公开(公告)号：US11694769B2

公开(公告)日：2023-07-04

申请号：US16226575

申请日：2018-12-19

Applicant: BIOINFORMATICS SOLUTIONS INC.

Inventor： Baozhen Shan ,  Ngoc Hieu Tran ,  Ming Li ,  Lei Xin ,  Rui Qiao ,  Xin Chen ,  Chuyi Liu

IPC: G01N33/48 ,  G01N33/50 ,  G16B40/10 ,  H01J49/00 ,  G01N33/68 ,  G16B30/20 ,  G16B40/20 ,  G06N3/02

CPC classification number: G16B40/10 ,  G01N33/6818 ,  G01N33/6848 ,  G06N3/02 ,  G16B30/20 ,  G16B40/20 ,  H01J49/0036

Abstract: The present systems and methods introduce deep learning to de novo peptide sequencing from tandem mass spectrometry data, and in particular mass spectrometry data obtained by data-independent acquisition. The systems and methods achieve improvements in sequencing accuracy over existing systems and methods and enables complete assembly of novel protein sequences without assisting databases. To sequence peptides from mass spectrometry data obtained by data-independent acquisition, precursor profiles representing intensities of one or more precursor ion signals associated with a precursor retention time and fragment ion spectra representing signals from fragment ions and fragment retention times are fed into a neural network.

公开(公告)号：US20240013860A1

公开(公告)日：2024-01-11

申请号：US18347105

申请日：2023-07-05

Applicant: BIOINFORMATICS SOLUTIONS INC.

Inventor： Hieu TRAN ,  Ming LI

IPC: G16B20/30 ,  G16B20/20 ,  G01N33/68

CPC classification number: G16B20/30 ,  G16B20/20 ,  G01N33/6878

Abstract: Personalized machine learning systems and methods are provided to predict the collective response of a patient's CD8+ T cells by modeling positive and negative selection processes. For each individual patient, HLA-I self peptides were used as negative selection, and allele-matched immunogenic T cell epitopes as positive selection. The negative and positive peptides were used to train a binary classification model, which was then applied to predict the immunogenicity of candidate neoantigens of that patient.

公开(公告)号：US11573239B2

公开(公告)日：2023-02-07

申请号：US16037949

申请日：2018-07-17

Applicant: BIOINFORMATICS SOLUTIONS INC.

Inventor： Baozhen Shan ,  Ngoc Hieu Tran ,  Ming Li ,  Lei Xin ,  Xianglilan Zhang

IPC: G01N33/48 ,  G01N33/50 ,  G01N33/68 ,  G06F17/16 ,  G16B20/00 ,  G16B40/00 ,  G16B50/00 ,  G16B30/20 ,  G16B40/10 ,  G16B40/20 ,  G16B50/20 ,  G16B50/10

Abstract: The present systems and methods introduce deep learning to de novo peptide sequencing from tandem mass spectrometry data. The systems and methods achieve improvements in sequencing accuracy over existing systems and methods and enables complete assembly of novel protein sequences without assisting databases. The present systems and methods are re-trainable to adapt to new sources of data and provides a complete end-to-end training and prediction solution, which is advantageous given the growing massive amount of data. The systems and methods combine deep learning and dynamic programming to solve optimization problems.

公开(公告)号：US20170336419A1

公开(公告)日：2017-11-23

申请号：US15599431

申请日：2017-05-18

Applicant: BIOINFORMATICS SOLUTIONS INC.

Inventor： Ngoc Hieu TRAN ,  Mohammad Ziaur RAHMAN ,  Lin HE ,  Lei XIN ,  Baozhen SHAN ,  Ming LI

IPC: G01N33/68 ,  G06F19/22 ,  G06F19/26

CPC classification number: G01N33/6818 ,  G01N33/6848 ,  G01N33/6854 ,  G01N2560/00 ,  G06F19/22 ,  G06F19/24 ,  G06F19/26

Abstract: Methods and systems for determining amino acid sequence of a polypeptide or protein from mass spectrometry data is provided, using a weighted de Bruijn graph. Extracted and purified protein is cleaved into a mixture of peptide and then analyzed using mass spectrometry. A list of peptide sequences is derived from mass spectrometry fragment data by de novo sequencing, and amino acid confidence scores are determined from peak fragment ion intensity. A weighted de Bruijn graph is constructed for the list of peptide sequences having node weights defined by k−1 mer confidence scores. At least one contig is assembled from the de Bruijn graph by identifying node weights having the highest k-1 mer confidence scores.

公开(公告)号：US11644470B2

公开(公告)日：2023-05-09

申请号：US16846817

申请日：2020-04-13

Applicant: BIOINFORMATICS SOLUTIONS INC.

