Added pPC101 capabilities.

pablocarderam · Jun 16, 2024 · 1984738 · 1984738
1 parent fcc6c77
commit 1984738
Show file tree

Hide file tree

Showing 8 changed files with 523 additions and 9 deletions.
diff --git a/README.md b/README.md
@@ -2,7 +2,7 @@
 
 GeneTargeter creates custom gene-editing constructs designed for knock-out or conditional knock-down in [_Plasmodium falciparum_](http://www.who.int/mediacentre/factsheets/fs094/en/). It is developed by the [Niles Lab at MIT](http://web.mit.edu/nileslab/) and [described in detail in this article](https://www.liebertpub.com/doi/epdf/10.1089/crispr.2021.0069).
 
-At the Niles Lab, GeneTargeter is used to deliver 3' or 5' UTR post-transcriptional regulatory element payload to a specific given gene ([Ganesan et al., 2016](https://dx.doi.org/10.1038%2Fncomms10727), [Nasamu et al., 2021](https://doi.org/10.1038/s41598-020-77644-4)). However, user-defined custom plasmids can be used as well.
+At the Niles Lab, GeneTargeter is used to deliver 3' or 5' UTR post-transcriptional regulatory element payload to a specific given gene ([Ganesan et al., 2016](https://dx.doi.org/10.1038%2Fncomms10727), [Nasamu et al., 2021](https://doi.org/10.1038/s41598-020-77644-4)). It can also deliver 5' synthetic transcriptional regulatory payloads (preprint forthcoming). User-defined custom plasmids can be used as well.
 
 Most applications can be served well through the web application running at [genetargeter.mit.edu](genetargeter.mit.edu) .
 

diff --git a/input/plasmids/ppc101-template.gb b/input/plasmids/ppc101-template.gb
diff --git a/main.py b/main.py
@@ -109,14 +109,14 @@ def gene_message(message):
     for gbName in geneGBs: # for every gb
         sigPep = chkSignalPeptide5Prime(gbName,signalPDB); # signalP info
         haTag = False; # don't use HA tags by default
-        if plasmidType == "pSN150" and ( haTagMsg == "Yes" or (haTagMsg == "Auto" and not sigPep) ): # if forcing HA tags or 5' end does not contain signal peptide and auto HA-tagging
+        if (plasmidType == "pSN150" or plasmidType == "pPC101") and ( haTagMsg == "Yes" or (haTagMsg == "Auto" and not sigPep) ): # if forcing HA tags or 5' end does not contain signal peptide and auto HA-tagging
             haTag = True; # use HA tags
 
         try:
             output = targetGene(gbName, geneGBs[gbName], codonOptimize=codonOptimize, useFileStrs=True, HRannotated=HRann,lengthLHR=lengthLHR, lengthRHR=lengthRHR, gibsonHomRange=lengthGib, optimRangeLHR=optimLHR, optimRangeRHR=optimRHR, endSizeLHR=endsLHR, endSizeRHR=endsRHR, endTempLHR=endTempLHR, endTempRHR=endTempRHR, gibTemp=gibTemp, gibTDif=gibTDif, maxDistLHR=maxDistLHR, maxDistRHR=maxDistRHR, minGBlockSize=minFragSize, maxGBlockSize=maxFragSize, codonSampling=codonSampling, minGRNAGCContent=minGRNAGCContent, onTargetMethod=onTargetMethod, minOnTargetScore=minOnTargetScore, offTargetMethod=offTargetMethod, minOffTargetScore=minOffTargetScore, maxOffTargetHitScore=maxOffTargetHitScore, enzyme=enzyme, PAM=PAM, gBlockDefault=gBlockDefault, plasmidType=plasmidType, haTag=haTag, sigPep=sigPep, setCoding=setCoding, bulkFile=bulkFile, prefix=prefix, basePlasmid=basePlasmidGB, basePlasmidName=basePlasmidName, locationType=locationType, filterCutSites=filterCutSites); # call result
 
