Remove tools notebooks upport

Author: thomas-a-neil

README.md

@@ -1,3 +1,7 @@
+# ESM
+
+[![Design a GFP](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/evolutionaryscale/esm/blob/main/cookbook/tutorials/4_forge_generate.ipynb)
+
 - [Installation ](#installation-)
 - [ESM 3](#esm-3-)
   - [Quickstart for ESM3 Open](#esm3-quickstart-)
@@ -39,10 +43,6 @@ ESM3-open, with 1.4B parameters, is the smallest and fastest model in the family
 
 ### Quickstart for ESM3-open <a name="esm3-quickstart"></a>
 
-```
-pip install esm
-```
-
 The weights are stored on HuggingFace Hub under [HuggingFace/EvolutionaryScale/esm3](https://huggingface.co/EvolutionaryScale/esm3).
 
 ```py
@@ -100,7 +100,11 @@ This enables a seamless transition from smaller and faster models, to our larges
 ### ESM3 Example Usage
  <a name="esm3-example"></a>
 
-Check out our [tutorials](./cookbook/tutorials) to learn how to use ESM3.
+[Generating a novel GFP with chain of thought generation using ESM3](./cookbook/tutorials/3_gfp_design.ipynb) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/evolutionaryscale/esm/blob/main/cookbook/tutorials/3_gfp_design.ipynb)
+
+[Advanced prompting with ESM3 input tracks](./cookbook/tutorials/4_forge_generate.ipynb) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/evolutionaryscale/esm/blob/main/cookbook/tutorials/4_forge_generate.ipynb)
+
+
 
 ## ESM C <a name="esm-c"></a>
 [ESM Cambrian](https://www.evolutionaryscale.ai/blog/esm-cambrian) is a parallel model family to our flagship ESM3 generative models. While ESM3 focuses on controllable generation of proteins, ESM C focuses on creating representations of the underlying biology of proteins.
@@ -230,7 +234,7 @@ print(logits_output.logits, logits_output.embeddings)
 ### ESM C Example Usage
  <a name="esm-c-example"></a>
 
-Check out our [tutorials](./cookbook/tutorials) to learn how to use ESM C.
+[Embedding a sequence using ESM C](./cookbook/tutorials/2_embed.ipynb) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/evolutionaryscale/esm/blob/main/cookbook/tutorials/2_embed.ipynb)
 
 ## Responsible Development <a name="responsible-development"></a>
 

cookbook/tutorials/1_esmprotein.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Input tracks of `ESMProtein`\n",
+    "# [Tutorial 1](https://github.com/evolutionaryscale/esm/tree/main/cookbook/tutorials): Input tracks of `ESMProtein`\n",
     "\n",
     "ESM3 is a frontier generative model for biology, able to jointly reason across three fundamental biological properties of proteins: sequence, structure, and function. These three data modalities are represented as tracks of discrete tokens at the input and output of ESM3. You can present the model with a combination of partial inputs across the tracks, and ESM3 will provide output predictions for all the tracks."
    ]

cookbook/tutorials/2_embed.ipynb

@@ -4,6 +4,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "# [Tutorial 2](https://github.com/evolutionaryscale/esm/tree/main/cookbook/tutorials): Embedding with ESM C\n",
+    "\n",
     "In this notebook we will see how to embed a batch of sequences using ESM C, as well as explore its different layers"
    ]
   },

cookbook/tutorials/3_gfp_design.ipynb

@@ -6,7 +6,7 @@
     "id": "zWXOAcBB8h3z"
    },
    "source": [
-    "# Design a GFP Candidate with ESM3\n",
+    "# [Tutorial 3](https://github.com/evolutionaryscale/esm/tree/main/cookbook/tutorials): Design a GFP Candidate with ESM3\n",
     "\n",
     "This notebook walks through the computational methods used to design esmGFP in [Hayes et al., 2024](https://doi.org/10.1101/2024.07.01.600583). esmGFP has similar brightness and spectral properties as GFPs found in nature despite being a far distance (58% identity) from known fluorescent proteins, but we also found many other bright new GFPs with similar or higher sequence identity. One can likely design a lot more new GFPs with the approach sketched in this notebook!\n",
     "\n",

cookbook/tutorials/4_forge_generate.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# ESM3\n",
+    "# [Tutorial 4](https://github.com/evolutionaryscale/esm/tree/main/cookbook/tutorials): Generating with ESM3\n",
     "\n",
     "ESM3 is a frontier generative model for biology, able to jointly reason across three fundamental biological properties of proteins: sequence, structure, and function. These three data modalities are represented as tracks of discrete tokens at the input and output of ESM3. You can present the model with a combination of partial inputs across the tracks, and ESM3 will provide output predictions for all the tracks.\n",
     "\n",

cookbook/tutorials/5_guided_generation.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Guided Generation with ESM3\n",
+    "# [Tutorial 5](https://github.com/evolutionaryscale/esm/tree/main/cookbook/tutorials): Guided Generation with ESM3\n",
     "\n",
     "Guided generation is a powerful tool that allows you to sample outputs out of ESM3 that maximize any kind of score function.\n",
     "\n",
@@ -19,9 +19,7 @@
     "In this notebook we will walk through a few examples to illustrate how to use guided generation. \n",
     "\n",
     "1. Guide towards high pTM for improved generation quality\n",
-    "\n",
     "2. Generate a protein with no cysteine (C) residues\n",
-    "\n",
     "3. Maximize protein globularity by minimizing the radius of gyration\n",
     "\n"
    ]
@@ -129,7 +127,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## pTM Guided Generation\n",
+    "## Guide towards high pTM for improved generation quality\n",
     "\n",
     "Once your scoring function is defined and you have initialized your model you can create an `ESM3GuidedDecoding` instance to sample from it"
    ]

tools/README.md

@@ -0,0 +1 @@
+Our tools have migrated to Apps under [Forge](https://forge.evolutionaryscale.ai/). Go check them out!