LIFE.PTML Models in Drug Development, Personalized Medicine, and Epidemiology
Humbert G. Díaz, Prof.
IKERBASQUE Senior Prof. Univ. of The Basque Country (UPV/EHU), Dept. Org. & Inorg. Chemistry│UPV/EHU-CSIC BIOFISIKA, PI CHEMIF.PTML Multi-Center Lab│UPV/EHU IKERDATA S.L. PI Founder (Lang: EN work, SP native, EU basic)
LIFE.PTML Information Fusion and Encoding, Perturbation Theory, and Machine Learning algorithms could be useful in Drug Discovery and Personalized Medicine to rationalize resources to time ratios, animal experimentation reduction, replacement or refination (3Rs), drug repurposing, treatments regime optimization, personalized treatment tayloring, drug epidemiological surveilance, etc. See some selected papers from CHEM.PTML LAB in this area. Read more about our group in our newsletter: https://www.dhirubhai.net/newsletters/chem-ptml-lab-newsletter-6924816402038071296/
Paper 1. Brain regions proteins targeting drugs
Elsevier Published: Identification of Riluzole Derivatives as Novel Calmodulin Inhibitors with Neuroprotective Activity by a joint Synthesis, Biosensor, and Computational guided strategy. Maider Baltasar Marchueta, Leire Llona, @Sara Alicante, Iratxe Barbolla, Markel Garcia Ibarluzea , Rafael Ramis Cortés, Ane Miren Salomon, Brenda de la Caridad Fundora Ortiz, Ariane Araujo, Arantza Muguruza Montero, Eider Nu?ez, Scarlett Pérez Olea, @Christian Villanueva, Aritz Leonardo Liceranzu, Sonia Arrasate Gil, Nuria Sotomayor, Alvaro Villarroel, Aitor Bergara, Esther Lete, and Humbert G. Díaz, Prof. BIOMED & PHARMACOTHER (2024) 174,?116602, doi: 10.1016/j.biopha.2024.116602.
Abstract: The development of new molecules for the treatment of calmodulin related cardiovascular or neurodegenerative diseases is an interesting goal. In this work, we introduce a novel strategy with four main steps: (1) chemical synthesis of target molecules, (2) F?rster Resonance Energy Transfer (FRET) biosensor development and in vitro biological assay of new derivatives, (3) IFPTML Cheminformatics models development and in vivo activity prediction, and (4) Docking studies.
Practical case: This strategy is illustrated with a case study. Firstly, a series of 4-substituted Riluzole derivatives 1–3 were synthetized through a strategy that involves the construction of the 4-bromoriluzole framework and its further functionalization via palladium catalysis or organolithium chemistry. Next, a FRET biosensor for monitoring Ca2+-dependent CaM-ligands interactions has been developed and used for the in vitro assay of Riluzole derivatives. In particular, the best inhibition (80%) was observed for 4-methoxyphenylriluzole 2b. Besides, we trained and validated a new Networks Invariant, Information Fusion, Perturbation Theory, and Machine Learning (NIFPTML) model for predicting probability profiles of in vivo biological activity parameters in different regions of the brain. Next, we used this model to predict the in vivo activity of the compounds experimentally studied in vitro. Last, docking study conducted on Riluzole and its derivatives has provided valuable insights into their binding conformations with the target protein, involving calmodulin and the SK4 channel. This new combined strategy may be useful to reduce assay costs (animals, materials, time, and human resources) in the drug discovery process of calmodulin inhibitors.
Linkedin comment: https://www.dhirubhai.net/posts/humbertgdiaz_riluzole-neuroprotective-synthesis-activity-7184541421410926592-f7JF?utm_source=share&utm_medium=member_desktop
Paper link: https://lnkd.in/dabqbHk6
Acknowledgements: Eskerrik asko, Thank you to all authors, affiliated/host instututions, and funding agencies!!!!
Affiliations: Department of Organic and Inorganic Chemistry, Departament of Physics, University of the Basque Country ZTF-FCT :: UPV/EHU, Universidad del País Vasco/Euskal Herriko Unibertsitatea, 48940, Leioa, Spain. Biofisika Institute, CSIC-UPV/EHU, Fundación Biofísica Bizkaia / Biofisika Bizkaia Fundazioa 48940, Leioa, Spain. Donostia International Physics Center (DIPC) , Donostia, Spain. Ikerbasque, Basque Foundation for Science, 48011, Bilbao, Spain.
