Upload app.py

app.py

@@ -223,7 +223,7 @@ def Chopchop(method,select_method):
     expander2.write("[ChopChop Paper](https://academic.oup.com/nar/article/47/W1/W171/5491735)")
     
 
-    expander3 = st.expander("Tool Options: All you can do with this tools")   
+    expander3 = st.expander("Tool Options: All you can do with this tool")   
     
     expander3.write(
     """
@@ -330,53 +330,79 @@ def Guidescan2(method,select_method):
     st.header("Guidescan2: "+method)
     #st.markdown("**Summary**")
     expander = st.expander("Summary")
-    expander.markdown("GuideScan2 employes Cas9 (tracrRNA and crRNA) and Cas12a, previously known as cpf1, (requires only crRNA) for sgRNA design for 8 organisms. It is a memory efficient and improved version of GuideScan that enables construction of high-specificity gRNA databases with reduced off-target effects.")
+    expander.markdown("GuideScan2 employes Cas9 (tracrRNA and crRNA) and Cas12a (also known as cpf1, requires only crRNA) for sgRNA **(single- and paired-gRNA)** design (coding and noncoding genomic regions) for 8 organisms. It enables construction of high-specificity gRNA databases with reduced off-target effects.")
     expander.markdown("CRISPR-Cas9 targets a 20-nucleotide spacer sequence at the end of the gRNA that is complementary to a DNA protospacer sequence followed immediately at the 3’ end by a PAM of the form NGG (more efficient targeting) or NAG (less efficient); here N stands for a ‘wildcard’, i.e. can match any nucleotide. Other natural and engineered CRISPR-Cas systems can **vary in PAM sequence, PAM position with respect to the protospacer sequence, and requirements on the level of similarity between gRNA and the target.**")
     expander.markdown("Given a genomic region, the task of gRNA design is to find gRNAs that can target anywhere in that region. Many potential gRNAs can target at multiple locations in the genome with varying efficiency. Typically a gRNA is designed to target a particular location with **perfect complementarity** with all other targets of this gRNA are being **off-targets**. **Goal** of gRNA design is typically to **maximize gRNA efficiency at the primary target site while minimizing off-targeting.**")
     expander.markdown("Variants and extensions of the gRNA design task include: paired gRNA design to select two gRNAs targeting flanking sites of a genomic region of interest; saturation experiment design to exhaustively select all gRNAs expected to target a selected region of interest; and library design to select a small number of the most effective gRNAs for each of hundreds or thousands of regions of interest.")
     expander1 = st.expander("How it works")
-    expander1.markdown('How it works')
+    
     expander1.write(
     """
-    - Input: Line delimited Genomic intervals (or DNA sequence) as a text file in the webapp **[here](https://guidescan.com/)** in the following format (of genomic range 30bp, 40bp etc):
-        - Line1: chr10:11676698-11676728
-        - Line2: chr1:152220435-152220465
-        - and so on
+    **Algorithm*:* 
+    -   A single gRNA is evaluated against a genome B (Burrows-Wheeler Transform compressed genome and index).
+        -   All occurences of the sgRNA (A spacer sequence g and PAM set P, for all g′ in a Hamming distance (depth-first search using rank-queries on the forward and reverse complement strands of the BWT of the genome) ball of radius k centered at g) in B are identified. 
+        -   These occurrences are validated against the PAM set P, **pruning** any occurrences that are not followed by a PAM in this set. 
+        -   This set of validated occurrences forms the **set of targets for this gRNA**. 
+            -   gRNAs that have multiple perfect occurrences (indistinguishable intended target) are **filtered out**.
+        -   **gRNA with a single perfect occurrence**, considered to be its primary target, is then included in the database.
+        -   All other **targets that contain mismatches are considered off-targets.**
+    
+    -   GuideScan allows: target sequences, PAM, PAM position relative to the gRNA binding sequence, and gRNA length. 
+    **Potential off-targets:**
+    -   Uses a retrieval tree (trie, preprocess the targetable space in the genome, i.e. **all 20-mers followed by primary and secondary PAMs**) data structure to efficiently and precisely enumerates all targetable sequences (with a specific number of mismatches) present in a given genome. 
     """
     )
-    expander1.markdown("- Output: A csv file containing all gRNAs within the genomic regions provided in the input file")
-    expander1.markdown("- **Columns of interest**: Cutting efficiency (**Higher the better**), Specificity (**Higher the better**) [Ref](https://www.biorxiv.org/content/10.1101/2022.05.02.490368v1.full.pdf)")
 
