Search

The present review has been developed as part of the VIRTUOUS project, funded by the European Union's Horizon 2020 research and innovation program under the Marie Sklodowska-Curie-RISE Grant Agreement No 872181 (https://www.virtuoush2020.com/)., Background: The perception of taste is a prime example of complex signal transduction at the subcellular level, involving an intricate network of molecular machinery, which can be investigated to great extent by the tools provided by Computational Molecular Modelling. The present review summarises the current knowledge on the molecular mechanisms at the root of taste transduction, in particular involving taste receptors, highly specialised proteins driving the activation/deactivation of specific cell signalling pathways and ultimately leading to the perception of the five principal tastes: sweet, umami, bitter, salty and sour. The former three are detected by similar G protein-coupled receptors, while the latter two are transduced by ion channels. Scope and approach: The main objective of the present review is to provide a general overview of the molecular structures investigated to date of all taste receptors and the techniques employed for their molecular modelling. In addition, we provide an analysis of the various ligands known to date for the above-listed receptors, including how they are activated in the presence of their target molecule. Key findings and conclusions: In the last years, numerous advances have been made in molecular research and computational investigation of ligand-receptor interaction related to taste receptors. This work aims to outline the progress in scientific knowledge about taste perception and understand the molecular mechanisms involved in the transfer of taste information., European Union's Horizon 2020 research and innovation program under the Marie Sklodowska-Curie-RISE Grant 872181

Purpose: Topical analgesics have gained acceptance in guidelines for the treatment of pain. The Kailo Pain Patch® is a topically applied analgesic adhesive patch, with a recent study showing reduced pain severity and interference scales in comparison to a control group. However, as with any analgesic modality, treatment response is variable. Advances in technology, such as pharmacogenomic evaluation and machine learning (artificial intelligence) have emerged as tools to assist clinicians with selecting the most suitable treatments for a variety of disease states. There is limited data on the use of these technologies for pain management; only limited studies have applied machine learning to personalize the treatment of chronic pain patients. This report analyzed the PREVENT Study using an existing modified interpretable machine learning method to personalize the selection of the most suitable protocol for use of the Kailo Pain Patch® and other topical analgesics. Patients and methods: Data from the IRB-approved observational PREVENT study were used in the present analysis of 128 (89 females,39 males) chronic pain patients and 20 controls answering the Brief Pain (BPI) questionnaire along with additional questions in the baseline and after 30 days of treatment with the Kailo Pain Patch®. An interpretable machine-learning model was used to build pain outcome prediction models. This method is a multi-objective ensemble classification/regression technique, which combines multi-objective evolutionary algorithms with Support Vector Machines, Random Forests, and feature filtering techniques to optimize the classification model and minimize the utilized feature subset. Three basic endpoints were examined as outputs to the prediction models including Total BPI Severity, Total BPI Interference, and Total medication changes in the follow- up period. Both classification and regression models were constructed for these endpoints and a “leave-one-out” cross-validation strategy was used to evaluate the generalization ability, classification, and regression performance of the deployed models. Results: Experimental results showed that the trained models with the proposed machine learning method were able to predict endpoints with extremely high accuracy, with the AUC exceeding 90% and Spearman correlation metric exceeding 0.4 for all endpoints, overcoming the classification and regression performances of other benchmark models, including the recently introduced XGBoost. The interpretable machine learning method was able to reduce the number of significant features to 15 and was able to identify some of the most important characteristics of responders and non-responders allowing for a personalized approach to creating an individualized pain treatment approach. Applying the trained model in a previous IRB-approved Observational Study (OPERA) dataset (631 chronic pain patients) demonstrated that most of the participants (>70%) who did not benefit from other topical analgesics therapies, as well as more than 50% of responders to OPERA study medications, would have noted improvement from the pain patch studied in PREVENT. Conclusions: Artificial intelligence and machine learning technologies are advancing multiple areas in fields of medicine, including pain management. A model has been developed which continues to be refined; here we show use of that model for predicting response to topical analgesic therapies. We will continue to refine these tools and make them available to front-line clinicians through a user-friendly web interface (https://kailo.insybio.com/) that can be used to support analgesic clinical decision making [15 questions].

Retinoids are widely used in diseases spanning from dermatological lesions to cancer, but exhibit severe adverse effects. A novel all-trans-Retinoic Acid (atRA)-spermine conjugate (termed RASP) has shown previously optimal in vitro and in vivo anti-inflammatory and anticancer efficacy, with undetectable teratogenic and toxic side-effects. To get insights, we treated HaCaT cells which resemble human epidermis with IC50 concentration of RASP and analyzed their miRNA expression profile. Gene ontology analysis of their predicted targets indicated dynamic networks involved in cell proliferation, signal transduction and apoptosis. Furthermore, DNA microarrays analysis verified that RASP affects the expression of the same categories of genes. A protein-protein interaction map produced using the most significant common genes, revealed hub genes of nodal functions. We conclude that RASP is a synthetic retinoid derivative with improved properties, which possess the beneficial effects of retinoids without exhibiting side-effects and with potential beneficial effects against skin diseases including skin cancer.

