{ "id": 491234, "title": "Some perusal materials to get started including research papers", "url": "/competitions/leash-BELKA/discussion/491234", "author_name": "", "post_date": "2024-04-05T05:06:44.165841300Z", "votes": 40, "comment_count": 8, "views": 0, "content": "

Hello everyone,

\n

I have handpicked some starter references for one to peruse and onboard. Hope they prove to be suitable for starters -

\n

CAFA 5 Protein Function Prediction

\n

Notebooks with good popularity

\n
    \n
  1. Most popular kernel
    2. \n
  2. Second most popular kernel
    3. \n
  3. Third most popular kernel
    4. \n
  4. Fourth most popular kernel
    5. \n
  5. Fifth most popular kernel
    6. \n
\n

Kernels with good score

\n
    \n
  1. https://www.kaggle.com/code/adaluodao/merge-datasets
    2. \n
  2. https://www.kaggle.com/code/siddhvr/cafa5-ems2-embeds-with-pytorch
    3. \n
  3. https://www.kaggle.com/code/siddhvr/cafa5-using-protbert-embeds
    4. \n
\n

Top solutions and approaches for perusal

\n
    \n
  1. Rank1 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/466917
    2. \n
  2. Rank2 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/434064
    3. \n
  3. Rank3 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/464437
    4. \n
  4. Rank4 -https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/433732
    5. \n
  5. Rank5 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/463009
    6. \n
  6. Rank6 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/466971
    7. \n
\n

Open Problems - Multimodal Single-Cell Integration

\n

Notebooks with good popularity

\n
    \n
  1. Most popular kernel -- this is an excellent starter EDA kernel in my opinion
    2. \n
  2. Second most popular kernel
    3. \n
  3. Third most popular kernel
    4. \n
  4. Fourth most popular kernel
    5. \n
  5. Fifth most popular kernel
    6. \n
\n

Kernels with good score

\n
    \n
  1. https://www.kaggle.com/code/shitovvladimir/2nd-place-gru-cite
    2. \n
  2. https://www.kaggle.com/code/bejeweled/rotate-2nd-place-cite-2d-cnn
    3. \n
  3. https://www.kaggle.com/code/bejeweled/rotate-xy-2nd-place-cite-2d-cnn
    4. \n
  4. https://www.kaggle.com/code/bejeweled/2nd-place-cite-2d-cnn
    5. \n
  5. https://www.kaggle.com/code/senkin13/2nd-place-gru-cite
    6. \n
\n

Top solutions and approaches for perusal

\n
    \n
  1. Rank1- https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366961
    2. \n
  2. Rank2 - https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366453
    3. \n
  3. Rank3 - https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366428
    4. \n
  4. Rank4 - https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366460
    5. \n
  5. Rank5 - https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366409
    6. \n
\n

Some adjutant research papers to refer

\n
    \n
  1. https://physics.paperswithcode.com/paper/poisson-boltzmann-model-for-protein-surface
    2. \n
  2. https://paperswithcode.com/paper/transformercpi-improving-compound-protein
    3. \n
  3. https://paperswithcode.com/paper/deepgo-predicting-protein-functions-from
    4. \n
  4. https://paperswithcode.com/paper/dips-plus-the-enhanced-database-of
    5. \n
  5. https://paperswithcode.com/paper/highly-accurate-protein-structure-prediction
    6. \n
  6. https://paperswithcode.com/paper/must-cnn-a-multilayer-shift-and-stitch-deep
    7. \n
  7. https://paperswithcode.com/paper/accurate-protein-structure-prediction-by
    8. \n
  8. https://paperswithcode.com/paper/sidechainnet-an-all-atom-protein-structure
    9. \n
  9. https://paperswithcode.com/paper/proteinnet-a-standardized-data-set-for
    10. \n
  10. https://paperswithcode.com/paper/proteinbert-a-universal-deep-learning-model
    11. \n
\n


Kindly use these research papers with caution as not all of them may be fully 100% relevant to the task at hand, though all of them belong to the same domain

\n

Hope these references provide some onboarding materials for new participants and others alike!
\nBest regards.