             outMsg = outMsg + sep + output["geneName"] + sep + output["geneFileStr"] + sep + output["plasmidFileStr"] + sep + output["editedLocusFileStr"] + sep + output["oligoFileStr"] + sep + output["gBlockFileStr"] + sep + output["gRNATable"] + sep + output["logFileStr"];
-            if haTag and plasmidType == "pSN150": # if using HA tags and pSN150,
+            if haTag and (plasmidType == "pSN150" or plasmidType == "pPC101"): # if using HA tags and pSN150,
                 outputHA = output["outputHA"]; # save HA outputs
                 outMsgHA = outMsgHA + sep + outputHA["geneName"] + sep + outputHA["geneFileStr"] + sep + outputHA["plasmidFileStr"] + sep + outputHA["editedLocusFileStr"] + sep + outputHA["oligoFileStr"] + sep + outputHA["gBlockFileStr"] + sep + outputHA["gRNATable"] + sep + outputHA["logFileStr"];
                 sendMsg(outMsgHA, "geneOutput", channel_id);

diff --git a/py/genetargeter/GeneTargeterMethods.py b/py/genetargeter/GeneTargeterMethods.py
@@ -124,7 +124,7 @@ def targetGene(geneName, geneGB, codonOptimize="T. gondii", HRannotated=False, l
 
 
 
-        elif plasmidType == "pSN150" or plasmidType == "pSN150-KO" or plasmidType == "pSN150-Ter" or plasmidType == "pSN150-KO-Ter": # if using 5' plasmid
+        elif plasmidType == "pSN150" or plasmidType == "pSN150-KO" or plasmidType == "pSN150-Ter" or plasmidType == "pSN150-KO-Ter" or plasmidType == "pPC101": # if using 5' plasmid
             if plasmidType == "pSN150" or plasmidType == "pSN150-KO": # if using the normal ones,
                 if enzyme == "Cas9": # if Cas9,
                     plasmid = pSN150_Cas9; # set plasmid
@@ -138,6 +138,9 @@ def targetGene(geneName, geneGB, codonOptimize="T. gondii", HRannotated=False, l
                 elif enzyme == "Cas12": # if Cas12,
                     plasmid = pSN150_Cas12_Ter; # set plasmid
 
+            elif plasmidType == "pPC101": # if using old version
+                plasmid = pPC101; # set plasmid
+
 
             closestGene = 0; # by default, assume next gene downstream is before start of file
             target3Prime = False; # this plasmid targets 5' end
@@ -207,6 +210,9 @@ def targetGene(geneName, geneGB, codonOptimize="T. gondii", HRannotated=False, l
             elif plasmidType=="pSN150-KO":
                 flankingSeqsLHR = ['ggcc','ggcc']
                 flankingSeqsRHR = ['cgcc','cccg']
+            elif plasmidType=="pPC101":
+                flankingSeqsLHR = ['ggcc','ggcc']
+                flankingSeqsRHR = ['','cgta']
             elif plasmidType=="custom":
                 flankingSeqsLHR = ['','']
                 flankingSeqsRHR = ['','']
@@ -219,7 +225,7 @@ def targetGene(geneName, geneGB, codonOptimize="T. gondii", HRannotated=False, l
                 LHR = chooseHR(geneGB, gene, doingHR='LHR', targetExtreme='start', lengthHR=lengthLHR, minTmEnds=endTempLHR, endsLength=endSizeLHR, targetRegionOverride=(plasmidType=="custom" or plasmidType=="pSN150-KO"), flankingSeqs=flankingSeqsLHR, filterCutSites=filterCutSites); # chooses LHR
                 if plasmidType == "pSN150-KO" or (plasmidType=="custom" and locationType=="center"): # if knocking gene out,
                     RHR = chooseHR(geneGB, gene, doingHR='RHR', targetExtreme='end', lengthHR=lengthRHR, minTmEnds=endTempRHR, endsLength=endSizeRHR, gBlockDefault=gBlockDefault, minGBlockSize=minGBlockSize, codingGene=codingGene, targetRegionOverride=(plasmidType=="custom" or plasmidType=="pSN150-KO"), flankingSeqs=flankingSeqsRHR, filterCutSites=filterCutSites); # chooses an RHR at end of gene!
-                elif plasmidType == "pSN150" or (plasmidType=="custom" and locationType=="5prime"): # otherwise if KD construct
+                elif plasmidType == "pSN150" or plasmidType == "pPC101" or (plasmidType=="custom" and locationType=="5prime"): # otherwise if KD construct
                     RHR = chooseHR(geneGB, gene, doingHR='RHR', targetExtreme='start', lengthHR=lengthRHR, minTmEnds=endTempRHR, endsLength=endSizeRHR, gBlockDefault=gBlockDefault, minGBlockSize=minGBlockSize, codingGene=codingGene, targetRegionOverride=(plasmidType=="custom" or plasmidType=="pSN150-KO"), flankingSeqs=flankingSeqsRHR, filterCutSites=filterCutSites); # chooses an RHR at beginning
 