Taste is a sensory modality crucial for nutrition and survival, since it allows the discrimination between healthy foods and toxic substances thanks to five tastes, i.e., sweet, bitter, umami, salty, and sour, associated with distinct nutritional or physiological needs. Today, taste prediction plays a key role in several fields, e.g., medical, industrial, or pharmaceutical, but the complexity of the taste perception process, its multidisciplinary nature, and the high number of potentially relevant players and features at the basis of the taste sensation make taste prediction a very complex task. In this context, the emerging capabilities of machine learning have provided fruitful insights in this field of research, allowing to consider and integrate a very large number of variables and identifying hidden correlations underlying the perception of a particular taste. This review aims at summarizing the latest advances in taste prediction, analyzing available food-related databases and taste prediction tools developed in recent years., Politecnico di Torino within the CRUI-CARE Agreement, European Union's Horizon 2020 research and innovation program 872181

Introduction: cAMP response element-binding protein (CREB) mediates proliferative and inflammatory transcription in neurodegeneration and cancer, but its role in malignant immune-evasion is obscure. Objectives: To discover the mechanisms underlying the oncogenic properties of CREB in KRAS-mutant lung adenocarcinoma (LUAD). Materials and Methods: We used conditional deletion, focal overexpression, and pharmacologic inhibition of CREB in different mouse and cellular models of early-stage and metastatic KRAS-mutant LUAD. We determined the neutrophil (ΝΦ) influx in the bronchoalveolar lavage (BAL) from LUAD-affected conditionally Creb1-deleted lungs. We employed The Cancer Genome Atlas, the GEO dataset GSE43458, and the human protein atlas to examine CREB and CXCR1 in human LUAD. Results: CREB is overexpressed in murine KRAS-mutant LUAD, pulmonary deletion of Creb1 (encoding murine CREB) inhibits LUAD development, and Creb1-overexpression augments the tumorigenicity of KRAS-mutant cells. Conditional Creb1 deletion in KRAS -mutant LUAD cells causes overexpression of CXCR1 ligands, and LUAD-bearing Creb1-deleted mice display increased pulmonary ΝΦ. Cxcr1-deficient mice are selectively permissive to KRAS-mutant tumor growth and show defective ΝΦ recruitment. The pro-tumor effects of CREB require intact host Cxcr1 and those of host Cxcr1 necessitate mutant KRAS in cancer cells. Pharmacologic CREB blockade prevents tumor growth and restores ΝΦ recruitment only when initiated before immune-evasion of KRAS-mutant LUAD. CREB and CXCR1 expression of human LUAD are compartmentalized to tumor and stromal cells, respectively, while CREB-controlled genes profoundly impact survival. Conclusions: CREB-mediated immune evasion of KRAS-mutant LUAD rests on signaling to ΝΦ CXCR1 and is actionable.

