Systems and methods for predicting the efficacy of cancer therapy

A system for generating a therapy indicator for use in assessing responsiveness to cancer therapy for a subject, the system including one or more electronic processing devices that:

• a) obtain subject data indicative of a sequence of a nucleic acid molecule from the subject;
• b) analyze the subject data to identify single nucleotide variations (SNVs) within the nucleic acid molecule;
• c) determine a plurality of metrics using the identified SNVs, the plurality of metrics including metrics from three or more metric groups selected from:
• i) a coding metric group including metrics associated with SNVs in a coding region of the nucleic acid molecule;
• ii) a non-coding metric group including metrics associated with SNVs in a non-coding region of the nucleic acid molecule;
• iii) a genomic metric group including metrics associated with SNVs in coding and non-coding regions of the nucleic acid molecule;
• iv) a codon context metric group including metrics associated with a codon context of SNVs;
• v) a transition/transversion metric group including metrics associated with SNVs that are transitions or transversions;
• vi) a synonymous/non-synonymous metric group including metrics associated with SNVs that are synonymous or non-synonymous;
• vii) a strand bias metric group including metrics associated with strand bias of SNVs;
• viii) a strand specific metric group that includes metrics associated with SNVs on a specific strand;
• ix) an AT/GC metric group that includes metrics associated with SNVs in which an adenine and thymine, and/or guanine and cytidine have been targeted;
• x) a motif metric group including metrics associated with SNVs in specific motifs;
• and,
• xi) a motif-independent metric group including metrics associated with SNVs irrespective of motif;
• and,
• d) apply the plurality of metrics to at least one computational model to determine a therapy indicator indicative of a predicted responsiveness to cancer therapy, the at least one computational model embodying a relationship between a responsiveness to cancer therapy and the plurality of metrics and being derived by applying machine learning to a plurality of reference metrics obtained from reference subjects having a known responsiveness to cancer therapy.

A system for use in calculating at least one computational model, the at least one computational model being used for generating therapy indicator for use in assessing responsiveness to cancer therapy for a subject, the system including one or more electronic processing devices that:

• a) for each of a plurality of reference subjects:
• i) obtain reference subject data indicative of:
• (1) a sequence of a nucleic acid molecule from the reference subject;
• and,
• (2) a responsiveness to cancer therapy;
• ii) analyze the reference subject data to identify single nucleotide variations (SNVs) within the nucleic acid molecule;
• iii) determine a plurality of metrics using the identified SNVs, the plurality of metrics including metrics from one or more of metric groups including:
• 1) a motif metric group including metrics associated with SNVs in specific motifs;
• 2) a codon context metric group including metrics associated with a codon context of SNVs;
• 3) a transition/transversion metric group including metrics associated with SNVs that are transitions or transversions;
• 4) a synonymous/non-synonymous metric group including metrics associated with SNVs that are synonymous or non-synonymous;
• 5) a strand bias metric group including metrics associated with strand bias of SNVs;
• 6) a strand specific metric group that includes metrics associated with SNVs on a specific strand;
• and
• 7) an AT/GC metric group that includes metrics associated with SNVs in which an adenine and thymine, and/or guanine and cytidine have been targeted;
• and,
• b) use the plurality of reference metrics and known responsiveness for a number of reference subjects to train at least one computational model, the at least one computational model embodying a relationship between a responsiveness to cancer therapy and the plurality of metrics.

A system for use in calculating at least one computational model, the at least one computational model being used for generating therapy indicator for use in assessing responsiveness to cancer therapy for a subject, the system including one or more electronic processing devices that:

• a) for each of a plurality of reference subjects:
• i) obtain reference subject data indicative of:
• (1) a sequence of a nucleic acid molecule from the reference subject;
• and,
• (2) a responsiveness to cancer therapy;
• ii) analyze the reference subject data to identify single nucleotide variations (SNVs) within the nucleic acid molecule;
• iii) determine a plurality of metrics using the identified SNVs, the plurality of metrics including metrics from three or more of metric groups including:
• 1) a coding metric group including metrics associated with SNVs in a coding region of the nucleic acid molecule;
• 2) a non-coding metric group including metrics associated with SNVs in a non-coding region of the nucleic acid molecule;
• 3) a genomic metric group including metrics associated with SNVs in coding and non-coding regions of the nucleic acid molecule;
• 4) a codon context metric group including metrics associated with a codon context of SNVs;
• 5) a transition/transversion metric group including metrics associated with SNVs that are transitions or transversions;
• 6) a synonymous/non-synonymous metric group including metrics associated with SNVs that are synonymous or non-synonymous;
• 7) a strand bias metric group including metrics associated with strand bias of SNVs;
• 8) a strand specific metric group that includes metrics associated with SNVs on a specific strand;
• 9) an AT/GC metric group that includes metrics associated with SNVs in which an adenine and thymine, and/or guanine and cytidine have been targeted;
• 10) a motif metric group including metrics associated with SNVs in specific motifs;
• and,
• 11) a motif-independent metric group including metrics associated with SNVs irrespective of motif;
• and,
• b) use the plurality of reference metrics and known responsiveness for a number of reference subjects to train at least one computational model, the at least one computational model embodying a relationship between a responsiveness to cancer therapy and the plurality of metrics.

