-
Notifications
You must be signed in to change notification settings - Fork 45
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
fix peptide hemolytic templates (#413)
- Loading branch information
1 parent
94a7772
commit 111cf18
Showing
1 changed file
with
148 additions
and
138 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,147 +1,157 @@ | ||
| --- | ||
| name: peptides_hemolytic | ||
| description: "Hemolysis is referred to the disruption of erythrocyte\nmembranes that decrease the life span of red blood cells and causes\nthe release of\ | ||
| \ Hemoglobin. It is critical to identify non-hemolytic\nantimicrobial peptides as a non-toxic and safe measure against bacterial\ninfections. However,\ | ||
| \ distinguishing between hemolytic and non-hemolytic\npeptides is a challenge, since they primarily exert their activity at the\ncharged surface of\ | ||
| \ the bacterial plasma membrane.\nThe data here comes from the Database of Antimicrobial Activity and Structure of\nPeptides (DBAASP v3). Hemolytic\ | ||
| \ activity is defined by extrapolating a measurement\nassuming dose response curves to the point\nat which 50% of red blood cells are lysed. Activities\ | ||
| \ below 100 mu g/ml, are\nconsidered hemolytic.\nThe data contains sequences of only L- and canonical amino acids. Each measurement\nis treated independently,\ | ||
| \ so sequences can appear multiple times. This experimental\ndataset contains noise, and in some observations (40%), an identical sequence appears\n\ | ||
| in both negative and positive class. As an example, sequence \"RVKRVWPLVIRTVIAGYNLYRAIKKK\"\nis found to be both hemolytic and\nnon-hemolytic in two\ | ||
| \ different lab experiments (i.e. two different training examples). " | ||
| description: "Hemolysis is referred to the disruption of erythrocyte\nmembranes that\ | ||
| \ decrease the life span of red blood cells and causes\nthe release of Hemoglobin.\ | ||
| \ It is critical to identify non-hemolytic\nantimicrobial peptides as a non-toxic\ | ||
| \ and safe measure against bacterial\ninfections. However, distinguishing between\ | ||
| \ hemolytic and non-hemolytic\npeptides is a challenge, since they primarily exert\ | ||
| \ their activity at the\ncharged surface of the bacterial plasma membrane.\nThe\ | ||
| \ data here comes from the Database of Antimicrobial Activity and Structure of\n\ | ||
| Peptides (DBAASP v3). Hemolytic activity is defined by extrapolating a measurement\n\ | ||
| assuming dose response curves to the point\nat which 50% of red blood cells are\ | ||
| \ lysed. Activities below 100 mu g/ml, are\nconsidered hemolytic.\nThe data contains\ | ||
| \ sequences of only L- and canonical amino acids. Each measurement\nis treated independently,\ | ||
| \ so sequences can appear multiple times. This experimental\ndataset contains noise,\ | ||
| \ and in some observations (40%), an identical sequence appears\nin both negative\ | ||
| \ and positive class. As an example, sequence \"RVKRVWPLVIRTVIAGYNLYRAIKKK\"\nis\ | ||
| \ found to be both hemolytic and\nnon-hemolytic in two different lab experiments\ | ||
| \ (i.e. two different training examples). " | ||
| targets: | ||
| - id: hemolytic | ||
| description: The ability of a peptide sequence to lyse red blood cells (1) or not (0). | ||
| units: | ||
| type: boolean | ||
| names: | ||
| - noun: hemolytic activity | ||
| - noun: hemolysis | ||
| - verb: lyse red blood cells | ||
| - adjective: hemolytic | ||
| - gerund: lysing red blood cells | ||
| uris: | ||
| - id: hemolytic | ||
| description: The ability of a peptide sequence to lyse red blood cells (1) or not | ||
| (0). | ||
| units: null | ||
| type: boolean | ||
| names: | ||
| - noun: hemolytic activity | ||
| - noun: hemolysis | ||
| - verb: lyse red blood cells | ||
| - adjective: hemolytic | ||
| - gerund: lysing red blood cells | ||
| uris: null | ||
| benchmarks: [] | ||
| identifiers: | ||
| - id: sequence | ||