Σκοπός της διατριβής ήταν η ανάπτυξη νέων μοντέλων Υπολογιστκής Νοημοσύνης με χαμηλές υπολογιστικές απαιτήσεις, για την αντιμετώπιση πραγματικών προβλημάτων από τον χώρο της Βιοπληροφορικής και της Επεξεργασίας Βιοσημάτων. Τα πραγματικά προβλήματα συνήθως δημιουργούν μεγάλα σύνολα δεδομένων και χαρακτηρίζονται από περίπλοκα όρια διαχωρισμού κλάσεων (class separation boundaries). Πρόσφατα, σχεδιασμένα μοντέλα όπως το μοντέλο των Support Vector Machines μπορούν να αντιμετωπίσουν περίπλοκα προβλήματα ταξινόμησης προτύπων (pattern classification problems), όμως ο τρόπος που χρησιμοποιούν είναι υπολογιστικά τόσο ατελέσφορος, που για μεγάλα σύνολα δεδομένων, η αριθμητική επίλυση (numerical evaluation) αυτών των μοντέλων καθίσταται σχεδόν απογορευτική. Τα μοντέλα μη-επιβλεπόμενης (unsupervised) μάθησης από την άλλη, αν και έχουν σημαντικά χαμηλότερες υπολογιστικές απαιτήσεις, έχουν μια εγγενή μειωμένη ικανότητα διαχωρισμού κλάσεων κοντά στα όρια των κλάσεων. Η διατριβή αυτή αποσκοπώντας στον συνδυασμό και των δυο μοντέλων (μη επιβλεπόμενων και επιβλεπόμενών) εισήγαγε μια νέα προσέγγιση που στηρίχθηκε σε ένα απλό γεγονός: ο χώρος καταστάσεων για πολλά περίπλοκα προβλήματα ταξινόμησης προτύπων, αποτελείται από περιοχές που βρίσκονται κοντά στα όρια διαχωρισμού κλάσεων και απαιτούν την κατασκευή περίπλοκων διαχωριστών (discriminants), ενώ για τις υπόλοιπες περιοχές το πρόβλημα της ταξινόμησης είναι αρκετά πιο απλό. Σύμφωνα με τα προηγούμενα, στο πρώτο μέρος της διατριβής σχεδιάστηκε το μοντέλο Supervised Network Self-Organizing Map (sNet-SOM) που εκμεταλλεύεται την ύπαρξη του ανομοιόμορφου χώρου καταστάσεων: Το μοντέλο sNetSOM χρησιμοποιεί μη-επιβλεπόμενη μάθηση για την ταξινόμηση στις απλές περιοχές και επιβλεπόμενη για τις περίπλοκες περιοχές (δηλαδή σε αυτές που είναι κοντά στα όρια διαχωρισμού κλάσεων). Ο αλγόριθμος μάθησης του sNetSOM διατυπώνεται επομένως σε δύο στάδια: Η μη-επιβλεπόμενη μάθηση επεκτείνει και προσαρμόζει τον αλγόριθμο SOM του Kohonen, ενώ η επιβλεπόμενη βασίζεται στα μοντέλα Generalized Radial Basis Functions Networks (GRBFN) και σε Support Vector Machines (SVM’s). Η απόδοση του sNet-SOM υπολογίστηκε κατά την εφαρμογή του σε συνθετικά δεδομένα, σε δεδομένα προσομοίωσης και σε πρόβλημα ανίχνευσης ισχαιμικών επεισοδίων με δεδομένα από την European ST-T βάση δεδομένων (καταγραφές Ηλεκτροκαρδιογραφημάτων). Σε όλες τις περιπτώσεις η χρήση του sNet-SOM, με επιβλεπόμενη μάθηση βασιζόμενη σε GRBFN και σε SVM’s, βελτίωσε σημαντικά τα αποτελέσματα που προκύπτουν μόνο από την χρήση του μη-επιβλεπόμενού SOM και μείωσε δραστικά της υπολογιστικές απαιτήσεις των επιβλεπόμενων μοντέλων, λόγω της λειτουργία τους στον σημαντικά μειωμένο χώρο των διφορούμενων περιοχών. Το δεύτερο μέρος της διατριβής αποσκοπούσε στην εφαρμογή του μοντέλου sNet- SOM για την ανάλυση δεδομένων γονιδιακής έκφρασης από μικροσυστοιχίες. Τώρα που το έργο της αλληλούχισης του ανθρώπινου γονιδιώματος οδεύει προς την πλήρη ολοκλήρωσή του (προγραμματισμένο για το 2003), η τεχνολογία των μικροσυστοιχιών ανοίγει νέους ορίζοντες για την μελέτη της πολυπλοκότητας του γονιδιώματος. Επιτρέποντας την μέτρηση της έκφρασης χιλιάδων γονιδίων ταυτόχρονα, βοηθάει στην ανακάλυψη της λειτουργίας των γονιδίων και αποσαφηνίζει σημαντικά βιολογικά μονοπάτια (biological pathways). Η ανάλυση των τεράστιων ποσοτήτων δεδομένων που προκύπτουν από αυτά τα πειράματα όμως, απαιτεί την χρήση προηγμένων υπολογιστικών εργαλείων. Το μοντέλο του sNet- SOM πληρούσε σε γενικές γραμμές τις προϋποθέσεις, έπρεπε όμως να επανασχεδιασθεί για να εναρμονιστεί με τις ιδιαιτερότητες των δεδομένων γονιδιακής έκφρασης. Επιπρόσθετα, επειδή προς το παρόν η αποκάλυψη της δομής των δεδομένων παραμένει βασικός στόχος της ανάλυσης των δεδομένων και όχι απλά η ταξινόμηση των γονιδίων, η δυνατότητα ομαδοποίησης του sNet-SOM ενισχύθηκε, προσθέτοντας, στη μη-επιβλεπόμενης φάση του, μια επιπλέον δυνατότητα επέκτασης. Η εφαρμογή του sNet-SOM για την ανάλυση δεδομένων γονιδιακής έκφρασης είχε απόδοση ταξινόμησης παρόμοια με αυτές άλλων προηγμένων μοντέλων ταξινόμησης, που έχουν χρησιμοποιηθεί πρόσφατα. Επιπλέον όμως είχε και το σημαντικό πλεονέκτημα των χαμηλών υπολογιστικών απαιτήσεων και την ικανότητα της αντιμετώπισης του γεγονότος, ότι τα γονίδια ανήκουν σε περισσότερες της μίας κλάσης (multi-labeling), το οποίο είτε αμελείται, είτε δεν μπορεί να αντιμετωπιστεί από τις περισσότερες άλλες μεθόδους. Επίσης, συγκρίνοντας με μοντέλα που είτε χρησιμοποιούν επιβλεπόμενη μάθηση και ταξινομούν τα δεδομένα, είτε χρησιμοποιούν μη-επιβλεπόμενη μάθηση και αποκαλύπτουν την δομή των δεδομένων, το σχεδιασμένο μοντέλο sNet-SOM καταφέρνει και συνδυάζει και τις δύο διεργασίες, γιατί παράλληλα με την ταξινόμηση παρέχει ένα εργαλείο εκτενούς εξερεύνησης των δεδομένων στο πλαίσιο της μη-επιβλεπόμενης ανάλυσης.

