update

_config.yml

@@ -82,9 +82,9 @@ analytics:
 author:
   name             : "James Wellnitz"
   avatar           : "jwellni.jpg"
-  bio              : "PhD student in Pharmaceutical Science @ UNC"
+  bio              : "PhD student in Pharmaceutical Science"
   location         : "Chapel Hill"
-  employer         :
+  employer         : "University of North Carolina Chapel Hill"
   pubmed           : 
   googlescholar    : "https://scholar.google.com/citations?user=ZhselLIAAAAJ&hl=en&authuser=1"
   email            : "jwellnitz@unc.edu"
@@ -103,7 +103,7 @@ author:
   impactstory      : #"https://profiles.impactstory.org/u/xxxx-xxxx-xxxx-xxxx"
   lastfm           :
   linkedin         : "james-wellnitz-3168b0150/"
-  orcid            : 
+  orcid            : "0000-0002-9181-3431"
   pinterest        :
   soundcloud       :
   stackoverflow    : # http://stackoverflow.com/users/123456/username

_pages/about.md

@@ -8,8 +8,17 @@ redirect_from:
   - /about.html
 ---
 
-I am a 2nd year PhD student in the pharmaceutical science program at [UNC Chapel Hill](https://pharmacy.unc.edu/education/phd/) advised by [Prof Alexander Tropsha](https://pharmacy.unc.edu/directory/tropsha/)
+I am a 3rd year PhD student in the pharmaceutical science program at [UNC Chapel Hill](https://pharmacy.unc.edu/education/phd/) co-advised by 
+[Prof Alexander Tropsha](https://pharmacy.unc.edu/directory/tropsha/) and [Prof Konstantin Popov](https://pharmacy.unc.edu/directory/kpopov/)
 
-My research broadly focus on devolping and applying machiene learning and artificial intelligence methodologies for early stage structual based drug design. More specificially, I am intrested in understanding weak points and limitations in both the use of these computational methods and the data used to construct them in order to make these methods more robust and useful to non-computational researchers.
+My research broadly focuses on developing and applying machine learning (ML) and artificial intelligence (AI) methodologies for 
+early-stage structural based drug discovery, specifically in regard to high-throughput virtual screening.
+More recently,
+I have been focusing on methods
+for leveraging ML alongside DNA Encoded Libraries to assist with rapid early stage discovery.
+My focus is split into three areas, development of novel methodologies, applying said methods in tangible discovery 
+campaigns alongside wet lab collaborators,
+and devolping more rigorous in-silico validation methods
+to better assess the quality and risk of utilizing a given ML model.
 
-Outside of work I am avid sewer of costumes for my goose, Goose Springsteen
+Outside of work, I am an avid sewer of costumes for my goose, Goose Springsteen, and like to read about herpetology (frogs).

_pages/cv.md

@@ -11,30 +11,39 @@ redirect_from:
 
 Education
 ======
-* B.S. in GitHub, GitHub University, 2012
-* M.S. in Jekyll, GitHub University, 2014
-* Ph.D in Version Control Theory, GitHub University, 2018 (expected)
+* B.S. in Biology & Data Science, Purdue University, 2021
+* Ph.D in Pharmaceutical Sciences, University of North Carolina Chapel Hill, 2026 (expected)
 
-Work experience
+Experience
 ======
-* Summer 2015: Research Assistant
-  * Github University
-  * Duties included: Tagging issues
-  * Supervisor: Professor Git
+* June 2023 — Current: Intern in Computational Drug Discovery
+  * Orogen Therapeutics
+  * Full-Time (Summer only), Part-Time
+  * Worked on various computational and machine learning project to accelerate early stage discovery
+
+* January 2023 — June 2023: Consultant in Computational Drug Discovery
+  * Animol Discovery
+  * Part-Time
+  * Worked on various computational and machine learning project to accelerate early stage discovery
+
+* Fall 2021 — Current: Graduate Research Assistant
+  * University of North Carolina Chapel Hill
+  * Co-Advisors: Alexander Tropsha & Konstantin Popov
+  * Work on research projects in the area of DNA encoded library machine learning and computational early stage drug discovery screening
 
