o UݢgK @sPdZddlmZddlmZddlZddlmZ ddl m Z ddl mZer,ddlmZdHd d ZdId d ZdIddZdIddZdIddZdIddZdIddZdIddZdJddZdIddZdIdd ZdId!d"Zd#Zd$Zd%Zd&Z dKd(d)Z!dKd*d+Z"dKd,d-Z#dKd.d/Z$ 0dLdMd5d6Z%dNd7d8Z&dNd9d:Z'd;Z(dOd>d?Z)dPdCdDZ*dQdFdGZ+dS)Rz4Utility functions for working with aligned segments.) annotations) TYPE_CHECKINGN)AlignedSegmentreadrreturntuplecCs |j|jfSN)tidposrr a/oak/stanford/groups/akundaje/marinovg/programs/cellranger-9.0.1/lib/python/cellranger/segment.py pos_sort_key rcC t|tjSr) _get_read_tag cr_constantsPROCESSED_BARCODE_TAGr r r r get_read_barcoderrcCrr)rrRAW_BARCODE_TAGr r r r get_read_raw_barcoderrcCrr)rrRAW_BARCODE_QUAL_TAGr r r r get_read_barcode_qualrrcCrr)rr UMI_QUAL_TAGr r r r get_read_umi_qual#rrcCrr)rrPROCESSED_UMI_TAGr r r r get_read_umi'rrcCrr)rr RAW_UMI_TAGr r r r get_read_raw_umi+rrcCs4t|tj}|dur dSt|tsJt|dS)zs_summary_. Args: read (AlignedSegment): _description_ Returns: _type_: _description_ N;)rrFEATURE_IDS_TAG isinstancestrrsplit)rZid_strr r r get_read_gene_ids/s r$NonecCs|j}||||_dSr)tagsextend)rr&Z read_tagsr r r set_read_tags?s  r(cCs.z ||}|s d}|WStyYdSwr)optKeyError)rtagrr r r rEs  rcCst|tjpdSNr)rrEXTRA_FLAGS_TAGr r r r get_read_extra_flagsOr/cCs@t|dksJ|jr dSt|dkr|dSt||j|S)z_summary_. Args: read (_type_): _description_ chroms (_type_): _description_ genomes (_type_): _description_ Returns: _type_: _description_ rN)len is_unmappedcr_utilsget_genome_from_strr )rchromsgenomesr r r get_genome_from_readSs   r8 boolcCt|t@dkSr-)r/EXTRA_FLAGS_LOW_SUPPORT_UMIr r r r is_read_low_support_umiqr0r@cCr>r-)r/EXTRA_FLAGS_FILTERED_TARGET_UMIr r r r is_read_filtered_target_umiur0rBcCr>r-)r/EXTRA_FLAGS_UMI_COUNTr r r r is_read_umi_countyr0rDcCr>r-)r/EXTRA_FLAGS_CONF_MAPPED_FEATUREr r r r is_read_conf_mapped_to_feature}r0rFThigh_conf_mapqintuse_corrected_umiuse_umiscCs^|rt|}nt|}|j o.|dup| o.t|duo.t| o.t| o.t||p.t|S)z_summary_. Args: read: _description_ high_conf_mapq: _description_ use_corrected_umi: _description_. Defaults to True. use_umis: _description_. Defaults to True. Returns: bool: _description_ N)rrZ is_secondaryrr@rB$is_read_conf_mapped_to_transcriptomerF)rrGrIrJZumir r r is_read_dupe_candidates    rLcCs|jrdS|j|kr dSdS)_summary_. Args: read (AlignedSegment): _description_ high_conf_mapq (int): _description_ Returns: bool: _description_ FT)r3Zmapq)rrGr r r is_read_conf_mappeds   rNcCs*t||rt|}|duot|dkSdS)rMNr1F)rNr$r2)rrGgene_idsr r r rKs rKs MIDNSHP=Xir"cCs tt|S)z-Pysam numeric codes to meaningful categories.)chr__CIGAR_CATEGORIES)rPr r r _cigar_numeric_to_category_maps rSstrandbytesdict[str, int]cCsi}|j}t|D]d\}\}}t|}t|}|dkr<|tjkr(|jr%dnd}n|jr-dnd}|dkr8|||<nd||<||d|||<|t|krm|tjkrY|j rVdnd}n|j r^dnd}|dkri|||<q d||<q |S)a+Get number of mismatches, insertions, deletions, ref skip, soft clip, hard clip bases from a read. Returns a dictionary by the element's CIGAR designation. Adds additional fields to distinguish between three and five prime soft-clipping for `R1` and `R2`: `R1_S_three_prime` and `R1_S_five_prime`, etc. to account for soft-clipped local alignments. Args: read (pysam.AlignedRead): aligned read object strand (string): + or - to indicate library orientation (MRO argument strand, for example) Returns: dict of str,int: Key of base type to base counts for metrics. Adds additional fields to distinguish between three and five prime soft-clipping: `S_three_prime` and `S_five_prime`. rR1_S_five_primeR2_S_three_primeR2_S_five_primeR1_S_three_primeS) cigar enumeraterSrHrREVERSE_STRANDis_read1getr2Zis_read2)rrT statisticsZ cigar_tuplesrPcategorycountmetricr r r get_cigar_summary_statss,     re.tuple[int, np.ndarray[int, np.dtype[np.byte]]]cCstj|jtjdtj}d}|jD]0\}}t|}|dkr(t||dg|}n|dvr9t |tj |||}|dvrA||7}q||fS)aaReturns base quality scores for the full read alignment. Inserts zeroes for deletions and removing inserted and soft-clipped bases. Therefore, only returns quality for truly aligned sequenced bases. Args: read (pysam.AlignedSegment): read to get quality scores for Returns: np.array: numpy array of quality scores )dtyperD)Ir[) np fromstringZqualbyte tk_constantsZILLUMINA_QUAL_OFFSETr\rSinsertdeletes_)rquality_scoresZ start_pos operationlengthr r r &get_full_alignment_base_quality_scoressrt)rrrr)rr)rrrr%)rrrr=)TT)rGrHrIr=rJr=rr=)rrrGrHrr=)rPrHrr")rrrTrUrrV)rrrrf),__doc__ __future__rtypingrnumpyrjcellranger.constants constantsrcellranger.utilsutilsr4Ztenkit.constantsrmZpysamrrrrrrrrr$r(rr/r8r?rCrErAr@rBrDrFrLrNrKrRrSrertr r r r sJ                        8