Dr. Adrian Jinich, Ph.D

Assistant Professor
Skaggs School of Pharmacy and Pharmaceutical Sciences
Department of Chemistry & Biochemistry

Adrian Jinich, Ph.D.


Teah Stacks

Human Resources

Lydia Heidt (formerly Napa)

Fund Management

Heidi Rosenthal

Research Summary

The Jinich laboratory is a mixed computational and experimental group. The overarching goal of the Jinich lab is to develop computational methods that predict enzyme substrate chemical structure based on amino acid sequence, thereby unveiling previously unknown enzyme functions and expanding the repertoire of characterized enzymes. We employ machine learning techniques to generate powerful protein representations, and use systems biochemistry and functional genetics to experimentally validate our substrate predictions. Additionally, we plan to establish high-throughput enzyme activity assays to generate data that will further improve our machine learning models. Accelerating the prediction of so-called "orphan" enzyme substrates will be of value across diverse fields, from enabling advances in metabolic engineering and environmental microbiology to transforming our understanding and treatment of infectious diseases.

Academic Achievements

Education: M.Sc Applied Mathematics (2011), Centro de Investigacion en Matematicas (CIMAT); Ph.D Systems Biology (2017), Harvard University; Postdoctoral studies (2018-2023), Weill Cornell Medicine

Awards and Honors: Inaugural cohort BID (Building Innovation through Diversity) at the Marine Biological Laboratory (MBL) (2022); Named one of “100 most inspiring Hispanic/Latinx scientists in America” by Cell Mentor/Cell Press (2020); Burroughs Wellcome Fund collaborative research travel award (2020); Hanna Gray Fellow, Howard Hughes Medical Institute (HHMI) (2019 - present); Cold Spring Harbor Laboratory (CSHL) Helmsley Fellow (June 2018).

Leadership Experience: Co-founder and president of the board of directors of Clubes de Ciencia Mexico (CdeCMx), a non-profit organization that sends young scientists from the most prestigious universities in the US to deliver hands-on STEM workshops for Mexican students.

Key Contributions
  • Development of a mixed quantum chemical and machine learning approach to predict redox potentials of small molecule metabolites from molecular structure with high accuracy.
  • Systematic analysis of redox reaction networks relevant to prebiotic chemistry from a thermodynamic lens.
  • Built the Mycobacterium tuberculosis transposon sequencing database (MtbTnDb), compiling TnSeq screens from the literature and other datasets that quantitatively describe what mycobacterial genes are essential in which conditions for over 150 experiments.
  • Development of a statistical method to identify fitness profile correlations from functional genetics data as enabled by transposon sequencing (TnSeq) screens.
  • Identification and experimental validation of an enzyme module in M. tuberculosis of seven co-essential genes which form an enzyme module that helps Mtb counter the toxic effects of itaconate, an important antibacterial compound produced by the host during infection.
Selected Publications
  • Rappoport, D. and Jinich, A., (2023). Enzyme Substrate Prediction from Three-Dimensional Feature Representations Using Space-Filling Curves. Journal of Chemical Information and Modeling, 63(5), pp.1637-1648.
  • Jinich, A., et al. Genome-wide co-essentiality analysis in Mycobacterium tuberculosis reveals an itaconate defense enzyme module. bioRxiv 2022.09.27.509804 (under review).
  • Jinich, A., Zaveri, A., et al. The Mycobacterium tuberculosis transposon sequencing database (MtbTnDB): a large-scale guide to genetic conditional essentiality. bioRxiv 2021.03.05.434127
  • Jinich, A. et al. (2020). A thermodynamic atlas of carbon redox chemical space. Proceedings of the National Academy of Sciences, 117(52), pp.32910-32918.
  • Jinich, A., Sanchez-Lengeling, B., et al. (2019). A Mixed Quantum Chemistry/Machine Learning Approach for the Fast and Accurate Prediction of Biochemical Redox Potentials and Its Large-Scale Application to 315 000 Redox Reactions. ACS central science, 5(7), pp.1199-1210.
  • Lengeling, T.S. and Jinich, A., (2019). Empowering young innovators. Science, 363(6433), pp.1294-1294.
  • Jinich, A., et al. (2018). Quantum chemistry reveals the thermodynamic principles of redox biochemistry. PLoS Comput Biol 14(10): e1006471.
Potential Collaborative Programs
  • Expertise in machine learning techniques in the realms of chemistry and biochemistry, including cheminformatics and protein language models. Specialized in designing computational models tailored for substrate class prediction across a diverse range of protein types.