Neeraj Kumar, PhD
Neeraj Kumar, PhD
Biography
As the Chief Data Scientist in the Advanced Computing, Mathematics, and Data Division at Pacific Northwest National Laboratory (PNNL), I am deeply committed to driving innovation in data science, computing, and applied mathematics. My career, spanning over a decade, has been dedicated to exploring and expanding the horizons of applied machine learning, artificial intelligence, probabilistic programming, natural language processing, quantum computing, and innovative modeling and simulation methods. These diverse areas of expertise are not just academic pursuits but are actively applied in science, bio/security and engineering mission, addressing both fundamental and applied scientific challenges. My role extends beyond pioneering new research avenues and leading technical programs; it involves a strategic focus on developing scalable AI/ML products, developing modeling, cloud computing, and advanced analytics in computational chemistry, materials science, and digital molecular discovery.
Our efforts span a broad spectrum of disciplines, including applied math, computational chemistry and biology, health science, and medical therapeutics, reflecting our commitment to multidisciplinary research and solution development. Our team, comprised of skilled data and computational scientists, operates at the forefront of technology, developing cutting-edge physics and bio-informed machine learning methods. These are seamlessly integrated with advanced generative AI to forge autonomous decision-making tools capable of handling the intricacies of unstructured and heterogeneous data. This innovative work is vital in tackling the diverse and complex challenges prevalent in our rapidly evolving scientific landscape.
At the core of my leadership philosophy lies a strong commitment to empowering our staff. I am dedicated to mentoring and cultivating our scientists and professionals, creating a culture that values continuous learning and innovation. My vision is to harness the transformative power of data and cutting-edge technology to not only decipher complex challenges but also to forge impactful, lasting solutions that benefit PNNL and our diverse stakeholders. By leading through example, I aim to inspire our team in their scientific endeavors and encourage the next generation of scientists to pursue discovery and make a significant impact in the broader fields.
Education
University of Louisville
Doctor of Philosophy, Computational Chemistry (Applied Math)
University of Louisville
Master of Science, Computational Chemistry
Panjab University
Master of Science, Computational Chemistry
Panjab University
Bachelor of Science, Math/Physics/Chemistry
Awards and Recognitions
- U.S. Department of Energy Research Award (2021)
- Ronald L. Brodzinski Award for Early Career Exceptional Achievement (2020)
- Outstanding Performance Award for Artificial Intelligence/Machine Learning Research, PNNL (2019)
- Appreciation award at the OLC International Biotechnology Conference (2019)
- Outstanding Performance Award for Machine Learning Research and Computer-aided Design, PNNL (2016)
- Awarded Graduate Dean’s Citation for Excellence in Graduate Studies at University of Louisville (2013)
- Lawrence Graduate Student Award, Lawrence Livermore National Laboratory (2012)
- Travel award, American Chemical Society national meeting (2012)
- Graduate Student Union Fellowship for Supercomputing, University of Louisville (2011)
- Travel award, International conference on High Perforformane Computing (2010)
Publications
(Select Publications)
2022
- Knutson, C, Bontha M, Pope, J, Kumar N*. Decoding the protein-ligand interactions with Graph Neural Networks. Nature’s Scientific Reports 12, 7624, 2022. https://doi.org/10.1038/s41598-022-10418-2
- Joshi R, Gebauer N, Bontha M, Khazaieli M, James RM, Brown JB, Kumar N*. 3D-Scaffold: A Deep Learning Framework to Generate 3D Coordinates of Antiviral Candidates (Covalent and Non Covalent) with Desired Scaffolds. Phys Chem B. 2021. doi: 10.1021/acs.jpcb.1c06437
- McNaughton, D., Knutson, C, Bontha M, Pope, J, Kumar N*. “De novo design of protein target specific scaffold-based inhibitors via reinforcement” learning. https://openreview.net/forum?id=MCXW5uQqb8P ICLR 2022 Machine Learning for Drug Discovery. https://arxiv.org/abs/2205.10473
- Louis, S. Y., Siriwardane, E. M. D., Joshi, R. P., Omee, S. S., Kumar, N., & Hu, J. (2022). Accurate Prediction of Voltage of Battery Electrode Materials Using Attention-Based Graph Neural Networks. ACS Applied Materials & Interfaces 2022, 14, 23, 26587 https://pubs.acs.org/doi/full/10.1021/acsami.2c00029
- Yulun, W; N, Choma, N, Chen, N, Cashman, M, Clyde, A, Brettin, A, de Jong, W, Kumar, N, Head, M, Stevens, M, Nugent, Peter, Jacobson, Danier, Brown, James. “Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery ” ICLR 2022. http://arxiv.org/abs/2106.02190.