A method for generating therapy indicator for use in assessing responsiveness to cancer therapy for a subject, the method including, in one or more electronic processing devices:

• a) obtaining subject data indicative of a sequence of a nucleic acid molecule from the subject;
• b) analyzing the subject data to identify single nucleotide variations (SNVs) within the nucleic acid molecule;
• c) determining a plurality of metrics using the identified SNVs, the plurality of metrics including metrics from one or more of metric groups including:
• i) a motif metric group including metrics associated with SNVs in specific motifs;
• ii) a codon context metric group including metrics associated with a codon context of SNVs;
• iii) a transition/transversion metric group including metrics associated with SNVs that are transitions or transversions;
• iv) a synonymous/non-synonymous metric group including metrics associated with SNVs that are synonymous or non-synonymous;
• v) a strand bias metric group including metrics associated with strand bias of SNVs;
• vi) a strand specific metric group that includes metrics associated with SNVs on a specific strand;
• and
• vii) an AT/GC metric group that includes metrics associated with SNVs in which an adenine and thymine, and/or guanine and cytidine have been targeted;
• and,
• d) applying the plurality of metrics to at least one computational model to determine a therapy indicator indicative of a predicted responsiveness to cancer therapy, the at least one computational model embodying a relationship between a responsiveness to cancer therapy and the plurality of metrics and being derived by applying machine learning to a plurality of reference metrics obtained from reference subjects having a known responsiveness to cancer therapy.

A method for generating therapy indicator for use in assessing responsiveness to cancer therapy for a subject, the method including, in one or more electronic processing devices:

• a) obtaining subject data indicative of a sequence of a nucleic acid molecule from the subject;
• b) analyzing the subject data to identify single nucleotide variations (SNVs) within the nucleic acid molecule;
• c) determining a plurality of metrics using the identified SNVs, the plurality of metrics including metrics from three or more of metric groups including:
• i) a coding metric group including metrics associated with SNVs in a coding region of the nucleic acid molecule;
• ii) a non-coding metric group including metrics associated with SNVs in a non-coding region of the nucleic acid molecule;
• iii) a genomic metric group including metrics associated with SNVs in coding and non-coding regions of the nucleic acid molecule;
• iv) a codon context metric group including metrics associated with a codon context of SNVs;
• v) a transition/transversion metric group including metrics associated with SNVs that are transitions or transversions;
• vi) a synonymous/non-synonymous metric group including metrics associated with SNVs that are synonymous or non-synonymous;
• vii) a strand bias metric group including metrics associated with strand bias of SNVs;
• viii) a strand specific metric group that includes metrics associated with SNVs on a specific strand;
• ix) an AT/GC metric group that includes metrics associated with SNVs in which an adenine and thymine, and/or guanine and cytidine have been targeted;
• x) a motif metric group including metrics associated with SNVs in specific motifs;
• and,
• xi) a motif-independent metric group including metrics associated with SNVs irrespective of motif;
• and,
• d) applying the plurality of metrics to at least one computational model to determine a therapy indicator indicative of a predicted responsiveness to cancer therapy, the at least one computational model embodying a relationship between a responsiveness to cancer therapy and the plurality of metrics and being derived by applying machine learning to a plurality of reference metrics obtained from reference subjects having a known responsiveness to cancer therapy.

