Published November 15, 2025
| Version v4
Dataset
Open
Datasets and models for Metagenomics-AI
Description
Datasets and models for Metagenome-AI framework and related manuscript
4 datasets in total: Global AMP prediction, Gram positive, Gram negative bacteria and toxicity.
3 Base models: ESM2-3B, ESM3 and ProteinTrans.
Proteins collected from extreme environments are given in 11379_corepeptides_scored_cAMP20250915-forRevision.tsv
Files
Files
(17.6 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:c4dad050786d514b5a67cf012eaca81a
|
5.1 MB | Download |
|
md5:c2c7dd0bb4151f1522b4d5c7c82e1317
|
419.8 kB | Download |
|
md5:41dc9318adb40aefbb6f46b26e71f5c9
|
3.3 MB | Download |
|
md5:d3bf2f1f4e878715f9bb2d74d5ce2ba3
|
416.3 kB | Download |
|
md5:a3676399e2c0fe25517a24fd68789def
|
359.7 kB | Download |
|
md5:2d4a5d21a4901f6c29b9760bbb5f3e72
|
2.9 MB | Download |
|
md5:7facd7ac6fc17efcd16479c1295730d2
|
361.4 kB | Download |
|
md5:2ea53973db392d93ab78fc08e1b62530
|
360.5 kB | Download |
|
md5:d2788d65b86e98f22b4ca25e7969021b
|
2.9 MB | Download |
|
md5:6408514ca8e872b4064aa5d4f2d8d437
|
364.8 kB | Download |
|
md5:dc99ee45e47f03fd902a1db4d8e1a4df
|
40.6 kB | Download |
|
md5:acd6fb1431125bb5eb36fdf0e4f5027b
|
40.7 kB | Download |
|
md5:99eaac62f9b009070ad276eb7994c4cf
|
40.7 kB | Download |
|
md5:23737becdf5c89043de6e600bf4e64f3
|
40.6 kB | Download |
|
md5:5817db41276b358ab0de24eb8430a2ce
|
64.8 kB | Download |
|
md5:84140ecb62039c96cff93aa7584768c8
|
64.8 kB | Download |
|
md5:ac8cf87c27535c209e716c8f98344ddb
|
64.8 kB | Download |
|
md5:2b7f281a122bd58f31a7e194b7428a32
|
64.8 kB | Download |
|
md5:f89d184b82216a16634433fe258d24ea
|
26.9 kB | Download |
|
md5:de624efe8f39080d50039996fe6613e4
|
26.9 kB | Download |
|
md5:cac0a3a5d2e21b9da628d0326fda12e1
|
26.9 kB | Download |
|
md5:cc090bda014bca5ffc6d94eb8c75b080
|
26.9 kB | Download |
|
md5:d5ea6b0133368fe4b53a7ba33ba010b7
|
64.8 kB | Download |
|
md5:4a587c236d4d8c14d2e568ed660595c5
|
515.6 kB | Download |
|
md5:aa3f5126d1409fcdd9c303b5bc629258
|
64.7 kB | Download |
Additional details
Dates
- Available
-
2025-10-29
Software
- Repository URL
- https://github.com/BGIResearch/Metagenome-AI
- Programming language
- Python
References
- The Extreme Environment Microbiome Catalog (EEMC): A Global Resource for Microbial Diversity2 and Antimicrobial Discovery, Puzi Jiang et. al.