2021
- McNaughton, D., Bredewig, E, Menzer, J., Zucker, J., Baker, S. Munoz, N., Peter, J., and Kumar, N*. " Bayesian Inference for Integrating Yarrowia lipolytica Multi-omics Datasets with Metabolic Modeling" ACS Synthetic Biology 2021. https://doi.org/10.1021/acssynbio.1c00267
- Joshi R.; Kumar N*. "Artificial Intelligence for Autonomous Molecular Design: A Perspective" (2021); Molecules 26 (22), 6761.
- Clyde A, Galanie S, Kneller DW, Ma H, Babuji Y, Blaiszik B, Brace A, Brettin T, Chard K, Chard R, Coates L, Foster I, Hauner D, Kertesz V, Kumar N, A, Ramanathan A, Head MS, Stevens R. High Throughput Virtual Screening and Validation of a SARS-CoV-2 Main Protease Non-Covalent Inhibitor. J. Chem. Inf. Model. 2021, doi: https://doi.org/10.1021/acs.jcim.1c00851.
- Choi R, Zhou M, Shek R, Wilson JW, Tillery L, Craig JK, Salukhe IA, Hickson SE, Kumar N, James RM, Buchko GW, Barrett LK, Hyde JL, Van Voorhis WC*. High-throughput screening of the ReFRAME, Pandemic Box, and COVID Box drug repurposing libraries against SARS-CoV-2 nsp15 endoribonuclease to identify small-molecule inhibitors of viral activity. PLoS One. 2021;16(4):e0250019.
- Matlock M.; Folmsbee, D.; Langkamp, L.; Hutchison, G. R.; Kumar, N.; Joshua, S. 2020. “Deep learning coordinate-free quantum chemistry.” J Phys Chem A. 2021 Oct 14;125(40):8978-8986. doi: 10.1021/acs.jpca.1c04462.
- Joshi, R., McNaughton, A.D., Thomas, D.G., Henry, C., Canon, S., McCue, L., and Kumar, N*. "Quantum Mechanical Methods Predict Accurate Thermodynamics of Biochemical Reactions" ACS Omega Omega. 2021 Apr 13; 6(14): 9948–9959. https://doi.org/10.1021/acsomega.1c00997
- Alexander F.J., J.A. Ang, S. Choudhury, S. Ghosh, Y. Huang, N. Kumar, and J.A. Bilbrey, et al. "Co-design Center for Exascale Machine Learning Technologies (ExaLearn)." The International Journal of High Performance Computing Applications. 2021;35(6):598-616.
- Ward, L; Bilbrey, J; Choudhury, S, Kumar, N*, Sivaraman G.. Evening the Score: Targeting SARS-CoV-2 Protease Inhibition in Graph Generative Models for Therapeutic Candidates. KDD 2021
arXiv:2102.04977. - Pion-Tonachini L., Bouchard, K., Garcia Martin, H., Peisert, S., Holtz, W., Aswani, A., Kumar, N and Dwivedi, D., et al. "Learning from learning machines: A new generation of AI technology to meet the needs of science." https://arxiv.org/abs/2111.13786
2020
- Artz, J. H.; Zadvornyy, O. A.; Mulder, D. W.; Keable, S. M.; Cohen, A. E.; Ratzloff, M. W.; Williams, S. G.; Ginovska, B.; Kumar, N.; Song, J.; McPhillips, S. E.; Davidson, C. M.; Lyubimov, A. Y.; Pence, N.; Schut, G. J.; Jones, A. K.; Soltis, S. M.; Adams, M. W. W.; Raugei, S.; King, P. W.; Peters, J. W., Tuning Catalytic Bias of Hydrogen Gas Producing Hydrogenases. J. Am. Chem. Soc. 2020, 142 (3), 1227-1235.
- Nakayasu E. S.; Chazin-Gray, A. M.; Auberry, D. L.; Munoz, N.; Cottam, J. A.; Zucker, J.D.; Kumar, N.; Nicora C. D.; Mitchell H. D.; Kim Y.; Nelson W. C.; Egbert R. G. "Resource reallocation in engineered Escherichia coli strains with reduced genomes" bioRxiv 2020.10.19.346155 (2020); doi: https://doi.org/10.1101/2020.10.19.346155
- Siriwardane, E.; Joshi, R.; Kumar, N.; and Cakir, D. “Machine Learning and DFT Prediction of Formation/Exfoliation Energy and Structure Correlation of MAB Phases.” ACS Appl. Mater. Interfaces 2020, 26 (12), 29424-29431.
- Gupta, R., Tanwar, S., Tyagi, S., & Kumar, N. (2020). Machine learning models for secure data analytics: A taxonomy and threat model. Computer Communications, 153, 406-440.
