Video record: https://youtu.be/vhnD4SR8cWI?si=uDZFrw8EG0mXB0bV
\nHere is webinar on another challenge - took place on Kaggle - CAFA5 - on prediсtion of the protein properties (Gene Ontology terms) from the leading experts in the field - authors of the DeepGO paper:
\nhttps://www.nature.com/articles/s42256-024-00795-w
\nEverybody is welcome , it is free. Link to zoom will be here just before the start
\n👨🔬 Robert Hoehndorf, Maxat Kulmanov, \"DeepGO-SE - Protein function prediction as approximate semantic entailment\"
\n⌚️ Thursday 6 June, 17.30 (CET time).
The Gene Ontology (GO) is a formal, axiomatic theory with over 100,000 axioms that describe the molecular functions, biological processes and cellular locations of proteins in three subontologies. Predicting the functions of proteins using the GO requires both learning and reasoning capabilities in order to maintain consistency and exploit the background knowledge in the GO. Many methods have been developed to automatically predict protein functions, but effectively exploiting all the axioms in the GO for knowledge-enhanced learning has remained a challenge.
\nIn this webinar, I will present DeepGO-SE, the latest version of DeepGO methods, that predicts GO functions from protein sequences using a pretrained large language model. DeepGO-SE incorporates the knowledge in GO by learning multiple approximate models of GO using an ontology embedding method. Furthermore, it uses a neural network to predict the truth values of statements about protein functions in these approximate models. We aggregate the truth values over multiple models so that DeepGO-SE approximates semantic entailment when predicting protein functions. We show, using several benchmarks, that the approach effectively exploits background knowledge in the GO and improves protein function prediction compared to state-of-the-art methods.
Video records: https://www.youtube.com/c/SciBerloga - subscribe !
", "messages": [ { "id": "2854641", "postDate": "06/04/2024 11:37:49", "content": "Video record: https://youtu.be/vhnD4SR8cWI?si=uDZFrw8EG0mXB0bV
\nHere is webinar on another challenge - took place on Kaggle - CAFA5 - on prediсtion of the protein properties (Gene Ontology terms) from the leading experts in the field - authors of the DeepGO paper:
\nhttps://www.nature.com/articles/s42256-024-00795-w
\nEverybody is welcome , it is free. Link to zoom will be here just before the start
\n👨🔬 Robert Hoehndorf, Maxat Kulmanov, \"DeepGO-SE - Protein function prediction as approximate semantic entailment\"
\n⌚️ Thursday 6 June, 17.30 (CET time).
The Gene Ontology (GO) is a formal, axiomatic theory with over 100,000 axioms that describe the molecular functions, biological processes and cellular locations of proteins in three subontologies. Predicting the functions of proteins using the GO requires both learning and reasoning capabilities in order to maintain consistency and exploit the background knowledge in the GO. Many methods have been developed to automatically predict protein functions, but effectively exploiting all the axioms in the GO for knowledge-enhanced learning has remained a challenge.
\nIn this webinar, I will present DeepGO-SE, the latest version of DeepGO methods, that predicts GO functions from protein sequences using a pretrained large language model. DeepGO-SE incorporates the knowledge in GO by learning multiple approximate models of GO using an ontology embedding method. Furthermore, it uses a neural network to predict the truth values of statements about protein functions in these approximate models. We aggregate the truth values over multiple models so that DeepGO-SE approximates semantic entailment when predicting protein functions. We show, using several benchmarks, that the approach effectively exploits background knowledge in the GO and improves protein function prediction compared to state-of-the-art methods.
Video records: https://www.youtube.com/c/SciBerloga - subscribe !
