Important

Are you an Immcantation user and/or interested in adaptive immune receptor repertoire analysis?

Register now for the upcoming Immcantation Users Group Meeting! It will be held virtually on January 30th, 2025, from 10 to 1:30pm (ET). All talks will be from user-submitted abstracts.

Full information here: https://immcantation.github.io/users-meeting/

changeo.Receptor

Receptor data structure

class changeo.Receptor.AIRRSchema

Bases: object

AIRR format to Receptor mappings

fields = ['sequence_id', 'sequence', 'sequence_alignment', 'germline_alignment', 'sequence_aa', 'sequence_aa_alignment', 'germline_aa_alignment', 'rev_comp', 'productive', 'stop_codon', 'vj_in_frame', 'v_frameshift', 'locus', 'v_call', 'd_call', 'j_call', 'c_call', 'junction', 'junction_start', 'junction_end', 'junction_length', 'junction_aa', 'junction_aa_length', 'np1_length', 'np2_length', 'np1_aa_length', 'np2_aa_length', 'v_sequence_start', 'v_sequence_end', 'v_sequence_length', 'v_germline_start', 'v_germline_end', 'v_germline_length', 'v_sequence_aa_start', 'v_sequence_aa_end', 'v_sequence_aa_length', 'v_germline_aa_start', 'v_germline_aa_end', 'v_germline_aa_length', 'd_sequence_start', 'd_sequence_end', 'd_sequence_length', 'd_germline_start', 'd_germline_end', 'd_germline_length', 'd_sequence_aa_start', 'd_sequence_aa_end', 'd_sequence_aa_length', 'd_germline_aa_start', 'd_germline_aa_end', 'd_germline_aa_length', 'j_sequence_start', 'j_sequence_end', 'j_sequence_length', 'j_germline_start', 'j_germline_end', 'j_germline_length', 'j_sequence_aa_start', 'j_sequence_aa_end', 'j_sequence_aa_length', 'j_germline_aa_start', 'j_germline_aa_end', 'j_germline_aa_length', 'germline_alignment_d_mask', 'v_score', 'v_identity', 'v_support', 'v_cigar', 'd_score', 'd_identity', 'd_support', 'd_cigar', 'j_score', 'j_identity', 'j_support', 'j_cigar', 'vdj_score', 'cdr1', 'cdr2', 'cdr3', 'fwr1', 'fwr2', 'fwr3', 'fwr4', 'cdr1_aa', 'cdr2_aa', 'cdr3_aa', 'fwr1_aa', 'fwr2_aa', 'fwr3_aa', 'fwr4_aa', 'cdr1_start', 'cdr1_end', 'cdr2_start', 'cdr2_end', 'cdr3_start', 'cdr3_end', 'fwr1_start', 'fwr1_end', 'fwr2_start', 'fwr2_end', 'fwr3_start', 'fwr3_end', 'fwr4_start', 'fwr4_end', 'n1_length', 'n2_length', 'p3v_length', 'p5d_length', 'p3d_length', 'p5j_length', 'd_frame', 'cdr3_igblast', 'cdr3_igblast_aa', 'duplicate_count', 'consensus_count', 'umi_count', 'clone_id', 'cell_id']

static fromReceptor(field)

Returns an AIRR column name from a Receptor attribute name

Parameters:

field – Receptor attribute name.

Returns:

AIRR column name.

Return type:

str

out_type = 'tsv'

required = ['sequence_id', 'sequence', 'sequence_alignment', 'germline_alignment', 'rev_comp', 'productive', 'stop_codon', 'vj_in_frame', 'locus', 'v_call', 'd_call', 'j_call', 'c_call', 'junction', 'junction_length', 'junction_aa', 'np1_length', 'np2_length', 'v_sequence_start', 'v_sequence_end', 'v_germline_start', 'v_germline_end', 'd_sequence_start', 'd_sequence_end', 'd_germline_start', 'd_germline_end', 'j_sequence_start', 'j_sequence_end', 'j_germline_start', 'j_germline_end']

static toReceptor(field)

Returns a Receptor attribute name from an AIRR column name

Parameters:

field – AIRR column name.

Returns:

Receptor attribute name.

