Quinn Dickinson

Quinn Dickinson

Auto-generated profile, based on publicly available information

Quinn Dickinson

Department of Biochemistry, Molecular Biology and Biophysics, University of Minnesota Medical School, Minneapolis, Minnesota

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 January 2022 in PLOS Computational Biology
Verified
Journal Article
Open access
PDF file
QDQuinn Dickinson
Quinn Dickinson
JMJesse Meyer
Jesse Meyer
Machine learning with multi-layered artificial neural networks, also known as “deep learning,” is effective for making biological predictions. However, model interpretation is challenging, especially for sequential input data used with recurrent neural network architectures. Here, we introduce a framework called “Positional SHAP” (PoSHAP) to interpret models trained from biological sequences by utilizing SHapely Additive exPlanations (SHAP) to generate positional model interpretations. We demonstrate this using three long short-term memory (LSTM) regression models that predict peptide properties, including binding affinity to major histocompatibility complexes (MHC), and collisional cross section (CCS) measured by ion mobility spectrometry. Interpretation of these models with PoSHAP reproduced MHC class I (rhesus macaque Mamu-A1*001 and human A*11:01) peptide binding motifs, reflected known properties of peptide CCS, and provided new insights into interpositional dependencies of amino acid interactions. PoSHAP should have widespread utility for interpreting a variety of models trained from biological sequences.

15 September 2022 in Bioinformatics
Verified
Journal Article
Open access
PDF file
QDQuinn Dickinson
Quinn Dickinson
AKAndreas Kohler
Andreas Kohler
MOMartin Ott
Martin Ott
JMJesse Meyer
Jesse Meyer
AAAndreas Kohler (né Aufschnaiter)
Andreas Kohler (né Aufschnaiter)
Cells respond to environments by regulating gene expression to exploit resources optimally. Recent advances in technologies allow for measuring the abundances of RNA, proteins, lipids and metabolites. These highly complex datasets reflect the states of the different layers in a biological system. Multi-omics is the integration of these disparate methods and data to gain a clearer picture of the biological state. Multi-omic studies of the proteome and metabolome are becoming more common as mass spectrometry technology continues to be democratized. However, knowledge extraction through the integration of these data remains challenging. Connections between molecules in different omic layers were discovered through a combination of machine learning and model interpretation. Discovered connections reflected protein control (ProC) over metabolites. Proteins discovered to control citrate were mapped onto known genetic and metabolic networks, revealing that these protein regulators are novel. Further, clustering the magnitudes of ProC over all metabolites enabled the prediction of five gene functions, each of which was validated experimentally. Two uncharacterized genes, YJR120W and YDL157C, were accurately predicted to modulate mitochondrial translation. Functions for three incompletely characterized genes were also predicted and validated, including SDH9, ISC1 and FMP52. A website enables results exploration and also MIMaL analysis of user-supplied multi-omic data. The website for MIMaL is at https://mimal.app. Code for the website is at https://github.com/qdickinson/mimal-website. Code to implement MIMaL is at https://github.com/jessegmeyerlab/MIMaL. Supplementary data are available at Bioinformatics online.

5 March 2021 in bioRxiv
Verified
Preprint
Open access
PDF file
QDQuinn Dickinson
Quinn Dickinson
JMJesse Meyer
Jesse Meyer
Machine learning with multi-layered artificial neural networks, also known as “deep learning,” is effective for making biological predictions. However, model interpretation is challenging, especially for sequential input data used with recurrent neural network architectures. Here, we introduce a framework called “Positional SHAP” (PoSHAP) to interpret models trained from biological sequences by utilizing SHapely Additive exPlanations (SHAP) to generate positional model interpretations. We demonstrate this using three long short-term memory (LSTM) regression models that predict peptide properties, including binding affinity to major histocompatibility complexes (MHC), and collisional cross section (CCS) measured by ion mobility spectrometry. Interpretation of these models with PoSHAP reproduced MHC class I (rhesus macaque Mamu-A1*001 and human A*11:01) peptide binding motifs, reflected known properties of peptide CCS, and provided new insights into interpositional dependencies of amino acid interactions. PoSHAP should have widespread utility for interpreting a variety of models trained from biological sequences.

