New model ready for testing!

[github-actions[bot]]

This model is ready for testing. If you are assigned to this issue, please try it out using the CLI, Google Colab and DockerHub and let us know if it works!

[HellenNamulinda]

Hi @GemmaTuron and @emmakodes, I tested the model using Colab, CLI and docker. It works well. CLI happens to use more decimal points when printing ouput. However, all file outputs have 3dps.

Test file: eml_canonical.csv

Colab Colab Output: eos3ae6_colab_output.csv

{
    "input": {
        "key": "MCGSCOLBFJQGHM-SCZZXKLOSA-N",
        "input": "Nc1nc(NC2CC2)c3ncn([C@@H]4C[C@H](CO)C=C4)c3n1",
        "text": "Nc1nc(NC2CC2)c3ncn([C@@H]4C[C@H](CO)C=C4)c3n1"
    },
    "output": {
        "whales": [
            -5.698,
            -4.167,
            -1.63,
            -1.057,
            -0.707,
            -0.515,
            0.292,
            0.401,
            0.942,
            1.353,
            2.489,
            -0.357,
            -0.266,
            -0.164,
            -0.124,
            -0.082,
            -0.063,
            0.064,
            0.068,
            0.091,
            0.236,
            0.343,
            -0.636,
            -0.154,
            -0.116,
            -0.086,
            -0.06,
            -0.038,
            0.059,
            0.138,
            0.161,
            0.188,
            0.324
        ]
    }
}

CLI eos3ae6_cli_fetch.log Output: eos3ae6_eml_cli_output.csv Pred_log: eos3ae6_cli_output.log

🚀 Serving model eos3ae6: whales-descriptor

   URL: http://0.0.0.0:59011
   PID: -1
   SRV: pulled_docker

👉 To run model:
   - run

💁 Information:
   - info
(ersilia) hellenah@hellenah-elitebook:~$ ersilia run -i "Nc1nc(NC2CC2)c3ncn([C@@H]4C[C@H](CO)C=C4)c3n1"
{
    "input": {
        "key": "MCGSCOLBFJQGHM-SCZZXKLOSA-N",
        "input": "Nc1nc(NC2CC2)c3ncn([C@@H]4C[C@H](CO)C=C4)c3n1",
        "text": "Nc1nc(NC2CC2)c3ncn([C@@H]4C[C@H](CO)C=C4)c3n1"
    },
    "output": {
        "whales": [
            -5.697999954223633,
            -4.166999816894531,
            -1.6299999952316284,
            -1.0570000410079956,
            -0.7070000171661377,
            -0.5149999856948853,
            0.2919999957084656,
            0.4009999930858612,
            0.9419999718666077,
            1.3530000448226929,
            2.489000082015991,
            -0.3569999933242798,
            -0.26600000262260437,
            -0.164000004529953,
            -0.12399999797344208,
            -0.0820000022649765,
            -0.06300000101327896,
            0.06400000303983688,
            0.06800000369548798,
            0.09099999815225601,
            0.23600000143051147,
            0.34299999475479126,
            -0.6359999775886536,
            -0.15399999916553497,
            -0.11599999666213989,
            -0.0860000029206276,
            -0.05999999865889549,
            -0.03799999877810478,
            0.05900000035762787,
            0.1379999965429306,
            0.16099999845027924,
            0.18799999356269836,
            0.3240000009536743
        ]
    }
}

Docker The prediction was somewhat slow, so I used the first 50 smiles in the eml dataset. Input: eml_50.csv Docker Output: eos3ae6_eml_docker_output.csv Output log: eos3ae6_docker_output.log

+ [ -z eos3ae6 ]
+ ersilia serve -p 3000 eos3ae6
🚀 Serving model eos3ae6: whales-descriptor

   URL: http://127.0.0.1:3000
   PID: 37
   SRV: conda

👉 To run model:
   - run

💁 Information:
   - info
Serving model eos3ae6...
+ echo Serving model eos3ae6...
263b351108a0   ersiliaos/eos3ae6   "sh /root/docker-ent…"   3 minutes ago   Up 3 minutes   80/tcp    amazing_albattani
hellenah@hellenah-elitebook:~$ docker exec -it 263b351108a0 /bin/bash
root@263b351108a0:~# ersilia run -i "Nc1nc(NC2CC2)c3ncn([C@@H]4C[C@H](CO)C=C4)c3n1"
{
    "input": {
        "key": "MCGSCOLBFJQGHM-SCZZXKLOSA-N",
        "input": "Nc1nc(NC2CC2)c3ncn([C@@H]4C[C@H](CO)C=C4)c3n1",
        "text": "Nc1nc(NC2CC2)c3ncn([C@@H]4C[C@H](CO)C=C4)c3n1"
    },
    "output": {
        "whales": [
            -5.698,
            -4.167,
            -1.63,
            -1.057,
            -0.707,
            -0.515,
            0.292,
            0.401,
            0.942,
            1.353,
            2.489,
            -0.357,
            -0.266,
            -0.164,
            -0.124,
            -0.082,
            -0.063,
            0.064,
            0.068,
            0.091,
            0.236,
            0.343,
            -0.636,
            -0.154,
            -0.116,
            -0.086,
            -0.06,
            -0.038,
            0.059,
            0.138,
            0.161,
            0.188,
            0.324
        ]
    }
}
root@263b351108a0:~#

Colab rarely returns empty outputs compared to CLI( probably my computational power). Nonetheless, no smiles are removed, all are returned with their output.

[simrantan]

@GemmaTuron @emmakodes The model works well on CLI, Colab, Docker! Colab Output CLI output3ae6.csv Docker output3ae6.csv