1
|
Wierenga RP, Golas S, Ho W, Coley C, Esvelt KM. PyLabRobot: An Open-Source, Hardware Agnostic Interface for Liquid-Handling Robots and Accessories. bioRxiv 2023:2023.07.10.547733. [PMID: 37502883 PMCID: PMC10369895 DOI: 10.1101/2023.07.10.547733] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/29/2023]
Abstract
Liquid handling robots are often limited by proprietary programming interfaces that are only compatible with a single type of robot and operating system, restricting method sharing and slowing development. Here we present PyLabRobot, an open-source, cross-platform Python interface capable of programming diverse liquid-handling robots, including Hamilton STARs, Tecan EVOs, and Opentron OT-2s. PyLabRobot provides a universal set of commands and representations for deck layout and labware, enabling the control of diverse accessory devices. The interface is extensible and can work with any robot that manipulates liquids within a Cartesian coordinate system. We validated the system through unit tests and several application demonstrations, including a browser-based simulator, a position calibration tool, and a path-teaching tool for complex movements. PyLabRobot provides a flexible, open, and collaborative programming environment for laboratory automation.
Collapse
Affiliation(s)
- Rick P. Wierenga
- Leiden University, Leiden, the Netherlands
- Media Lab, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Stefan Golas
- Media Lab, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Wilson Ho
- Media Lab, Massachusetts Institute of Technology, Cambridge, MA, USA
- Department of Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Connor Coley
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Kevin M. Esvelt
- Media Lab, Massachusetts Institute of Technology, Cambridge, MA, USA
| |
Collapse
|
2
|
Stuyver T, Coley C. Machine Learning-Guided Computational Screening of New Candidate Reactions with High Bioorthogonal Click Potential. Chemistry 2023; 29:e202300387. [PMID: 36787246 DOI: 10.1002/chem.202300387] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2023] [Revised: 02/14/2023] [Accepted: 02/14/2023] [Indexed: 02/15/2023]
Abstract
Bioorthogonal click chemistry has become an indispensable part of the biochemist's toolbox. Despite the wide variety of applications that have been developed in recent years, only a limited number of bioorthogonal click reactions have been discovered so far, most of them based on (substituted) azides. In this work, we present a computational workflow to discover new candidate reactions with promising kinetic and thermodynamic properties for bioorthogonal click applications. Sampling only around 0.05% of an overall search space of over 10,000,000 dipolar cycloadditions, we develop a machine learning model able to predict DFT-computed activation and reaction energies within ~2-3 kcal/mol across the entire space. Applying this model to screen the full search space through iterative rounds of learning, we identify a broad pool of candidate reactions with rich structural diversity, which can be used as a starting point or source of inspiration for future experimental development of both azide-based and non-azide-based bioorthogonal click reactions.
