Broomfield, CO, United States
Broomfield, CO, United States
SEARCH FILTERS
Time filter
Source Type

A programmed computer functioning as a classifier operates on mass spectral data obtained from a blood-based patient sample to predict indolence or aggressiveness of prostate cancer. Methods of generating the classifier and conducting a test on a blood-based sample from a prostate cancer patient using the classifier are described.


A method is disclosed of predicting cancer patient response to immune checkpoint inhibitors, e.g., an antibody drug blocking ligand activation of programmed cell death 1 (PD-1) or CTLA4. The method includes obtaining mass spectrometry data from a blood-based sample of the patient, obtaining integrated intensity values in the mass spectrometry data of a multitude of pre-determined mass-spectral features; and operating on the mass spectral data with a programmed computer implementing a classifier. The classifier compares the integrated intensity values with feature values of a training set of class-labeled mass spectral data obtained from a multitude of melanoma patients with a classification algorithm and generates a class label for the sample. A class label early or the equivalent predicts the patient is likely to obtain relatively less benefit from the antibody drug and the class label late or the equivalent indicates the patient is likely to obtain relatively greater benefit from the antibody drug.


A test to identify whether a lung patient is likely to benefit from combination therapy in the form of an epidermal growth factor receptor inhibitor (EGFR-I) and a monoclonal antibody drug targeting hepatocyte growth factor (HGF) as compared to EGFR-I monotherapy. The test makes use of a mass spectrum obtained from a serum or plasma sample and a computer configured as a classifier operating on the mass spectrum and a training set in the form of class-labeled mass spectra from other cancer patients. The computer classifier executes a classification algorithm, such as K-nearest neighbor, and assigns a class label to the serum or plasma sample. Samples classified as Poor or the equivalent are associated with patients which are likely to benefit from the combination therapy more than from EGFR-I monotherapy. The invention also includes improved methods of treating patients predicted by the test.


A method of analyzing a biological sample, for example serum or other blood-based samples, using a MALDI-TOF mass spectrometer instrument is described. The method includes the steps of applying the sample to a sample spot on a MALDI-TOF sample plate and directing more than 20,000 laser shots to the sample at the sample spot and collecting mass-spectral data from the instrument. In some embodiments at least 100,000 laser shots and even 500,000 shots are directed onto the sample. It has been discovered that this approach, referred to as deep-MALDI, leads to a reduction in the noise level in the mass spectra and that a significant amount of additional spectral information can be obtained from the sample. Moreover, peaks visible at lower number of shots become better defined and allow for more reliable comparisons between samples.


A test for predicting whether a non-small-cell lung cancer patient is more likely to benefit from an EGFR-I as compared to chemotherapy uses a computer-implemented classifier operating on a mass spectrum of a blood-based sample obtained from the patient. The classifier makes use of a training set which includes mass spectral data from blood-based samples of other cancer patients who are members of a class of patients predicted to have overall survival benefit on EGFRI-Is, e.g., those patients testing VS Good under the test described in U.S. Pat. No. 7,736,905. This class-labeled group is further subdivided into two subsets, i.e., those patients which exhibited early (class label early) and late (class label late) progression of disease after administration of the EGFR-I in treatment of cancer.


Classifier generation methods are described in which features used in classification (e.g., mass spectral peaks) are selected, or deselected using bagged filtering. A development sample set is split into two subsets, one of which is used as a training set the other of which is set aside. We define a classifier (e.g., K-nearest neighbor, decision tree, margin-based classifier or other) using the training subset and at least one of the features (or subsets of two or more features in combination). We apply the classifier to a subset of samples. A filter is applied to the performance of the classifier on the sample subset and the at least one feature is added to a filtered feature list if the classifier performance passes the filter. We do this for many different realizations of the separation of the development sample set into two subsets, and, for each realization, different features or sets of features in combination. After all the iterations are performed the filtered feature list is used to either select features, or deselect features, for a final classifier.


A programmed computer functioning as a classifier operates on mass spectral data obtained from a blood-based patient sample to predict indolence or aggressiveness of prostate cancer. Methods of generating the classifier and conducting a test on a blood-based sample from a prostate cancer patient using the classifier are described.


Hepatocellular carcinoma (HCC) is detected in a patient with liver disease. Mass spectrometry data from a blood-based sample from the patient is compared to a reference set of mass-spectrometry data from a multitude of other patients with liver disease, including patients with and without HCC, in a general purpose computer configured as a classifier. The classifier generates a class label, such as HCC or No HCC, for the test sample. A laboratory system for early detection of HCC in patients with liver disease is also disclosed. Alternative testing strategies using AFP measurement and a reference set for classification in the form of class-labeled mass spectral data from blood-based samples of lung cancer patients are also described, including multi-stage testing.


A testing method for identification whether a cancer patient is a member of a group or class of cancer patients that are not likely to benefit from administration of a platinum-based chemotherapy agent, e.g., cisplatin, carboplatin or analogs thereof, either alone or in combination with other non-platinum chemotherapy agents, e.g., gemcitabine and paclitaxel. This identification can be made in advance of treatment. The method uses a mass spectrometer obtaining a mass spectrum of a blood-based sample from the patient, and a computer operating as a classifier and using a stored training set comprising class-labeled spectra from other cancer patients.


A method for classifier generation includes a step of obtaining data for classification of a multitude of samples, the data for each of the samples consisting of a multitude of physical measurement feature values and a class label. Individual mini-classifiers are generated using sets of features from the samples. The performance of the mini-classifiers is tested, and those that meet a performance threshold are retained. A master classifier is generated by conducting a regularized ensemble training of the retained/filtered set of mini-classifiers to the classification labels for the samples, e.g., by randomly selecting a small fraction of the filtered mini-classifiers (drop out regularization) and conducting logistical training on such selected mini-classifiers. The set of samples are randomly separated into a test set and a training set. The steps of generating the mini-classifiers, filtering and generating a master classifier are repeated for different realizations of the separation of the set of samples into test and training sets, thereby generating a plurality of master classifiers. A final classifier is defined from one or a combination of more than one of the master classifiers.

Loading Biodesix collaborators
Loading Biodesix collaborators