     expander2 = st.expander("References")    
     
     expander2.write("[GuideScan2 Web App](https://guidescan.com)")
     expander2.write("[GuideScan2 Paper](https://www.biorxiv.org/content/10.1101/2022.05.02.490368v1)")
     
-    expander3 = st.expander("Tool Options: All you can do with this tools")
+    expander3 = st.expander("Tool Options: All you can do with this tool")
     
     expander3.write(
     """
-    - This tool offers sgRNA design for:
-        - **CRISPR/Cas9**
-        - **CRISPR/Cpf1**
-        - **Please note that this tool work best for genomic intervals >30bp.**
+    This tool offers sgRNA design for:
+    - **CRISPR/Cas9**
+    - **CRISPR/Cpf1**
+    - **Please note that this tool work best for genomic intervals >30bp.**
+    **Input:**  
+    -   Line delimited Genomic intervals (or DNA sequence) as a text file in the webapp **[here](https://guidescan.com/)** in the following format (of genomic range 30bp, 40bp etc):
+        - Line1: chr10:11676698-11676728
+        - Line2: chr1:152220435-152220465
+        - and so on
+    **Output:**
+    -   A csv file containing all gRNAs within the genomic regions provided in the input file
+    **Columns of interest (at most 6 gRNAa are reported from all possible)**:
+    -   gRNA-Seq and Target-Seq
+    -   PAM
+    -   Number of off-targets
+    -   Cutting efficiency (**Higher the better**)
+    -   Specificity (**Higher the better**) [Ref](https://www.biorxiv.org/content/10.1101/2022.05.02.490368v1.full.pdf)
+    -   Rank:
+        -   Uses a score that balances maximizing the gRNA specificity and cutting efficiency.
+        
     """
     )
-
+    expander3.markdown(gene_rank)
+    
     expander4 = st.expander("Scoring")
     expander4.markdown(
         """
-        **Efficiency:** Rule Set 2
+        **Efficiency (Please see Scoring and Quality Matrices of the README section of this app):** Rule Set 2 [DOENCH 2016](https://www.nature.com/articles/nbt.3437)
         -   sgRNAs were filtered out with cutting efficiency less than 0.25 or specificity less than 0.20
-        -   Selected six gRNAs for each gene. For genes with more than siz sgRNAs, Ranked Genes and (selected six genes)
-            -   ranked gRNAs for each gene using a simple score that balances maximizing the gRNA specificity and cutting efficiency.
-            -   nucleotide at the 5’ end of gRNA (called g) is replaced with a G (called g') for better efficiency
-            -   ranking gRNAs for each gene is defined as
-        gRNA specificity score using the formula from a previous publication [22] based on the CFD score:
+        -   Selected six gRNAs for each gene. For genes with more than six sgRNAs, Ranked Genes and (selected six genes)
+            -   Ranked gRNAs for each gene using a simple score that balances maximizing the gRNA specificity and cutting efficiency.
+            -   Nucleotide at the 5’ end of gRNA (called g) is replaced with a G (called g') for better efficiency
+            -   Ranking gRNAs for each gene is defined as
+        **sgRNA Specificity and Rank score:** [DOENCH 2016](https://www.nature.com/articles/nbt.3437)
         """
     )
     expander4.markdown(latext2)
+    #expander4.markdown('sgRNA Specifity (off-target) Score')
+    expander4.markdown('sgRNA Rank Score')
     expander4.markdown(gene_rank)
+    
     st.markdown("**Please note that the software was run with Cas9 (NGG PAM) and cpf1 (TTG PAM) option with all other options left as default.**")
     st.markdown(tips,unsafe_allow_html=True)
     st.markdown(caution,unsafe_allow_html=True)
@@ -391,9 +417,9 @@ def Pnbdesigner(method,select_method):
     #expander.markdown("END NEW")
     expander.markdown(
         """
-        DNA base editors (BEs), cytosine base editors which employes cytidine-deaminase  (CBEs: C/G -> T/A converters) and adenine base editors which employes Adenine-deaminase (ABEs: A/T -> G/C converters) **can only introduce 4 edits** via sgRNA. 
+        Single base editors (BEs) employe cytidine-deaminase (Cytosine BE, CBEs: C/G -> T/A converters) or Adenine-deaminase (Adenine BE, ABEs: A/T -> G/C converters) **can only introduce 4 edits** via sgRNA. 
         