", "rawMarkdown": "Video record: https://youtu.be/vhnD4SR8cWI?si=uDZFrw8EG0mXB0bV\n\nHere is webinar on another challenge - took place on Kaggle - CAFA5 - on prediсtion of the protein properties (Gene Ontology terms) from the leading experts in the field - authors of the DeepGO paper:\n\nhttps://www.nature.com/articles/s42256-024-00795-w\n\nEverybody is welcome , it is free. Link to zoom will be here just before the start \n\n👨🔬 Robert Hoehndorf, Maxat Kulmanov, \"DeepGO-SE - Protein function prediction as approximate semantic entailment\" \n⌚️ Thursday 6 June, 17.30 (CET time). \n\n[Add to Google Calendar](https://calendar.google.com/calendar/render?action=TEMPLATE&dates=20240606T153000Z%2F20240606T173000Z&details=Robert%20Hoehndorf%2C%20Maxat%20Kulmanov%2C%20%22DeepGO-SE%20-%20Protein%20function%20prediction%20as%20approximate%20semantic%20entailment%22%20&text=%40SBERLOGABIO%20webinar%20on%20bionformatics%20and%20data%20science%3A)\n\n\nThe Gene Ontology (GO) is a formal, axiomatic theory with over 100,000 axioms that describe the molecular functions, biological processes and cellular locations of proteins in three subontologies. Predicting the functions of proteins using the GO requires both learning and reasoning capabilities in order to maintain consistency and exploit the background knowledge in the GO. Many methods have been developed to automatically predict protein functions, but effectively exploiting all the axioms in the GO for knowledge-enhanced learning has remained a challenge.\nIn this webinar, I will present DeepGO-SE, the latest version of DeepGO methods, that predicts GO functions from protein sequences using a pretrained large language model. DeepGO-SE incorporates the knowledge in GO by learning multiple approximate models of GO using an ontology embedding method. Furthermore, it uses a neural network to predict the truth values of statements about protein functions in these approximate models. We aggregate the truth values over multiple models so that DeepGO-SE approximates semantic entailment when predicting protein functions. We show, using several benchmarks, that the approach effectively exploits background knowledge in the GO and improves protein function prediction compared to state-of-the-art methods.\n\n Video records: https://www.youtube.com/c/SciBerloga - subscribe !", "votes": null }, { "id": "2858606", "postDate": "06/06/2024 15:21:38", "content": "Here is zoom link: https://us02web.zoom.us/j/89626483324?pwd=7vPcTC5UunabohCDHlS891f832WikL.1
", "rawMarkdown": "Here is zoom link: https://us02web.zoom.us/j/89626483324?pwd=7vPcTC5UunabohCDHlS891f832WikL.1", "votes": null }, { "id": "2859762", "postDate": "06/07/2024 08:27:40", "content": "Video record: https://youtu.be/vhnD4SR8cWI?si=uDZFrw8EG0mXB0bV
", "rawMarkdown": "Video record: https://youtu.be/vhnD4SR8cWI?si=uDZFrw8EG0mXB0bV", "votes": null } ], "comments": [ { "id": 2858606, "author_name": "alexandervc", "author_url": "", "post_date": "06/06/2024 15:21:38", "content": "Here is zoom link: https://us02web.zoom.us/j/89626483324?pwd=7vPcTC5UunabohCDHlS891f832WikL.1
", "votes": null, "replies": [] }, { "id": 2859762, "author_name": "alexandervc", "author_url": "", "post_date": "06/07/2024 08:27:40", "content": "Video record: https://youtu.be/vhnD4SR8cWI?si=uDZFrw8EG0mXB0bV
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "2854641": "Video record: https://youtu.be/vhnD4SR8cWI?si=uDZFrw8EG0mXB0bV\n\nHere is webinar on another challenge - took place on Kaggle - CAFA5 - on prediсtion of the protein properties (Gene Ontology terms) from the leading experts in the field - authors of the DeepGO paper:\n\nhttps://www.nature.com/articles/s42256-024-00795-w\n\nEverybody is welcome , it is free. Link to zoom will be here just before the start \n\n👨🔬 Robert Hoehndorf, Maxat Kulmanov, \"DeepGO-SE - Protein function prediction as approximate semantic entailment\" \n⌚️ Thursday 6 June, 17.30 (CET time). \n\n[Add to Google Calendar](https://calendar.google.com/calendar/render?action=TEMPLATE&dates=20240606T153000Z%2F20240606T173000Z&details=Robert%20Hoehndorf%2C%20Maxat%20Kulmanov%2C%20%22DeepGO-SE%20-%20Protein%20function%20prediction%20as%20approximate%20semantic%20entailment%22%20&text=%40SBERLOGABIO%20webinar%20on%20bionformatics%20and%20data%20science%3A)\n\n\nThe Gene Ontology (GO) is a formal, axiomatic theory with over 100,000 axioms that describe the molecular functions, biological processes and cellular locations of proteins in three subontologies. Predicting the functions of proteins using the GO requires both learning and reasoning capabilities in order to maintain consistency and exploit the background knowledge in the GO. Many methods have been developed to automatically predict protein functions, but effectively exploiting all the axioms in the GO for knowledge-enhanced learning has remained a challenge.\nIn this webinar, I will present DeepGO-SE, the latest version of DeepGO methods, that predicts GO functions from protein sequences using a pretrained large language model. DeepGO-SE incorporates the knowledge in GO by learning multiple approximate models of GO using an ontology embedding method. Furthermore, it uses a neural network to predict the truth values of statements about protein functions in these approximate models. We aggregate the truth values over multiple models so that DeepGO-SE approximates semantic entailment when predicting protein functions. We show, using several benchmarks, that the approach effectively exploits background knowledge in the GO and improves protein function prediction compared to state-of-the-art methods.\n\n Video records: https://www.youtube.com/c/SciBerloga - subscribe !", "2858606": "Here is zoom link: https://us02web.zoom.us/j/89626483324?pwd=7vPcTC5UunabohCDHlS891f832WikL.1", "2859762": "Video record: https://youtu.be/vhnD4SR8cWI?si=uDZFrw8EG0mXB0bV" }, "source": "meta" }