             if LHR["out"] is None or RHR["out"] is None and not HRannotated: # if searches fail and HR's not provided,
@@ -271,6 +277,8 @@ def targetGene(geneName, geneGB, codonOptimize="T. gondii", HRannotated=False, l
                     flankingSeqsRec = [LHR.seq[-4:],'gcga'] # 054
                     if plasmidType=="pSN150":
                         flankingSeqsRec = ['tagc',RHR.seq[0:4]]
+                    if plasmidType=="pPC101":
+                        flankingSeqsRec = ['gATG',RHR.seq[0:4]]
                     elif plasmidType=="custom":
                         flankingSeqsRec = ['','']
 
@@ -356,7 +364,7 @@ def postProcessPlasmid(geneName, geneGB, gene, plasmidArmed, recoded, outputDic,
             extIndex = ( minGBlockSize - gibsonHomRange[1]*2 ) # extension length of gBlock such that it satisfies minimum gBlock length
             if plasmidType=="pSN054": # extend in different directions depending on plasmid
                 recodedGBlock = GenBankAnn(gene.label + " extension", "misc_feature", plasmidArmed.origin[recodedOnPlasmid.index[0]:recodedOnPlasmid.index[0]+extIndex], False, [recodedOnPlasmid.index[0],recodedOnPlasmid.index[0]+extIndex]) # make extended recoded region gBlock annotation
-            elif plasmidType=="pSN150":
+            elif plasmidType=="pSN150" or plasmidType=="pPC101":
                 recodedGBlock = GenBankAnn(gene.label + " extension", "misc_feature", plasmidArmed.origin[recodedOnPlasmid.index[1]-extIndex:recodedOnPlasmid.index[1]], False, [recodedOnPlasmid.index[1]-extIndex,recodedOnPlasmid.index[1]]) # make extended recoded region gBlock annotation
             elif plasmidType=="custom":
                 recodedGBlock = GenBankAnn(gene.label + " extension", "misc_feature", plasmidArmed.origin[recodedOnPlasmid.index[0]:recodedOnPlasmid.index[0]+extIndex], False, [recodedOnPlasmid.index[0],recodedOnPlasmid.index[0]+extIndex]) # make extended recoded region gBlock annotation
@@ -413,7 +421,7 @@ def postProcessPlasmid(geneName, geneGB, gene, plasmidArmed, recoded, outputDic,
         if plasmidType == "pSN054": # if using pSN150 instead of pSN054,
             gRNACassetteStart = plasmidArmed.findAnnsLabel("Lox")[0].index[0] + 4; # gBlock starts at first Lox +4 bp to avoid error due to repeated lox sequence
             gRNACassetteEnd = plasmidArmed.findAnnsLabel("RHR_vector overlap_left")[0].index[1]; # gBlock ends at RHR_vector overlap_left
-        if plasmidType == "pSN150": # if using pSN150 instead of pSN054,
+        if plasmidType == "pSN150" or plasmidType=="pPC101": # if using pSN150 instead of pSN054,
             gRNACassetteStart = plasmidArmed.findAnnsLabel(geneName + " RHR")[0].index[1]; # gBlock starts at end of RHR
             gRNACassetteEnd = max(gRNACassetteStart + minGBlockSize,findFirst(plasmidArmed.origin, cut_AsiSI)+len(cut_AsiSI)+gibsonHomRange[1]); # gBlock ends after AsiSI
         elif plasmidType == "pSN150-KO": # if using pSN150-KO instead of pSN054,