| type: Other | ||
| description: amino acid sequence | ||
| - id: sequence | ||
| type: Other | ||
| description: amino acid sequence | ||
| license: CC BY 4.0 | ||
| links: | ||
| - url: https://doi.org/10.1021/acs.jcim.2c01317 | ||
| description: corresponding publication | ||
| - url: https://doi.org/10.1093/nar/gkaa991 | ||
| description: data source | ||
| - url: https://doi.org/10.1021/acs.jcim.2c01317 | ||
| description: corresponding publication | ||
| - url: https://doi.org/10.1093/nar/gkaa991 | ||
| description: data source | ||
| num_points: 6541 | ||
| bibtex: | ||
| - |- | ||
| @article{Martins2012, | ||
| doi = {10.1021/ci300124c}, | ||
| url = {https://doi.org/10.1021/ci300124c}, | ||
| year = {2012}, | ||
| month = jun, | ||
| publisher = {American Chemical Society (ACS)}, | ||
| volume = {52}, | ||
| number = {6}, | ||
| pages = {1686--1697}, | ||
| author = {Ines Filipa Martins and Ana L. Teixeira and Luis Pinheiro | ||
| and Andre O. Falcao}, | ||
| title = {A Bayesian Approach to in Silico Blood-Brain Barrier Penetration Modeling}, | ||
| journal = {Journal of Chemical Information and Modeling} | ||
| - |- | ||
| @article{Wu2018, | ||
| doi = {10.1039/c7sc02664a}, | ||
| url = {https://doi.org/10.1039/c7sc02664a}, | ||
| year = {2018}, | ||
| publisher = {Royal Society of Chemistry (RSC)}, | ||
| volume = {9}, | ||
| number = {2}, | ||
| pages = {513--530}, | ||
| author = {Zhenqin Wu and Bharath Ramsundar and Evan~N. Feinberg and Joseph | ||
| Gomes and Caleb Geniesse and Aneesh S. Pappu and Karl Leswing and Vijay Pande}, | ||
| title = {MoleculeNet: a benchmark for molecular machine learning}, | ||
| journal = {Chemical Science} | ||
| - |- | ||
| @article{Martins2012, | ||
| doi = {10.1021/ci300124c}, | ||
| url = {https://doi.org/10.1021/ci300124c}, | ||
| year = {2012}, | ||
| month = jun, | ||
| publisher = {American Chemical Society (ACS)}, | ||
| volume = {52}, | ||
| number = {6}, | ||
| pages = {1686--1697}, | ||
| author = {Ines Filipa Martins and Ana L. Teixeira and Luis Pinheiro | ||
| and Andre O. Falcao}, | ||
| title = {A Bayesian Approach to in Silico Blood-Brain Barrier Penetration Modeling}, | ||
| journal = {Journal of Chemical Information and Modeling} | ||
| - |- | ||
| @article{Wu2018, | ||
| doi = {10.1039/c7sc02664a}, | ||
| url = {https://doi.org/10.1039/c7sc02664a}, | ||
| year = {2018}, | ||
| publisher = {Royal Society of Chemistry (RSC)}, | ||
| volume = {9}, | ||
| number = {2}, | ||
| pages = {513--530}, | ||
| author = {Zhenqin Wu and Bharath Ramsundar and Evan~N. Feinberg and Joseph | ||
| Gomes and Caleb Geniesse and Aneesh S. Pappu and Karl Leswing and Vijay Pande}, | ||
| title = {MoleculeNet: a benchmark for molecular machine learning}, | ||
| journal = {Chemical Science} | ||
| templates: | ||
| - The sequence of {#amino acids|AAs!} {sequence#} {#shows|exhibits|demonstrates!} {hemolytic#no &NULL}{hemolytic__names__adjective} properties. | ||
| - The amino acid sequence {sequence#} {#shows|exhibits|displays!} {hemolytic#no &NULL}{hemolytic__names__adjective} properties. | ||
| - Based on the {sequence__description} {#representation |!}{sequence#}, the amino acid sequence has {hemolytic#no &NULL}{hemolytic__names__adjective} | ||
| {#properties|characteristics|features!}. | ||
| - The {sequence__description} {sequence#} {#represents|is from!} an amino acid sequence that is {hemolytic#not &NULL}identified as {hemolytic__names__adjective}. | ||
| - The {#amino acid sequence |!}{sequence__description} {sequence#} is {hemolytic#not &NULL}{hemolytic__names__adjective}. | ||
| - |- | ||
| Task: Please classify a amino acid sequence based on the description. | ||
| Description: A amino acid sequence that is {hemolytic__names__adjective}. | ||
| {#amino acid sequence |!}{sequence__description}: {sequence#} | ||
| Constraint: Even if you are {#uncertain|not sure!}, you must pick either "True" or "False" without using any {#other|additional!} words. | ||