19 May 2026 in Nature Communications
Verified
Journal Article
Open access
DJDeepika Jayaprakash
Deepika Jayaprakash
JPJosie Gannon Patterson
Josie Gannon Patterson
RMRuthie Mulvaney
Ruthie Mulvaney
QDQuinn Dickinson
Quinn Dickinson
CLCourtney Lovejoy
Courtney Lovejoy
RBRahul Bhowmick
Rahul Bhowmick
Accurate genome duplication requires tight-regulation of replication fork progression, and disruptions to this process are a major source of genomic instability, yet how fork dynamics are controlled during unperturbed S-phase remains unclear. We found replication forks elongate slowly in early S (ES) and faster in late S, independent of transcription or nucleotide availability. Elevated origin firing coupled with low TOP2A in ES generates torsional stress, causing replisome uncoupling, reduced fork speed, and basal ATR-CHK1 activation. Overexpression of TOP2A enhances fork speed and reduces replication stress in ES. Thus, TOP2A is a limiting replication factor during unperturbed ES, and basal ATR-CHK1 signaling is driven by transient replisome uncoupling. Also, TOP2A overexpression suppresses oncogene-driven replication stress. Given that TOP2A is frequently upregulated in cancers, it may function as a compensatory response to oncogene-induced replication stress. Together, these findings establish TOP2A as a central regulator of replication fork dynamics.

19 March 2026 in Genome Research
Verified
Journal Article
Open access
PDF file
LMLakshana Sruthi Sadu Murari
Lakshana Sruthi Sadu Murari
QDQuinn Dickinson
Quinn Dickinson
SMSilvia Meyer
Silvia Meyer
JRJuan Carlos Rivera-Mulia
Juan Carlos Rivera-Mulia
The human genome is partitioned into functional compartments that replicate at specific times during S-phase. This temporal program, referred to as replication timing (RT), is coregulated with the 3D genome organization, is cell type–specific, and changes during development in coordination with gene expression. Moreover, RT alterations are linked to abnormal gene expression, genome instability, and structural variation in multiple diseases, including cancer. However, mechanistic links between RT, large-scale 3D genome architecture, and transcriptional regulation remain poorly understood. A major limitation is that current approaches require the separate profiling of RT and transcriptomes from independent batches of samples, which obscures the complex coregulation between the epigenome and transcriptome. Here, we present PARTAGE , a multiomics approach that enables joint profiling of copy number variation (CNV), RT, and gene expression from the same sample, providing a more accurate integrated view of the complex relationships between RT and gene regulation.

11 May 2022 in bioRxiv
Verified
Preprint
Open access
PDF file
QDQuinn Dickinson
Quinn Dickinson
AAAndreas Kohler (né Aufschnaiter)
Andreas Kohler (né Aufschnaiter)
MOMartin Ott
Martin Ott
JMJesse Meyer
Jesse Meyer
Cells respond to environments by regulating gene expression to exploit resources optimally. Recent advances in technologies allow the ability to gather information of cellular states of its components, measuring abundances of transcripts, their translation, the accumulation of proteins, lipids and metabolites. These highly complex datasets reflect the state of the different layers in a biological system. Multi-omics is the integration of these disparate methods and data to gain a clearer picture of the biological state. Multi-omic studies of the proteome and metabolome are becoming more common as mass spectrometry technology continues to be democratized. However, knowledge extraction through integration of these data remains challenging. Here we show that connections between omic layers can be discovered through a combination of machine learning and model interpretation. We find that model interpretation values connecting proteins to metabolites are valid experimentally and reveal also largely new connections. Further, clustering the magnitudes of protein control over all metabolites enabled prediction of gene five gene functions, each of which was validated experimentally. We accurately predicted that two uncharacterized genes in yeast modulate mitochondrial translation, YJR120W and YLD157C .We also predict and validate functions for several incompletely characterized genes, including SDH9, ISC1 , and FMP52 . Our work demonstrates that multi-omic analysis with machine learning (MIMaL) views multi-omic data through a new lens to reveal new insight that was not possible using existing methods.