diff --git a/py/genetargeter/constants.py b/py/genetargeter/constants.py
@@ -35,6 +35,7 @@
     'pSN054_V5' : [cut_FseI,cut_AsiSI,cut_IPpoI,cut_ISceI,cut_AflII,cut_AhdI],
     'pSN150-Ter' : [cut_FseI,cut_AsiSI,cut_IPpoI,cut_AhdI,cut_XmaI,cut_NheI],
     'pSN150-KO-Ter' : [cut_FseI,cut_AsiSI,cut_IPpoI,cut_AhdI,cut_AscI,cut_XmaI,cut_NheI],
+    'pPC101' : [cut_FseI,cut_AsiSI,cut_BsiWI],
     'custom' : []
     }
 
@@ -66,6 +67,9 @@
 pSN150_Cas12 = GenBank();
 pSN150_Cas12.load("input/plasmids/psn150_cas12.gb",loadFromFile=True); # load Cas9 plasmid sequence from GenBank format
 pSN150_Cas12.setAllColors(annColors['otherAnnColor'])
+pPC101 = GenBank();
+pPC101.load("input/plasmids/ppc101-template.gb",loadFromFile=True); # load Cas12 plasmid sequence from GenBank format
+pPC101.setAllColors(annColors['otherAnnColor'])
 
 # Codon usage tables
 codonUsageTables = {
@@ -91,11 +95,14 @@
 
 instructions_pSN150_KO = '\n*** Assembly instructions for pSN150-type constructs for knock-out: ***\n\n   1. Obtain primers in Oligo csv file and gene fragments in gBlock fasta file \n      from DNA synthesis\n   2. PCR the RHR and LHR fragments from genomic DNA using the corresponding\n      Gibson Assembly primers in Oligo csv file\n   3. Digest empty parent vector with restriction enzyme FseI\n   4. Gibson Assembly to insert LHR into digestion product\n   5. Digest resulting vector with restriction enzymes AhdI and AsiSI\n   6. Gibson Assembly to insert sgRNA cassette and RHR into digestion product; if design includes \n      recoded region, include in assembly as well\n   7. Check all steps by sequencing\n   8. Transfect into Cas9 or Cas12-containing cell lines!'
 
+instructions_pPC101 = '\n*** Assembly instructions for pPC101-type constructs for transcriptional conditional knock-down: ***\n\n   1. Obtain primers in Oligo csv file and gene fragments in gBlock fasta file \n      from DNA synthesis\n   2. PCR the LHR and RHR* fragments from genomic DNA using the corresponding \n      Gibson Assembly primers in Oligo csv file\n   3. Digest empty parent vector with restriction enzyme FseI\n   4. Gibson Assembly to insert LHR into digestion product\n   5. Digest resulting vector with restriction enzyme AsiSI\n   6. Gibson Assembly to insert RHR and sgRNA cassette into digestion product; if design includes \n      recoded region, include in assembly as well\n   7. Check all steps by sequencing\n   8. Transfect into Cas9 or Cas12-containing cell lines!\n * Alternatively, the tags, recoded region, RHR, and sgRNA \ncassette can often be synthesized commercially as \na single gene fragment to be inserted in a simpler Gibson reaction.'
+
 instructions_custom = '\n*** Assembly instructions for custom base plasmid constructs: ***\n\n   1. Obtain primers in Oligo csv file and gene fragments in gBlock fasta file \n      from DNA synthesis\n   2. PCR the RHR and LHR fragments from genomic DNA using the corresponding\n      Gibson Assembly primers in Oligo csv file\n   3. Digest empty parent vector with restriction enzymes as needed for the custom plasmid\n   4. Gibson Assembly fragments as required for custom plasmid\n   5. Check all steps by sequencing\n   6. Transfect into Cas9 or Cas12-containing cell lines!'
 