A computer program product for generating therapy indicator for use in assessing responsiveness to cancer therapy for a subject, the computer program product including computer executable code, which when executed by one or more suitably programmed electronic processing devices, causes the one or more electronic processing devices to:

• a) obtain subject data indicative of a sequence of a nucleic acid molecule from the subject;
• b) analyze the subject data to identify single nucleotide variations (SNVs) within the nucleic acid molecule;
• c) determine a plurality of metrics using the identified SNVs, the plurality of metrics including metrics from one or more of metric groups including:
• i) a coding metric group including metrics associated with SNVs in a coding region of the nucleic acid molecule;
• ii) a non-coding metric group including metrics associated with SNVs in a non-coding region of the nucleic acid molecule;
• iii) a genomic metric group including metrics associated with SNVs in coding and non-coding regions of the nucleic acid molecule;
• iv) a codon context metric group including metrics associated with a codon context of SNVs;
• v) a transition/transversion metric group including metrics associated with SNVs that are transitions or transversions;
• vi) a synonymous/non-synonymous metric group including metrics associated with SNVs that are synonymous or non-synonymous;
• vii) a strand bias metric group including metrics associated with strand bias of SNVs;
• viii) a strand specific metric group that includes metrics associated with SNVs on a specific strand;
• ix) an AT/GC metric group that includes metrics associated with SNVs in which an adenine and thymine, and/or guanine and cytidine have been targeted;
• x) a motif metric group including metrics associated with SNVs in specific motifs;
• and,
• xi) a motif-independent metric group including metrics associated with SNVs irrespective of motif;
• and,
• d) apply the plurality of metrics to at least one computational model to determine a therapy indicator indicative of a predicted responsiveness to cancer therapy, the at least one computational model embodying a relationship between a responsiveness to cancer therapy and the plurality of metrics and being derived by applying machine learning to a plurality of reference metrics obtained from reference subjects having a known responsiveness to cancer therapy.

A computer program product for generating therapy indicator for use in assessing responsiveness to cancer therapy for a subject, the computer program product including computer executable code, which when executed by one or more suitably programmed electronic processing devices, causes the one or more electronic processing devices to:

• a) obtain subject data indicative of a sequence of a nucleic acid molecule from the subject;
• b) analyze the subject data to identify single nucleotide variations (SNVs) within the nucleic acid molecule;
• c) determine a plurality of metrics using the identified SNVs, the plurality of metrics including metrics from one or more of metric groups including:
• i) a coding metric group including metrics associated with SNVs in a coding region of the nucleic acid molecule;
• ii) a non-coding metric group including metrics associated with SNVs in a non-coding region of the nucleic acid molecule;
• iii) a genomic metric group including metrics associated with SNVs in coding and non-coding regions of the nucleic acid molecule;
• iv) a codon context metric group including metrics associated with a codon context of SNVs;
• v) a transition/transversion metric group including metrics associated with SNVs that are transitions or transversions;
• vi) a synonymous/non-synonymous metric group including metrics associated with SNVs that are synonymous or non-synonymous;
• vii) a strand bias metric group including metrics associated with strand bias of SNVs;
• viii) a strand specific metric group that includes metrics associated with SNVs on a specific strand;
• ix) an AT/GC metric group that includes metrics associated with SNVs in which an adenine and thymine, and/or guanine and cytidine have been targeted;
• x) a motif metric group including metrics associated with SNVs in specific motifs;
• and,
• xi) a motif-independent metric group including metrics associated with SNVs irrespective of motif;
• and,
• d) apply the plurality of metrics to at least one computational model to determine a therapy indicator indicative of a predicted responsiveness to cancer therapy, the at least one computational model embodying a relationship between a responsiveness to cancer therapy and the plurality of metrics and being derived by applying machine learning to a plurality of reference metrics obtained from reference subjects having a known responsiveness to cancer therapy.

A computer program product for use in calculating at least one computational model, the at least one computational model being used for generating therapy indicator for use in assessing responsiveness to cancer therapy for a biological subject, the computer program product including computer executable code, which when executed by one or more suitably programmed electronic processing devices, causes the one or more electronic processing devices to:

