On the additive artificial intelligence-based discovery of nanoparticle neurodegenerative disease drug delivery systems

• Shan He,
• Julen Segura Abarrategi,
• Harbil Bediaga,
• Sonia Arrasate and
• Humberto González-Díaz

Beilstein J. Nanotechnol. 2024, 15, 535–555, doi:10.3762/bjnano.15.47

• experimental/theoretical study of new 1,3-rasagiline derivatives potentially useful in neurodegenerative diseases [51], as well as QSAR and complex networks in pharmaceutical design, microbiology, parasitology, toxicology, cancer, and neurosciences [52]. Furthermore, this new model also has been used for very

• coworkers. These researchers employed this database to create advanced predictive models known as multitarget or multiplexing QSAR. These models are designed to forecast both the potential neurotoxicity and neuroprotective effects of drugs across various experimental setups, including multiple assays, drug

• interact with targets within the CNS interactome [58]. Speck-Planche et al. compiled manually a database of NPs from the literature. They constructed a QSAR model to investigate multiple antibacterial profiles of NPs under diverse experimental conditions. Furthermore, Ortega-Tenezaca et al. enriched the NP

Exploring the relationships between physiochemical properties of nanoparticles and cell damage to combat cancer growth using simple periodic table-based descriptors

• Joyita Roy and
• Kunal Roy

Beilstein J. Nanotechnol. 2024, 15, 297–309, doi:10.3762/bjnano.15.27

• this does not contribute to the variations in zeta potential values due to solvents. This work is similar to imputation in quantitative structure–activity relationship (QSAR) modeling, where a missing value is replaced by a predicted value from another model [30]. The training set with 111 MeOx NPs

• embedded within another model. Instead of using dummy variables for quantitative prediction, a useful imputation method can predict various types of inputs. It is worth noting that many existing works utilize imputation techniques [41]. In QSAR studies, it is not unusual to use a model-derived prediction

• knowledge for treating cancerous cells through cell damage techniques. The study can pave the way for researchers to use nanoparticles in clinical practice with confidence. Workflow for developing QSPR (model 1) and QSAR (model 2) models. Bubble plot for dataset 1 (model 1) and dataset 2 (model 2). Williams

Prediction of cytotoxicity of heavy metals adsorbed on nano-TiO₂ with periodic table descriptors using machine learning approaches

• Joyita Roy,
• Souvik Pore and
• Kunal Roy

Beilstein J. Nanotechnol. 2023, 14, 939–950, doi:10.3762/bjnano.14.77

• metals into organisms. Thus, the present study reports nanoscale quantitative structure–activity relationship (nano-QSAR) models, which are based on an ensemble learning approach, for predicting the cytotoxicity of heavy metals adsorbed on nano-TiO2 to human renal cortex proximal tubule epithelial (HK-2

• cause of cytotoxicity. To demonstrate the predictive ability of the developed nano-QSAR models, simple periodic table descriptors requiring low computational resources were utilized. The nano-QSAR models generated good R2 values (0.99–0.89), Q2 values (0.64–0.77), and Q2F1 values (0.99–0.71). Thus, the

• present work manifests that ML in conjunction with periodic table descriptors can be used to explore the features and predict unknown compounds with similar properties. Keywords: heavy metals; HK-2 cell; ML algorithm; periodic table descriptors; QSAR; Introduction Nanoparticles (NPs) have gained much

Identifying diverse metal oxide nanomaterials with lethal effects on embryonic zebrafish using machine learning

• Richard Liam Marchese Robinson,
• Haralambos Sarimveis,
• Philip Doganis,
• Xiaodong Jia,
• Marianna Kotzabasaki,
• Christiana Gousiadou,
• Stacey Lynn Harper and
• Terry Wilkins

Beilstein J. Nanotechnol. 2021, 12, 1297–1325, doi:10.3762/bjnano.12.97

• -fertilisation data were found to be harder to predict, which could reflect different exposure routes. Hence, subsequent analysis focused on the prediction of excess lethality at 120 hours-post fertilisation. The use of two data augmentation approaches, applied for the first time in nano-QSAR research, was

• these modelling results are on truly external data, which were not used to select the single descriptor model. This will require further laboratory work to generate comparable data to those studied herein. Keywords: data augmentation; embryonic zebrafish; machine learning; nanosafety; nano-QSAR

• (i.e., depending on the exposure medium) physicochemical characteristics [18][19][20]. However, concerns have been raised regarding the human health relevance of the endpoints modelled in many nano-QSAR studies [21]. There is a need for models that can predict human safety relevant endpoints

Evaluating the toxicity of TiO₂-based nanoparticles to Chinese hamster ovary cells and Escherichia coli: a complementary experimental and computational approach

• Alicja Mikolajczyk,
• Natalia Sizochenko,
• Ewa Mulkiewicz,
• Anna Malankowska,
• Michal Nischk,
• Przemyslaw Jurczak,
• Seishiro Hirano,
• Grzegorz Nowaczyk,
• Adriana Zaleska-Medynska,
• Jerzy Leszczynski,
• Agnieszka Gajewicz and
• Tomasz Puzyn