-* Fall 2015: Research Assistant
-  * Github University
-  * Duties included: Merging pull requests
-  * Supervisor: Professor Hub
 
 Skills
 ======
-* Skill 1
-* Skill 2
-  * Sub-skill 2.1
-  * Sub-skill 2.2
-  * Sub-skill 2.3
-* Skill 3
+* Python
+  * Numpy
+  * Scikit-Learn
+  * PyTorch
+  * RDKit
+* Large scale virtual screening
+* Schrodinger Suite
+* Molecular Docking
+* Molecular Dynamics
+* Quantitative Structure Activity Relationship (QSAR) Modeling
 
 Publications
 ======
@@ -44,16 +53,10 @@ Publications
 
 Talks
 ======
-  <ul>{% for post in site.talks %}
-    {% include archive-single-talk-cv.html %}
-  {% endfor %}</ul>
+  2023 — Oral presentation, Southeastern Regional Meeting of American Chemical Society (SERMACS), Medical Chemistry division (MEDI)
 
 Teaching
 ======
   <ul>{% for post in site.teaching %}
     {% include archive-single-cv.html %}
   {% endfor %}</ul>
-
-Service and leadership
-======
-* Currently signed in to 43 different slack teams

_publications/b-barrel-reveiw.md

@@ -0,0 +1,16 @@
+---
+title: "The assembly of β-barrel membrane proteins by BAM and SAM"
+collection: publications
+permalink: /publication/beta-barrel-review
+excerpt: 'Gram-negative bacteria, mitochondria, and chloroplasts all possess an outer membrane populated with a host of β-barrel outer-membrane proteins (βOMPs)... Here, we will review these recent studies and highlight their contributions toward understanding βOMP biogenesis in Gram-negative bacteria and in mitochondria.'
+date: 2020-12-03
+venue: 'Molecular Microbiology'
+paperurl: 'https://onlinelibrary.wiley.com/doi/full/10.1111/mmi.14666'
+citation: 'Recommended citation: Y Lundquist, K, Billings, E, Bi, M, Wellnitz, J, Noinaj, N. The assembly of β-barrel membrane proteins by BAM and SAM. <i>Mol Microbiol.</i> 2021; 115: 425–435.'
+---
+Gram-negative bacteria, mitochondria, and chloroplasts all possess an outer membrane populated with a host of β-barrel outer-membrane proteins (βOMPs). These βOMPs play crucial roles in maintaining viability of their hosts, and therefore, it is essential to understand the biogenesis of this class of membrane proteins. In recent years, significant structural and functional advancements have been made toward elucidating this process, which is mediated by the β-barrel assembly machinery (BAM) in Gram-negative bacteria, and by the sorting and assembly machinery (SAM) in mitochondria. Structures of both BAM and SAM have now been reported, allowing a comparison and dissection of the two machineries, with other studies reporting on functional aspects of each. Together, these new insights provide compelling support for the proposed budding mechanism, where each nascent βOMP forms a hybrid-barrel intermediate with BAM/SAM in route to its biogenesis into the membrane. Here, we will review these recent studies and highlight their contributions toward understanding βOMP biogenesis in Gram-negative bacteria and in mitochondria. We will also weigh the evidence supporting each of the two leading mechanistic models for how BAM/SAM function, and offer an outlook on future studies within the field.
+
+Recommended citation: Y Lundquist, K, Billings, E, Bi, M, Wellnitz, J,
+Noinaj, N. The assembly of β-barrel membrane proteins by BAM and SAM.
+<i>Mol Microbiol.</i> 2021; 115: 425–435.
+https://doi.org/10.1111/mmi.14666 