", "messages": [ { "id": "2736212", "postDate": "04/05/2024 05:06:44", "content": "

Hello everyone,

\n

I have handpicked some starter references for one to peruse and onboard. Hope they prove to be suitable for starters -

\n

CAFA 5 Protein Function Prediction

\n

Notebooks with good popularity

\n
    \n
  1. Most popular kernel
    2. \n
  2. Second most popular kernel
    3. \n
  3. Third most popular kernel
    4. \n
  4. Fourth most popular kernel
    5. \n
  5. Fifth most popular kernel
    6. \n
\n

Kernels with good score

\n
    \n
  1. https://www.kaggle.com/code/adaluodao/merge-datasets
    2. \n
  2. https://www.kaggle.com/code/siddhvr/cafa5-ems2-embeds-with-pytorch
    3. \n
  3. https://www.kaggle.com/code/siddhvr/cafa5-using-protbert-embeds
    4. \n
\n

Top solutions and approaches for perusal

\n
    \n
  1. Rank1 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/466917
    2. \n
  2. Rank2 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/434064
    3. \n
  3. Rank3 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/464437
    4. \n
  4. Rank4 -https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/433732
    5. \n
  5. Rank5 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/463009
    6. \n
  6. Rank6 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/466971
    7. \n
\n

Open Problems - Multimodal Single-Cell Integration

\n

Notebooks with good popularity

\n
    \n
  1. Most popular kernel -- this is an excellent starter EDA kernel in my opinion
    2. \n
  2. Second most popular kernel
    3. \n
  3. Third most popular kernel
    4. \n
  4. Fourth most popular kernel
    5. \n
  5. Fifth most popular kernel
    6. \n
\n

Kernels with good score

\n
    \n
  1. https://www.kaggle.com/code/shitovvladimir/2nd-place-gru-cite
    2. \n
  2. https://www.kaggle.com/code/bejeweled/rotate-2nd-place-cite-2d-cnn
    3. \n
  3. https://www.kaggle.com/code/bejeweled/rotate-xy-2nd-place-cite-2d-cnn
    4. \n
  4. https://www.kaggle.com/code/bejeweled/2nd-place-cite-2d-cnn
    5. \n
  5. https://www.kaggle.com/code/senkin13/2nd-place-gru-cite
    6. \n
\n

Top solutions and approaches for perusal

\n
    \n
  1. Rank1- https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366961
    2. \n
  2. Rank2 - https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366453
    3. \n
  3. Rank3 - https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366428
    4. \n
  4. Rank4 - https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366460
    5. \n
  5. Rank5 - https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366409
    6. \n
\n

Some adjutant research papers to refer

\n
    \n
  1. https://physics.paperswithcode.com/paper/poisson-boltzmann-model-for-protein-surface
    2. \n
  2. https://paperswithcode.com/paper/transformercpi-improving-compound-protein
    3. \n
  3. https://paperswithcode.com/paper/deepgo-predicting-protein-functions-from
    4. \n
  4. https://paperswithcode.com/paper/dips-plus-the-enhanced-database-of
    5. \n
  5. https://paperswithcode.com/paper/highly-accurate-protein-structure-prediction
    6. \n
  6. https://paperswithcode.com/paper/must-cnn-a-multilayer-shift-and-stitch-deep
    7. \n
  7. https://paperswithcode.com/paper/accurate-protein-structure-prediction-by
    8. \n
  8. https://paperswithcode.com/paper/sidechainnet-an-all-atom-protein-structure
    9. \n
  9. https://paperswithcode.com/paper/proteinnet-a-standardized-data-set-for
    10. \n
  10. https://paperswithcode.com/paper/proteinbert-a-universal-deep-learning-model
    11. \n
\n


Kindly use these research papers with caution as not all of them may be fully 100% relevant to the task at hand, though all of them belong to the same domain

\n

Hope these references provide some onboarding materials for new participants and others alike!
\nBest regards.