-        Prime Editors **(PEs)**, employing Cas9 nickase fused to an engineered reverse transcriptase via a gRNA called prime editing guide RNA (pegRNA), on the other hand **can do all 12 edits.** PEs use pegRNA consisting of a 20 nt guide sequence, a primer binding site (PBS) and a reverse transcriptase template (RTT). The guide directs the Cas enzyme to a target site, the PBS hybridizes to the opposite strand to prime the reverse transcriptase, and the RTT integrates the desired genomic alteration. **Optimized** PE2, called PE3 and PE3b with reduced off-targets are used. 
+        Prime Editors **(PEs)**, employing Cas9 nickase fused to an engineered reverse transcriptase template **(RTT, a wild-type Moloney Murine Leukemia Virus (M-MLV) for PE1 and mutagenised M-MLV in PE2 systems for enhanced DNA-RNA affinity, enzyme processivity, and thermostability)** via a gRNA called prime editing guide RNA **(pegRNA)**, on the other hand **can do all 12 edits.** PEs use pegRNA consisting of a 20 nt guide sequence, a primer binding site **(PBS)** and an RTT. The guide directs the Cas enzyme to a target site, the PBS hybridizes to the opposite strand to prime the reverse transcriptase, and the RTT integrates the desired genomic alteration. **Optimized** PE2, called (by employing additional sgRNA to nick the unedited strand so that cell's natural repair system copies the information in the edited strand to the complementary strand, permanently installing the edit) PE3 and PE3b with reduced off-targets are used. 
         
         **PnB Designer** allows design of pegRNAs for PEs and guide RNAs for CBE and the most recent ABEs such as ABEmax and ABE8e. PnB Designer makes it easy to design targeting guide RNAs for single or multiple targets on a variant or reference genome from organisms (and non-model organisms or synthetic constructs) spanning multiple kingdoms. **PnB Designer enables design of pegRNAs for all known disease causing mutations available in ClinVar**
         