- Bilbrey J.A., Ward, L.; Choudhury, S.; Sivaraman, N.; Kumar, N. "Benchmarking Deep Graph Generative Models for Optimizing New Drug Molecules for COVID-19." In The Second International Workshop on Deep Learning on Graphs: Methods and Applications (DLG-KDD’20).
2019
- Kumar, N.; Bucher, D.; Kozlowski, P. M. “Reaction Mechanism for the Initial Step of B12-Dependent Methylmalonyl CoA Mutase” Journal of Physical Chemistry B 2019, 123, 2210-2216.
- Pegis, M. L.; Martin, D. J.; Wise, C. F.; Brezny, A. C.; Johnson, S. I.; Johnson, L. E.; Kumar, N.; Raugei, S.; Mayer, J. M. “Mechanism of Catalytic O2 Reduction by Iron Tetraphenylporphyrin” J. Am. Chem. Soc. 2019 141 (20), 8315-8326.
- Cannon, W., Britton, S., Zucker, J., Baxter, D., Kumar, N., et. al. “Prediction of Metabolite Concentrations Using Maximum Entropy-Based Simulations with Application to Central Metabolism of Neurospora crassa” Biophysical Journal, 2019, 116(3), 130.
- Kumar, N.; Darmon, J.; Weiss, C.; Helm, M.; Raugei, S.; Bullock, M. R. “Outer Coordination Sphere Proton Relay Base and Proximity Effects on Hydrogen Oxidation with Iron Electrocatalysts” Organometallics, 2019. DOI:10.1021/acs.organomet.8b00805
2018
- Hurley, J. M.; Jankowski, M. S.; Crowell, A.; Fordyce, S.; Zucker, J. D.; Kumar, N.; De Los Santos, H.; Purvine, S.; Robinson, E.; Shukla, A.; Zink, E.; Cannon, W. R.; Baker, S.; Loros, J. J.; Dunlap, J. C., Circadian proteomic analysis uncovers mechanisms of post-transcriptional regulation in metabolic pathways. Cell Systems 2018, 7, 613-626.
- Smallwood, C. R., Chen J-H, Kumar, N., Chrisler, W. B., Purvine, S. O., Kyle, J. E., Nicora. C. D., Boudreau, R., Ekman, A., Hixson. K. H., Moore, R. J., Mcdermott, G., Cannon, R., Evans, J. E. "Integrated systems biology and imaging of the smallest free-living eukaryote" BioRxiv (2018) doi: 10.1101/293704
- Cannon WR, JD Zucker, DJ Baxter, N Kumar, SE Baker, J Hurley, and JC Dunlap. 2018. "Prediction of Metabolite Concentrations, Rate Constants and Post-Translational Regulation using Maximum Entropy-based Simulations with Application to Central Metabolism of Neurospora crassa." Processes 6(6):Article No. 63. doi:10.3390/pr6060063
2016
- Cardenas AJ, B Ginovska-Pangovska, N Kumar, J Hou, S Raugei, ML Helm, AM Appel, RM Bullock, and MJ O'Hagan. 2016. "Controlling Proton Delivery with Catalyst Structural Dynamics." Angewandte Chemie International Edition 55(43):13509-13513. doi:10.1002/anie.201607460
- Pegis ML, BA McKeown, N Kumar, K Lang, DJ Wasylenko, P Zhang, S Raugei, and JM Mayer. 2016. "Homogenous Electrocatalytic Oxiygen Reduction Rates Correlate with Reaction Overpotential in Acidic Organic Solutions." ACS Central Science 2(11):850-856. doi:10.1021/acscentsci.6b00261
- Brady, G; Kumar, N.; Jaworska, M.; Lodowski, P.; Kozlowski, P. M. “Electronically Excited States of Cob(II)alamin: Insights from CASSCF/XMCQDPT2 and TD-DFT Calculations” Phys. Chem. Chem. Phys., 2016, 18, 4513-4526.
2015
- Hulley E, N Kumar, S Raugei, and RM Bullock. 2015. "Manganese-Based Molecular Electrocatalysts for Oxidation of Hydrogen." ACS Catalysis 5(11):6838-6847. doi:10.1021/acscatal.5b01751
- Darmon JM, N Kumar, E Hulley, CJ Weiss, S Raugei, RM Bullock, and ML Helm. 2015. "Increasing the Rate of Hydrogen Oxidation without Increasing the Overpotential: A Bio-Inspired Iron Molecular Electrocatalyst with an Outer Coordination Sphere Proton Relay." Chemical Science 6(5):2737-2745. doi:10.1039/C5SC00398A (Selected as cover page for the journal).