Collapse
Affiliation(s)
- Thijs Stuyver
- Massachusetts Institute of Technology, Chemical Engineering, 77 Massachusetts Avenue, 02139, Boston, UNITED STATES
| | - Connor Coley
- Massachusetts Institute of Technology, Chemical Engineering, UNITED STATES
| |
Collapse
|
3
|
Yang K, Swanson K, Jin W, Coley C, Eiden P, Gao H, Guzman-Perez A, Hopper T, Kelley B, Mathea M, Palmer A, Settels V, Jaakkola T, Jensen K, Barzilay R. Correction to Analyzing Learned Molecular Representations for Property Prediction. J Chem Inf Model 2019; 59:5304-5305. [PMID: 31814400 PMCID: PMC8154261 DOI: 10.1021/acs.jcim.9b01076] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Affiliation(s)
- Kevin Yang
- Computer Science and Artificial Intelligence Laboratory , MIT , Cambridge , Massachusetts 02139 , United States
| | - Kyle Swanson
- Computer Science and Artificial Intelligence Laboratory , MIT , Cambridge , Massachusetts 02139 , United States
| | - Wengong Jin
- Computer Science and Artificial Intelligence Laboratory , MIT , Cambridge , Massachusetts 02139 , United States
| | - Connor Coley
- Department of Chemical Engineering , MIT , Cambridge , Massachusetts 02139 , United States
| | | | - Hua Gao
- Amgen Inc. , Cambridge , Massachusetts 02141 , United States
| | | | - Timothy Hopper
- Amgen Inc. , Cambridge , Massachusetts 02141 , United States
| | - Brian Kelley
- Novartis Institutes for BioMedical Research , Cambridge , Massachusetts 02139 , United States
| | | | | | | | - Tommi Jaakkola
- Computer Science and Artificial Intelligence Laboratory , MIT , Cambridge , Massachusetts 02139 , United States
| | - Klavs Jensen
- Department of Chemical Engineering , MIT , Cambridge , Massachusetts 02139 , United States
| | - Regina Barzilay
- Computer Science and Artificial Intelligence Laboratory , MIT , Cambridge , Massachusetts 02139 , United States
| |
Collapse
|
4
|
Yang K, Swanson K, Jin W, Coley C, Eiden P, Gao H, Guzman-Perez A, Hopper T, Kelley B, Mathea M, Palmer A, Settels V, Jaakkola T, Jensen K, Barzilay R. Analyzing Learned Molecular Representations for Property Prediction. J Chem Inf Model 2019; 59:3370-3388. [PMID: 31361484 PMCID: PMC6727618 DOI: 10.1021/acs.jcim.9b00237] [Citation(s) in RCA: 533] [Impact Index Per Article: 106.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/18/2019] [Indexed: 12/23/2022]
Abstract
Advancements in neural machinery have led to a wide range of algorithmic solutions for molecular property prediction. Two classes of models in particular have yielded promising results: neural networks applied to computed molecular fingerprints or expert-crafted descriptors and graph convolutional neural networks that construct a learned molecular representation by operating on the graph structure of the molecule. However, recent literature has yet to clearly determine which of these two methods is superior when generalizing to new chemical space. Furthermore, prior research has rarely examined these new models in industry research settings in comparison to existing employed models. In this paper, we benchmark models extensively on 19 public and 16 proprietary industrial data sets spanning a wide variety of chemical end points. In addition, we introduce a graph convolutional model that consistently matches or outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary data sets. Our empirical findings indicate that while approaches based on these representations have yet to reach the level of experimental reproducibility, our proposed model nevertheless offers significant improvements over models currently used in industrial workflows.
Collapse
Affiliation(s)
- Kevin Yang
- Computer
Science and Artificial Intelligence Laboratory, MIT, Cambridge, Massachusetts 02139, United States
| | - Kyle Swanson
- Computer
Science and Artificial Intelligence Laboratory, MIT, Cambridge, Massachusetts 02139, United States
| | - Wengong Jin
- Computer
Science and Artificial Intelligence Laboratory, MIT, Cambridge, Massachusetts 02139, United States
| | - Connor Coley
- Department
of Chemical Engineering, MIT, Cambridge, Massachusetts 02139, United States
| | | | - Hua Gao
- Amgen Inc., Cambridge, Massachusetts 02141, United States
| | | | - Timothy Hopper
