2020/03/26 by Ezequiel Álvarez, Alvarez, Ezequiel, Federico Lamagna +3
Biochemistry, Genetics and Molecular Biology · Computer Science · Psychology · #Bioinformatics and Genomic Networks #Cell Image Analysis Techniques #Computational Drug Discovery Methods #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Healthcare #Mental Health Research Topics #Populations and Evolution (q-bio.PE) #Quantitative Methods (q-bio.QM)
paper · pdf · doi:10.48550/arxiv.2003.12454
openalex publication_date 2020/03/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The appearance of a new dangerous and contagious disease requires the\ndevelopment of a drug therapy faster than what is foreseen by usual mechanisms.\nMany drug therapy developments consist in investigating through different\nclinical trials the effects of different specific drug combinations by\ndelivering it into a test group of ill patients, meanwhile a placebo treatment\nis delivered to the remaining ill patients, known as the control group. We\ncompare the above technique to a new technique in which all patients receive a\ndifferent and reasonable combination of drugs and use this outcome to feed a\nNeural Network. By averaging out fluctuations and recognizing different patient\nfeatures, the Neural Network learns the pattern that connects the patients\ninitial state to the outcome of the treatments and therefore can predict the\nbest drug therapy better than the above method. In contrast to many available\nworks, we do not study any detail of drugs composition nor interaction, but\ninstead pose and solve the problem from a phenomenological point of view, which\nallows us to compare both methods. Although the conclusion is reached through\nmathematical modeling and is stable upon any reasonable model, this is a\nproof-of-concept that should be studied within other expertises before\nconfronting a real scenario. All calculations, tools and scripts have been made\nopen source for the community to test, modify or expand it. Finally it should\nbe mentioned that, although the results presented here are in the context of a\nnew disease in medical sciences, these are useful for any field that requires a\nexperimental technique with a control group.\n