| Result: {hemolytic#False&True} | ||
| - |- | ||
| Task: Please classify a amino acid sequence based on the description. | ||
| Description: A amino acid sequence that is {hemolytic__names__adjective}. | ||
| {#amino acid sequence |!}{sequence__description}: {sequence#} | ||
| Constraint: Answer the question in a {#full|complete!} sentence. | ||
| Result: This amino acid sequence is {hemolytic#not &NULL}{hemolytic__names__adjective}. | ||
| - |- | ||
| Task: Please {#give me|create|generate!} a {#amino acid sequence |!}{sequence__description} based on the {#text |!}description{# below|!}. | ||
| Description: A amino acid sequence that is {hemolytic__names__adjective}. | ||
| Result: {sequence#} | ||
| - |- | ||
| User: Can you {#tell me|derive|estimate!} if the amino acid sequence with the {sequence__description} {sequence#} is {hemolytic__names__adjective}? | ||
| Assistant: {hemolytic#No&Yes}, this amino acid sequence is {hemolytic#not &NULL}{hemolytic__names__adjective}. | ||
| - |- | ||
| User: Is the amino acid sequence with the {sequence__description} {sequence#} {hemolytic__names__adjective}? | ||
| Assistant: {hemolytic#No&Yes}, it is {hemolytic#not &NULL}{hemolytic__names__adjective}. | ||
| - |- | ||
| User: Can you {#give me|create|generate!} the {sequence__description} of a amino acid sequence that is {hemolytic#not &NULL}{hemolytic__names__adjective}? | ||
| Assistant: {#Yes|Of course|Sure|Yes, I'm happy to help!}, here you go: {sequence#} | ||
| - |- | ||
| User: I'm {#searching|looking!} for the {sequence__description} of a amino acid sequence that is {hemolytic#not &NULL}{hemolytic__names__adjective}? | ||
| Assistant: This is a amino acid sequence that is {hemolytic#not &NULL}{hemolytic__names__adjective}: {sequence#} | ||
| - |- | ||
| User: I want to {#come up with|create|generate!} a {#amino acid sequence |!}{sequence__description}. | ||
| Assistant: {#This sounds very exciting. |This sounds very interesting. !}Should I consider any {#constraints|specific points!} for the {#generation|creation!}? | ||
| User: Yes, please. The amino acid sequence should {hemolytic#not &NULL}be {hemolytic__names__adjective}. | ||
| Assistant: {#Ok|Got it!},{# here you go,|!} this {sequence__description} is {hemolytic#not &NULL}{hemolytic__names__adjective}: {sequence#} | ||
| - |- | ||
| User: I want to {#come up with|create|generate!} a {#amino acid sequence |!}{sequence__description}. | ||
| Assistant: {#This sounds very exciting. |This sounds very interesting. !}Should it be a special {#amino acid sequence|one!}? | ||
| User: Yes, the amino acid sequence should {hemolytic#not &NULL}be {hemolytic__names__adjective}. | ||
| Assistant: {#Understood|Got it|Ok!}, this {sequence__description} is {hemolytic#not &NULL}{hemolytic__names__adjective}: {sequence#} | ||
| - Is the {sequence__description} {sequence#} {hemolytic__names__adjective}:<EOI> {hemolytic#no&yes} | ||
| - |- | ||
| Task: Please classify a amino acid sequence based on the description. | ||
| Description: A amino acid sequence that is {hemolytic__names__adjective}. | ||
| {#amino acid sequence |!}{sequence__description}: {sequence#} | ||
| Constraint: Even if you are {#uncertain|not sure!}, you must pick either "True" or "False" without using any {#other|additional!} words. | ||
| Result:<EOI> {hemolytic#False&True} | ||
| - |- | ||
| Task: Please {#give me|create|generate!} a {#amino acid sequence |!}{sequence__description} based on the {#text |!}description{# below|!}. | ||
| Description: A amino acid sequence that is {hemolytic__names__adjective}. | ||
| Result:<EOI> {sequence#} | ||
| - |- | ||
| Task: Please answer the multiple choice question. | ||
| Question: Is the amino acid sequence with the {sequence__description} {#representation of |!}{sequence#} {hemolytic__names__adjective}? | ||
| Constraint: Even if you are {#uncertain|not sure!}, you must pick either {%multiple_choice_enum%2%aA1} without using any {#other|additional!} words. | ||