2014
- Kumar N, DM Camaioni, M Dupuis, S Raugei, and AM Appel. 2014. "Mechanistic Insights into Hydride Transfer for Catalytic Hydrogenation of CO2 with Cobalt Complexes." Dalton Transactions 43(31):11803-11806. doi:10.1039/c4dt01551g (Selected as cover page for the journal).
- Kumar, N.; Kozlowski, P. M. “Mechanistic Insights for the formation of organometallic Co-C bond in the reaction catalyzed by methionine synthase” J. Phys. Chem. B, 2013, 117, 16044-16057.
- Kumar, N. Camaioni, D. M., Dupuis, M., Raugei S., Appel, A. M. “Inside Front Cover for Mechanistic Insights into Hydride Transfer for Catalytic Hydrogenation of CO2 with Cobalt Complexes” Dalton Trans., 2014, 43, 11770.
2013
- Kumar, N.; Kuta, J.; Galezowski, W.; Kozlowski, P. M. “One-Electron-Oxidized Form of the Methylcobalamin Cofactor: Spin Density Distribution and Pseudo-Jahn-Teller Effect” Inor. Chem. 2013, 52, 1762-1771.
- Koziol, L.; Kumar, N.; Wong, E. S.; Lightstone, F. C. “Molecular recognition of aromatic rings by flavin: electrostatics and dispersion determine ring positioning above isoalloxazine” J. Phys. Chem. A, 2013, 117, 12946-12952.
- Kumar, N.; Kozlowski, P. M. “Mechanistic Insights for the formation of organometallic Co-C bond in the reaction catalyzed by methionine synthase” J. Phys. Chem. B, 2013, 117, 16044-16057.
- Kornobis, K.; Kumar, N.; Wong, B. M.; Jaworska, M.; Lodowski, P.; Kozlowski, P. M. “Electronic Structure of S1 State in Methylcobalamin: Benchmark Analysis Including CASSCF/MC-XQDPT2, EOM-CCSD and TD-DFT Calculations” J. Comput. Chem. 2013, 44, 1987-1004.
- Kumar, N.; Liu S. B.; Kozlowski, P.M. “Charge Separation Propensity of the Coenzyme B12–Tyrosine Complex in Adenosylcobalamin-Dependent Methylmalonyl–CoA Mutase Enzyme” J. Phys. Chem. Letters 2012, 3, 1035-1038.
2012
- Kumar, N.; Liu S. B.; Kozlowski, P.M. “Charge Separation Propensity of the Coenzyme B12–Tyrosine Complex in Adenosylcobalamin-Dependent Methylmalonyl–CoA Mutase Enzyme” J. Phys. Chem. Letters 2012, 3, 1035-1038.
- Kumar, M.; Kumar, N.; Hirao, H.; Kozlowski, P. M. “Co2+/Co1+ Redox Tuning in Methyltransferases Induced by a Conformational Change at the Axial Ligand” Inorg. Chem. 2012, 51, 5533-5538.
2011
- Kumar, N.; Alfonso-Prieto, M.; Rovira, C.; Jaworska, M.; Lodowski, P.; Kozlowski, P. M. “Role of the Axial Base in the Modulation of the Cob(I)alamin Electronic Properties: Insight from QM/MM, MD, and CASSCF Calculations” J. Chem. Theory Comput. 2011, 7, 1541-1551.
- Kumar, N.; Jaworska, M.; Lodowski, P.; Kumar, M.; Kozlowski, P. M. “Electronic Structure of Cofactor_Substrate Reactant Complex Involved in the Methyl Transfer Reaction Catalyzed by Cobalamin-Dependent Methionine Synthase” J. Phys. Chem. B 2011, 115, 6722-6731.
- Kornobis, K.; Kumar, N.; Wong, B. M.; Jaworska, M.; Lodowski, P.; Andruniow, T.; Ruud, K.; Kozlowski, P. M. “Electronically Excited States of Vitamin B12: Benchmark Calculations Including Time-Dependent Density Functional Theory and Correlated ab Initio Methods” J. Phys. Chem. A 2011, 115, 1280-1292.
Related Research Highlights
- Deep Learning Approach to Identify Novel Molecules for Therapeutics
- Decoding Protein Interactions with Domain-Aware Machine Learning
- Making quantum chemistry more user-friendly
- With the invention of AlphaFold2 from DeepMind, the GNN model can take their predicted 3-D protein structures as an input to identify molecular candidates
- From Molecule to Medicine via Machine Learning
- Machine learning, Bayesian inference, and metabolic modeling help design biofuel-producing yeast
- Using Quantum Computation to Design Better Microbes
- New quantum chemistry pipeline can help predict the effects of bioengineering
- New Method Helps Predict Metabolite Concentrations, Rate Constants, and Enzyme Regulation Within Cells
- Predicting the effects of microbial engineering in KBase