update

app.py

@@ -837,8 +837,8 @@ class UnifiedPeptidePredictor:
                 'path': 'models/best_model_nonfouling.json',
                 'unit': 'Probability',
                 'display_name': '👯 Non-Fouling',
-                'positive_label': 'Non-toxic',
-                'negative_label': 'Toxic'
+                'positive_label': 'Non-fouling',
+                'negative_label': 'Fouling'
             },
             'nonfouling_smiles': {
                 'type': 'xgboost',
@@ -846,8 +846,8 @@ class UnifiedPeptidePredictor:
                 'path': 'models/nonfouling-xgboost_smiles.json',
                 'unit': 'Probability',
                 'display_name': '👯 Non-Fouling',
-                'positive_label': 'Stable',
-                'negative_label': 'Unstable'
+                'positive_label': 'Non-fouling',
+                'negative_label': 'Fouling'
             },
             'binding_affinity': {
                 'type': 'binding',

description.md

@@ -9,34 +9,34 @@ Our models are trained on curated datasets from multiple sources:
 - **Secondary Source:** [peptideBERT](https://pubs.acs.org/doi/abs/10.1021/acs.jpclett.3c02398)
 - **Size:** 9,316 peptides, with 19.6% being positive (hemolytic) and 80.4% being negative (nonhemolytic)
 - **Description:** Probability of peptide disrupting red blood cell membranes.
-- **Download:** [hemolysis_training_data.csv](#)
+- **Download:** [hemo-positive.npz](https://huggingface.co/ChatterjeeLab/Classifier_Weight/blob/main/training_data/hemo-positive.npz)
 
 #### Solubility Dataset
 - **Primary Source:** [PROSO-II](https://febs.onlinelibrary.wiley.com/doi/abs/10.1111/j.1742-4658.2012.08603.x)
 - **Secondary Source:** [peptideBERT](https://pubs.acs.org/doi/abs/10.1021/acs.jpclett.3c02398)
 - **Size:** 18,453 sequences, with 47.6% being labeled as positives and 52.4% being labeled as negatives
 - **Description:** Probability of peptide remaining dissolved in aqueous conditions.
-- **Download:** [solubility_training_data.csv](#)
+- **Download:** [sol-positive.npz](https://huggingface.co/ChatterjeeLab/Classifier_Weight/blob/main/training_data/sol-positive.npz)
 
 #### Non-Fouling Dataset
 - **Primary Source:** [Classifying antimicrobial and multifunctional peptides with Bayesian network models](https://doi.org/10.1002/pep2.24079)
 - **Secondary Source:** [peptideBERT](https://pubs.acs.org/doi/abs/10.1021/acs.jpclett.3c02398)
 - **Size:** 3,600 positive, 13,585 negative
 - **Description:** A nonfouling peptide resists nonspecific interactions and protein adsorption.
-- **Download:** [solubility_training_data.csv](#)
+- **Download:** [nf-positive.npz](https://huggingface.co/ChatterjeeLab/Classifier_Weight/blob/main/training_data/nf-positive.npz)
 
 #### Permeability Dataset
 - **Primary Source:** [CycPeptMPDB](https://pubs.acs.org/doi/abs/10.1021/acs.jcim.2c01573), [PAMPA](https://doi.org/10.1517/17425255.1.2.325)
 - **Secondary Source:** [PepLand](https://arxiv.org/abs/2311.04419)
 - **Size:** 1162 positive and negative for nanonical samples each (22 relevant cell-penetrating peptide databases by compiling literature on existing cell-penetrating peptide prediction models ); CycPeptMPDB provides extra 7334 cyclic peptides
 - **Description:** Probability of peptide penetrating the cell membrane.
-- **Download:** [binding_affinity_training_data.csv](#)
+- **Download:** [nc-CPP-processed.csv](https://huggingface.co/ChatterjeeLab/Classifier_Weight/blob/main/training_data/nc-CPP-processed.csv)
 
 #### Half-life Dataset
 - **Primary Source:** [Thpdb2](https://doi.org/10.1016/j.drudis.2024.104047), [PepTherDia](https://doi.org/10.1016/j.drudis.2021.02.019), [peplife](https://www.nature.com/articles/srep36617)
 - **Size:** 105 wt, 275 wt+noncanonical, human-only
 - **Clean-ups:** Data are all transformed into log\(hour\)
-- **Download:** [binding_affinity_training_data.csv](#)
+- **Download:** [binding_affinity_training_data.csv](https://huggingface.co/ChatterjeeLab/Classifier_Weight/blob/main/training_data/half_life_smiles.csv)
 
 
 #### Binding Affinity Dataset
@@ -44,7 +44,7 @@ Our models are trained on curated datasets from multiple sources:
 - **Size:** 1,781 protein-peptide complexes, canonical and non-canonical
 - **Description:** Binding probability normalized in PepLand already. It's a combination of IC50/EC50.
 - **Quality:** Binding class cutoffs: Tight ≥ 7.5, Medium 6.0–7.5, Weak < 6.0
-- **Download:** [binding_affinity_training_data.csv](#)
+- **Download:** [binding_affinity_training_data.csv](https://huggingface.co/ChatterjeeLab/Classifier_Weight/blob/main/training_data/c-binding.csv)
 
 ### Model Architecture
 
@@ -53,6 +53,9 @@ Our models are trained on curated datasets from multiple sources:
 - **CNN Models:** 1D convolutional networks with attention mechanisms
 - **Binding Model:** Cross-attention between protein and peptide representations
 
+### Model Training and Weight Hosting
+- [Classifier_weights](https://huggingface.co/ChatterjeeLab/Classifier_Weight)
+
 ### Citation
 
 If you use this tool, please cite:

tokenizer/new_vocab.txt

@@ -92,7 +92,6 @@ b
 c
 cc
 ccc
-cccc
 ccn
 cco
 ccs

training_data/half_life_smiles.csv

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d90293170442bc81af2cf9f64656c40bf884733947ca52b2f9308f42220680c3
-size 174323

training_data/hemo-negative.npz

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f83aad41f160deb6401bc0801bddc931488da6e1785749e6f72de6d0f154a37f
-size 109451

training_data/hemo-positive.npz

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:96cb24d5a7617f7e211cd48d2b0b424a46affa95716b96058058902068068d27
-size 27840

training_data/nf-negative.npz

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e506e52e101308dd3882ca6bd45833a6e0837f9f240aa85d575c2a41e305b854
-size 21845190

training_data/nf-positive.npz

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:78caae183fe840b145275d9486a3f94a963989deb9d55a57995653bf1d497bf2
-size 41326

training_data/sol-negative.npz

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c3b6d380024e0483e15e3e219a7cbf23f4d178d823287cef24bc1bd918a817b6
-size 15469064

training_data/sol-positive.npz

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:46169267fd0d37d8a063a4e9fc1cdd9b701a9211b1f16515e3d569fcf2d4d859
-size 14056264