", "rawMarkdown": "Hello everyone,\n\nI have handpicked some starter references for one to peruse and onboard. Hope they prove to be suitable for starters - \n\n# [CAFA 5 Protein Function Prediction](https://www.kaggle.com/competitions/cafa-5-protein-function-prediction)\n## Notebooks with good popularity\n1. [Most popular kernel](https://www.kaggle.com/code/leonidkulyk/eda-cafa5-pfp-interactive-dags-plotly)\n2. [Second most popular kernel](https://www.kaggle.com/code/henriupton/proteinet-pytorch-ems2-t5-protbert-embeddings)\n3. [Third most popular kernel](https://www.kaggle.com/code/alexandervc/baseline-multilabel-to-multitarget-binary)\n4. [Fourth most popular kernel](https://www.kaggle.com/code/thedrcat/cafa-5-protein-function-prediction-eda)\n5. [Fifth most popular kernel](https://www.kaggle.com/code/siddhvr/cafa5-ems2-embeds-with-pytorch)\n\n## Kernels with good score\n1. https://www.kaggle.com/code/adaluodao/merge-datasets\n2. https://www.kaggle.com/code/siddhvr/cafa5-ems2-embeds-with-pytorch\n3. https://www.kaggle.com/code/siddhvr/cafa5-using-protbert-embeds\n\n## Top solutions and approaches for perusal\n1. Rank1 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/466917\n2. Rank2 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/434064 \n3. Rank3 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/464437\n4. Rank4 -https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/433732 \n5. Rank5 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/463009\n6. Rank6 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/466971\n\n# [Open Problems - Multimodal Single-Cell Integration](https://www.kaggle.com/competitions/open-problems-multimodal)\n## Notebooks with good popularity\n1. [Most popular kernel](https://www.kaggle.com/code/ambrosm/msci-eda-which-makes-sense) -- this is an excellent starter EDA kernel in my opinion\n2. [Second most popular kernel](https://www.kaggle.com/code/ambrosm/msci-citeseq-quickstart)\n3. [Third most popular kernel](https://www.kaggle.com/code/pourchot/all-in-one-citeseq-multiome-with-keras)\n4. [Fourth most popular kernel](https://www.kaggle.com/code/ambrosm/msci-citeseq-keras-quickstart)\n5. [Fifth most popular kernel](https://www.kaggle.com/code/vslaykovsky/lb-0-811-normalized-ensembles-for-pearson-s-r)\n\n## Kernels with good score\n1. https://www.kaggle.com/code/shitovvladimir/2nd-place-gru-cite\n2. https://www.kaggle.com/code/bejeweled/rotate-2nd-place-cite-2d-cnn\n3. https://www.kaggle.com/code/bejeweled/rotate-xy-2nd-place-cite-2d-cnn\n4. https://www.kaggle.com/code/bejeweled/2nd-place-cite-2d-cnn\n5. https://www.kaggle.com/code/senkin13/2nd-place-gru-cite\n\n## Top solutions and approaches for perusal\n1. Rank1- https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366961 \n2. Rank2 - https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366453 \n3. Rank3 - https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366428\n4. Rank4 - https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366460 \n5. Rank5 - https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366409 \n\n# Some adjutant research papers to refer\n1. https://physics.paperswithcode.com/paper/poisson-boltzmann-model-for-protein-surface\n2. https://paperswithcode.com/paper/transformercpi-improving-compound-protein\n3. https://paperswithcode.com/paper/deepgo-predicting-protein-functions-from\n4. https://paperswithcode.com/paper/dips-plus-the-enhanced-database-of\n5. https://paperswithcode.com/paper/highly-accurate-protein-structure-prediction\n6. https://paperswithcode.com/paper/must-cnn-a-multilayer-shift-and-stitch-deep\n7. https://paperswithcode.com/paper/accurate-protein-structure-prediction-by\n8. https://paperswithcode.com/paper/sidechainnet-an-all-atom-protein-structure\n9. https://paperswithcode.com/paper/proteinnet-a-standardized-data-set-for\n10. https://paperswithcode.com/paper/proteinbert-a-universal-deep-learning-model\n\n
**Kindly use these research papers with caution as not all of them may be fully 100% relevant to the task at hand, though all of them belong to the same domain**\n\nHope these references provide some onboarding materials for new participants and others alike! \nBest regards.", "votes": null }, { "id": "2736349", "postDate": "04/05/2024 06:36:51", "content": "

these dishes already looking good chef. what a choice

", "rawMarkdown": "these dishes already looking good chef. what a choice", "votes": null }, { "id": "2736356", "postDate": "04/05/2024 06:39:01", "content": "

That is a unique rejoinder! I like to cook food, in fact cooking is one of my long run interests @beckpro

", "rawMarkdown": "That is a unique rejoinder! I like to cook food, in fact cooking is one of my long run interests @beckpro", "votes": null }, { "id": "2736504", "postDate": "04/05/2024 08:32:57", "content": "

this is fantastic, thank you @ravi20076!

