Antimicrobial resistance has prompted research and the development of new antibiotic treatments. Efforts to discover new drugs with antibacterial activity have generated large data sets from multiple preclinical trials with different experimental conditions. Predicting the activity of new chemical compounds on pathogenic microorganisms with different Metabolic Reaction Networks (MRNs) has become an important objective in the field. PTMLIF (Perturbation Theory, Machine Learning and Information Fusion) models are the combination of perturbation theory with machine learning and information fusion. In this document, we merge >100000 preclinical antibacterial assays from the ChEMBL database with the structural information for >40 MRNs of different microorganisms reported by the Barabási group. Non-linear PTMLIF models were applied to apply Random Forest (RF), J48- decision tree, and Bayesian Network (BN) algorithms. BN and RF models presented better results, specificity (˃88%), sensitivity (˃95%), AUROC (˃95%), and accuracy (~90%), In this work, we also demonstrated the power of information fusion of experimental characteristics of drugs/compounds and MRN for the prediction of antibacterial activity of chemical compounds.

Nanoparticles may have anti-bacterial activity so they become interesting alternatives to drugs in a context of emergence of resistant bacteria. These bacteria have different metabolic networks. In a recent work we developed a information fusion perturbation-theory machine learning (IFPTML) model to predicting nanoparticles vs. bacteria with topological changes on metabolic networks. The dataset studied had 15 classes of nanoparticles (1-100 nm) with most cases in the range of 1-50 nm vs. >20 pathogenic bacteria species with different metabolic networks. The nanoparticles studied included metal nanoparticles of Au, Ag, and Cu; oxide nanoparticles of Zn, Cu, La, Al, Fe, Sn, Ti, Cd, and Si; and metal salt nanoparticles of CuI and CdS. We used the SOFT.PTML software (our own application) with a user-friendly interface for the IFPTML calculations and a control statistics package. Using SOFT.PTML, we found a random forest model with Sn and Sp = 98-99% in the training/validation series.

Ref: B. Ortega-Tenezaca, H. González-Díaz. IFPTML mapping of nanoparticle antibacterial activity vs. pathogen metabolic networks. Nanoscale 2021 Jan 7. doi: 10.1039/d0nr07588d.

Talk presented on the JClubBiofisika, Coordinated by Prof. Alvaro Villaroel, Basque Center for Biophysics, CSIC-UPVEHU, Leioa, Basque Country, Spain. https://balanbbb.corp.csic.es/playback/presentation/2.0/playback.html?meetingId=464d38fbcdb87ce995bb1094f6074c813a1c5f28-1609404921659

Talk presented on the JClubBiofisika, Coordinated by Prof. Alvaro Villaroel, Basque Center for Biophysics, CSIC-UPVEHU, Leioa, Basque Country, Spain. Please, follow the link to see the talk and slides, audio in Spanish: https://balanbbb.corp.csic.es/playback/presentation/2.0/playback.html?meetingId=464d38fbcdb87ce995bb1094f6074c813a1c5f28-1610458120252

A series of C-10 substituted pyrrolo[1,2-b]isoquinolines have been synthesized via palladium-catalyzed Heck/Suzuki and Heck/anion capture cascade reactions. These compounds have shown antileishmanial activity against cutaneous (L. amazonensis) leishmaniasis, being even 10-fold more potent and selective than the drug of reference, Miltefosine. A Perturbation Theory Machine Learning (PTML) model has also been developed for the prediction of the probability with which a query compound reaches a desired level for multiple parameters vs. different Leishmania species and target proteins.

Site selective monoacylation of pyrroles has been achieved via Pd(II)-catalyzed C-H activiation with aldehydes in the presence of TBHP as oxidant using the 3-methyl-2-pyridine as directing group. The reaction has been extended to different aromatic and heteroaromatic aldehydes for the synthesis of a series of di(hetero)aryl ketones. The utility of the methodloogy has been demonstrated in the synthesis of pyrrolomycins, as Celastramycin analogues and Tolmetin.

The variability of methicillin-resistant Staphylococcus aureus (MRSA), its rapid adaptive response against environmental changes, and its continued acquisition of antibiotic resistance determinants, have made it a habitual resident of hospitals, where it causes a problem of multidrug resistance.

In this study, molecular topology was used to develop several discriminant equations capable of classifying compounds according to
their anti-MRSA activity.

Topological indices were used as structural descriptors and their relationship to anti-MRSA activity was determined by applying linear discriminant analysis (LDA) on a group of quinolones and quinolone-like compounds.

Four extra equations were constructed, named DFMRSA1, DFMRSA2, DFMRSA3 and DFMRSA4 (DFMRSA was built in a previous study), all with good statistical parameters such as Fisher-Snedecor F (> 68 in all cases), Wilk’s lambda (< 0.13 in all cases) and percentage of correct classification (> 94 % in all cases), which allows a reliable extrapolation prediction of antibacterial activity in any organic compound.

The results obtained clearly reveal the high efficiency of combining molecular topology with LDA for the prediction of anti-MRSA activity.

In a recent paper we analyzed in detail the principles of EU food and nanotechnology regulations perspectives for Machine Learning application towards safety issues analysis. In-depth review and discussion of the regulation opportunities to apply ML models of nanoparticles was presented involving EU foods nanotechnology regulation. It is concluded Machine Learning could improve the application of nanotechnology food regulation. ML can be applied on this area following the principles lined up by the standards of OECD, EU regulations and EFSA.

Ref: Machine Learning as a Proposal for a Better Application of Food Nanotechnology Regulation in the European UnionRicardo Santana ^{1 2 3}, Enrique Onieva ¹, Robin Zuluaga ⁴, Aliuska Duardo-Sánchez ⁵, Piedad Gañán ⁶ Curr Top Med Chem. 2020;20(4):324-332. doi: 10.2174/1568026619666191205152538.