Corresponding authors: AV = [email protected] (Biological assays); AB = [email protected](Docking studies); EL = [email protected] (Organic synthesis); HGD =[email protected] (Machine Learning).
Sponsors: European Commission hashtag#NextGenerationEU funds, IKERDATA S.L. - Lanbide hashtag#Investigo program, Basque Government / Eusko Jaurlaritza - Gobierno Vasco (IT1558-22), ELKARTEK SPRI Group grants CardiCaM (KK-2020/00110) are acknowledged for financial support. We also acknowledge Ministry of Science and Innovation of Spain (PID2019-104148GB-100, PID2021-128286NB-100, PID2022-137365NB-100 funded by MCIN/AEI/10.13039/501100011033). Technical and human support provided by Servicios Generales de Investigación SGIker (UPV/EHU, MINECO, GV/EJ, ERDF and ESF) is also acknowledged. B.F. also acknowledges kind support of Fundación Carolina (STEM scholarship for higher education graduates, call 2019-2020).
Paper 2. Prediction of warfarin blood levels
Wolters Kluwer Published. Machine Learning guided prediction of warfarin blood levels for personalized medicine based on clinical longitudinal data from cardiac surgery patients: a prospective observational study, by Ling Xue, Shan He, Dr. Rajeev K Singla,?Qiong Qin,?Yinglong Ding,?Linsheng Liu,?Xiaoliang Ding, Harbil Bediaga Ba?eres, Sonia Arrasate Gil, Aliuska Duardo-Sanchez,?Yuzhen Zhang,?Zhenya Shen, Bairong Shen,?Liyan Miao, Humbert G. Díaz, Prof. INT J SUR (2024) Jun 4.?doi:10.1097/JS9.0000000000001734, Congratulations to all authors. ??♂?
Abstract (Background):?
Warfarin is a common oral anticoagulant, and its effects vary widely among individuals. Numerous dose-prediction algorithms have been reported based on cross-sectional data generated via multiple linear regression or machine learning. This study aimed to construct an information fusion perturbation theory and machine learning prediction model of warfarin blood levels based on clinical longitudinal data from cardiac surgery patients.
Methods and Material:?
The data of 246 patients were obtained from electronic medical records. Continuous variables were processed by calculating the distance of the raw data with the moving average (MA ?vki(sj)), and categorical variables in different attribute groups were processed using Euclidean distance (ED ∥?vk(sj)∥). Regression and classification analyses were performed on the raw data, MA ?vki(sj), and ED ∥?vk(sj)∥. Different machine-learning algorithms were chosen for the STATISTICA and WEKA software.
Results:?
The random forest (RF) algorithm was the best for predicting continuous outputs using the raw data. The correlation coefficients of the RF algorithm were 0.978 and 0.595 for the training and validation sets, respectively, and the mean absolute errors were 0.135 and 0.362 for the training and validation sets, respectively. The proportion of ideal predictions of the RF algorithm was 59.0%. General discriminant analysis (GDA) was the best algorithm for predicting the categorical outputs using the MA ?vki(sj) data. The GDA algorithm’s total true positive rate (TPR) was 95.4% and 95.6% for the training and validation sets, respectively, with MA ?vki(sj) data.
Conclusions:?
An information fusion perturbation theory and machine learning model for predicting warfarin blood levels was established. A model based on the RF algorithm could be used to predict the target international normalized ratio (INR), and a model based on the GDA algorithm could be used to predict the probability of being within the target INR range under different clinical scenarios.
Tags: #MachineLearning, #PersonalizedMedicine, #Surgery, #Warfarin, #Prospective studies.
Acknowledgements: Mila Esker, Xie Xie, Thank you to all authors, affiliated/host institutions, and funding agencies!!!!
Affiliations: West China Hospital, Sichuan University, Soochow University (CN), Lovely Professional University, ZTF-FCT :: UPV/EHU, Universidad del País Vasco/Euskal Herriko Unibertsitatea, 48940, Leioa, Spain. Fundación Biofísica Bizkaia / Biofisika Bizkaia Fundazioa, 48940, Leioa, Spain. Ikerbasque, Basque Foundation for Science, 48011, Bilbao, Spain.
