About

Martin D. Burke is the May and Ving Lee Professor for Chemical Innovation at the University of Illinois Urbana-Champaign, where he is also the Founding Director of the Molecule Maker Lab and co-Founder of the Molecule Maker Lab Institute. He holds a B.A. in Chemistry from Johns Hopkins University, a Ph.D. in Chemistry from Harvard University, and an M.D. from the Harvard-MIT Health Sciences and Technology Program. Burke helped launch the Carle Illinois College of Medicine, serving as its inaugural Associate Dean for Research. His research focuses on developing blocc chemistry, a modular platform for small molecule synthesis that is friendly to automation, AI, and non-specialists, aiming to overcome the long-standing synthesis bottleneck in molecular innovation. His lab has leveraged this technology to create molecular prosthetics, renal sparing antifungals, and organic lasers, integrating AI to enable closed-loop discovery of new molecular functions. Burke has co-founded five biotech companies, advancing multiple drug candidates into clinical trials, and is an elected member of the National Academy of Medicine and a Fellow of the AAAS. His work emphasizes democratizing molecular design and empowering the next generation of molecular inventors worldwide.

Research topics

• Computer Science
• Biology
• Machine Learning
• Chemistry
• Computational biology
• Microbiology
• Artificial Intelligence
• Virology
• Medicine
• Biochemistry
• Pathology
• Epistemology
• Environmental health
• Theoretical computer science
• Telecommunications
• Psychology
• Pharmacology
• Botany
• Nursing

Selected publications

• mCLM: A Modular Chemical Language Model that Generates Functional and Makeable Molecules

  ArXiv.org · 2025-05-18 · 1 citations

  preprintOpen access

  Despite their ability to understand chemical knowledge, large language models (LLMs) remain limited in their capacity to propose novel molecules with desired functions (e.g., drug-like properties). In addition, the molecules that LLMs propose can often be challenging to make, and are almost never compatible with automated synthesis approaches. To better enable the discovery of functional small molecules, LLMs need to learn a new molecular language that is more effective in predicting properties and inherently synced with automated synthesis technology. Current molecule LLMs are limited by representing molecules based on atoms. In this paper, we argue that just like tokenizing texts into meaning-bearing (sub-)word tokens instead of characters, molecules should be tokenized at the level of functional building blocks, i.e., parts of molecules that bring unique functions and serve as effective building blocks for real-world automated laboratory synthesis. This motivates us to propose mCLM, a modular Chemical-Language Model that comprises a bilingual language model that understands both natural language descriptions of functions and molecular blocks. mCLM front-loads synthesizability considerations while improving the predicted functions of molecules in a principled manner. Experiments on FDA-approved drugs showed that mCLM is capable of significantly improving chemical functions. mCLM, with only 3B parameters, also achieves improvements in synthetic accessibility relative to 7 other leading generative AI methods including GPT-5. When tested on 122 out-of-distribution medicines using only building blocks/tokens that are compatible with automated modular synthesis, mCLM outperforms all baselines in property scores and synthetic accessibility. mCLM can also reason on multiple functions and iteratively self-improve to rescue drug candidates that failed late in clinical trials ("fallen angels").

  PublisherOA PDFDOI

• Molecular Prosthetics and CFTR Modulators Additively Increase Secretory HCO ₃ ^– Flux in Cystic Fibrosis Airway Epithelia