Return type:

str

class changeo.Receptor.AIRRSchemaAA

Bases: AIRRSchema

AIRR format to Receptor amino acid mappings

required = ['sequence_id', 'sequence', 'sequence_alignment', 'germline_alignment', 'sequence_aa', 'sequence_aa_alignment', 'germline_aa_alignment', 'rev_comp', 'productive', 'stop_codon', 'locus', 'v_call', 'd_call', 'j_call', 'c_call', 'junction', 'junction_length', 'junction_aa', 'v_sequence_aa_start', 'v_sequence_aa_end', 'v_germline_aa_start', 'v_germline_aa_end']

class changeo.Receptor.ChangeoSchema

Bases: object

Change-O to Receptor mappings

fields = ['SEQUENCE_ID', 'SEQUENCE_INPUT', 'SEQUENCE_AA_INPUT', 'FUNCTIONAL', 'IN_FRAME', 'STOP', 'MUTATED_INVARIANT', 'INDELS', 'V_FRAMESHIFT', 'LOCUS', 'V_CALL', 'D_CALL', 'J_CALL', 'C_CALL', 'SEQUENCE_VDJ', 'SEQUENCE_IMGT', 'SEQUENCE_AA_VDJ', 'SEQUENCE_AA_IMGT', 'V_SEQ_START', 'V_SEQ_LENGTH', 'V_GERM_START_VDJ', 'V_GERM_LENGTH_VDJ', 'V_GERM_START_IMGT', 'V_GERM_LENGTH_IMGT', 'V_SEQ_AA_START', 'V_SEQ_AA_LENGTH', 'V_GERM_AA_START_VDJ', 'V_GERM_AA_LENGTH_VDJ', 'V_GERM_AA_START_IMGT', 'V_GERM_AA_LENGTH_IMGT', 'NP1_LENGTH', 'NP1_AA_LENGTH', 'D_SEQ_START', 'D_SEQ_LENGTH', 'D_GERM_START', 'D_GERM_LENGTH', 'D_SEQ_AA_START', 'D_SEQ_AA_LENGTH', 'D_GERM_AA_START', 'D_GERM_AA_LENGTH', 'NP2_LENGTH', 'NP2_AA_LENGTH', 'J_SEQ_START', 'J_SEQ_LENGTH', 'J_GERM_START', 'J_GERM_LENGTH', 'J_SEQ_AA_START', 'J_SEQ_AA_LENGTH', 'J_GERM_AA_START', 'J_GERM_AA_LENGTH', 'JUNCTION', 'JUNCTION_LENGTH', 'GERMLINE_IMGT', 'GERMLINE_AA_IMGT', 'JUNCTION_START', 'V_SCORE', 'V_IDENTITY', 'V_EVALUE', 'V_BTOP', 'V_CIGAR', 'D_SCORE', 'D_IDENTITY', 'D_EVALUE', 'D_BTOP', 'D_CIGAR', 'J_SCORE', 'J_IDENTITY', 'J_EVALUE', 'J_BTOP', 'J_CIGAR', 'VDJ_SCORE', 'FWR1_IMGT', 'FWR2_IMGT', 'FWR3_IMGT', 'FWR4_IMGT', 'CDR1_IMGT', 'CDR2_IMGT', 'CDR3_IMGT', 'FWR1_AA_IMGT', 'FWR2_AA_IMGT', 'FWR3_AA_IMGT', 'FWR4_AA_IMGT', 'CDR1_AA_IMGT', 'CDR2_AA_IMGT', 'CDR3_AA_IMGT', 'N1_LENGTH', 'N2_LENGTH', 'P3V_LENGTH', 'P5D_LENGTH', 'P3D_LENGTH', 'P5J_LENGTH', 'D_FRAME', 'CDR3_IGBLAST', 'CDR3_IGBLAST_AA', 'CONSCOUNT', 'DUPCOUNT', 'UMICOUNT', 'CLONE', 'CELL']

static fromReceptor(field)

Returns a Change-O column name from a Receptor attribute name

Parameters:

field – Receptor attribute name.

Returns:

Change-O column name.

Return type:

str

out_type = 'tab'

required = ['SEQUENCE_ID', 'SEQUENCE_INPUT', 'FUNCTIONAL', 'IN_FRAME', 'STOP', 'MUTATED_INVARIANT', 'INDELS', 'LOCUS', 'V_CALL', 'D_CALL', 'J_CALL', 'SEQUENCE_VDJ', 'SEQUENCE_IMGT', 'V_SEQ_START', 'V_SEQ_LENGTH', 'V_GERM_START_VDJ', 'V_GERM_LENGTH_VDJ', 'V_GERM_START_IMGT', 'V_GERM_LENGTH_IMGT', 'NP1_LENGTH', 'D_SEQ_START', 'D_SEQ_LENGTH', 'D_GERM_START', 'D_GERM_LENGTH', 'NP2_LENGTH', 'J_SEQ_START', 'J_SEQ_LENGTH', 'J_GERM_START', 'J_GERM_LENGTH', 'JUNCTION', 'JUNCTION_LENGTH', 'GERMLINE_IMGT']

static toReceptor(field)

Returns a Receptor attribute name from a Change-O column name

Parameters:

field – Change-O column name.

Returns:

Receptor attribute name.