• a) for each of a plurality of reference subjects:
• i) obtain reference subject data indicative of:
• (1) a sequence of a nucleic acid molecule from the reference subject;
• and,
• (2) a responsiveness to cancer therapy;
• ii) analyze the reference subject data to identify single nucleotide variations (SNVs) within the nucleic acid molecule;
• iii) determine a plurality of metrics using the identified SNVs, the plurality of metrics including metrics from one or more of metric groups including:
• 1) a motif metric group including metrics associated with SNVs in specific motifs;
• 2) a codon context metric group including metrics associated with a codon context of SNVs;
• 3) a transition/transversion metric group including metrics associated with SNVs that are transitions or transversions;
• 4) a synonymous/non-synonymous metric group including metrics associated with SNVs that are synonymous or non-synonymous;
• 5) a strand bias metric group including metrics associated with strand bias of SNVs;
• 6) a strand specific metric group that includes metrics associated with SNVs on a specific strand;
• and
• 7) an AT/GC metric group that includes metrics associated with SNVs in which an adenine and thymine, and/or guanine and cytidine have been targeted;
• and,
• d) use the plurality of reference metrics and known responsiveness for a number of reference subjects to train at least one computational model, the at least one computational model embodying a relationship between a responsiveness to cancer therapy and the plurality of metrics.

A computer program product for use in calculating at least one computational model, the at least one computational model being used for generating therapy indicator for use in assessing responsiveness to cancer therapy for a biological subject, the computer program product including computer executable code, which when executed by one or more suitably programmed electronic processing devices, causes the one or more electronic processing devices to:

• a) for each of a plurality of reference subjects:
• i) obtain reference subject data indicative of:
• (1) a sequence of a nucleic acid molecule from the reference subject;
• and,
• (2) a responsiveness to cancer therapy;
• ii) analyze the reference subject data to identify single nucleotide variations (SNVs) within the nucleic acid molecule;
• iii) determine a plurality of metrics using the identified SNVs, the plurality of metrics including metrics from one or more of metric groups including:
• 1) a coding metric group including metrics associated with SNVs in a coding region of the nucleic acid molecule;
• 2) a non-coding metric group including metrics associated with SNVs in a non-coding region of the nucleic acid molecule;
• 3) a genomic metric group including metrics associated with SNVs in coding and non-coding regions of the nucleic acid molecule;
• 4) a codon context metric group including metrics associated with a codon context of SNVs;
• 5) a transition/transversion metric group including metrics associated with SNVs that are transitions or transversions;
• 6) a synonymous/non-synonymous metric group including metrics associated with SNVs that are synonymous or non-synonymous;
• 7) a strand bias metric group including metrics associated with strand bias of SNVs;
• 8) a strand specific metric group that includes metrics associated with SNVs on a specific strand;
• 9) an AT/GC metric group that includes metrics associated with SNVs in which an adenine and thymine, and/or guanine and cytidine have been targeted;
• 10) a motif metric group including metrics associated with SNVs in specific motifs;
• and,
• 11) a motif-independent metric group including metrics associated with SNVs irrespective of motif;
• and,
• d) use the plurality of reference metrics and known responsiveness for a number of reference subjects to train at least one computational model, the at least one computational model embodying a relationship between a responsiveness to cancer therapy and the plurality of metrics.

A method for use in calculating at least one computational model, the at least one computational model being used for generating therapy indicator for use in assessing responsiveness to cancer therapy for a biological subject, the method including, in one or more electronic processing devices:

• a) for each of a plurality of reference subjects:
• i) obtaining reference subject data indicative of:
• (1) a sequence of a nucleic acid molecule from the reference subject;
• and,
• (2) a responsiveness to cancer therapy;
• ii) analyzing the reference subject data to identify single nucleotide variations (SNVs) within the nucleic acid molecule;
• iii) determining a plurality of metrics using the identified SNVs, the plurality of metrics including metrics from one or more of metric groups including:
• 1) a motif metric group including metrics associated with SNVs in specific motifs;
• 2) a codon context metric group including metrics associated with a codon context of SNVs;
• 3) a transition/transversion metric group including metrics associated with SNVs that are transitions or transversions;
• 4) a synonymous/non-synonymous metric group including metrics associated with SNVs that are synonymous or non-synonymous;
• 5) a strand bias metric group including metrics associated with strand bias of SNVs;
• 6) a strand specific metric group that includes metrics associated with SNVs on a specific strand;
• and
• 7) an AT/GC metric group that includes metrics associated with SNVs in which an adenine and thymine, and/or guanine and cytidine have been targeted;
• and,
• b) using the plurality of reference metrics and known responsiveness for a number of reference subjects to train at least one computational model, the at least one computational model embodying a relationship between a responsiveness to cancer therapy and the plurality of metrics.