_publications/hidden-gem.md

@@ -0,0 +1,14 @@
+---
+title: "Hit Discovery using Docking ENriched by GEnerative Modeling (HIDDEN GEM): A Novel Computational Workflow for Accelerated Virtual Screening of Ultra-large Chemical Libraries"
+collection: publications
+permalink: /publication/hidden-gem
+excerpt: 'We present a novel computational methodology termed HIDDEN GEM (<b>HI</b>t Discovery using <b>D</b>ocking <b>EN</b>riched by <b>GE</b>nerative <b>M</b>odeling) that greatly accelerates virtual screening. This workflow uniquely integrates machine learning, generative chemistry, massive chemical similarity searching and molecular docking of small, selected libraries in the beginning and the end of the workflow.'
+date: 2023-10-06
+venue: 'Molecular Informatics'
+paperurl: 'https://onlinelibrary.wiley.com/doi/abs/10.1002/minf.202300207'
+citation: 'Wellnitz, J., Popov, K.I., Maxfield, T, and Tropsha, A. (2023), Hit Discovery using Docking ENriched by GEnerative Modeling (HIDDEN GEM): A Novel Computational Workflow for Accelerated Virtual Screening of Ultra-large Chemical Libraries.. <i>Mol. Inf.<\i>. Accepted Author Manuscript.'
+---
+
+Recent rapid expansion of make-on-demand, purchasable, chemical libraries comprising dozens of billions or even trillions of molecules has challenged the efficient application of traditional structure-based virtual screening methods that rely on molecular docking. We present a novel computational methodology termed HIDDEN GEM ( <b>HI</b>t Discovery using <b>D</b>ocking <b>EN</b>riched by <b>GE</b>nerative <b>M</b>odeling) that greatly accelerates virtual screening. This workflow uniquely integrates machine learning, generative chemistry, massive chemical similarity searching and molecular docking of small, selected libraries in the beginning and the end of the workflow. For each target, HIDDEN GEM nominates a small number of top-scoring virtual hits prioritized from ultra-large chemical libraries. We have benchmarked HIDDEN GEM by conducting virtual screening campaigns for 16 diverse protein targets using Enamine REAL Space library comprising 37 billion molecules. We show that HIDDEN GEM yields the highest enrichment factors as compared to state of the art accelerated virtual screening methods, while requiring the least computational resources. HIDDEN GEM can be executed with any docking software and employed by users with limited computational resources.
+
+Wellnitz, J., Popov, K.I., Maxfield, T, and Tropsha, A. (2023), Hit Discovery using Docking ENriched by GEnerative Modeling (HIDDEN GEM): A Novel Computational Workflow for Accelerated Virtual Screening of Ultra-large Chemical Libraries.. <i>Mol. Inf.<\i>. Accepted Author Manuscript. https://doi.org/10.1002/minf.202300207

_publications/lies-and-liabilities.md

@@ -0,0 +1,16 @@
+---
+title: "Lies and Liabilities: Computational Assessment of High-Throughput Screening Hits to Identify Artifact Compounds"
+collection: publications
+permalink: /publication/lies-and-liabilities
+excerpt: 'Hits from high-throughput screening (HTS) of chemical libraries are often false positives due to their interference with assay detection technology. In response, we generated the largest publicly available library of chemical liabilities and developed “Liability Predictor,” a free web tool to predict HTS artifacts.'
+date: 2023-09-07
+venue: 'Journal of Medicinal Chemistry'
+paperurl: 'https://pubs.acs.org/doi/10.1021/acs.jmedchem.3c00482#'
+citation: 'Alves, V. M., Yasgar, A., Wellnitz, J., Rai, G., Rath, M., Braga, R. C., … Tropsha, A. (2023). Lies and Liabilities: Computational Assessment of High-Throughput Screening Hits to Identify Artifact Compounds. <i>Journal of Medicinal Chemistry</i>, 66(18), 12828–12839.'
+---
+Hits from high-throughput screening (HTS) of chemical libraries are often false positives due to their interference with assay detection technology. In response, we generated the largest publicly available library of chemical liabilities and developed “Liability Predictor,” a free web tool to predict HTS artifacts. More specifically, we generated, curated, and integrated HTS data sets for thiol reactivity, redox activity, and luciferase (firefly and nano) activity and developed and validated quantitative structure–interference relationship (QSIR) models to predict these nuisance behaviors. The resulting models showed 58–78% external balanced accuracy for 256 external compounds per assay. QSIR models developed and validated herein identify nuisance compounds among experimental hits more reliably than do popular PAINS filters. Both the models and the curated data sets were implemented in “Liability Predictor,” publicly available at https://liability.mml.unc.edu/. “Liability Predictor” may be used as part of chemical library design or for triaging HTS hits.
+
+Alves, V. M., Yasgar, A., Wellnitz, J., Rai, G., Rath, M., Braga, R. C., … Tropsha, A. (2023).
+Lies and Liabilities: Computational Assessment of High-Throughput Screening Hits to Identify Artifact Compounds.
+<i>Journal of Medicinal Chemistry</i>, 66(18), 12828–12839.
+doi:10.1021/acs.jmedchem.3c00482