Return type:

str

class changeo.Receptor.ChangeoSchemaAA

Bases: ChangeoSchema

Change-O to Receptor amino acid mappings

required = ['SEQUENCE_ID', 'SEQUENCE_AA_INPUT', 'STOP', 'INDELS', 'LOCUS', 'V_CALL', 'SEQUENCE_AA_VDJ', 'SEQUENCE_AA_IMGT', 'V_SEQ_AA_START', 'V_SEQ_AA_LENGTH', 'V_GERM_AA_START_VDJ', 'V_GERM_AA_LENGTH_VDJ', 'V_GERM_AA_START_IMGT', 'V_GERM_AA_LENGTH_IMGT', 'GERMLINE_AA_IMGT']

class changeo.Receptor.Receptor(data)

Bases: object

A class defining a V(D)J sequence and its annotations

property d_germ_aa_end

Position of the last amino acid in the D germline amino acid alignment

property d_germ_end

Position of the last nucleotide in the D germline sequence alignment

property d_seq_aa_end

Position of the last D amino acid in the input amino acid sequence

property d_seq_end

Position of the last D nucleotide in the input sequence

getAIRR(field, seq=False)

Get an attribute from an AIRR field name

Parameters:

• field – AIRR column name as a string

• seq – if True return the attribute as a Seq object

Returns:

Value in the AIRR field. Returns None if the field cannot be found.

getAlleleCalls(calls, action='first')

Get multiple allele calls

Parameters:

• calls – iterable of calls to get; one or more of (‘v’,’d’,’j’)

• actions – One of (‘first’,’set’)

Returns:

List of requested calls in order

Return type:

list

getAlleleNumbers(calls, action='first')

Get multiple allele numeric identifiers

Parameters:

• calls – iterable of calls to get; one or more of (‘v’,’d’,’j’)

• actions – One of (‘first’,’set’)

Returns:

List of requested calls in order

Return type:

list

getChangeo(field, seq=False)

Get an attribute from a Change-O field name

Parameters:

• field – Change-O column name as a string

• seq – if True return the attribute as a Seq object

Returns:

Value in the Change-O field. Returns None if the field cannot be found.

getDAllele(action='first', field=None)

D segment allele getter

Parameters:

• actions – One of ‘first’, ‘set’ or ‘list’

• field – attribute or annotation name containing the D call. Use d_call attribute if None.

Returns:

String of the allele when action is ‘first’; tuple : Tuple of allele calls for ‘set’ or ‘list’ actions.

Return type:

str

getDAlleleNumber(action='first', field=None)

D segment allele number getter

Parameters:

• actions – One of ‘first’, ‘set’ or list’

• field – attribute or annotation name containing the D call. Use d_call attribute if None.

Returns:

String of the allele when action is ‘first’; tuple : Tuple of allele numbers for ‘set’ or ‘list’ actions.

Return type:

str

getDFamily(action='first', field=None)

D segment family getter

Parameters:

• actions – One of ‘first’, ‘set’ or list’

• field – attribute or annotation name containing the D call. Use d_call attribute if None.

Returns:

String of the allele when action is ‘first’; tuple : Tuple of allele calls for ‘set’ or ‘list’ actions.

Return type:

str

getDGene(action='first', field=None)

D segment gene getter

Parameters:

• actions – One of ‘first’, ‘set’ or list’

• field – attribute or annotation name containing the D call. Use d_call attribute if None.

Returns:

String of the allele when action is ‘first’; tuple : Tuple of allele calls for ‘set’ or ‘list’ actions.

Return type:

str

getFamilyCalls(calls, action='first')

Get multiple family calls

Parameters:

• calls – iterable of calls to get; one or more of (‘v’,’d’,’j’)

• actions – One of (‘first’,’set’)

Returns:

List of requested calls in order

Return type:

list

getField(field)

Get an attribute or annotation value

Parameters:

field – attribute name as a string

Returns:

Value in the attribute. Returns None if the attribute cannot be found.

getGeneCalls(calls, action='first')

Get multiple gene calls

Parameters:

• calls – iterable of calls to get; one or more of (‘v’,’d’,’j’)

• actions – One of (‘first’,’set’)

Returns:

List of requested calls in order

Return type:

list

getJAllele(action='first', field=None)

J segment allele getter

Parameters:

• actions – One of ‘first’, ‘set’ or ‘list’

• field – attribute or annotation name containing the J call. Use j_call attribute if None.

Returns:

String of the allele when action is ‘first’; tuple : Tuple of allele calls for ‘set’ or ‘list’ actions.

Return type:

str

getJAlleleNumber(action='first', field=None)

J segment allele number getter

Parameters:

• actions – One of ‘first’, ‘set’ or list’

• field – attribute or annotation name containing the J call. Use j_call attribute if None.

Returns:

String of the allele when action is ‘first’; tuple : Tuple of allele numbers for ‘set’ or ‘list’ actions.