A method for use in calculating at least one computational model, the at least one computational model being used for generating therapy indicator for use in assessing responsiveness to cancer therapy for a biological subject, the method including, in one or more electronic processing devices:

• a) for each of a plurality of reference subjects:
• i) obtaining reference subject data indicative of:
• (1) a sequence of a nucleic acid molecule from the reference subject;
• and,
• (2) a responsiveness to cancer therapy;
• ii) analyzing the reference subject data to identify single nucleotide variations (SNVs) within the nucleic acid molecule;
• iii) determining a plurality of metrics using the identified SNVs, the plurality of metrics including metrics from one or more of metric groups including:
• 1) a coding metric group including metrics associated with SNVs in a coding region of the nucleic acid molecule;
• 2) a non-coding metric group including metrics associated with SNVs in a non-coding region of the nucleic acid molecule;
• 3) a genomic metric group including metrics associated with SNVs in coding and non-coding regions of the nucleic acid molecule;
• 4) a codon context metric group including metrics associated with a codon context of SNVs;
• 5) a transition/transversion metric group including metrics associated with SNVs that are transitions or transversions;
• 6) a synonymous/non-synonymous metric group including metrics associated with SNVs that are synonymous or non-synonymous;
• 7) a strand bias metric group including metrics associated with strand bias of SNVs;
• 8) a strand specific metric group that includes metrics associated with SNVs on a specific strand;
• 9) an AT/GC metric group that includes metrics associated with SNVs in which an adenine and thymine, and/or guanine and cytidine have been targeted;
• 10) a motif metric group including metrics associated with SNVs in specific motifs;
• and,
• 11) a motif-independent metric group including metrics associated with SNVs irrespective of motif;
• and,
• b) using the plurality of reference metrics and known responsiveness for a number of reference subjects to train at least one computational model, the at least one computational model embodying a relationship between a responsiveness to cancer therapy and the plurality of metrics.

A method for determining the likelihood that a subject with cancer will respond to a cancer therapy or will continue to respond to a cancer therapy, the method comprising:

• analyzing the sequence of a nucleic acid molecule from a subject with cancer to detect SNVs within the nucleic acid molecule;
• determining a plurality of metrics based on the number and/or type of SNVs detected so as to obtain a subject profile of metrics, wherein the plurality of metrics includes metrics from one or more of the following metric groups:
• i) a motif metric group including metrics associated with SNVs in specific motifs;
• ii) a codon context metric group including metrics associated with a codon context of SNVs;
• iii) a transition/transversion metric group including metrics associated with SNVs that are transitions or transversions;
• iv) a synonymous/non-synonymous metric group including metrics associated with SNVs that are synonymous or non-synonymous;
• v) a strand bias metric group including metrics associated with strand bias of SNVs;
• vi) a strand specific metric group that includes metrics associated with SNVs on a specific strand;
• and
• vii) an AT/GC metric group that includes metrics associated with SNVs in which an adenine and thymine, and/or guanine and cytidine have been targeted;
• and,
• determining the likelihood of a subject responding to cancer therapy based on a comparison between the subject profile and a reference profile of metrics.

A method for determining the likelihood that a subject with cancer will respond to a cancer therapy or will continue to respond to a cancer therapy, the method comprising:

• analyzing the sequence of a nucleic acid molecule from a subject with cancer to detect SNVs within the nucleic acid molecule;
• determining a plurality of metrics based on the number and/or type of SNVs detected so as to obtain a subject profile of metrics, wherein the plurality of metrics includes metrics from three or more of the following metric groups:
• i) a coding metric group including metrics associated with SNVs in a coding region of the nucleic acid molecule;
• ii) a non-coding metric group including metrics associated with SNVs in a non-coding region of the nucleic acid molecule;
• iii) a genomic metric group including metrics associated with SNVs in coding and non-coding regions of the nucleic acid molecule;
• iv) a codon context metric group including metrics associated with a codon context of SNVs;
• v) a transition/transversion metric group including metrics associated with SNVs that are transitions or transversions;
• vi) a synonymous/non-synonymous metric group including metrics associated with SNVs that are synonymous or non-synonymous;
• vii) a strand bias metric group including metrics associated with strand bias of SNVs;
• viii) a strand specific metric group that includes metrics associated with SNVs on a specific strand;
• ix) an AT/GC metric group that includes metrics associated with SNVs in which an adenine and thymine, and/or guanine and cytidine have been targeted;
• x) a motif metric group including metrics associated with SNVs in specific motifs;
• and,
• xi) a motif-independent metric group including metrics associated with SNVs irrespective of motif;
• and,
• determining the likelihood of a subject responding to cancer therapy based on a comparison between the subject profile and a reference profile of metrics.