", "rawMarkdown": "this is fantastic, thank you @ravi20076!", "votes": null }, { "id": "2737402", "postDate": "04/05/2024 18:45:12", "content": "

Thank you. For the 1st, second etc. most popular kernel, you should check if the number of votes do not change in time. :-)

", "rawMarkdown": "Thank you. For the 1st, second etc. most popular kernel, you should check if the number of votes do not change in time. :-)", "votes": null }, { "id": "2738352", "postDate": "04/06/2024 09:36:36", "content": "

Thanks for sharing

", "rawMarkdown": "Thanks for sharing", "votes": null }, { "id": "2739148", "postDate": "04/06/2024 20:53:24", "content": "

Wow these are great resources, thank you!

", "rawMarkdown": "Wow these are great resources, thank you!", "votes": null }, { "id": "2740110", "postDate": "04/07/2024 15:20:22", "content": "

Amazing! Thank you :)

", "rawMarkdown": "Amazing! Thank you :)", "votes": null }, { "id": "2911057", "postDate": "07/08/2024 05:21:38", "content": "

That would be very helpful for us
\nThanks @ravi20076

", "rawMarkdown": "That would be very helpful for us \nThanks @ravi20076", "votes": null } ], "comments": [ { "id": 2736349, "author_name": "beckpro", "author_url": "", "post_date": "04/05/2024 06:36:51", "content": "

these dishes already looking good chef. what a choice

", "votes": null, "replies": [ { "id": 2736356, "author_name": "ravi20076", "author_url": "", "post_date": "04/05/2024 06:39:01", "content": "

That is a unique rejoinder! I like to cook food, in fact cooking is one of my long run interests @beckpro

", "votes": null, "replies": [] } ] }, { "id": 2736504, "author_name": "sahirmaharajj", "author_url": "", "post_date": "04/05/2024 08:32:57", "content": "

this is fantastic, thank you @ravi20076!

", "votes": null, "replies": [] }, { "id": 2737402, "author_name": "catadanna", "author_url": "", "post_date": "04/05/2024 18:45:12", "content": "

Thank you. For the 1st, second etc. most popular kernel, you should check if the number of votes do not change in time. :-)

", "votes": null, "replies": [] }, { "id": 2738352, "author_name": "mdismielhossenabir", "author_url": "", "post_date": "04/06/2024 09:36:36", "content": "

Thanks for sharing

", "votes": null, "replies": [] }, { "id": 2739148, "author_name": "yyyu54", "author_url": "", "post_date": "04/06/2024 20:53:24", "content": "

Wow these are great resources, thank you!

", "votes": null, "replies": [] }, { "id": 2740110, "author_name": "xjoannax88", "author_url": "", "post_date": "04/07/2024 15:20:22", "content": "

Amazing! Thank you :)

", "votes": null, "replies": [] }, { "id": 2911057, "author_name": "raja6242", "author_url": "", "post_date": "07/08/2024 05:21:38", "content": "