Return type:

str

getJFamily(action='first', field=None)

J segment family getter

Parameters:

• actions – One of ‘first’, ‘set’ or list’

• field – attribute or annotation name containing the J call. Use j_call attribute if None.

Returns:

String of the allele when action is ‘first’; tuple : Tuple of allele calls for ‘set’ or ‘list’ actions.

Return type:

str

getJGene(action='first', field=None)

J segment gene getter

Parameters:

• actions – One of ‘first’, ‘set’ or list’

• field – attribute or annotation name containing the J call. Use j_call attribute if None.

Returns:

String of the allele when action is ‘first’; tuple : Tuple of allele calls for ‘set’ or ‘list’ actions.

Return type:

str

getSeq(field)

Get an attribute value converted to a Seq object

Parameters:

field – variable name as a string

Returns:

Value in the field as a Seq object

Return type:

Bio.Seq.Seq

getVAllele(action='first', field=None)

V segment allele getter

Parameters:

• actions – One of ‘first’, ‘set’ or list’

• field – attribute or annotation name containing the V call. Use v_call attribute if None.

Returns:

String of the allele when action is ‘first’; tuple : Tuple of allele calls for ‘set’ or ‘list’ actions.

Return type:

str

getVAlleleNumber(action='first', field=None)

V segment allele number getter

Parameters:

• actions – One of ‘first’, ‘set’ or list’

• field – attribute or annotation name containing the V call. Use v_call attribute if None.

Returns:

String of the allele when action is ‘first’; tuple : Tuple of allele numbers for ‘set’ or ‘list’ actions.

Return type:

str

getVFamily(action='first', field=None)

V segment family getter

Parameters:

• actions – One of ‘first’, ‘set’ or list’

• field – attribute or annotation name containing the V call. Use v_call attribute if None.

Returns:

String of the allele when action is ‘first’; tuple : Tuple of allele calls for ‘set’ or ‘list’ actions.

Return type:

str

getVGene(action='first', field=None)

V segment gene getter

Parameters:

• actions – One of ‘first’, ‘set’ or list’

• field – attribute or annotation name containing the V call. Use v_call attribute if None.

Returns:

String of the allele when action is ‘first’; tuple : Tuple of allele calls for ‘set’ or ‘list’ actions.

Return type:

str

property j_germ_aa_end

Position of the last amino acid in the J germline amino acid alignment

property j_germ_end

Position of the last nucleotide in the J germline sequence alignment

property j_seq_aa_end

Position of the last J amino acid in the input amino sequence

property j_seq_end

Position of the last J nucleotide in the input sequence

property junction_end

Position of the last junction nucleotide in the input sequence

setDict(data, parse=False)

Adds or updates multiple attributes and annotations

Parameters:

• data – a dictionary of annotations to add or update.

• parse – if True pass values through string parsing functions for known fields.

Returns:

updates attribute values and the annotations attribute.

Return type:

None

setField(field, value, parse=False)

Set an attribute or annotation value

Parameters:

• field – attribute name as a string

• value – value to assign

• parse – if True pass values through string parsing functions for known fields.

Returns:

None. Updates attribute or annotation.

toDict()

Convert the namespace to a dictionary

Returns:

member fields with values converted to appropriate strings

Return type:

dict

property v_germ_aa_end_imgt

Position of the last nucleotide in the IMGT-gapped V germline sequence alignment

property v_germ_aa_end_vdj

Position of the last nucleotide in the ungapped V germline sequence alignment

property v_germ_end_imgt

Position of the last nucleotide in the IMGT-gapped V germline sequence alignment

property v_germ_end_vdj

Position of the last nucleotide in the ungapped V germline sequence alignment

property v_seq_aa_end

Position of the last V nucleotide in the input sequence

property v_seq_end

Position of the last V nucleotide in the input sequence

class changeo.Receptor.ReceptorData

Bases: object

A class containing type conversion methods for Receptor data attributes

sequence_id

unique sequence identifier.

Type:

str

rev_comp

whether the alignment is relative to the reverse compliment of the input sequence.

Type:

bool

functional

whether sample V(D)J sequence is predicted to be functional.

Type:

bool

in_frame

whether junction region is in-frame.

Type:

bool

stop

whether a stop codon is present in the V(D)J sequence.

Type:

bool

mutated_invariant

whether the conserved amino acids are mutated in the V(D)J sequence.

Type:

bool

indels

whether the V(D)J nucleotide sequence contains insertions and/or deletions.

Type:

bool

v_frameshift

whether the V segment contains a frameshift

Type:

bool

sequence_input

input nucleotide sequence.

Type:

Bio.Seq.Seq

sequence_vdj

Aligned V(D)J nucleotide sequence without IMGT-gaps.

Type:

Bio.Seq.Seq

sequence_imgt

IMGT-gapped V(D)J nucleotide sequence.

Type:

Bio.Seq.Seq

sequence_aa_input

input amino acid sequence.

