Machine learning identifies the independent role of dysplasia in the prediction of response to chemotherapy in AML

Heisenberg exchange spin coupling between metal centers is essential for describing and understanding the electronic structure of many molecular catalysts, metalloenzymes, and molecular magnets for potential application in information technology. We explore the machine-learnability of exchange spin coupling, which has not been studied yet. We employ Gaussian process regression since it can potentially deal with small training sets (as likely associated with the rather complex molecular structures required for exploring spin coupling) and since it provides uncertainty estimates (“error bars”) along with predicted values. We compare a range of descriptors and kernels for 257 small dicopper complexes and find that a simple descriptor based on chemical intuition, consisting only of copper-bridge angles and copper-copper distances, clearly outperforms several more sophisticated descriptors when it comes to extrapolating towards larger experimentally relevant complexes. Exchange spin coupling is similarly easy to learn as the polarizability, while learning dipole moments is much harder. The strength of the sophisticated descriptors lies in their ability to linearize structure-property relationships, to the point that a simple linear ridge regression performs just as well as the kernel-based machine-learning model for our small dicopper data set. The superior extrapolation performance of the simple descriptor is unique to exchange spin coupling, reinforcing the crucial role of choosing a suitable descriptor, and highlighting the interesting question of the role of chemical intuition vs. systematic or automated selection of features for machine learning in chemistry and material science.

Download Full-text

Leveraging Machine Learning to Characterize the Role of Socio-Economic Determinants on Physical Health and Well-Being Among Veterans

SSRN Electronic Journal ◽

10.2139/ssrn.3686845 ◽

2020 ◽

Author(s):

Christos Makridis ◽

David Zhao ◽

Cosmin (Adi) Bejan ◽

Gil Alterovitz

Keyword(s):

Machine Learning ◽

Physical Health ◽

Well Being ◽

Economic Determinants ◽

Health And Well Being

Download Full-text

Ex vivo programmed cell death and the prediction of response to chemotherapy

Current Treatment Options in Oncology ◽

10.1007/s11864-006-0045-2 ◽

2006 ◽

Vol 7 (2) ◽

pp. 103-110 ◽

Cited By ~ 22

Author(s):

Robert A. Nagourney

Keyword(s):

Cell Death ◽

Programmed Cell Death ◽

Ex Vivo ◽

Prediction Of Response ◽

Response To Chemotherapy

Download Full-text

Role of machine learning algorithms over heart diseases prediction

10.1063/5.0030743 ◽

2020 ◽

Author(s):

Siva Kumar Jonnavithula ◽

Abhilash Kumar Jha ◽

Modepalli Kavitha ◽

Singaraju Srinivasulu

Keyword(s):

Machine Learning ◽

Heart Diseases ◽

Learning Algorithms ◽

Machine Learning Algorithms

Download Full-text

Role of Long Non-Coding RNA Polymorphisms in Cancer Chemotherapeutic Response

Journal of Personalized Medicine ◽

10.3390/jpm11060513 ◽

2021 ◽

Vol 11 (6) ◽

pp. 513

Author(s):

Zheng Zhang ◽

Meng Gu ◽

Zhongze Gu ◽

Yan-Ru Lou

Keyword(s):

Molecular Mechanisms ◽

Neurological Diseases ◽

Cellular Processes ◽

Dna And Rna ◽

Chemotherapeutic Response ◽

Non Coding Rna ◽

Response To Chemotherapy ◽

Personalized Oncology ◽

Long Non Coding Rna

Genetic polymorphisms are defined as the presence of two or more different alleles in the same locus, with a frequency higher than 1% in the population. Since the discovery of long non-coding RNAs (lncRNAs), which refer to a non-coding RNA with a length of more than 200 nucleotides, their biological roles have been increasingly revealed in recent years. They regulate many cellular processes, from pluripotency to cancer. Interestingly, abnormal expression or dysfunction of lncRNAs is closely related to the occurrence of human diseases, including cancer and degenerative neurological diseases. Particularly, their polymorphisms have been found to be associated with altered drug response and/or drug toxicity in cancer treatment. However, molecular mechanisms are not yet fully elucidated, which are expected to be discovered by detailed studies of RNA–protein, RNA–DNA, and RNA–lipid interactions. In conclusion, lncRNAs polymorphisms may become biomarkers for predicting the response to chemotherapy in cancer patients. Here we review and discuss how gene polymorphisms of lncRNAs affect cancer chemotherapeutic response. This knowledge may pave the way to personalized oncology treatments.

Download Full-text