Search

Motivation: Post-translational modifications (PTMs) increase the diversity of the proteome and are vital to organismal life and therapeutic strategies. Deep learning has been used to predict PTM locations. Still, limitations in datasets and their analyses compromise success., Results: We evaluated the use of known PTM sites in prediction via sequence-based deep learning algorithms. For each PTM, known locations of that PTM were encoded as a separate amino acid before sequences were encoded via word embedding and passed into a convolutional neural network that predicts the probability of that PTM at a given site. Without labeling known PTMs, our models are on par with others. With labeling, however, we improved significantly upon extant models. Moreover, knowing PTM locations can increase the predictability of a different PTM. Our findings highlight the importance of PTMs for the installation of additional PTMs. We anticipate that including known PTM locations will enhance the performance of other proteomic machine learning algorithms., Availability and Implementation: Sitetack is available as a web tool at https://sitetack.net; the source code, representative datasets, instructions for local use, and select models are available at https://github.com/clair-gutierrez/sitetack., (© The Author(s) 2024. Published by Oxford University Press.)

Post-translational modifications (PTMs) increase the diversity of the proteome and are vital to organismal life and therapeutic strategies. Deep learning has been used to predict PTM locations. Still, limitations in datasets and their analyses compromise success. Here we evaluate the use of known PTM sites in prediction via sequence-based deep learning algorithms. Specifically, PTM locations were encoded as a separate amino acid before sequences were encoded via word embedding and passed into a convolutional neural network that predicts the probability of a modification at a given site. Without labeling known PTMs, our model is on par with others. With labeling, however, we improved significantly upon extant models. Moreover, knowing PTM locations can increase the predictability of a different PTM. Our findings highlight the importance of PTMs for the installation of additional PTMs. We anticipate that including known PTM locations will enhance the performance of other proteomic machine learning algorithms.

Background: The prescription stimulants methylphenidate, amphetamine, and lisdexamfetamine are sympathomimetic drugs with therapeutic use. They are designated in the United States as Schedule II substances, defined by the 1970 Controlled Substances Act as having a "high potential for abuse". Changing criteria for the diagnosis of Attention Deficit Hyperactivity Disorder in 2013 and the approval of lisdexamfetamine for binge eating disorder in 2015 may have impacted usage patterns. This report compared the pharmacoepidemiology of these stimulants in the United States from 2010-2017., Methods: Distribution of amphetamine, methylphenidate, lisdexamfetamine were examined via weights extracted from the Drug Enforcement Administration's (DEA) Automated Reports and Consolidated Ordering System (ARCOS). Median stimulant Daily Dosage per patient was determined for a regional analysis. The percent of cost and prescriptions attributable to each stimulant and atomoxetine in Medicaid from the "Drug Utilization 2018 - National Total" from the Centers for Medicare and Medicaid was determined., Results: There was a rise in amphetamine (+67.5%) and lisdexamfetamine (+76.7%) from 2010-2017. The change in methylphenidate (-3.0%) was modest. Persons/day stimulant usage was lower in the West than in other US regions from 2014-2017. There was a negative correlation ( r (48) = -0.43 to -0.65, p < .05) between the percent Hispanic population per state and the Daily Dosage/population per stimulant. Methylphenidate formulations accounted for over half (51.7%) of the $3.8 billion reimbursed by Medicaid and the plurality (45.4%) of the 22.0 million prescriptions. Amphetamine was responsible for less than one-fifth (18.4%) of cost but one-third of prescriptions (33.6%). Lisdexamfetamine's cost (26.0%) exceeded prescriptions (16.3%)., Conclusion: The rising amphetamine and lisdexamfetamine distribution may correspond with a rise in adult ADHD diagnoses. Regional analysis indicates that stimulant distribution in the West may be distinct from that in other regions. The lower stimulant distribution in areas with greater Hispanic populations may warrant further study., Competing Interests: Brian J Piper is part of an osteoarthritis research team supported by Pfizer. The other authors declare that they have no competing interests., (©2021 Vaddadi et al.)