Type:

Bio.Seq.Seq

sequence_aa_vdj

Aligned V(D)J nucleotide sequence without IMGT-gaps.

Type:

Bio.Seq.Seq

sequence_aa_imgt

IMGT-gapped V(D)J amino sequence.

Type:

Bio.Seq.Seq

junction

ungapped junction region nucletide sequence.

Type:

Bio.Seq.Seq

junction_aa

ungapped junction region amino acid sequence.

Type:

Bio.Seq.Seq

junction_start

start positions of the junction in the input nucleotide sequence.

Type:

int

junction_length

length of the junction in nucleotides.

Type:

int

germline_vdj

full ungapped germline V(D)J nucleotide sequence.

Type:

Bio.Seq.Seq

germline_vdj_d_mask

ungapped germline V(D)J nucleotides sequence with Ns masking the NP1-D-NP2 regions.

Type:

Bio.Seq.Seq

germline_imgt

full IMGT-gapped germline V(D)J nucleotide sequence.

Type:

Bio.Seq.Seq

germline_imgt_d_mask

IMGT-gapped germline V(D)J nucleotide sequence with ns masking the NP1-D-NP2 regions.

Type:

Bio.Seq.Seq

germline_aa_vdj

full ungapped germline V(D)J amino acid sequence.

Type:

Bio.Seq.Seq

germline_aa_imgt

full IMGT-gapped germline V(D)J amino acid sequence.

Type:

Bio.Seq.Seq

v_call

V allele assignment(s).

Type:

str

d_call

D allele assignment(s).

Type:

str

j_call

J allele assignment(s).

Type:

str

c_call

C region assignment.

Type:

str

v_seq_start

position of the first V nucleotide in the input sequence (1-based).

Type:

int

v_seq_length

number of V nucleotides in the input sequence.

Type:

int

v_germ_start_imgt

position of the first V nucleotide in IMGT-gapped V germline sequence alignment (1-based).

Type:

int

v_germ_length_imgt

length of the IMGT numbered germline V alignment.

Type:

int

v_germ_start_vdj

position of the first nucleotide in ungapped V germline sequence alignment (1-based).

Type:

int

v_germ_length_vdj

length of the ungapped germline V alignment.

Type:

int

v_seq_aa_start

position of the first V amino acid in the amino acid input sequence (1-based).

Type:

int

v_seq_aa_length

number of V amino acid in the amino acid input sequence.

Type:

int

v_germ_aa_start_imgt

position of the first V amino acid in IMGT-gapped V germline amino acid alignment (1-based).

Type:

int

v_germ_aa_length_imgt

length of the IMGT numbered germline V amino acid alignment.

Type:

int

v_germ_aa_start_vdj

position of the first amino acid in ungapped V germline amino acid alignment (1-based).

Type:

int

v_germ_aa_length_vdj

length of the ungapped germline V amino acid alignment.

Type:

int

np1_start

position of the first untemplated nucleotide between the V and D segments in the input sequence (1-based).

Type:

int

np1_length

number of untemplated nucleotides between the V and D segments.

Type:

int

np1_aa_start

position of the first untemplated amino acid between the V and D segments in the input amino acid sequence (1-based).

Type:

int

np1_aa_length

number of untemplated amino acids between the V and D segments.

Type:

int

d_seq_start

position of the first D nucleotide in the input sequence (1-based).

Type:

int

d_seq_length

number of D nucleotides in the input sequence.

Type:

int

d_germ_start

position of the first nucleotide in D germline sequence alignment (1-based).

Type:

int

d_germ_length

length of the germline D alignment.

Type:

int

d_seq_aa_start

position of the first D amino acid in the input amino acidsequence (1-based).

Type:

int

d_seq_aa_length

number of D amino acids in the input amino acid sequence.

Type:

int

d_germ_aa_start

position of the first amino acid in D germline amino acid alignment (1-based).

Type:

int

d_germ_aa_length

length of the germline D amino acid alignment.

Type:

int

np2_start

position of the first untemplated nucleotide between the D and J segments in the input sequence (1-based).

Type:

int

np2_length

number of untemplated nucleotides between the D and J segments.

Type:

int

np2_aa_start

position of the first untemplated amino acid between the D and J segments in the input amino acid sequence (1-based).

Type:

int

np2_aa_length

number of untemplated amino acid between the D and J segments.

Type:

int

j_seq_start

position of the first J nucleotide in the input sequence (1-based).

Type:

int

j_seq_length

number of J nucleotides in the input sequence.

Type:

int

j_germ_start

position of the first nucleotide in J germline sequence alignment (1-based).

Type:

int

j_germ_length

length of the germline J alignment.

Type:

int

j_seq_aa_start

position of the first J amino acid in the input amino acidsequence (1-based).

Type:

int

j_seq_aa_length

number of J amino acid in the input amino acidsequence.