| Options: | ||
| {hemolytic%} | ||
| Answer: {%multiple_choice_result} | ||
| - |- | ||
| Task: Please answer the multiple choice question. | ||
| Question: Is the amino acid sequence with the {sequence__description} {#representation of |!}{sequence#} {hemolytic__names__adjective}? | ||
| Constraint: Even if you are {#uncertain|not sure!}, you must pick either {%multiple_choice_enum%2%aA1} without using any {#other|additional!} words. | ||
| Options: | ||
| {hemolytic%} | ||
| Answer:<EOI> {%multiple_choice_result} | ||
| - |- | ||
| Task: Please answer the multiple choice question. | ||
| Question: Which amino acid sequences are {hemolytic#not &NULL}{hemolytic__names__adjective}? | ||
| Constraint: You must select none, one or more options from {%multiple_choice_enum%2-5%aA1} without using any {#other|additional!} words. | ||
| Options: | ||
| {sequence%hemolytic%} | ||
| Answer: {%multiple_choice_result} | ||
| - |- | ||
| Task: Please answer the multiple choice question. | ||
| Question: Which amino acid sequences are {hemolytic#not &NULL}{hemolytic__names__adjective}? | ||
| Constraint: You must select none, one or more options from {%multiple_choice_enum%2-5%aA1} without using any {#other|additional!} words. | ||
| Options: | ||
| {sequence%hemolytic%} | ||
| Answer:<EOI> {%multiple_choice_result} | ||
| - The sequence of {#amino acids|AAs!} {sequence#} {#shows|exhibits|demonstrates!} {hemolytic#no | ||
| &NULL}{hemolytic__names__adjective} properties. | ||
| - The amino acid sequence {sequence#} {#shows|exhibits|displays!} {hemolytic#no &NULL}{hemolytic__names__adjective} | ||
| properties. | ||
| - Based on the {#amino acid sequence |sequence of amino acids !}{sequence#}, the peptide has {hemolytic#no &NULL}{hemolytic__names__adjective} {#properties|characteristics|features!}. | ||
| - The {sequence__description} {sequence#} {#represents|is from!} a peptide | ||
| that is {hemolytic#not &NULL}identified as {hemolytic__names__adjective}. | ||
| - The {#amino acid sequence|sequence of amino acids!} {sequence#} is {hemolytic#not | ||
| &NULL}{hemolytic__names__adjective}. | ||
| - |- | ||
| Task: Please classify a peptide based on the description. | ||
| Description: A amino acid sequence that is {hemolytic__names__adjective}. | ||
| {#amino acid sequence |sequence of amino acids!}: {sequence#} | ||
| Constraint: Even if you are {#uncertain|not sure!}, you must pick either "True" or "False" without using any {#other|additional!} words. | ||
| Result: {hemolytic#False&True} | ||
| - |- | ||
| Task: Please classify a amino acid sequence based on the description. | ||
| Description: A amino acid sequence that is {hemolytic__names__adjective}. | ||
| {#amino acid sequence |sequence of amino acids !}: {sequence#} | ||
| Constraint: Answer the question in a {#full|complete!} sentence. | ||
| Result: This amino acid sequence is {hemolytic#not &NULL}{hemolytic__names__adjective}. | ||
| - |- | ||
| Task: Please {#give me|create|generate!} a {#amino acid sequence|sequence of amino acids!} based on the {#text |!}description{# below|!}. | ||
| Description: A amino acid sequence that is {hemolytic__names__adjective}. | ||
| Result: {sequence#} | ||
| - |- | ||
| User: Can you {#tell me|derive|estimate!} if the peptide with the {#amino acid sequence|sequence of amino acids!} {sequence#} is {hemolytic__names__adjective}? | ||
| Assistant: {hemolytic#No&Yes}, this amino acid sequence is {hemolytic#not &NULL}{hemolytic__names__adjective}. | ||
| - |- | ||
| User: Is the peptide with the {#amino acid sequence|sequence of amino acids!} {sequence#} {hemolytic__names__adjective}? | ||
| Assistant: {hemolytic#No&Yes}, it is {hemolytic#not &NULL}{hemolytic__names__adjective}. | ||
| - |- | ||
| User: Can you {#give me|create|generate!} the {sequence__description} of a peptide that is {hemolytic#not &NULL}{hemolytic__names__adjective}? | ||