- Amgen Inc., Cambridge, Massachusetts 02141, United States
| | - Brian Kelley
- Novartis
Institutes
for BioMedical Research, Cambridge, Massachusetts 02139, United States
| | | | | | | | - Tommi Jaakkola
- Computer
Science and Artificial Intelligence Laboratory, MIT, Cambridge, Massachusetts 02139, United States
| | - Klavs Jensen
- Department
of Chemical Engineering, MIT, Cambridge, Massachusetts 02139, United States
| | - Regina Barzilay
- Computer
Science and Artificial Intelligence Laboratory, MIT, Cambridge, Massachusetts 02139, United States
| |
Collapse
|
5
|
Yassaee M, Fiorentino D, Okawa J, Taylor L, Coley C, Troxel AB, Werth VP. Modification of the cutaneous dermatomyositis disease area and severity index, an outcome instrument. Br J Dermatol 2009; 162:669-73. [PMID: 19863510 DOI: 10.1111/j.1365-2133.2009.09521.x] [Citation(s) in RCA: 43] [Impact Index Per Article: 2.9] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
Abstract
BACKGROUND Validated outcome measures in dermatology help standardize and improve patient care. A scoring system of skin disease severity in dermatomyositis known as the Cutaneous Dermatomyositis Disease Area and Severity Index (CDASI) has been developed. OBJECTIVES To simplify and improve the tool for clinical research and care, we modified the CDASI and validated the new version, v2. METHODS The original CDASI has four activity and two damage measures. The modified CDASI has three activity and two damage measures. The skin disease of 20 patients with dermatomyositis was evaluated by the same dermatologist using both the original and the modified CDASI. Global validation measures were implemented to assess overall skin disease state, skin disease activity and skin damage. Spearman's rho (r(sp)), adjusted for multiple observations on subjects, was used to determine the relationship between the two versions of the CDASI and their correlation with the physician global measures (PGMs). RESULTS The total score and activity and damage subscores of the original and the modified CDASI correlated perfectly with each other (r(sp) = 0.99, 1.00, 1.00). The PGM-overall skin scale correlated with the total scores (r(sp) = 0.72, r(sp) = 0.76) and activity subscores (r(sp) = 0.68, r(sp) = 0.63) but not with the damage subscores (r(sp) = 0.14, r(sp) = 0.15) of the original and the modified CDASI, respectively. However, the PGM-activity and PGM-damage scales correlated with the activity (r(sp) = 0.76, r(sp) = 0.75) and damage subscores (r(sp) = 0.90, r(sp) = 0.90), respectively, of the original and the modified CDASI. CONCLUSIONS The modified CDASI is perfectly correlated with the original CDASI. It has equally good concurrent validity with the PGM-overall skin and PGM-activity scales. The CDASI subscores have equally good concurrent validity with the PGM-activity and PGM-damage scales. We suggest that PGMs of skin disease activity and damage should be assessed separately for greater specificity. The modified CDASI is a refined and equally as useful outcome measure.
Collapse
Affiliation(s)
- M Yassaee
- Veterans Affairs Medical Center, University of Pennsylvania, Philadelphia, PA 19104-2676, USA
| | | | | | | | | | | | | |
Collapse
|
6
|
Carroll P, Coley C, McLeod D, Schellhammer P, Sweat G, Wasson J, Zietman A, Thompson I. Prostate-specific antigen best practice policy--part II: prostate cancer staging and post-treatment follow-up. Urology 2001; 57:225-9. [PMID: 11182325 DOI: 10.1016/s0090-4295(00)00994-8] [Citation(s) in RCA: 36] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
Affiliation(s)
- P Carroll
- Department of Urology, University of California, San Francisco, Medical Center, San Francisco, California, USA
| | | | | | | | | | | | | | | |
Collapse
|
7
|
Carroll P, Coley C, McLeod D, Schellhammer P, Sweat G, Wasson J, Zietman A, Thompson I. Prostate-specific antigen best practice policy--part I: early detection and diagnosis of prostate cancer. Urology 2001; 57:217-24. [PMID: 11182324 DOI: 10.1016/s0090-4295(00)00993-6] [Citation(s) in RCA: 64] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Affiliation(s)
- P Carroll
- Department of Urology, University of California, San Francisco, Medical Center, San Francisco, California, USA
| | | | | | | | | | | | | | | |