Type:

int

j_germ_aa_start

position of the first amino acid in J germline amino acid alignment (1-based).

Type:

int

j_germ_aa_length

length of the germline J amino acid alignment.

Type:

int

v_score

alignment score for the V.

Type:

float

v_identity

alignment identity for the V.

Type:

float

v_evalue

E-value for the alignment of the V.

Type:

float

v_btop

BTOP for the alignment of the V.

Type:

str

v_cigar

CIGAR for the alignment of the V.

Type:

str

d_score

alignment score for the D.

Type:

float

d_identity

alignment identity for the D.

Type:

float

d_evalue

E-value for the alignment of the D.

Type:

float

d_btop

BTOP for the alignment of the D.

Type:

str

d_cigar

CIGAR for the alignment of the D.

Type:

str

j_score

alignment score for the J.

Type:

float

j_identity

alignment identity for the J.

Type:

float

j_evalue

E-value for the alignment of the J.

Type:

float

j_btop

BTOP for the alignment of the J.

Type:

str

j_cigar

CIGAR for the alignment of the J.

Type:

str

vdj_score

alignment score for the V(D)J.

Type:

float

fwr1_imgt

IMGT-gapped FWR1 nucleotide sequence.

Type:

Bio.Seq.Seq

fwr2_imgt

IMGT-gapped FWR2 nucleotide sequence.

Type:

Bio.Seq.Seq

fwr3_imgt

IMGT-gapped FWR3 nucleotide sequence.

Type:

Bio.Seq.Seq

fwr4_imgt

IMGT-gapped FWR4 nucleotide sequence.

Type:

Bio.Seq.Seq

cdr1_imgt

IMGT-gapped CDR1 nucleotide sequence.

Type:

Bio.Seq.Seq

cdr2_imgt

IMGT-gapped CDR2 nucleotide sequence.

Type:

Bio.Seq.Seq

cdr3_imgt

IMGT-gapped CDR3 nucleotide sequence.

Type:

Bio.Seq.Seq

cdr3_igblast

CDR3 nucleotide sequence assigned by IgBLAST.

Type:

Bio.Seq.Seq

fwr1_aa_imgt

IMGT-gapped FWR1 amino acid sequence.

Type:

Bio.Seq.Seq

fwr2_aa_imgt

IMGT-gapped FWR2 amino acid sequence.

Type:

Bio.Seq.Seq

fwr3_aa_imgt

IMGT-gapped FWR3 amino acid sequence.

Type:

Bio.Seq.Seq

fwr4_aa_imgt

IMGT-gapped FWR4 amino acid sequence.

Type:

Bio.Seq.Seq

cdr1_aa_imgt

IMGT-gapped CDR1 amino acid sequence.

Type:

Bio.Seq.Seq

cdr2_aa_imgt

IMGT-gapped CDR2 amino acid sequence.

Type:

Bio.Seq.Seq

cdr3_aa_imgt

IMGT-gapped CDR3 amino acid sequence.

Type:

Bio.Seq.Seq

cdr3_igblast_aa

CDR3 amino acid sequence assigned by IgBLAST.

Type:

Bio.Seq.Seq

n1_length

M nucleotides 5’ of the D segment.

Type:

int

n2_length

nucleotides 3’ of the D segment.

Type:

int

p3v_length

palindromic nucleotides 3’ of the V segment.

Type:

int

p5d_length

palindromic nucleotides 5’ of the D segment.

Type:

int

p3d_length

palindromic nucleotides 3’ of the D segment.

Type:

int

p5j_length

palindromic nucleotides 5’ of the J segment.

Type:

int

d_frame

D segment reading frame.

Type:

int

conscount

number of reads contributing to the UMI consensus sequence.

Type:

int

dupcount

copy number of the sequence.

Type:

int

umicount

number of UMIs representing the sequence.

Type:

int

clone

clonal cluster identifier.

Type:

str

cell

origin cell identifier.

Type:

str

annotations

dictionary containing all unknown fields.

Type:

dict

static aminoacid(v, deparse=False)

static double(v, deparse=False)