 instructions = {
 'pSN054':instructions_pSN054,
 'pSN150':instructions_pSN150,
 'pSN150-KO':instructions_pSN150_KO,
+'pPC101': instructions_pPC101,
 'custom': instructions_custom
 }
diff --git a/py/genetargeter/plasmidConstruction.py b/py/genetargeter/plasmidConstruction.py
@@ -54,7 +54,6 @@ def insertTargetingElementsPSN054(plasmid, geneName, gRNA, LHR, recodedRegion, R
     return plas; # returns modified plasmid
 
 
-
 """
 Inserts targeting elements given as arguments into pSN150 at predetermined
 sites. Elements given as arguments must be strings, not GenBankAnn objects.
@@ -118,6 +117,46 @@ def insertTargetingElementsPSN150(plasmid, geneName, gRNA, LHR, recodedRegion, R
 
     return plas; # returns modified plasmid
 
+def insertTargetingElementsPPC101(plasmid, geneName, gRNA, LHR, recodedRegion, RHR, haTag=True):
+    plas = copy.deepcopy(plasmid); # makes a copy of the plasmid object to modify without altering the original
+
+    inLHR = findFirst(plas.origin, cut_FseI) + len(cut_FseI); # index of LHR start site (at end of FseI cut sequence)
+    plas.insertSeq(LHR.upper() + cut_FseI, inLHR); # inserts LHR sequence
+    annLHR = GenBankAnn(geneName+" LHR", "misc_feature", LHR, False, [inLHR,inLHR+len(LHR)], annColors['LHRColor']); # annotation object
+    plas.features.append(annLHR); # adds annotation
+
+    endRHR = findFirst(plas.origin, cut_BsiWI); # index of RHR end site is middle of AhdI cut sequence, conserves frame
+    startRHR = findFirst(plas.origin, cut_AsiSI) + 3; # assume keeping HA tag
+    plas.removeSeq([startRHR, startRHR+2]); # removes sequence that RHR will replace
+
+    if len(recodedRegion) > 0: # if there is a recoded region,
+        inRecode = startRHR; # index of recoded region start site (middle of AhdI cut sequence)
+        plas.insertSeq(recodedRegion.upper(), inRecode); # inserts recoded region sequence
+
+        annRecoded = GenBankAnn(geneName+" Recoded Region", "misc_feature", recodedRegion, False, [inRecode,inRecode+len(recodedRegion)], annColors['recodedRegionColor']); # annotation object
+        plas.features.append(annRecoded); # adds annotation
+        startRHR = inRecode + len(recodedRegion); # shift RHR start site downstream of recoded region
+        if haTag: # if recoded region contains HA tag,
+            annHATag1 = GenBankAnn("HA tag (recoded)", "misc_feature", recodedRegion[9:len(ha_tag)+9], False, [inRecode+9,inRecode+len(ha_tag)+9], annColors['otherAnnColor']); # annotation object for HA tag
+            annHATag2 = GenBankAnn("HA tag (recoded)", "misc_feature", recodedRegion[15+len(ha_tag):len(ha_tag)*2+15], False, [inRecode+15+len(ha_tag),inRecode+len(ha_tag)*2+15], annColors['otherAnnColor']); # annotation object for HA tag
+            plas.features.append(annHATag1); # adds annotation
+            plas.features.append(annHATag2); # adds annotation
+            # plas.insertSeq('ATG', inRecode); # inserts recoded region sequence
+            # startRHR = startRHR + 3; # shift RHR start site downstream of recoded region
+
+    plas.insertSeq(RHR.upper(), startRHR); # inserts RHR sequence
+    annRHR = GenBankAnn(geneName+" RHR", "misc_feature", RHR, False, [startRHR,startRHR+len(RHR)], annColors['RHRColor']); # annotation object
+    plas.features.append(annRHR); # adds annotation
+
+    startGRNA = findFirst(plas.origin, 'AGGGTATACAGGGATATCGA'); # index of gRNA start site (at start of I-PpoI cut sequence)
+    endGRNA = startGRNA + len('AGGGTATACAGGGATATCGA'); # index of gRNA end site (at end of I-PpoI cut sequence)
+    plas.removeSeq([startGRNA, endGRNA]); # removes sequence that gRNA will replace
+    plas.insertSeq(gRNA.upper(), startGRNA); # inserts gRNA sequence with gg sequence used by T7 polymerase
+    annGRNA = GenBankAnn(geneName+" gRNA", "misc_feature", gRNA, False, [startGRNA,startGRNA+len(gRNA)], annColors['gRNAColor']); # annotation object. Note that gRNA starts after "gg" added for T7 polymerase
+    plas.features.append(annGRNA); # adds annotation
+
+    return plas; # returns modified plasmid
+
 