Collapse
|
8
|
Coley C, Woodward R, Johansson AM, Strange PG, Naylor LH. Effect of multiple serine/alanine mutations in the transmembrane spanning region V of the D2 dopamine receptor on ligand binding. J Neurochem 2000; 74:358-66. [PMID: 10617140 DOI: 10.1046/j.1471-4159.2000.0740358.x] [Citation(s) in RCA: 33] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022]
Abstract
Three conserved serine residues (Ser193, Ser194, and Ser197) in transmembrane spanning region (TM) V of the D2 dopamine receptor have been mutated to alanine, individually and in combination, to explore their role in ligand binding and G protein coupling. The multiple Ser -->Ala mutations had no effect on the binding of most antagonists tested, including [3H]spiperone, suggesting that the multiple mutations did not affect the overall conformation of the receptor protein. Double or triple mutants containing an Ala197 mutation showed a decrease in affinity for domperidone, whereas Ala193 mutants showed an increased affinity for a substituted benzamide, remoxipride. However, dopamine showed large decreases in affinity (>20-fold) for each multiple mutant receptor containing the Ser193Ala mutation, and the high-affinity (coupled) state of the receptor (in the absence of GTP) could not be detected for any of the multiple mutants. A series of monohydroxylated phenylethylamines and aminotetralins was tested for their binding to the native and multiple mutant D2 dopamine receptors. The results obtained suggest that Ser193 interacts with the hydroxyl of S-5-hydroxy-2-dipropylaminotetralin (OH-DPAT) and Ser197 with the hydroxyl of R-5-OH-DPAT. We predict that Ser193 interacts with the hydroxyl of R-7-OH-DPAT and the 3-hydroxyl (m-hydroxyl) of dopamine. Therefore, the conserved serine residues in TMV of the D2 dopamine receptor are involved in hydrogen bonding interactions with selected antagonists and most agonists tested and also enable agonists to stabilise receptor-G protein coupling.
Collapse
Affiliation(s)
- C Coley
- Department of Biosciences, University of Kent at Canterbury, England, UK
| | | | | | | | | |
Collapse
|
9
|
Woodward R, Coley C, Daniell S, Naylor LH, Strange PG. Investigation of the role of conserved serine residues in the long form of the rat D2 dopamine receptor using site-directed mutagenesis. J Neurochem 1996; 66:394-402. [PMID: 8522980 DOI: 10.1046/j.1471-4159.1996.66010394.x] [Citation(s) in RCA: 50] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/31/2023]
Abstract
Three serine residues (Ser193, Ser194, Ser197) in the fifth transmembrane-spanning region of the D2 dopamine receptor have been mutated separately to alanine and the effects of the mutations determined in ligand-binding experiments with [3H] spiperone. For many antagonists the mutations had little effect, showing that the overall conformation of the mutant receptors was similar to that of the native, although there were effects on the binding of certain antagonists. The effect of the mutations on agonist binding to the free receptor (uncoupled from G proteins) was determined in the presence of GTP (100 microM). This showed that there was no single mode of binding of catecholamine agonists to the receptor and that all three serine residues can participate in the binding of some agonists, possibly through hydrogen bonds to the catechol hydroxyl groups. Coupling of the mutant receptors to G proteins was assessed from agonist-binding curves in the absence of GTP, when higher and lower affinity agonist-binding sites were seen. Receptor/G protein coupling was generally unaffected by the Ala193 and Ala194 mutations, but the Ala197 mutation eliminated receptor/G protein coupling for some agonists. These data show that the interactions of agonists with the free and coupled forms of the receptor are different.
Collapse
Affiliation(s)
- R Woodward
- Research School of Biosciences, University, Canterbury, Kent, England
| | | | | | | | | |
Collapse
|
10
|
Affiliation(s)
- L Naylor
- Research School of Biosciences, University of Kent, Canterbury, U.K
| | | | | | | | | |
Collapse
|
11
|
Affiliation(s)
- C Coley
- Research School of Biosciences, University of Kent at Canterbury, U.K
| | | | | | | |
Collapse
|
12
|
|