Computerized learning machines applied to chemical problems.  Molecular formula determination from low resolution mass spectrometry

Jurs, Peter C.; Kowalski, Bruce R.; Isenhour, T. L.

doi:10.1021/ac60270a002

Cited by 140 publications

(36 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several of the very first papers that tried to use multivariate data analysis for chemical problems deal with the automatic recognition of substance classes from low resolution mass spectra (Crawford & Morrison, 1968;Jurs, Kowalski, & Isenhour, 1969). Classification of the presence or absence of substructures based on mass spectral data has found great interest and has been suggested as a tool in systematic structure elucidation of organic molecules (Chapman, 1993;Klawun & Wilkins, 1996;Varmuza & Werther, 1996;Varmuza, 2000).…”

Section: A Overviewmentioning

confidence: 99%

Exploration of anthropological specimens by GC‐MS and chemometrics

Вармуза

Makristathis

Schwarzmeier

et al. 2004

Mass Spectrometry Reviews

View full text Add to dashboard Cite

Anthropological specimens combine a variety of unfavorable characteristics, rendering their evaluation an analytical challenge. Their remarkable status is primarily based on two characteristics: (i) these very rare samples of human origin are testimonies of human history and are, therefore, available only in minute amounts for analytical purposes, and (ii) the analysis of these samples is extremely limited by the decomposition of molecules, which are easily detected in living organisms, such as nucleic acids and proteins, but are subject to rapid post-mortem decay. In this article, we review the methods and results of archaeometry, emphasizing the role of MS combined with chemometrics. Focusing on experimental results for fatty acid profiles, specimens from mummies from different civilizations were compared. Considering in particular the Tyrolean Iceman, the application of chemometric methods to GC-MS data recovers essential information about the preservation and the storage conditions of mummies.

show abstract

Section: A Overviewmentioning

confidence: 99%

Exploration of anthropological specimens by GC‐MS and chemometrics

Вармуза

Makristathis

Schwarzmeier

et al. 2004

Mass Spectrometry Reviews

View full text Add to dashboard Cite

show abstract

“…Molecular recognition through hybridization of complementary base pairs allows matching of data to form symmetrical internal loops if incorrectly matched. Symmetric internal loops of DNA [41,42,43] are used to correlate the differences in training instances. This physical DNA structure is used to determine the degree of matching between two complementary strands for pattern matching.…”

Section: Learning With Enzymatic Weight Updatementioning

confidence: 99%

Machine Learning Algorithm for DNA-Based Molecular Ligands

Baek¹,

Lee²,

Lee³

et al. 2019

Preprint

View full text Add to dashboard Cite

Recent research in DNA nanotechnology has demonstrated that biological substrates can be used for computing at a molecular level. However, in vitro demonstrations of DNA computations use preprogrammed, rule-based methods which lack the adaptability that may be essential in developing molecular systems that function in dynamic environments. Here, we introduce an in vitro molecular algorithm that ‘learns’ molecular models from training data, opening the possibility of ‘machine learning’ in wet molecular systems. Our algorithm enables enzymatic weight update by targeting internal loop structures in DNA and ensemble learning, based on the hypernetwork model. This novel approach allows massively parallel processing of DNA with enzymes for specific structural selection for learning in an iterative manner. We also introduce an intuitive method of DNA data construction to dramatically reduce the number of unique DNA sequences needed to cover the large search space of feature sets. By combining molecular computing and machine learning the proposed algorithm makes a step closer to developing molecular computing technologies for future access to more intelligent molecular systems.

show abstract

“…This is an especially important feature in the environmental field. Those interested in the details of the procedures will want to consult the reference works used in the development of the ADAPT program [Tou and Gonzalez, 1975;Jurs et al, 1969;Morgan and Deming, 1974;Ritter et al, 19751. In addition, the actual statistical and pattern recognition routines used were obtained from Dixon [ 19771. The last step in the ADAPT analysis of a database is feature selection.…”

Section: Alvmentioning

confidence: 99%

Structure‐activity relationships (SARs) among mutagens and carcinogens: A review

1986

View full text Add to dashboard Cite

This review is an introduction to methods for evaluating structure-activity relationships (SARs), and, in particular, to those methods that have been applied to study mutagenicity and carcinogenicity. A brief history and some background material on the earliest attempts to correlate molecular structure and biological activity are included. Most of the discussion focuses on modern methods utilizing extrathermodynamic and physical property variables such as the Hansch method and SIMCA, and approaches based on molecular connectivity such as the ADAPT, CASE, and Enslein methods. In general, the latter class is potentially the most useful in the study of the large and structurally diverse databases so often encountered in the study of mutagenicity and carcinogenicity. They also are not very sensitive to lab-to-lab variances in reported activities and outright misclassifications in activities of some compounds. This is chiefly because the statistical treatments used in these methods tend to dilute the importance of outliers. The methods using physicochemical and extrathermodynamic variables are especially important in relatively small, congeneric databases and can help fine-tune the role of physicochemical properties in mechanistic hypotheses. All of the above methods have been used to look at mutagenicity and carcinogenicity and some of the results reported in the literature are reviewed here. As far as specific methods go, ADAPT, CASE, SIMCA and the Enslein approach all seem to have similar classification powers (in the range of 75-95%), depending very much on the database studied. The emphasis in this review is on showing that the use of these computer-aided storage, retrieval and analysis techniques is a timely approach to predicting and even understanding the toxicity of environmental substances. However, each of the methods discussed is still under development, and their potential usefulness for predictive purposes is still being explored.

show abstract

Computerized learning machines applied to chemical problems. Molecular formula determination from low resolution mass spectrometry

Cited by 140 publications

References 8 publications

Exploration of anthropological specimens by GC‐MS and chemometrics

Exploration of anthropological specimens by GC‐MS and chemometrics

Machine Learning Algorithm for DNA-Based Molecular Ligands

Structure‐activity relationships (SARs) among mutagens and carcinogens: A review

Contact Info

Product

Resources

About