  ACS Chemical Biology · 2025-10-20

  articleOpen accessSenior authorCorresponding

  Cystic fibrosis (CF) is caused by loss-of-function mutations in the gene encoding the cystic fibrosis transmembrane conductance regulator (CFTR), an anion channel predominantly expressed on the apical membrane of epithelial cells. Reduced Cl– and HCO3– secretion due to dysfunctional CFTR results in a decrease in lung function and is the leading cause of morbidity in individuals with CF. Recent therapies, known as highly effective CFTR modulator therapy (HEMT), help improve the lung function in individuals with specific CF-causing mutations by enhancing the folding, trafficking, and gating of CFTR. However, variability in HEMT responsiveness leads to suboptimal clinical outcomes in some people with CF undergoing modulator therapy. A potential strategy is to complement their function with a CFTR-independent mechanism. One possibility is the use of ion channel-forming small molecules such as amphotericin B, which has shown promise in restoring function and host defenses in CF airway disease models. Amphotericin B functions as a molecular prosthetic for CFTR and may thus complement CFTR modulators. Here, we show that cotreatment of CF airway epithelia with HEMT and amphotericin B results in greater increases in both HCO3– secretory flux and ASL pH compared to treatment with either agent alone. These findings suggest that coadministration of CFTR modulators and molecular prosthetics may provide additive therapeutic benefits for individuals with CF.

  PublisherOA PDFDOI

• Automated Iterative N-C and C-C Bond Formation

  ChemRxiv · 2025-05-09

  preprintOpen accessSenior author

  Small molecule solutions to many contemporary societal challenges await discovery, but the artisanal and manual process via which this class of chemical matter is typically accessed limits the discovery of new functions. Automated iterative cross-coupling with (N-methyl iminodiacetic acid) MIDA or (tetramethyl N-methyl iminodiacetic acid) TIDA boronate building blocks alternatively enables generalized and automated preparation of many different types of small molecules in a modular fashion. But in its current form, this engine cannot leverage nitrogen atoms as iteration handles. Here, we disclose a new iteration-enabling group, CbzT, that reversibly attenuates the reactivity of nitrogen atoms and enables generalized catch-and-release purification. CbzT is leveraged to achieve the automated modular synthesis of Imatinib (Gleevec), an archetypical clinically approved kinase inhibitor, in which building blocks are iteratively linked by both N-C and C-C bonds. This work substantially expands the types of small molecules that can be made in an automated modular fashion. It also advances the concept of intentionally developing chemistry that machines can do.

  PublisherOA PDFDOI

• Automated Iterative N─C and C─C Bond Formation

  Angewandte Chemie · 2025-06-18

  articleSenior authorCorresponding

  Abstract Small molecule solutions to many contemporary societal challenges await discovery, but the artisanal and manual process via which this class of chemical matter is typically accessed limits the discovery of new functions. Automated assembly of (N‐methyl iminodiacetic acid) MIDA or (tetramethyl N‐methyl iminodiacetic acid) TIDA boronate building blocks via iterative C─C bond formation, an approach we call “block chemistry”, alternatively enables generalized and automated preparation of many different types of small molecules in a modular fashion. But in its current form, this engine cannot also leverage nitrogen atoms as iteration handles. Here, we disclose a new iteration‐enabling group, CbzT ( p‐ TIDA boronate‐substituted carboxybenzyl), that reversibly attenuates the reactivity of nitrogen atoms and enables generalized catch‐and‐release purification. CbzT is leveraged to achieve the automated modular synthesis of Imatinib (Gleevec), an archetypical clinically approved kinase inhibitor, in which building blocks are iteratively linked by both N─C and C─C bonds. This work substantially expands the types of small molecules that can be iteratively assembled in an automated modular fashion. It also advances the concept of intentionally developing chemistry that machines can do.

  PublisherDOI

• Automated Iterative N─C and C─C Bond Formation

  Angewandte Chemie International Edition · 2025-06-18 · 3 citations

  articleOpen accessSenior authorCorresponding

  Small molecule solutions to many contemporary societal challenges await discovery, but the artisanal and manual process via which this class of chemical matter is typically accessed limits the discovery of new functions. Automated assembly of (N-methyl iminodiacetic acid) MIDA or (tetramethyl N-methyl iminodiacetic acid) TIDA boronate building blocks via iterative C─C bond formation, an approach we call "block chemistry", alternatively enables generalized and automated preparation of many different types of small molecules in a modular fashion. But in its current form, this engine cannot also leverage nitrogen atoms as iteration handles. Here, we disclose a new iteration-enabling group, CbzT (p-TIDA boronate-substituted carboxybenzyl), that reversibly attenuates the reactivity of nitrogen atoms and enables generalized catch-and-release purification. CbzT is leveraged to achieve the automated modular synthesis of Imatinib (Gleevec), an archetypical clinically approved kinase inhibitor, in which building blocks are iteratively linked by both N─C and C─C bonds. This work substantially expands the types of small molecules that can be iteratively assembled in an automated modular fashion. It also advances the concept of intentionally developing chemistry that machines can do.