@@ -419,49 +445,83 @@ def Pnbdesigner(method,select_method):
         """
     )
     image = Image.open('pe1.png')
-    expander1.image(image, caption='Prime Editing. Figure from: https://www.addgene.org/crispr/prime-edit/')
-
+    expander1.image(image, caption='Prime Editing. https://www.addgene.org/crispr/prime-edit/')
+    expander1.markdown(
+    """
+    **Design strategy for pegRNAs:**
+    -   PnB Designer scans the sense and antisense strands to find all possible 5′-NGG-3′ protospacer adjacent motif (PAM) sites around the edit position, beginning+6 nt to the 3′ end of the desired edit and then scanning 100 nt in the 5′ direction, giving the user the option to choose also very distant PAMs. 
+    -   All possible NGG PAMs are stored and evaluated in respect to their distance from the edit position and the input RTT length. 
+    -   A pegRNA is considered a possible candidate if the edit is fully covered by the RTT. 
+    -   PnB Designer then stores the protospacer, PBS, and RTT sequences. 
+    -   Nicking guides for the PE3 and PE3b systems are designed and filtered to provide a suitable selection of gRNAs. 
+    -   For PE3, only nicking guides 40–100 nt up/downstream of the initial nick are considered. 
+    **Design strategy for BEs gRNAs:**
+    **Input:**
+    -   Sequence:
+        -   Upstream and downstream sequence with desired edit such as  (one of A>G, T>C, C>T, G>A)
+    -   Genomic coordinates: Retrieves the genomic sequence from the selected reference genome and converts the specific variant sequence to include the SNV. 
+        -   The resulting sequence is searched for **PAM (5′-NGG-3′ (SpCas9), 5′-NGA-3′ (SpCas9-VRQR), 5′-NGCG-3′ (SpCas9-NG), 5′-NNGRRT-3′ (SaCas9), 5′-NNNRRT-3′ (SaCas9-KKH), SpG 5′-NGN-3′, SpRY 5′-NRN-3′ and 5′-NYN-3′)** sites in the right distance to the SNV given the described editing windows of the Cas9-ABE and -CBE variants. 
+        -   With ABEs, C → T genomic variants can be reverted by A → G conversion on the antisense strand to achieve the intended edit on the sense strand. 
+        -   With CBEs, C → T and G → A conversions are possible. All previously described PAM variants with their respective editing window are tested against the edit.
+        -   Editing windows are defined based on the experimental data. 
+            -   ABEmax was implemented with an editing window from base 5–7, with base 1 being the most distal from the PAM site. 
+            -   For BE3 (R33A/K34A), the strong sequence preference for a 5′ T next to the edit has been included as well
+    """
+    )
     expander2 = st.expander("References")
     
     expander2.write("[PnB Designer Web App](https://fgcz-shiny.uzh.ch/PnBDesigner/)")
     expander2.write("[PnB Designer Paper](https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-021-04034-6)")
     
-    expander3 = st.expander("Tool Options: All you can do with this tools")
+    expander3 = st.expander("Tool Options: All you can do with this tool")
     