That would be very helpful for us
\nThanks @ravi20076

", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "2736212": "Hello everyone,\n\nI have handpicked some starter references for one to peruse and onboard. Hope they prove to be suitable for starters - \n\n# [CAFA 5 Protein Function Prediction](https://www.kaggle.com/competitions/cafa-5-protein-function-prediction)\n## Notebooks with good popularity\n1. [Most popular kernel](https://www.kaggle.com/code/leonidkulyk/eda-cafa5-pfp-interactive-dags-plotly)\n2. [Second most popular kernel](https://www.kaggle.com/code/henriupton/proteinet-pytorch-ems2-t5-protbert-embeddings)\n3. [Third most popular kernel](https://www.kaggle.com/code/alexandervc/baseline-multilabel-to-multitarget-binary)\n4. [Fourth most popular kernel](https://www.kaggle.com/code/thedrcat/cafa-5-protein-function-prediction-eda)\n5. [Fifth most popular kernel](https://www.kaggle.com/code/siddhvr/cafa5-ems2-embeds-with-pytorch)\n\n## Kernels with good score\n1. https://www.kaggle.com/code/adaluodao/merge-datasets\n2. https://www.kaggle.com/code/siddhvr/cafa5-ems2-embeds-with-pytorch\n3. https://www.kaggle.com/code/siddhvr/cafa5-using-protbert-embeds\n\n## Top solutions and approaches for perusal\n1. Rank1 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/466917\n2. Rank2 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/434064 \n3. Rank3 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/464437\n4. Rank4 -https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/433732 \n5. Rank5 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/463009\n6. Rank6 - https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/466971\n\n# [Open Problems - Multimodal Single-Cell Integration](https://www.kaggle.com/competitions/open-problems-multimodal)\n## Notebooks with good popularity\n1. [Most popular kernel](https://www.kaggle.com/code/ambrosm/msci-eda-which-makes-sense) -- this is an excellent starter EDA kernel in my opinion\n2. [Second most popular kernel](https://www.kaggle.com/code/ambrosm/msci-citeseq-quickstart)\n3. [Third most popular kernel](https://www.kaggle.com/code/pourchot/all-in-one-citeseq-multiome-with-keras)\n4. [Fourth most popular kernel](https://www.kaggle.com/code/ambrosm/msci-citeseq-keras-quickstart)\n5. [Fifth most popular kernel](https://www.kaggle.com/code/vslaykovsky/lb-0-811-normalized-ensembles-for-pearson-s-r)\n\n## Kernels with good score\n1. https://www.kaggle.com/code/shitovvladimir/2nd-place-gru-cite\n2. https://www.kaggle.com/code/bejeweled/rotate-2nd-place-cite-2d-cnn\n3. https://www.kaggle.com/code/bejeweled/rotate-xy-2nd-place-cite-2d-cnn\n4. https://www.kaggle.com/code/bejeweled/2nd-place-cite-2d-cnn\n5. https://www.kaggle.com/code/senkin13/2nd-place-gru-cite\n\n## Top solutions and approaches for perusal\n1. Rank1- https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366961 \n2. Rank2 - https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366453 \n3. Rank3 - https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366428\n4. Rank4 - https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366460 \n5. Rank5 - https://www.kaggle.com/competitions/open-problems-multimodal/discussion/366409 \n\n# Some adjutant research papers to refer\n1. https://physics.paperswithcode.com/paper/poisson-boltzmann-model-for-protein-surface\n2. https://paperswithcode.com/paper/transformercpi-improving-compound-protein\n3. https://paperswithcode.com/paper/deepgo-predicting-protein-functions-from\n4. https://paperswithcode.com/paper/dips-plus-the-enhanced-database-of\n5. https://paperswithcode.com/paper/highly-accurate-protein-structure-prediction\n6. https://paperswithcode.com/paper/must-cnn-a-multilayer-shift-and-stitch-deep\n7. https://paperswithcode.com/paper/accurate-protein-structure-prediction-by\n8. https://paperswithcode.com/paper/sidechainnet-an-all-atom-protein-structure\n9. https://paperswithcode.com/paper/proteinnet-a-standardized-data-set-for\n10. https://paperswithcode.com/paper/proteinbert-a-universal-deep-learning-model\n\n
**Kindly use these research papers with caution as not all of them may be fully 100% relevant to the task at hand, though all of them belong to the same domain**\n\nHope these references provide some onboarding materials for new participants and others alike! \nBest regards.", "2736349": "these dishes already looking good chef. what a choice", "2736356": "That is a unique rejoinder! I like to cook food, in fact cooking is one of my long run interests @beckpro", "2736504": "this is fantastic, thank you @ravi20076!", "2737402": "Thank you. For the 1st, second etc. most popular kernel, you should check if the number of votes do not change in time. :-)", "2738352": "Thanks for sharing", "2739148": "Wow these are great resources, thank you!", "2740110": "Amazing! Thank you :)", "2911057": "That would be very helpful for us \nThanks @ravi20076" }, "source": "meta" }