diff --git a/resume_builder/examples/example_resume.pdf b/resume_builder/examples/example_resume.pdf index 14cab03..4b2ad99 100644 Binary files a/resume_builder/examples/example_resume.pdf and b/resume_builder/examples/example_resume.pdf differ diff --git a/resume_builder/examples/output/e2e_whitfield_proteineng_resume.tex b/resume_builder/examples/output/e2e_whitfield_proteineng_resume.tex index 4486109..874c383 100644 --- a/resume_builder/examples/output/e2e_whitfield_proteineng_resume.tex +++ b/resume_builder/examples/output/e2e_whitfield_proteineng_resume.tex @@ -50,31 +50,31 @@ Computational biologist with 8+ years combining \textbf{protein language models} \begin{rSection}{Technical Skills} \begin{skillgroup}{Molecular Simulation \& Modeling} -\skilldash{\textbf{GROMACS}, OpenMM, AMBER -- metadynamics, replica exchange MD, free energy perturbation} -\skilldash{AlphaFold2, Rosetta, AutoDock Vina -- protein structure prediction and molecular docking} -\skilldash{CHARMM36m, AMBER ff19SB, OPLS-AA/M -- force field benchmarking for disordered proteins} -\skilldash{Collective variable design, enhanced sampling protocol development, convergence analysis} +\skilldash{\textbf{GROMACS}, OpenMM, AMBER -- metadynamics, replica exchange MD, free energy perturbation, umbrella sampling} +\skilldash{AlphaFold2, Rosetta, AutoDock Vina -- protein structure prediction, homology modeling, and molecular docking} +\skilldash{CHARMM36m, AMBER ff19SB, OPLS-AA/M -- force field selection and benchmarking for disordered proteins} +\skilldash{Collective variable design, enhanced sampling protocol development, convergence analysis, MM/PBSA free energy} \end{skillgroup} \begin{skillgroup}{Machine Learning \& Data Science} -\skilldash{\textbf{Protein language models} (ESM-2), graph neural networks, transfer learning, active learning} -\skilldash{\textbf{PyTorch}, scikit-learn, BioPython -- model fine-tuning, feature engineering, sequence analysis} -\skilldash{Regression, cross-validation, Spearman/RMSE benchmarking, dataset curation from public DBs} +\skilldash{\textbf{Protein language models} (ESM-2, 650M params), graph neural networks, transfer learning, active learning loops} +\skilldash{\textbf{PyTorch}, scikit-learn, BioPython -- model fine-tuning, embedding extraction, feature engineering, sequence analysis} +\skilldash{Regression, classification, cross-validation, Spearman/RMSE benchmarking, dataset curation from public databases} \end{skillgroup} \begin{skillgroup}{Programming \& HPC} -\skilldash{\textbf{Python}, Bash, SQL -- scientific computing, analysis pipelines, database management} -\skilldash{\textbf{SLURM}, Snakemake, Git, DVC -- HPC workflow automation and reproducible research} +\skilldash{\textbf{Python}, Bash, SQL -- scientific computing, data pipelines, automated analysis workflows, database management} +\skilldash{\textbf{SLURM}, Snakemake, Git, DVC -- HPC job scheduling, workflow automation, version control, reproducible research} \end{skillgroup} \begin{skillgroup}{Analysis \& Visualization} -\skilldash{MDAnalysis, ProDy, PyMOL, matplotlib, seaborn -- trajectory analysis, publication figures} -\skilldash{PostgreSQL, pandas -- curated stability databases with automated quality filters for ML} +\skilldash{MDAnalysis, ProDy, PyMOL, matplotlib, seaborn -- trajectory analysis, structural visualization, publication figures} +\skilldash{PostgreSQL, pandas, NumPy -- curated stability databases with automated quality filters for ML pipelines} \end{skillgroup} \begin{skillgroup}{Domain Expertise} -\skilldash{Protein engineering, enzyme thermostability, folding thermodynamics, drug discovery} -\skilldash{Intrinsically disordered proteins, ligand binding, biocatalysis, directed evolution} +\skilldash{Protein engineering, enzyme thermostability, folding thermodynamics, drug discovery, virtual screening workflows} +\skilldash{Intrinsically disordered proteins, ligand binding free energy, biocatalysis, directed evolution, rational design} \end{skillgroup} \end{rSection} @@ -90,12 +90,15 @@ Computational biologist with 8+ years combining \textbf{protein language models} \item Co-developed transfer learning framework from protein language models reducing labeled training data by 60\% across 5 enzyme families, released as open-source tool with 200+ GitHub stars. \item Extended protein language model to predict enzyme solvent