Inventor： Rui Qiao ,  Ngoc Hieu Tran ,  Lei Xin ,  Xin Chen ,  Baozhen Shan ,  Ali Ghodsi ,  Ming Li

IPC: G01N33/00 ,  G01N33/68 ,  G16B40/00 ,  G16B20/00 ,  G16B30/00

CPC classification number: G01N33/6848 ,  G16B20/00 ,  G16B30/00 ,  G16B40/00

Abstract: The present systems and methods are directed to de novo identification of peptide sequences from tandem mass spectrometry data. The systems and methods uses unconverted mass spectrometry data from which features are extracted. Using unconverted mass spectrometry data reduces the loss of information and provides more accurate sequencing of peptides. The systems and methods combine deep learning and neural networks to sequencing of peptides.

公开(公告)号：US20200243164A1

公开(公告)日：2020-07-30

申请号：US16775947

申请日：2020-01-29

Applicant: BIOINFORMATICS SOLUTIONS INC.

Inventor： Rui Qiao ,  Ngoc Hieu Tran ,  Lei Xin ,  Xin Chen ,  Baozhen Shan ,  Ming Li

IPC: G16B40/10 ,  G16B30/00 ,  G16B25/10 ,  G16B50/30 ,  G01N33/68

Abstract: The present systems and workflows identify neoantigens for cancer immunotherapy by introducing deep learning to de novo peptide sequencing from tandem mass spectrometry data. The systems and workflow allows for patient specific identification of neoantigens for personalized immunotherapy.

公开(公告)号：US10309968B2

公开(公告)日：2019-06-04

申请号：US15599431

申请日：2017-05-18

Applicant: BIOINFORMATICS SOLUTIONS INC.

Inventor： Ngoc Hieu Tran ,  Mohammad Ziaur Rahman ,  Lin He ,  Lei Xin ,  Baozhen Shan ,  Ming Li

IPC: G01N33/68 ,  G06F19/22 ,  G06F19/26 ,  G06F19/24

Abstract: Methods and systems for determining amino acid sequence of a polypeptide or protein from mass spectrometry data is provided, using a weighted de Bruijn graph. Extracted and purified protein is cleaved into a mixture of peptide and then analyzed using mass spectrometry. A list of peptide sequences is derived from mass spectrometry fragment data by de novo sequencing, and amino acid confidence scores are determined from peak fragment ion intensity. A weighted de Bruijn graph is constructed for the list of peptide sequences having node weights defined by k−1 mer confidence scores. At least one contig is assembled from the de Bruijn graph by identifying node weights having the highest k−1 mer confidence scores.

公开(公告)号：US20190147983A1

公开(公告)日：2019-05-16

申请号：US16226575

申请日：2018-12-19

Applicant: BIOINFORMATICS SOLUTIONS INC.

Inventor： Baozhen Shan ,  Ngoc Hieu Tran ,  Ming Li ,  Lei Xin ,  Rui Qiao ,  Xin Chen ,  Chuyi Liu

IPC: G16B40/10 ,  H01J49/00

Abstract: The present systems and methods introduce deep learning to de novo peptide sequencing from tandem mass spectrometry data, and in particular mass spectrometry data obtained by data-independent acquisition. The systems and methods achieve improvements in sequencing accuracy over existing systems and methods and enables complete assembly of novel protein sequences without assisting databases. To sequence peptides from mass spectrometry data obtained by data-independent acquisition, precursor profiles representing intensities of one or more precursor ion signals associated with a precursor retention time and fragment ion spectra representing signals from fragment ions and fragment retention times are fed into a neural network.

公开(公告)号：US20190018019A1

公开(公告)日：2019-01-17

申请号：US16037949

申请日：2018-07-17

Applicant: BIOINFORMATICS SOLUTIONS INC.

Inventor： Baozhen Shan ,  Ngoc Hieu Tran ,  Ming Li ,  Lei Xin ,  Xianglilan Zhang

IPC: G01N33/68 ,  G06F19/18 ,  G06F19/24 ,  G06F19/28 ,  G06F17/16

Abstract: The present systems and methods introduce deep learning to de novo peptide sequencing from tandem mass spectrometry data. The systems and methods achieve improvements in sequencing accuracy over existing systems and methods and enables complete assembly of novel protein sequences without assisting databases. The present systems and methods are re-trainable to adapt to new sources of data and provides a complete end-to-end training and prediction solution, which is advantageous given the growing massive amount of data. The systems and methods combine deep learning and dynamic programming to solve optimization problems.

公开(公告)号：US20200326348A1

公开(公告)日：2020-10-15

申请号：US16846817

申请日：2020-04-13

Applicant: BIOINFORMATICS SOLUTIONS INC.

Inventor： Rui QIAO ,  Ngoc Hieu Tran ,  Lei XIN ,  Xin CHEN ,  Baozhen Shan ,  Ali GHODSI ,  Ming LI

IPC: G01N33/68 ,  G16B30/00 ,  G16B20/00 ,  G16B40/00

Abstract: The present systems and methods are directed to de novo identification of peptide sequences from tandem mass spectrometry data. The systems and methods uses unconverted mass spectrometry data from which features are extracted. Using unconverted mass spectrometry data reduces the loss of information and provides more accurate sequencing of peptides. The systems and methods combine deep learning and neural networks to sequencing of peptides.