Drug-decorated nanoparticles (DDNPs) have important medical applications. The current work combined Perturbation Theory with Machine Learning and Information Fusion (PTMLIF). Thus, PTMLIF models were proposed to predict the probability of nanoparticle–compound/drug complexes having antimalarial activity (against Plasmodium). The aim is to save experimental resources and time by using a virtual screening for DDNPs. The raw data was obtained by the fusion of experimental data for nanoparticles with compound chemical assays from the ChEMBL database. The inputs for the eight Machine Learning classifiers were transformed features of drugs/compounds and nanoparticles as perturbations of molecular descriptors in specific experimental conditions (experiment-centered features). The resulting dataset contains 107 input features and 249,992 examples. The best classification model was provided by Random Forest, with 27 selected features of drugs/compounds and nanoparticles in all experimental conditions considered. The high performance of the model was demonstrated by the mean Area Under the Receiver Operating Characteristics (AUC) in a test subset with a value of 0.9921 ± 0.000244 (10-fold cross-validation). The results demonstrated the power of information fusion of the experimental-centered features of drugs/compounds and nanoparticles for the prediction of nanoparticle–compound antimalarial activity. The scripts and dataset for this project are available in the open GitHub repository.

The theoretical prediction of drug-decorated nanoparticles (DDNPs) has become a very important task in medical applications. For the current paper, Perturbation Theory Machine Learning (PTML) models were built to predict the probability of different pairs of drugs and nanoparticles creating DDNP complexes with anti-glioblastoma activity. PTML models use the perturbations of molecular descriptors of drugs and nanoparticles as inputs in experimental conditions. The raw dataset was obtained by mixing the nanoparticle experimental data with drug assays from the ChEMBL database. Ten types of machine learning methods have been tested. Only 41 features have been selected for 855,129 drug-nanoparticle complexes. The best model was obtained with the Bagging classifier, an ensemble meta-estimator based on 20 decision trees, with an area under the receiver operating characteristic curve (AUROC) of 0.96, and an accuracy of 87% (test subset). This model could be useful for the virtual screening of nanoparticle-drug complexes in glioblastoma. All the calculations can be reproduced with the datasets and python scripts, which are freely available as a GitHub repository from authors.

Conference: Proceedings of the conference MOL2NET International Conference on Multidisciplinary Sciences (4th edition), 2018 is part of a year-round worldwide conference series hosted by MDPI Sciforum, Basel, Switzerland. This conference series has had organized more than 20 associated workshop series in universities worldwide: USA, France, Portugal, Spain, China, Chile, Brazil, India, etc. These workshop series run in person and/or online. Some of these workshops are the SRI-10 St Thomas University (STU)- Miami Dade College (MDC), Miami, USA; USINEWS-02 University of Minnesota, USA; BIOCHEMPHYS-01 CNAM, Paris, France; WCUCW, West Coast University, Miami, USA; IWMEDIC UDC, Coruña, Spain, LAWSCI-02, UPV/EHU, Bilbao, Spain, etc. Workshops allow both in person and/or online only publication of papers, research highlights of previous papers, letters, short reviews, etc. Topics: The topics are multidisciplinary covering, but not limited to, Chemistry (All areas), Physics , Biology , Ecology , Statistics , Bioinformatics , Education , Nanotechnology , Materials , Computational , Complex Networks, Legal, and Social sciences, etc. Statistics: This edition hosted >10 workshops that attracted >300 communications submitted by >700 authors. We organized 7 special issues published in JCR journals (MDPI editorial) such as Molecules, Entropy, and Appl. Sci. We also organized 3 bootcamps, hand-training, or capstone courses in MDC, Miami, WCU Miami, and UPV/EHU Bilbao. Proceedings Book: The present book of proceedings have been released in two versions. The first is a short version without communications including links to online versions of all communications (only 94 pages). The second one is the long version including full text of all communications and abstracts (2985 pages). Download short version from MDPI AG Sciforum publisher link: https://sciforum.net/paper/view/conference/6143. We released long versiong to Researchgate public repository: https://www.researchgate.net/project/Mol2Net-conf-series. Thank you very much to all colleagues for your kind support.

We are glad to invite all colleagues worldwide to participate on a new edition of this International Conference Series. The official title of this conference series is MOL2NET International Conference Series on Multidisciplinary Sciences. MOL2NET (the conference running title) is the acronym of the lemma of the conference: From Molecules to Networks. This running title is inspired by the possibility of multidisciplinary collaborations in science. The topics of interest include, but are not limited to, Chemistry (All areas), Mathematics (Applied), Physics (Applied), Materials Science, Nanotechnology, Biology and Life Sciences (All areas), Medicine, Biomedical Engineering, Education, along with Computer Sciences, Data Analysis, Statistics, Artificial Intelligence, Deep Learning, Bioinformatics, Systems Biology, and Complex Networks Sciences. See the following note to authors on topics outside the scope of the conference and associated workshops . The Scientific Headquarters (HQs) of this conference series are in the Faculty of Science and Technology, University of Basque Country (UPV/EHU), Biscay. However, the idea of this multidisciplinary conference emerged from the melting pot formed as the result of multiple collaborations of professors from many centers worldwide. Locally, the founders and strongest supporters of the conference are professors endowed by IKERBASQUE, Basque Foundation for Sciences, professors from the two departments Department of Organic Chemistry I and Department of Organic Chemistry II of the University of Basque Country (UPV/EHU), and professors from the Department of Computer Sciences of the University of Coruña (UDC). In addition, professors / researchers from the Center for the Study of Biological Complexity of the Virginia Commonwealth University (VCU), USA, the Natural Resources Research Institute, of the University of Minnesota, USA, and many other institutions are also founders and supporters of this conference, please see full committees lists.

Parham cyclisation – intermolecular α-amidoalkylation sequence constitute a route to trans thiazolo[4,3-a]isoquinolinones. These thiazolidindiones, that incorporate allyl groups at C-1 and C-10b, are efficient precursors of thiaerythrinanes by ring-closing methathesis reactions.