end_fields = {'cdr1_end': ('cdr1_start', 'cdr1_length'), 'cdr2_end': ('cdr2_start', 'cdr2_length'), 'cdr3_end': ('cdr3_start', 'cdr3_length'), 'd_germ_aa_end': ('d_germ_aa_start', 'd_germ_aa_length'), 'd_germ_end': ('d_germ_start', 'd_germ_length'), 'd_seq_aa_end': ('d_seq_aa_start', 'd_seq_aa_length'), 'd_seq_end': ('d_seq_start', 'd_seq_length'), 'fwr1_end': ('fwr1_start', 'fwr1_length'), 'fwr2_end': ('fwr2_start', 'fwr2_length'), 'fwr3_end': ('fwr3_start', 'fwr3_length'), 'fwr4_end': ('fwr4_start', 'fwr4_length'), 'j_germ_aa_end': ('j_germ_aa_start', 'j_germ_aa_length'), 'j_germ_end': ('j_germ_start', 'j_germ_length'), 'j_seq_aa_end': ('j_seq_aa_start', 'j_seq_aa_length'), 'j_seq_end': ('j_seq_start', 'j_seq_length'), 'junction_end': ('junction_start', 'junction_length'), 'v_alignment_aa_end': ('v_alignment_aa_start', 'v_alignment_aa_length'), 'v_alignment_end': ('v_alignment_start', 'v_alignment_length'), 'v_germ_aa_end_imgt': ('v_germ_aa_start_imgt', 'v_germ_aa_length_imgt'), 'v_germ_aa_end_vdj': ('v_germ_aa_start_vdj', 'v_germ_aa_length_vdj'), 'v_germ_end_imgt': ('v_germ_start_imgt', 'v_germ_length_imgt'), 'v_germ_end_vdj': ('v_germ_start_vdj', 'v_germ_length_vdj'), 'v_seq_aa_end': ('v_seq_aa_start', 'v_seq_aa_length'), 'v_seq_end': ('v_seq_start', 'v_seq_length')}

static identity(v, deparse=False)

static integer(v, deparse=False)

length_fields = {'cdr1_length': ('cdr1_start', 'cdr1_end'), 'cdr2_length': ('cdr2_start', 'cdr2_end'), 'cdr3_length': ('cdr3_start', 'cdr3_end'), 'd_germ_aa_length': ('d_germ_aa_start', 'd_germ_aa_end'), 'd_germ_length': ('d_germ_start', 'd_germ_end'), 'd_seq_aa_length': ('d_seq_aa_start', 'd_seq_aa_end'), 'd_seq_length': ('d_seq_start', 'd_seq_end'), 'fwr1_length': ('fwr1_start', 'fwr1_end'), 'fwr2_length': ('fwr2_start', 'fwr2_end'), 'fwr3_length': ('fwr3_start', 'fwr3_end'), 'fwr4_length': ('fwr4_start', 'fwr4_end'), 'j_germ_aa_length': ('j_germ_aa_start', 'j_germ_aa_end'), 'j_germ_length': ('j_germ_start', 'j_germ_end'), 'j_seq_aa_length': ('j_seq_aa_start', 'j_seq_aa_end'), 'j_seq_length': ('j_seq_start', 'j_seq_end'), 'junction_length': ('junction_start', 'junction_end'), 'v_alignment_aa_length': ('v_alignment_aa_start', 'v_alignment_aa_end'), 'v_alignment_length': ('v_alignment_start', 'v_alignment_end'), 'v_germ_aa_length_imgt': ('v_germ_aa_start_imgt', 'v_germ_aa_end_imgt'), 'v_germ_aa_length_vdj': ('v_germ_aa_start_vdj', 'v_germ_aa_end_vdj'), 'v_germ_length_imgt': ('v_germ_start_imgt', 'v_germ_end_imgt'), 'v_germ_length_vdj': ('v_germ_start_vdj', 'v_germ_end_vdj'), 'v_seq_aa_length': ('v_seq_aa_start', 'v_seq_aa_end'), 'v_seq_length': ('v_seq_start', 'v_seq_end')}

static logical(v, deparse=False)

static nucleotide(v, deparse=False)

