction data were collected on approximately 1000 crystals at the Australian Synchrotron, and these data were subsequently processed, and the preliminary analysis was performed with a custom software application (Jigsaw), which combines available software packages for structure solution and analysis.

Seminal fluid drives expansion of the CD4+CD25+ T regulatory cell pool and induces tolerance to paternal alloantigens in mice.

T regulatory (Treg) cells are implicated in maternal immune tolerance of the conceptus at implantation; however, the antigenic and regulatory signals controlling Treg cells in early pregnancy are undefined. To examine the role of male seminal fluid in tolerance induction, the effect of exposure to seminal fluid at mating on responsiveness to paternal alloantigens was examined using paternal tumor cell grafts and by delayed-type hypersensitivity (DTH) challenge on Day 3.5 postcoitum. Exposure to seminal fluid inhibited rejection of paternal tumor cells, independently of fertilization and embryo development, while seminal fluid from major histocompatability complex (MHC)-dissimilar males was less effective. Similarly, mating with intact males suppressed the DTH response to paternal alloantigens in an MHC-specific fashion. Excision of the seminal vesicle glands diminished the tolerance-inducing activity of seminal fluid. Mating with intact males caused an increase in CD4(+)CD25(+) cells expressing FOXP3 in the para-aortic lymph nodes draining the uterus, beyond the estrus-associated peak in cycling mice. The increase in CD4(+)CD25(+) cells was abrogated when males were vasectomized or seminal vesicles were excised. Collectively, these data provide evidence that exposure to seminal fluid at mating promotes a state of functional tolerance to paternal alloantigens that may facilitate maternal acceptance of the conceptus at implantation, and the effects of seminal fluid are likely to be mediated by expansion of the Treg cell pool. Both seminal plasma and sperm components of the seminal fluid are necessary to confer full tolerance and elicit the Treg cell response, potentially through provision of immune-deviating cytokines and antigens, respectively.