_publications/mixtures.md

@@ -0,0 +1,14 @@
+---
+title: "The N-ary in the Coal Mine: Avoiding Mixture Model Failure with Proper Validation"
+collection: publications
+permalink: /publication/mixtures
+excerpt: 'We extend these previously defined validation strategies for QSAR modeling of binary mixtures to the more complex case of general, N-ary mixtures and argue that these strategies are applicable to many modeling tasks beyond simple chemical mixtures.'
+date: 2023-08-11
+venue: 'Arxiv Preprint'
+paperurl: 'https://arxiv.org/abs/2308.06347'
+citation: 'Travis Maxfield, Joshua Hochuli, James Wellnitz, Cleber Melo-Filho, Konstantin I. Popov, Eugene Muratov, & Alex Tropsha. (2023). The N-ary in the Coal Mine: Avoiding Mixture Model Failure with Proper Validation.'
+---
+Modeling the properties of chemical mixtures is a difficult but important part of any modeling process intended to be applicable to the often messy and impure phenomena of everyday life, including food and environmental safety, healthcare, etc. Part of this difficulty stems from the increased complexity of designing suitable model validation schemes for mixture data, a fact which has been elucidated in previous work only in the case of binary mixture models. We extend these previously defined validation strategies for QSAR modeling of binary mixtures to the more complex case of general, N-ary mixtures and argue that these strategies are applicable to many modeling tasks beyond simple chemical mixtures. Additionally, we propose a method of establishing a baseline model performance for each mixture dataset to be in used in model selection comparisons. This baseline is intended to account for the statistical dependence generically present between the properties of mixtures that share constituents. We contend that without such a baseline, estimates of model performance can be dramatically overestimated, and we demonstrate this with multiple case studies using real and simulated data. 
+
+Travis Maxfield, Joshua Hochuli, James Wellnitz, Cleber Melo-Filho, Konstantin I. Popov, Eugene Muratov, & Alex Tropsha. (2023). The N-ary in the Coal Mine: Avoiding Mixture Model Failure with Proper Validation.
+

_teaching/cbmc-805.md

@@ -0,0 +1,15 @@
+---
+title: "CBMC/BOIC 805 Molecular Modeling"
+collection: teaching
+type: "Graduate course"
+permalink: /teaching/cbmc805
+venue: "UNC Chapel Hill, Eshelman School of Pharmacy "
+location: "Chapel Hill, United States"
+---
+
+Teaching assistant for introduction class on molecular modeling, 2022 and 2023
+
+Overview
+======
+Ran the lab section of the class, developing and revamping the syllabus and content covered in the lab along with creating an application focus final project assignment.
+This required the development of new code and packages for the class, as students are not expected to have nor are taught programing in this course, instead focusing on how appropriately utilize available tools to answer questions computationally.