parsers = {'c_call': 'identity', 'cdr1_aa_imgt': 'aminoacid', 'cdr1_imgt': 'nucleotide', 'cdr2_aa_imgt': 'aminoacid', 'cdr2_imgt': 'nucleotide', 'cdr3_aa_imgt': 'aminoacid', 'cdr3_igblast': 'nucleotide', 'cdr3_igblast_aa': 'aminoacid', 'cdr3_imgt': 'nucleotide', 'cell': 'identity', 'clone': 'identity', 'conscount': 'integer', 'd_btop': 'identity', 'd_call': 'identity', 'd_cigar': 'identity', 'd_evalue': 'double', 'd_frame': 'integer', 'd_germ_aa_length': 'integer', 'd_germ_aa_start': 'integer', 'd_germ_length': 'integer', 'd_germ_start': 'integer', 'd_identity': 'double', 'd_score': 'double', 'd_seq_aa_length': 'integer', 'd_seq_aa_start': 'integer', 'd_seq_length': 'integer', 'd_seq_start': 'integer', 'dupcount': 'integer', 'functional': 'logical', 'fwr1_aa_imgt': 'aminoacid', 'fwr1_imgt': 'nucleotide', 'fwr2_aa_imgt': 'aminoacid', 'fwr2_imgt': 'nucleotide', 'fwr3_aa_imgt': 'aminoacid', 'fwr3_imgt': 'nucleotide', 'fwr4_aa_imgt': 'aminoacid', 'fwr4_imgt': 'nucleotide', 'germline_aa_imgt': 'aminoacid', 'germline_aa_vdj': 'aminoacid', 'germline_imgt': 'nucleotide', 'germline_imgt_d_mask': 'nucleotide', 'germline_vdj': 'nucleotide', 'germline_vdj_d_mask': 'nucleotide', 'in_frame': 'logical', 'indels': 'logical', 'j_btop': 'identity', 'j_call': 'identity', 'j_cigar': 'identity', 'j_evalue': 'double', 'j_germ_aa_length': 'integer', 'j_germ_aa_start': 'integer', 'j_germ_length': 'integer', 'j_germ_start': 'integer', 'j_identity': 'double', 'j_score': 'double', 'j_seq_aa_length': 'integer', 'j_seq_aa_start': 'integer', 'j_seq_length': 'integer', 'j_seq_start': 'integer', 'junction': 'nucleotide', 'junction_aa': 'aminoacid', 'junction_length': 'integer', 'junction_start': 'integer', 'locus': 'identity', 'mutated_invariant': 'logical', 'n1_length': 'integer', 'n2_length': 'integer', 'np1_aa_length': 'integer', 'np1_aa_start': 'integer', 'np1_length': 'integer', 'np1_start': 'integer', 'np2_aa_length': 'integer', 'np2_aa_start': 'integer', 'np2_length': 'integer', 'np2_start': 'integer', 'p3d_length': 'integer', 'p3v_length': 'integer', 'p5d_length': 'integer', 'p5j_length': 'integer', 'rev_comp': 'logical', 'sequence_aa_imgt': 'aminoacid', 'sequence_aa_input': 'aminoacid', 'sequence_aa_vdj': 'aminoacid', 'sequence_id': 'identity', 'sequence_imgt': 'nucleotide', 'sequence_input': 'nucleotide', 'sequence_vdj': 'nucleotide', 'stop': 'logical', 'umicount': 'integer', 'v_btop': 'identity', 'v_call': 'identity', 'v_cigar': 'identity', 'v_evalue': 'double', 'v_frameshift': 'logical', 'v_germ_aa_length_imgt': 'integer', 'v_germ_aa_length_vdj': 'integer', 'v_germ_aa_start_imgt': 'integer', 'v_germ_aa_start_vdj': 'integer', 'v_germ_length_imgt': 'integer', 'v_germ_length_vdj': 'integer', 'v_germ_start_imgt': 'integer', 'v_germ_start_vdj': 'integer', 'v_identity': 'double', 'v_score': 'double', 'v_seq_aa_length': 'integer', 'v_seq_aa_start': 'integer', 'v_seq_length': 'integer', 'v_seq_start': 'integer', 'vdj_score': 'double'}

start_fields = {'cdr1_start': ('cdr1_length', 'cdr1_end'), 'cdr2_start': ('cdr2_length', 'cdr2_end'), 'cdr3_start': ('cdr3_length', 'cdr3_end'), 'd_germ_aa_start': ('d_germ_aa_length', 'd_germ_aa_end'), 'd_germ_start': ('d_germ_length', 'd_germ_end'), 'd_seq_aa_start': ('d_seq_aa_length', 'd_seq_aa_end'), 'd_seq_start': ('d_seq_length', 'd_seq_end'), 'fwr1_start': ('fwr1_length', 'fwr1_end'), 'fwr2_start': ('fwr2_length', 'fwr2_end'), 'fwr3_start': ('fwr3_length', 'fwr3_end'), 'fwr4_start': ('fwr4_length', 'fwr4_end'), 'j_germ_aa_start': ('j_germ_aa_length', 'j_germ_aa_end'), 'j_germ_start': ('j_germ_length', 'j_germ_end'), 'j_seq_aa_start': ('j_seq_aa_length', 'j_seq_aa_end'), 'j_seq_start': ('j_seq_length', 'j_seq_end'), 'junction_start': ('junction_length', 'junction_end'), 'v_alignment_aa_start': ('v_alignment_aa_length', 'v_alignment_aa_end'), 'v_alignment_start': ('v_alignment_length', 'v_alignment_end'), 'v_germ_aa_start_imgt': ('v_germ_aa_length_imgt', 'v_germ_aa_end_imgt'), 'v_germ_aa_start_vdj': ('v_germ_aa_length_vdj', 'v_germ_aa_end_vdj'), 'v_germ_start_imgt': ('v_germ_length_imgt', 'v_germ_end_imgt'), 'v_germ_start_vdj': ('v_germ_length_vdj', 'v_germ_end_vdj'), 'v_seq_aa_start': ('v_seq_aa_length', 'v_seq_aa_end'), 'v_seq_start': ('v_seq_length', 'v_seq_end')}