Sponsors: European Commission hashtag#NextGenerationEU funds, IKERDATA S.L. - Lanbide, hashtag#Investigo program, Basque Government / Eusko Jaurlaritza - Gobierno Vasco (IT1558-22), ELKARTEK SPRI Group AIMOFGIFT (KK-2022/00032) grant. Ministerio de Ciencia, Innovación y Universidades (PID2022-137365NB-I00). National Science Foundation of China (grant number 81803628, 8237052); the Jiangsu Provincial Science and Technology Plan Special Fund (BM2023003); the Jiangsu Provincial Medical Key Discipline (grant number ZDXK202247); the Key R&D Program of Jiangsu Province (grant number BE2021644); the Suzhou Health Leading Talent (grant number GSWS2019001); the Talent Project established by the Chinese Pharmaceutical Association Hospital Pharmacy Department (grant number CPA-Z05-ZC-2023-003); the Priority Academic Program Development of the Jiangsu Higher Education Institutes (grant number PAPD), the hashtag#Suzhou Science and Technology Project under Grant (SKY2023163).
Paper 3. Prediction LDL Receptor Variants
Wiley Journal Advanced Science Published our paper: OptiMo-LDLr: An Integrated In Silico Model with Enhanced Predictive Power for LDL Receptor Variants, Unraveling Hot Spot Pathogenic Residues. Asier Larrea Sebal, I?aki Sasiain Casado, Shifa Jebari-Benslaiman, Unai Galicia García, Kepa B. Uribe, Asier Benito, Irene Gracia Rubio, Harbil Bediaga Ba?eres, Sonia Arrasate Gil, Ana Cenarro,?Fernando Civeira, Humbert G. Díaz, Prof.,?Cesar Martín Plagaro. Advanced Science (2024) 23o5177, doi: 10.1002/advs.202305177.
Affiliations: Universidad del País Vasco/Euskal Herriko Unibertsitatea, Ikerbasque, Fundación Biofísica Bizkaia / Biofisika Bizkaia Fundazioa, Hospital Universitario Miguel Servet.
Sponsors: Eusko Jaurlaritza - Gobierno Vasco, Ministry of Science and Innovation of Spain, Thank you to all co-authors, host, and funding institutions!!!
Paper 4. Antileshmanial compounds
Elsevier (Open Access) Glad For Publishing this Interesting Paper: Palladium-mediated synthesis and biological evaluation of C-10b substituted Dihydropyrrolo[1,2-b]isoquinolines as antileishmanial agents. Iratxe Barbolla, Hernández-Suárez L, Viviana Quevedo-Tumailli, Deyani Nocedo Mena, Sonia Arrasate Gil, María Auxiliadora Dea-Ayuela, González-Díaz H, Sotomayor N, Esther Lete, Eur J Med Chem. 2021 Aug 5;220:113458. doi: 10.1016/j.ejmech.2021.113458.
Abstract: The development of new molecules for the treatment of leishmaniasis is, a neglected parasitic disease, is urgent as current anti-leishmanial therapeutics are hampered by drug toxicity and resistance. The pyrrolo[1,2-b]isoquinoline core was selected as starting point, and palladium-catalyzed Heck-initiated cascade reactions were developed for the synthesis of a series of C-10 substituted derivatives. Their in?vitro leishmanicidal activity against visceral (L.?donovani) and cutaneous (L.?amazonensis) leishmaniasis was evaluated. The best activity was found, in general, for the 10-arylmethyl substituted pyrroloisoquinolines. In particular, 2ad (IC50?=?3.30?μM, SI?>?77.01) and 2bb (IC50?=?3.93?μM, SI?>?58.77) were approximately 10-fold more potent and selective than the drug of reference (miltefosine), against L.?amazonensis on in?vitro promastigote assays, while 2ae was the more active compound in the in?vitro amastigote assays (IC50?=?33.59?μM, SI?>?8.93). Notably, almost all compounds showed low cytotoxicity, CC50?>?100?μg/mL in J774?cells, highest tested dose. In addition, we have developed the first Perturbation Theory Machine Learning (PTML) algorithm able to predict simultaneously multiple biological activity parameters (IC50, Ki, etc.) vs. any Leishmania species and target protein, with high values of specificity (>98%) and sensitivity (>90%) in both training and validation series. Therefore, this model may be useful to reduce time and assay costs (material and human resources) in the drug discovery process.