  PublisherOA PDFDOI

• New antifungal breaks the mould

  Nature · 2025-03-19

  articleSenior author
  PublisherDOI

• Molecular prosthetics for CFTR designed for anion selectivity outperform amphotericin B in cultured cystic fibrosis airway epithelia

  bioRxiv (Cold Spring Harbor Laboratory) · 2025-08-28

  preprintOpen accessSenior authorCorresponding

  The ion channel-forming natural product amphotericin B (AmB) can serve as a molecular prosthetic for the cystic fibrosis transmembrane conductance regulator (CFTR) anion channel and thereby restore host defenses in cultured cystic fibrosis (CF) airway epithelia. This is despite the fact that the permeability of AmB-based channels favors cations, and these channels lose their capacity to increase airway surface liquid (ASL) pH in CF airway epithelia at high concentrations. We hypothesize that modifying such channels to favor anion permeability would make them more CFTR-like and thus increase their potential therapeutic effects compared to AmB. Here we show that a synthetic derivative of AmB, AmB-AA, which has an added positively charged appendage and forms ion channels with an improved relative permeability to anions, outperformed AmB in increasing the ASL pH in CF airway epithelia at both low and high concentrations. Further modifications led to another AmB derivative, C2'epiAmB-AA, that also minimized cholesterol binding and thus toxicity to cultured CF airway epithelia and was an effective surrogate for CFTR in primary cultured airway epithelia from people with CF.

  PublisherOA PDFDOI

• Automated Iterative N-C and C-C Bond Formation

  ChemRxiv · 2025-06-13

  preprintOpen accessSenior author

  Small molecule solutions to many contemporary societal challenges await discovery, but the artisanal and manual process via which this class of chemical matter is typically accessed limits the discovery of new functions. Automated assembly of (N-methyl iminodiacetic acid) MIDA or (tetramethyl N-methyl iminodiacetic acid) TIDA boronate building blocks via iterative C-C bond formation, an approach we call “block chemistry”, alternatively enables generalized and automated preparation of many different types of small molecules in a modular fashion. But in its current form, this engine cannot also leverage nitrogen atoms as iteration handles. Here, we disclose a new iteration-enabling group, CbzT, that reversibly attenuates the reactivity of nitrogen atoms and enables generalized catch-and-release purification. CbzT is leveraged to achieve the automated modular synthesis of Imatinib (Gleevec), an archetypical clinically approved kinase inhibitor, in which building blocks are iteratively linked by both N-C and C-C bonds. This work substantially expands the types of small molecules that can be iteratively assembled in an automated modular fashion. It also advances the concept of intentionally developing chemistry that machines can do.

  PublisherOA PDFDOI

• Illuminating the Interface of Blocc Chemistry and Data Science: Maximizing Function with ML-Guided Discovery and a Digital Molecule Maker

