Life Technologies Corporation

Yong Chu

Xin Mathers

Jeffrey A Marks

Jacob K Freudenthal

David C Woo

Hon Siu Shin

Thomas Wessel

Manjula Aliminati

Stephanie Jo Schneider

Yongzhi Chen

Nivedita Majumbar

Kevin Papenfuss

Rylan Schaeffer

Way Xuang Lee

Chin Yong Koo

Zeqi Tan

Lian Seng Loh

Zeng Wei Chu

Michael Uy

Kok Siong Teo

Lik Seng Lau

Huei Steven Yeo

Mauro Aguanno

Tiong Han Toh

Mingsong Chen

Kuan Moon Boo

Wei Fuh Teo

Soo Yong Lau

Stephanie Schneider

David Woo

A system and methods are provided for image driven quality control for array based PCR. The system comprises a PCR unit, a reaction array plate, a convolutional neural network (CNN) configured to receive a sequence of images of the reaction array plate in the PCR system, and an output of the CNN coupled to a control for the reaction array plate. The method comprises applying a sequence of images from a plurality of subarrays of the reaction array plate to a plurality of CNNs during operation of the PCR system on the reaction plate array, operating the CNNs to generate failure mode predictions for the reaction plate based on the sequence of images, and coupling an output of the CNNs to one or more of a setting for manufacture of the reaction array plate or to control the PCR system.

Image driven quality control for array-based PCR

A method of automatically sequencing or basecalling one or more DNA (deoxyribonucleic acid) molecules of a biological sample is described. The method comprises using a capillary electrophoresis genetic analyzer to measure the biological sample to obtain at least one input trace comprising digital data corresponding to fluorescence values for a plurality of scans. Scan labelling probabilities for the plurality of scans are generated using a trained artificial neural network comprising a plurality of layers including convolutional layers. A basecall sequence comprising a plurality of basecalls for the one or more DNA molecules based on the scan labelling probabilities for the plurality of scans is determined.

Basecaller with dilated convolutional neural network

In one exemplary embodiment, a method for validating an instrument is provided. The method includes receiving amplification data from a validation plate to generate a plurality of amplification curves. The validation plate includes a sample of a first quantity and a second quantity, and each amplification curve includes an exponential region. The method further includes determining a set of fluorescence thresholds based on the exponential regions of the plurality of amplification curves and determining, for each fluorescence threshold of the set, a first set of cycle threshold (C) values of amplification curves generated from the samples of the first quantity and a second set of Cvalues of amplification curves generated from the samples of the second quantity. The method includes calculating if the first and second quantities are sufficiently distinguishable based on Cvalues at each of the plurality of fluorescence thresholds.

Methods and systems for instrument validation

Some embodiments describe a computer-implemented method for calibrating a fluorescent dye. The method can comprise imaging a sample holder, loaded into an instrument, at more than one channel. The sample holder can comprise a plurality of reaction sites and more than one dye type, with each dye occupying more than one reaction site. The method can further comprise identifying a peak channel for each dye on the sample holder, normalizing each channel to the peak channel for each dye, and producing a dye matrix that can comprise a set of dye reference values.

System and methods for calibrating binding dyes

A method for analyzing biological reaction systems is provided. The method includes receiving an image of a substrate including a plurality of reaction sites after a biological reaction has taken place. Next, the method includes removing a noise background from the first image. The method includes determining an initial position of each reaction site based on an intensity threshold to generate a initial position set, then refining the initial position set of each reaction site based on an expected pattern of locations of the plurality of reaction sites to generate a first refined position set. The method further includes determining a presence or absence of a fluorescent emission from each reaction site based on the first refined position set and the first image.

Methods and systems for analyzing biological reaction systems

In one exemplary embodiment, a method for calibrating an instrument is provided. The instrument includes an optical system capable of imaging florescence emission from a plurality of reaction sites. The method includes performing a region-of-interest (ROI) calibration to determine reaction site positions in an image. The method further includes performing a pure dye calibration to determine the contribution of a fluorescent dye used in each reaction site by comparing a raw spectrum of the fluorescent dye to a pure spectrum calibration data of the fluorescent dye. The method further includes performing an instrument normalization calibration to determine a filter normalization factor. The method includes performing an RNase P validation to validate the instrument is capable of distinguishing between two different quantities of sample.

Methods and systems for biological instrument calibration

The present teachings relate to a method and system for determining Regions of Interest (ROI) for one or more biological samples in a laboratory instrument. The method can include an optical system capable of imaging florescence emission from a plurality of sample wells. An initial ROI, its center location and size can be estimated from the fluorescence detected from each well. From this information the average size of the ROIs can be determined and global gridding models can be derived to better locate each of the ROIs. The global gridding models can then be applied to the ROIs to improve the precision of the ROI center locations. Sample wells not originally providing fluorescence ROIs can be recovered through the use of mapping functions. The radius of each ROI can then be adjusted to improve the signal-to-noise ratio of the optical system.

Methods and systems for determining optical regions of interest

Growing community of inventors

Castro Valley, CA, United States of America

Yong Chu