tolerance across 8 organic co-solvent systems, validating against 50-ns explicit-solvent MD for 80 enzyme variants and identifying 4 candidates for green chemistry. \item Automated sequence-to-simulation pipeline using Snakemake workflow manager, reducing per-variant setup from 4 hours to 10 minutes and supporting 6 researchers across 3 active projects. +\item Revealed sequence-dependent enzyme unfolding pathway divergence at 340 K through 200-ns replica exchange MD simulations, identifying stabilizing salt bridge networks that informed rational design criteria. +\item Mentored 3 graduate students on protein ML pipelines and MD simulation workflows, with 1 student co-authoring a peer-reviewed publication within 8 months of joining. \end{rSubsection} \begin{rSubsection}{Enhanced Sampling Methods for Protein Folding and Ligand Binding}{\textcolor{black!60}{Aug 2018 -- Jul 2023}}{Ph.D.\ Researcher, Westfield Institute of Technology}{} \item Developed metadynamics-based enhanced sampling protocol for protein folding free energy landscapes, predicting folding temperatures within 8 K of experiment across 6 small proteins. \item Calculated relative binding free energies for 40 congeneric ligand pairs via free energy perturbation, achieving 0.9 kcal/mol RMSE against experimental IC50 data across 3 drug target families. \item Built curated protein thermostability database integrating 12,000 experimental melting temperatures from 3 public sources, with automated quality filters adopted by 8 lab members for ML training set construction. +\item Benchmarked 4 protein force fields on 15 intrinsically disordered protein sequences, establishing CHARMM36m as the optimal choice for IDP conformational ensemble prediction with 40\% better agreement with SAXS data. \end{rSubsection} \begin{rSubsection}{Computational Biophysics and Structural Analysis}{\textcolor{black!60}{May 2016 -- Jul 2018}}{Undergraduate Research Assistant, Eastgate University}{} @@ -133,6 +136,10 @@ Computational biologist with 8+ years combining \textbf{protein language models} \item \textbf{J.\ Chen}, P.\ Kowalski, L.\ Alvarez. ``Force Field Benchmarking for Intrinsically Disordered Protein Ensembles.'' \textit{J.\ Chem.\ Theory Comput.}, 2021. +\item \textbf{J.\ Chen}, P.\ Kowalski, L.\ Alvarez. ``Curated Thermostability Database for ML-Ready Protein Engineering Benchmarks.'' \textit{Bioinformatics}, 2021. + +\item \textbf{J.\ Chen}, T.\ Yamamoto, K.\ Holmberg. ``Predicting Enzyme Solvent Tolerance with Fine-Tuned Protein Language Models.'' \textit{Proteins: Struct., Funct., Bioinf.}, 2025 (under review). + \end{rSection2} \vspace{-0.15cm} @@ -143,6 +150,19 @@ Computational biologist with 8+ years combining \textbf{protein language models} \item \textbf{NSF Graduate Research Fellowship}, National Science Foundation (2019). Three-year fellowship supporting doctoral research in computational protein engineering. \item \textbf{Best Oral Presentation}, Westfield Biophysics Symposium (2022). Enhanced sampling methods for protein folding thermodynamics. \item \textbf{Dean's Teaching Award}, Westfield Institute of Technology (2021). Outstanding TA in computational biology. +\item \textbf{Outstanding Poster Award}, Gordon Research Conference on Proteins (2023). ML-guided enzyme thermostability screening. +\end{rSection2} +\vspace{-0.15cm} + +%---------------------------------------------------------------------------------------- +% SELECTED PRESENTATIONS +%---------------------------------------------------------------------------------------- +\begin{rSection2}{Selected Presentations} +\item ``ML-Guided Screening of Thermostable Enzyme Variants.'' \textit{Gordon Research Conference on Proteins}, Ventura, CA (2023). Poster. +\item ``Transfer Learning from Protein Language Models for Low-Data Enzyme Property Prediction.'' \textit{ACS National Meeting}, San Francisco, CA (2024). Oral. +\item ``Enhanced Sampling Protocols for Protein Folding Free Energy Landscapes.'' \textit{Biophysical Society Annual Meeting}, San Diego, CA (2022). Oral. +\item ``Force Field Benchmarking for Intrinsically Disordered Protein Ensembles.'' \textit{AIChE Annual Meeting}, Boston, MA (2021). Poster. +\item ``Automated Screening Pipelines for ML-Guided Enzyme Engineering.'' \textit{Lakewood University Computational Biology Seminar Series} (2024). Invited talk. \end{rSection2} \vspace{-0.1cm}