  Journal of Chemical Education · 2025-11-06

  articleOpen accessSenior author

  The intersection of automatable blocc chemistry for iterative carbon-carbon bond formation with artificial intelligence is amplifying molecular innovation in new and exciting ways. In this lab, students are introduced to concepts and tools that help them gain familiarity and confidence with this emerging area of chemistry. Students specifically learn about four automated synthesis platforms, each of which stitches together a bounded set of molecular building blocks using just one type of robust bond-forming reaction. Students then analyze a variety of small molecules and biopolymers to identify the most redundant types of bonds in each molecule that are compatible with iterative formation from bifunctional building blocks. Based on their analysis, students then select an appropriate iterative automated synthesis platform and determine which molecular building blocks would be required to assemble the desired targets. Students next investigate two case studies where blocc chemistry was used used in concert with artificial intelligence to discover new molecular functions. In the first case, students identify high-performing blocks from selected data sets to optimize a single objective function related to organic laser properties. In the second case, students engage with a new online platform inspired by Scratch, dubbed the Digital Molecule Maker (DMM), to perform a multi-objective optimization of organic photovoltaic candidates (OPV). To conclude the lab, students manually perform the blocc chemistry that is foundational for the DMM. This activity series is the second installment of a sequence of undergraduate laboratories designed to illuminate the functional discovery-enabling interface of AI and automated blocc chemistry.

  PublisherOA PDFDOI

• Molecular prosthetics and CFTR modulators additively increase secretory HCO ₃ ⁻ flux in cystic fibrosis airway epithelia

  bioRxiv (Cold Spring Harbor Laboratory) · 2025-06-24

  preprintOpen accessSenior authorCorresponding

  ABSTRACT Cystic Fibrosis (CF) is caused by loss-of-function mutations in the gene encoding the cystic fibrosis transmembrane conductance regulator (CFTR), an anion channel predominantly expressed on the apical membrane of epithelial cells. Reduced Cl − and HCO 3 − secretion due to dysfunctional CFTR results in a decrease in lung function and is the leading cause of morbidity in individuals with CF. Recent therapies, known as highly effective CFTR modulator therapy (HEMT), help improve the lung function in individuals with specific CF-causing mutations by enhancing the folding, trafficking, and gating of CFTR. However, variability in HEMT responsiveness leads to sub-optimal clinical outcomes in some people with CF undergoing modulator therapy. A potential strategy is to complement their function with a CFTR-independent mechanism. One possibility is the use of ion channel-forming small molecules such as amphotericin B, which has shown promise in restoring function and host defenses in CF airway disease models. Amphotericin B functions as a molecular prosthetic for CFTR and may thus complement CFTR modulators. Here we show that co-treatment of CF airway epithelia with HEMT and amphotericin B results in greater increases in both HCO 3 − secretory flux and ASL pH compared to treatment with either agent alone. These findings suggest that co- administration of CFTR modulators and molecular prosthetics may provide additive therapeutic benefits for individuals with CF.

  PublisherOA PDFDOI

Recent grants

• Synthesis and Study of Amphotericin B Derivatives

  NIH · $3.2M · 2007–2017

• NIH Grant R01GM090153

  NIH · $1.2M · 2014

• Using a small molecule iron transporter to understand and treat FPN1 deficiencies in mice

  NIH · $2.8M · 2018–2023

• Iterative Csp3 Cross Coupling for Natural Products Synthesis

  NSF · $806k · 2020–2025

• CAREER: Small Molecule Synthesis via Iterative Cross-Coupling

  NSF · $575k · 2008–2013

Frequent coauthors

• Bartosz A. Grzybowski

  Polish Academy of Sciences

  64 shared

• Alán Aspuru‐Guzik

  Vector Institute

  37 shared

• Daniel J. Blair

  University of Illinois Urbana-Champaign

  35 shared

• Rafał Roszak

  Highland Community College - Illinois

  34 shared

• Agnieszka Wołos

  Polish Academy of Sciences

  32 shared

• Jason E. Hein

  Structural Genomics Consortium

  31 shared

• Eric M. Woerly

  Eli Lilly (United States)

  28 shared

• Chad M. Rienstra

  Resonance Research (United States)

  28 shared

Labs

• BurkeLabPI

  Welcome to Blocc Chemistry.

Awards & honors

• Member, National Academy of Medicine (2022)
• Fellow, American Association for the Advancement of Science…
• Elias J. Corey Award for Outstanding Original Contribution i…
• Arthur C. Cope Scholar Award, American Chemical Society (201…
• Kavli Foundation Emerging Leader in Chemistry Award, America…