Free Download: https://lnkd.in/eY-2GMj9Data
Sources: European Bioinformatics Institute | EMBL-EBI hashtag#ChEMBL database.
Paper 4. Antibacterials vs. Metabolic Networks
American Chemical Society Journal Published our Work: MachineLearning Study of MetabolicNetworks vs ChEMBL Data of Antibacterial Compounds. Karel Dieguez Santana, Gerardo M. Casanola-Martin, Roldán Torres Gutiérrez, Bakhtiyor Rasulev, James Green,?and Humbert G. Díaz, Prof. Mol. Pharmaceutics?(2022) 19, 7, 2151–2163.
Abstract: Antibacterial drugs (AD) change the metabolic status of bacteria, contributing to bacterial death. However, antibiotic resistance and the emergence of multidrug-resistant bacteria increase interest in understanding metabolic network (MN) mutations and the interaction of AD vs MN. In this study, we employed the IFPTML = Information Fusion (IF) + Perturbation Theory (PT) + Machine Learning (ML) algorithm on a huge dataset from the ChEMBL database, which contains >155,000 AD assays vs >40 MNs of multiple bacteria species. We built a linear discriminant analysis (LDA) and 17 ML models centered on the linear index and based on atoms to predict antibacterial compounds. The IFPTML-LDA model presented the following results for the training subset: specificity (Sp) = 76% out of 70,000 cases, sensitivity (Sn) = 70%, and Accuracy (Acc) = 73%. The same model also presented the following results for the validation subsets: Sp = 76%, Sn = 70%, and Acc = 73.1%. Among the IFPTML nonlinear models, the k nearest neighbors (KNN) showed the best results with Sn = 99.2%, Sp = 95.5%, Acc = 97.4%, and Area Under Receiver Operating Characteristic (AUROC) = 0.998 in training sets. In the validation series, the Random Forest had the best results: Sn = 93.96% and Sp = 87.02% (AUROC = 0.945). The IFPTML linear and nonlinear models regarding the ADs vs MNs have good statistical parameters, and they could contribute toward finding new metabolic mutations in antibiotic resistance and reducing time/costs in antibacterial drug research.
Affiliations: (1) Dept. hashtag#Organic & hashtag#Inorganic hashtag#Chemistry, UPV/EHU :: FCT-ZTF, Universidad del País Vasco/Euskal Herriko Unibertsitatea, hashtag#Basquecountry, (2) Universidad Regional Amazónica Ikiam, hashtag#Ecuador, (3) North Dakota State University, hashtag#USA, (4) Dept. Carleton University Systems and Computer Engineering, Carleton University, hashtag#Canada, (5) Fundación Biofísica Bizkaia / Biofisika Bizkaia Fundazioa, (6) Ikerbasque, hashtag#BasqueCountry.Data
Sources: European Bioinformatics Institute | EMBL-EBI hashtag#ChEMBL database.
Paper 5. Antiviral Compounds
American Chemical Society hashtag#JCIM Accepted (just): Implementation of IFPTML computational models in Drugdiscovery against Flaviviridae family. Yendrek Andres Velasquez Lopez; Andrea Ruiz Escudero; Sonia Arrasate Gil; Humbert G. Díaz, Prof. J Chem. Info. Model. (2024) doi: 10.1021/acs.jcim.3c01796
Affiliations: Universidad del País Vasco/Euskal Herriko Unibertsitatea, Ikerbasque, Universidad de Las Américas (EC), IKERDATA S.L., Fundación Biofísica Bizkaia / Biofisika Bizkaia Fundazioa.
Sponsors: European Commission hashtag#NextgenerationEU, Eusko Jaurlaritza - Gobierno Vasco, Lanbide hashtag#Investigo Program, Ministry of Science and Innovation of Spain, Thank you to all co-authors, hosts, and funding institutions!!!
Data Sources: European Bioinformatics Institute | EMBL-EBI hashtag#ChEMBL database.