 """
 Inserts targeting elements given as arguments into a custom plasmid.
@@ -223,6 +262,8 @@ def insertTargetingElements(plasmid, geneName, gRNA, LHR, recodedRegion, RHR, pl
         out = insertTargetingElementsPSN150(plasmid, geneName, gRNA, LHR, recodedRegion, RHR, haTag); # use other method
     elif plasmidType == 'pSN150-KO': # if using pSN150-KO,
         out = insertTargetingElementsPSN150(plasmid, geneName, gRNA, LHR, recodedRegion, RHR, haTag, KO=True); # use other method
+    elif plasmidType == 'pPC101':
+        out = insertTargetingElementsPPC101(plasmid, geneName, gRNA, LHR, recodedRegion, RHR, haTag); # use other method
     elif plasmidType == 'custom':
         out = insertTargetingElementsCustom(plasmid, geneName, gRNA, LHR, recodedRegion, RHR); # use other method
 

diff --git a/static/js/main_v1.js → static/js/main_v2.js b/static/js/main_v1.js → static/js/main_v2.js
@@ -820,6 +820,9 @@ function changeUTRTarget() {
     else if (document.getElementById('plasmidType').value === 'pSN150') {
         document.getElementById('locationType').value = '5prime';
     }
+    else if (document.getElementById('plasmidType').value === 'pPC101') {
+        document.getElementById('locationType').value = '5prime';
+    }
     else if (document.getElementById('plasmidType').value === 'pSN150-KO') {
         document.getElementById('locationType').value = 'center';
     }

diff --git a/templates/index.html b/templates/index.html
@@ -25,7 +25,7 @@
 		<link rel="stylesheet" href="static/css/style_v1.css">
 		<script type="text/javascript" src="static/js/jszip.js"></script>
 		<script type="text/javascript" src="static/js/FileSaver.min.js"></script>
-		<script type="text/javascript" src="static/js/main_v1.js"></script>
+		<script type="text/javascript" src="static/js/main_v2.js"></script>
 		<script type="text/javascript" src="static/js/EPPZScroll.js"></script>
 	</head>
 
@@ -65,6 +65,7 @@
 						<option value="pSN054">pSN054 (3' knockdown)</option>
 						<option value="pSN150">pSN150 (5' knockdown)</option>
 						<option value="pSN150-KO">pSN150 (knockout)</option>
+						<option value="pPC101">pPC101 (5' transcriptional knockdown)</option>
 						<option value="custom">Custom plasmid</option>
 						<!-- <option value="pSN150-Ter">pSN150 with Nhe1-free T7 terminator (5' payload)</option> -->
 						<!-- <option value="pSN150-KO-Ter">pSN150 with Nhe1-free T7 terminator (KO construct)</option> -->