| Assistant: {#Yes|Of course|Sure|Yes, I'm happy to help!}, here you go: {sequence#} | ||
| - |- | ||
| User: I'm {#searching|looking!} for the {sequence__description} of a peptide that is {hemolytic#not &NULL}{hemolytic__names__adjective}? | ||
| Assistant: This is a amino acid sequence that is {hemolytic#not &NULL}{hemolytic__names__adjective}: {sequence#} | ||
| - |- | ||
| User: I want to {#come up with|create|generate!} a {#amino acid sequence|sequence of amino acids|peptide!}. | ||
| Assistant: {#This sounds very exciting. |This sounds very interesting. !}Should I consider any {#constraints|specific points!} for the {#generation|creation!}? | ||
| User: Yes, please. The amino acid sequence should {hemolytic#not &NULL}be {hemolytic__names__adjective}. | ||
| Assistant: {#Ok|Got it!},{# here you go,|!} this {sequence__description} is {hemolytic#not &NULL}{hemolytic__names__adjective}: {sequence#} | ||
| - |- | ||
| User: I want to {#come up with|create|generate!} a {#amino acid sequence|sequence of amino acids|peptide!}. | ||
| Assistant: {#This sounds very exciting. |This sounds very interesting. !}Should it be a special {#amino acid sequence|one!}? | ||
| User: Yes, the amino acid sequence should {hemolytic#not &NULL}be {hemolytic__names__adjective}. | ||
| Assistant: {#Understood|Got it|Ok!}, this {sequence__description} is {hemolytic#not &NULL}{hemolytic__names__adjective}: {sequence#} | ||
| - Is the {sequence__description} {sequence#} {hemolytic__names__adjective}:<EOI> {hemolytic#no&yes} | ||
| - |- | ||
| Task: Please classify a {#amino acid sequence|sequence of amino acids|peptide!} based on the description. | ||
| Description: A amino acid sequence that is {hemolytic__names__adjective}. | ||
| {#amino acid sequence|sequence of amino acids!}: {sequence#} | ||
| Constraint: Even if you are {#uncertain|not sure!}, you must pick either "True" or "False" without using any {#other|additional!} words. | ||
| Result:<EOI> {hemolytic#False&True} | ||
| - |- | ||
| Task: Please {#give me|create|generate!} a {#amino acid sequence|sequence of amino acids|peptide!} based on the {#text |!}description{# below|!}. | ||
| Description: A {#amino acid sequence|sequence of amino acids|peptide!} that is {hemolytic__names__adjective}. | ||
| Result:<EOI> {sequence#} | ||
| - |- | ||
| Task: Please answer the multiple choice question. | ||
| Question: Is the peptide with the {sequence__description} {#representation of |!}{sequence#} {hemolytic__names__adjective}? | ||
| Constraint: Even if you are {#uncertain|not sure!}, you must pick either {%multiple_choice_enum%2%aA1} without using any {#other|additional!} words. | ||
| Options: | ||
| {hemolytic%} | ||
| Answer: {%multiple_choice_result} | ||
| - |- | ||
| Task: Please answer the multiple choice question. | ||
| Question: Is the peptide with the {sequence__description} {#representation of |!}{sequence#} {hemolytic__names__adjective}? | ||
| Constraint: Even if you are {#uncertain|not sure!}, you must pick either {%multiple_choice_enum%2%aA1} without using any {#other|additional!} words. | ||
| Options: | ||
| {hemolytic%} | ||
| Answer:<EOI> {%multiple_choice_result} | ||
| - |- | ||
| Task: Please answer the multiple choice question. | ||
| Question: Which amino acid sequences are {hemolytic#not &NULL}{hemolytic__names__adjective}? | ||
| Constraint: You must select none, one or more options from {%multiple_choice_enum%2-5%aA1} without using any {#other|additional!} words. | ||
| Options: | ||
| {sequence%hemolytic%} | ||
| Answer: {%multiple_choice_result} | ||
| - |- | ||
| Task: Please answer the multiple choice question. | ||
| Question: Which amino acid sequences are {hemolytic#not &NULL}{hemolytic__names__adjective}? | ||
| Constraint: You must select none, one or more options from {%multiple_choice_enum%2-5%aA1} without using any {#other|additional!} words. | ||
| Options: | ||
| {sequence%hemolytic%} | ||
| Answer:<EOI> {%multiple_choice_result} |