{
  "topic": {
    "id": 402565,
    "title": "Protein Language Models",
    "authorName": "Darek Kłeczek",
    "commentCount": 7,
    "votes": 41,
    "postDate": "2023-04-18T21:36:01.888000"
  },
  "comments": [
    {
      "id": 2230303,
      "authorName": "Alexander Chervov",
      "votes": 2,
      "postDate": "2023-04-22T08:03:05.483000",
      "content": "<p>Cool ! Thanks for sharing !</p>\n<p>Some colleagues say that ESM-2 is the most powerful model. But inference for our lengths may take about 1 minute.<br>\nDoes it correspond to your experience?</p>\n<p>We have 280 000 proteins,  if inference is 1 minute , that is unreal for most of us.</p>"
    },
    {
      "id": 2230906,
      "authorName": "Darek Kłeczek",
      "votes": 2,
      "postDate": "2023-04-22T21:51:23.390000",
      "content": "<p>I think ESM-2 is trained in multiple sizes, from small to large parameter size, might be worth starting with the small and then scale up… even the larger models should be significantly faster than 1 min with sufficiently big GPU I think, but haven't tried myself yet. </p>"
    },
    {
      "id": 2269100,
      "authorName": "Kaushalya Madhawa",
      "votes": 0,
      "postDate": "2023-05-22T08:08:17.983000",
      "content": "<p>How did you run ESM-2 models on longer amino acid sequences? Did you truncate the sequence of tokens? Even the smallest ESM-2 model can't scale up cross-attention for very long proteins.</p>"
    },
    {
      "id": 2361243,
      "authorName": "Dan Ofer",
      "votes": 1,
      "postDate": "2023-07-27T09:37:01.497000",
      "content": "<p>I truncated. Tis annoying</p>"
    },
    {
      "id": 2401281,
      "authorName": "Amelie Schreiber",
      "votes": 0,
      "postDate": "2023-08-21T14:40:56.200000",
      "content": "<p>I'm curious to know how others did with ESM-2. </p>"
    },
    {
      "id": 2307094,
      "authorName": "Maryam Mohammadi",
      "votes": 0,
      "postDate": "2023-06-17T19:51:44.290000",
      "content": "<p>I have studied using NLP for predicting protein structure in different papers …but i am really enthusiastic to know how we can do it practically?</p>"
    },
    {
      "id": 2309470,
      "authorName": "",
      "votes": 0,
      "postDate": "2023-06-19T16:50:48.217000",
      "content": ""
    }
  ],
  "index": {
    "id": "402565",
    "title": "Protein Language Models",
    "authorName": "",
    "commentCount": "7",
    "votes": "41",
    "postDate": "2023-04-18 21:36:01.888000"
  },
  "competition": "cafa-5-protein-function-prediction"
}