Purpose: Topical analgesics have shown efficacy for patients experiencing mild and moderate pain. Due to high variability in patient demographics, clinical profile, and analgesic response, identifying the most suitable treatment for pain patients is difficult. Artificial intelligence and machine learning techniques have shown promise in individualizing treatments. This analysis reviews an interpretable machine learning method to individualize treatment. Due to adverse effects associated with many analgesics, the ability to predict treatment response has a tremendous benefit to clinicians and patients. Patients and methods: Data were evaluated from 186 pain patients enrolled in an Institutional Review Board approved study (RELIEF) after use of a topical pain-relieving analgesic patch for 14 days. A novel interpretable machine learning method was developed based on a multi-objective ensemble classification/regression technique. Data was expanded to increase predictive accuracy with pre- and post-modeling techniques to raise interpretability. 85 features were identified that allowed calculation of data between testing and training groups. Data were split into training (n=152) and testing (n=34) patient sets in a stratified manner. Three basic endpoints were examined for the prediction models: total BPI Severity scores, total BPI Interference scores, and changes in the total drugs. Results: Results demonstrated that the machine learning models were able to predict endpoints with extremely high accuracy, with the AUC exceeding 90% and Spearman correlation metric exceeding 0.4 for all endpoints, far exceeding the test set performance of other benchmark models. The machine learning method reduced the number of significant features from 85 to 19 and defined well characterized groups of responders and non-responders. Conclusion: The machine learning model demonstrated that predictions of positive response could have been made prospectively for patients that benefited from the topical pain-relieving patch. This predictive analytic methodology can be applied to separate and larger datasets and used retrospectively to analyze whether a certain treatment might be effective in a given population.

Introduction: cAMP response element-binding protein (CREB) mediates proliferative and inflammatory transcription in neurodegeneration and cancer, but its role in malignant immune-evasion is obscure. Objectives: To discover the mechanisms underlying the oncogenic properties of CREB in KRAS-mutant lung adenocarcinoma (LUAD). Materials and Methods: We used conditional deletion, focal overexpression, and pharmacologic inhibition of CREB in different mouse and cellular models of early-stage and metastatic KRAS-mutant LUAD. We determined the neutrophil (ΝΦ) influx in the bronchoalveolar lavage (BAL) from LUAD-affected conditionally Creb1-deleted lungs. We employed The Cancer Genome Atlas, the GEO dataset GSE43458, and the human protein atlas to examine CREB and CXCR1 in human LUAD. Results: CREB is overexpressed in murine KRAS-mutant LUAD, pulmonary deletion of Creb1 (encoding murine CREB) inhibits LUAD development, and Creb1-overexpression augments the tumorigenicity of KRAS-mutant cells. Conditional Creb1 deletion in KRAS -mutant LUAD cells causes overexpression of CXCR1 ligands, and LUAD-bearing Creb1-deleted mice display increased pulmonary ΝΦ. Cxcr1-deficient mice are selectively permissive to KRAS-mutant tumor growth and show defective ΝΦ recruitment. The pro-tumor effects of CREB require intact host Cxcr1 and those of host Cxcr1 necessitate mutant KRAS in cancer cells. Pharmacologic CREB blockade prevents tumor growth and restores ΝΦ recruitment only when initiated before immune-evasion of KRAS-mutant LUAD. CREB and CXCR1 expression of human LUAD are compartmentalized to tumor and stromal cells, respectively, while CREB-controlled genes profoundly impact survival. Conclusions: CREB-mediated immune evasion of KRAS-mutant LUAD rests on signaling to ΝΦ CXCR1 and is actionable.