Beilstein J. Nanotechnol. 2017, 8, 2171–2180, doi:10.3762/bjnano.8.216

• obtained cytotoxicity data were analyzed by means of computational methods (quantitative structure–activity relationships, QSAR approach). Based on a combined experimental and computational approach, predictive models were developed, and relationships between cytotoxicity, size, and specific surface area

• (Brunauer–Emmett–Teller surface, BET) of nanoparticles were discussed. Keywords: Au/Pd–TiO2 photocatalyst; bimetallic nanoparticles; nanotoxicity; nano-QSAR; second-generation nanoparticles; Introduction Unmodified titania (TiO2) nanoparticles (so-called first-generation NPs) represent a material that

• Chemicals) regulations, which pronounce that information about risk assessment of chemicals should be generated whenever possible by means other than vertebrate animal tests, through the use of alternative methods, for example quantitative structure–activity relationship models (QSAR) [25][26]. This

Modeling adsorption of brominated, chlorinated and mixed bromo/chloro-dibenzo-p-dioxins on C₆₀ fullerene using Nano-QSPR

• Piotr Urbaszek,
• Agnieszka Gajewicz,
• Celina Sikorska,
• Maciej Haranczyk and
• Tomasz Puzyn

Beilstein J. Nanotechnol. 2017, 8, 752–761, doi:10.3762/bjnano.8.78

• for Economic Co-operation and Development (OECD) QSAR validation recommendations [27] and fulfills all the validation criteria. The presented model has a well-defined endpoint (ΔEads - adsorption energy of a C60@PXDD complex) and well-known algorithms (GA-PLS). According to OECD guidelines, it is

An ISA-TAB-Nano based data collection framework to support data-driven modelling of nanotoxicology

• Richard L. Marchese Robinson,
• Mark T. D. Cronin,
• Andrea-Nicole Richarz and
• Robert Rallo

Beilstein J. Nanotechnol. 2015, 6, 1978–1999, doi:10.3762/bjnano.6.202

• weaknesses of the resources are discussed along with possible future developments. Keywords: databases; ISA-TAB-Nano; nanoinformatics; nanotoxicology; quantitative structure–activity relationship (QSAR); Introduction Nanotechnology, which may be considered the design and application of engineered

• vitro assays [4][84]. A number of nano-QSAR models have been developed for cytotoxicity [13][85][86][87][88][89][90][91] and some models have also been developed for nanomaterial genotoxicity [9][92][93]. The genotoxicity Assay file template (“a_InvID_genotoxicity_Method.xls”) was designed to capture

NanoE-Tox: New and in-depth database concerning ecotoxicity of nanomaterials

• Katre Juganson,
• Angela Ivask,
• Irina Blinova,
• Monika Mortimer and
• Anne Kahru

Beilstein J. Nanotechnol. 2015, 6, 1788–1804, doi:10.3762/bjnano.6.183

• models, including valid QSAR models, for predicting toxic potential of ENMs. Methodology The process of creating the nanoecotoxicological database can be roughly divided into three steps: selecting keywords for literature search, performing the literature search in Thomson Reuters WoS, collecting and

• database. Median EC50 values were calculated because these are the most precise estimates derived from the concentration–effect curve [62] and also, median EC50 values are often used in the QSAR analysis [63]. Analysis of the sources of the median values showed that most of the data in one data point

The eNanoMapper database for nanomaterial safety information

• Nina Jeliazkova,
• Charalampos Chomenidis,
• Philip Doganis,
• Bengt Fadeel,
• Roland Grafström,
• Barry Hardy,
• Janna Hastings,
• Markus Hegi,
• Vedrin Jeliazkov,
• Nikolay Kochev,
• Pekka Kohonen,
• Cristian R. Munteanu,
• Haralambos Sarimveis,
• Bart Smeets,
• Pantelis Sopasakis,
• Georgia Tsiliki,
• David Vorgrimmler and
• Egon Willighagen

Beilstein J. Nanotechnol. 2015, 6, 1609–1634, doi:10.3762/bjnano.6.165

• machine learning and QSAR community. PMML documents are essentially XML documents that contain all necessary information to reproduce a model including the definition of input parameters, targets (predicted properties), preprocessing steps (e.g., scaling, normalization, transformation of inputs), and the

Using natural language processing techniques to inform research on nanotechnology

• Nastassja A. Lewinski and
• Bridget T. McInnes

Beilstein J. Nanotechnol. 2015, 6, 1439–1449, doi:10.3762/bjnano.6.149

• ) and PubMED retrieved 2 records (2 excluded). The following exclusion criteria were applied to the retrieved records: Bioinformatics papers not specifically focused on nanotechnology were not included. Bibliometric approaches were not included. Non-text based approaches (such as QSAR or image analysis