     expander3.write(
     """
-    - Input: Multiple lines provided in as a csv file in the webapp **[here](https://fgcz-shiny.uzh.ch/PnBDesigner/)** in the following format:
+    This tool can be run in **two modes**:
+    - **Base editing mode:**
+        - Does not allow A>T or G>C, dels, or insertions.
+        - Only **180**/414 variants could be targeted. 
+        - **Columns of interest**: Protospacer, PAM and Base Editor (the system for producing the base edit). 
+        -   **There is no score**.
+    - **Prime editing mode:**
+        - Requires two guides: detailed in two files.
+        - pegRNA oligos for cloning.
+        - **Score: Higer is better**.
+        - Nicking guides: the corresponding nicking guides
+    
+    **Input**
+    -   Multiple lines provided in as a csv file in the webapp **[here](https://fgcz-shiny.uzh.ch/PnBDesigner/)** in the following format:
         - Prime editing:
             - varinat, chromosome num, genomic location, Edit, gene orientation, PBS, RTT
             - Ex: rs7412, 19, 44908822, insA, +, 13, 13
         - Base editing
             - varinat, chromosome num, genomic location, SNO, gene orientation, PBS, RTT
             - Ex: rs7412, 19, 44908822, C>T, +
+    **Output:** A csv file
+    -   Base editing  
+        -   20 nt protospacer sequence (targeting the variant sequence)
+        -   Edit position
+        -   PAM site
+        -   Suggested base editor that can target the variant
+        -   Score: No score is provided
+    -   Prime editing
+        -   pegRNA (protospacer and extension seq for both strands)
+        -   Edit position
+        -   PAM and PAM strand
+        -   Score (Higher the better)
+        -   PBS and RTT length
+        -   Nicking guides (PE3 or PE3b system) shown by selecting Nicking_guides_PE3_PE3B from the side bar.
     """
     )
-    expander3.markdown("- Output: A csv file")
-    expander3.markdown(tips,unsafe_allow_html=True)
-    expander3.write(
-    """
-    - This tool can be run in two modes:
-        - **Base editing mode:**
-            - Does not allow A>T or G>C, dels, or insertions.
-            - Only **180**/414 variants could be targeted. 
-            - - **Columns of interest**: Protospacer, PAM and Base Editor (the system for producing the base edit). **There is no score**.
-        - **Prime editing mode:**
-            - Requires two guides: detailed in two files.
-            - pegRNA oligos for cloning.
-            - **Score: Higer is better**.
-            - Nicking guides: the corresponding nicking guides
-    """
-    )
+    
+    #expander3.markdown(tips,unsafe_allow_html=True)
     expander4 = st.expander("Scoring")
     expander4.markdown(
         """
-        Scoring
-        **Prime Editing:** PBS and RTT length are important parameters for successful pegRNA design
-        -   in PnB Designer, PBS and RTT lengths are by default set at suggested values of 13 nt
-        **pegRNA Score:** Sum of all penalties
+        **Prime Editing:**  
+        Primer binding site (PBS) and reverse transcriptase templeta (RTT) length are important parameters for successful pegRNA design. In PnB Designer, PBS and RTT lengths are by default set at suggested values of 13 nt. The pegRNA Score follows a [penalty system](https://www.nature.com/articles/s41586-019-1711-4) with **larger negative numbers** are indicative of worse pegRNA designs.  
+        
+        **pegRNA Score (Sum of all penalties):**
         -   Penalty system
             -   C as the first base in the 3′ extension: penalty score =  − 28
             -   T (thymine) > 4 nucleotides in the 3′ extension of the pegRNA are strongly penalized with a score =  − 50
@@ -482,34 +542,26 @@ def SNPcrispr(method,select_method):
         """
         **SNP-CRISPR** 
         -   Facilitate identification of sgRNAs in **non-reference genomes**, **across varying genetic backgrounds** or for specific targeting of **SNP-containing alleles** (for example, disease relevant mutations). 
-        -   It computes **efficiency and specificity** scores for sgRNA designs targeting **both the variant and the reference.**
+        -   It computes **efficiency and specificity** scores for sgRNA designs targeting **both** the **variant** and the **reference**.
+        -   Can be used to design sgRNAs based on public variant data sets or user-identified variants
         -   Design sgRNAs for NGG and NAG PAM sequences
         """
     )
-    expander1 = st.expander("How it works: Input and Output")
+    expander1 = st.expander("How it works")
     expander1.write(
     """
-    **Design:** 
+    **Design:**  
     - SNP-CRISPR validates the input reference sequences and **warn if the submitted reference sequences does not match**, which might reflect a different version of the genome assembly being used in the user input vs. SNP-CRISPR and re-constructs the template sequence, swapping the reference nucleotide with the variant nucleotide for SNPs, while inserting or deleting the corresponding fragment for indel type variants.
-    - Computes potential variant-targeting sgRNAs based on availability of PAM sequences in the neighboring region. 
-    - sgRNA designs that contain four or more consecutive thymine residues, which can result in termination of RNA transcription by RNA polymerase III, are filtered out.
-    - Computes efficiency and specificity (based on BLAST results against the reference genome) scores [Housden et al. 2015](https://pubmed.ncbi.nlm.nih.gov/26350902/).
-    - **For identification of the best variant-specific sgRNAs, following information are provided.**
-        -   Iinformation on both sgRNAs targeting specific variants and sgRNAs targeting the reference sequence in the same region. 
-        -   The efficiency score and an off-target score, 
-        -   Positions of relevant SNPs or indels in the sgRNA are included.
-    """
-    )
-    expander1.write(
-    """
-    - **Input:** Multiple lines provided in as a (6 columns) csv file uploaded to the webapp **[here](https://www.flyrnai.org/tools/snp_crispr/web/)** in the following format:
-        - varinat, chromosome, position, strand, reference, variant
-        - Ex: rs7412, 19, 44908822, C, +, T
+    - Computes potential variant-targeting sgRNAs based on **availability of PAM (NGG or NAG) sequences** in the neighboring region. 
+    - sgRNA designs that contain **four or more consecutive thymine residues**, which can result in termination of RNA transcription by RNA polymerase III, **are filtered out**.
+    - Computes efficiency [Housden et al. 2015](https://pubmed.ncbi.nlm.nih.gov/26350902/) and specificity (based on BLAST results against the reference genome) scores.  
+    **For identification of the best variant-specific sgRNAs, following information are provided.**
+    -   Iinformation on both sgRNAs targeting specific variants and sgRNAs targeting the reference sequence in the same region. 
+    -   The efficiency score and an off-target score
+    -   Positions of relevant SNPs or indels in the sgRNA are included.
     """
     )
-    expander1.markdown("- **Output:** A csv file")
-    expander1.markdown("- **Columns of interest**: Housden Efficiency Score [Ref](https://www.ncbi.nlm.nih.gov/pubmed/26350902) (Range from 1.47-12.32 **(higher is better, > 5 recommended))** and Off Target Score (Range from 0-5441.73 (lower is better, < 1 recommended))")
-    expander1.markdown("**To facilitate identification of the best variant-specific sgRNAs, we provide information about both sgRNAs targeting specific variants and sgRNAs targeting the reference sequence in the same region. The efficiency score and an off-target score are provided, and the positions of relevant SNPs or indels in the sgRNA are included so that users can select the most suitable sgRNA or filter out less optimal ones.**")
+    #expander1.markdown("**To facilitate identification of the best variant-specific sgRNAs, we provide information about both sgRNAs targeting specific variants and sgRNAs targeting the reference sequence in the same region. The efficiency score and an off-target score are provided, and the positions of relevant SNPs or indels in the sgRNA are included so that users can select the most suitable sgRNA or filter out less optimal ones.**")
     
     
     expander2 = st.expander("References")
@@ -517,15 +569,22 @@ def SNPcrispr(method,select_method):
     expander2.write("[SNP_CRISPR Paper](https://academic.oup.com/g3journal/article/10/2/489/6026318)")
     
     
-    expander3 = st.expander("Tool Options: All you can do with this tools")
-    expander3.markdown(tips,unsafe_allow_html=True)
+    expander3 = st.expander("Tool Options: All you can do with this tool")
+    #expander3.markdown(tips,unsafe_allow_html=True)
     expander3.write(
     """
-    - This tool can design guides for:
-        - **NGG.**
-        - **NAG.**
-        - **Target multiple variants within the same guide.**
-        - Public variant data sets or user-identified variants.
+    This tool can design guides for:
+    - **NGG.**
+    - **NAG.**
+    - **Target multiple variants within the same guide.**
+    - Public variant data sets or user-identified variants.  
+    **Input:** Multiple lines provided in as a (6 columns) csv file uploaded to the webapp **[here](https://www.flyrnai.org/tools/snp_crispr/web/)** in the following format:
+    - varinat, chromosome, position, strand, reference, variant
+    - Ex: rs7412, 19, 44908822, C, +, T
+    **Output:** A csv file  
+    -   **Columns of interest**: 
+        -   Housden Efficiency Score [Ref](https://www.ncbi.nlm.nih.gov/pubmed/26350902) (Range from 1.47-12.32 **(higher is better, > 5 recommended))**
+        -   Off Target Score (Range from 0-5441.73 (lower is better, < 1 recommended))
     """
     )
     
@@ -572,7 +631,7 @@ def ecrisp(select_method):
     expander2 = st.expander("References")
     expander2.write("[E-CRISP Web App](http://www.e-crisp.org/E-CRISP/)")
     expander2.write("[E-CRISP Paper](https://www.nature.com/articles/nbt.3026)")
-    expander3 = st.expander("Tool Options: All you can do with this tools")
+    expander3 = st.expander("Tool Options: All you can do with this tool")
     expander3.write(
     """
     - This tool offers single or paired sgRNA and: