SentenceTransformer based on NeuML/pubmedbert-base-embeddings

This is a sentence-transformers model finetuned from NeuML/pubmedbert-base-embeddings on 4 datasets. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: NeuML/pubmedbert-base-embeddings
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Training Datasets:
Language: code

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): MMContextEncoder(
    (text_encoder): BertModel(
      (embeddings): BertEmbeddings(
        (word_embeddings): Embedding(30522, 768, padding_idx=0)
        (position_embeddings): Embedding(512, 768)
        (token_type_embeddings): Embedding(2, 768)
        (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (encoder): BertEncoder(
        (layer): ModuleList(
          (0-11): 12 x BertLayer(
            (attention): BertAttention(
              (self): BertSdpaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): BertSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): BertIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
              (intermediate_act_fn): GELUActivation()
            )
            (output): BertOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
        )
      )
      (pooler): BertPooler(
        (dense): Linear(in_features=768, out_features=768, bias=True)
        (activation): Tanh()
      )
    )
    (text_adapter): AdapterModule(
      (net): Identity()
    )
    (pooling): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
    (omics_adapter): AdapterModule(
      (net): Sequential(
        (0): Linear(in_features=3936, out_features=768, bias=True)
        (1): BatchNorm1d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (omics_encoder): MiniOmicsModel(
      (embeddings): Embedding(90155, 3936, padding_idx=0)
    )
  )
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("jo-mengr/mmcontext-pubmedbert-gs-mixed-num_adapter")
# Run inference
sentences = [
    'MALAT1 EEF1A1 FTH1 JUND TPT1 EIF1 NFKBIA GAPDH JUN FOS FTL H3-3B ZFAS1 PTMA VIM FAU NACA RACK1 PNRC1 CEBPB DUSP1 UBC EIF4A1 TMSB4X CD44 PPP1R15A HSP90AB1 NEAT1 TNFAIP3 SAT1 BTF3 TM4SF1 NPM1 GADD45B ZFP36 CD63 IGFBP7 JUNB YBX1 HSP90AA1 LGALS1 SERF2 EPS8 EEF2 UBB SNHG8 TMSB10 YBX3 CD59 HES1 EGR1 SLC38A2 HNRNPDL IER2 ANXA5 ID4 NME2 EEF1G SLC25A5 KLF6 LAPTM4A PABPC1 SLC25A3 HNRNPC',
    "This measurement was conducted with 10x 3' v3. Mural cells derived from a 45-year old female breast (organoid) tissue, following prophylactic mastectomy.",
    "This measurement was conducted with 10x 3' v3. Supernatant sample containing fibroblasts from the mammary gland of a 36-year-old female who underwent prophylactic mastectomy.",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.0205, 0.0425],
#         [0.0205, 1.0000, 0.8263],
#         [0.0425, 0.8263, 1.0000]])

Evaluation

Metrics

Triplet

Datasets: cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_1_caption, cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_2_caption, gene_description and cell_type_description
Evaluated with TripletEvaluator

Metric	cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_1_caption	cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_2_caption	gene_description	cell_type_description
cosine_accuracy	0.8082	0.5296	0.159	0.793

Training Details

Training Datasets

cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_1_caption

Dataset: cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_1_caption at b141493
Size: 81,143 training samples
Columns: anchor, positive, negative_1, and negative_2

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative_1	negative_2
type	string	string	string	string
details	min: 56 characters mean: 58.72 characters max: 60 characters	min: 22 tokens mean: 48.4 tokens max: 159 tokens	min: 23 tokens mean: 48.65 tokens max: 158 tokens	min: 56 characters mean: 58.75 characters max: 60 characters

Samples:

anchor	positive	negative_1	negative_2
`sample_idx:census_218acb0f-9f2f-4f76-b90b-15a4b7c7f629_26009`	`This measurement was conducted with 10x 3' v2. A proliferating lymphocyte cell sample, obtained from a 34-year-old female Asian individual, derived from peripheral blood mononuclear cells.`	`This measurement was conducted with 10x 3' v2. Sample is a 25-year-old female with European ethnicity, having CD8-positive, alpha-beta T cell type. This cell type exhibits elevated expression of type 1 interferon-stimulated genes (ISGs) in monocytes, reduction of naïve CD4+ T cells correlating with monocyte ISG expression, and expansion of repertoire-restricted cytotoxic GZMH+ CD8+ T cells.`	`sample_idx:census_218acb0f-9f2f-4f76-b90b-15a4b7c7f629_14165`
`sample_idx:census_1b9d8702-5af8-4142-85ed-020eb06ec4f6_6333`	`This measurement was conducted with 10x 5' v1. Sample is a cell from the omentum tissue, specifically an effector memory CD4-positive, alpha-beta T cell, from a female in her sixth decade.`	`This measurement was conducted with 10x 5' v2. Conventional dendritic cell from the jejunal epithelium of a female in her eighth decade.`	`sample_idx:census_1b9d8702-5af8-4142-85ed-020eb06ec4f6_2714`
`sample_idx:census_adda0684-f8ea-4403-b393-2a25607077c4_271`	`This measurement was conducted with 10x 3' v3. Neuron cell type from a 29-year-old male, specifically from the thalamic complex, specifically the thalamus (THM) - posterior nuclear complex of thalamus (PoN) - medial geniculate nuclei (MG).`	`This measurement was conducted with 10x 3' v3. Neuron from the thalamic complex (thalamus, posterior nuclear complex of thalamus, medial geniculate nuclei) of a 42-year-old male, identified as a midbrain-derived inhibitory neuron.`	`sample_idx:census_adda0684-f8ea-4403-b393-2a25607077c4_425`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_2_caption

Dataset: cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_2_caption at f099f27
Size: 81,143 training samples
Columns: anchor, positive, negative_1, and negative_2

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative_1	negative_2
type	string	string	string	string
details	min: 135 tokens mean: 152.0 tokens max: 185 tokens	min: 22 tokens mean: 48.4 tokens max: 159 tokens	min: 23 tokens mean: 48.65 tokens max: 158 tokens	min: 135 tokens mean: 151.82 tokens max: 181 tokens

Samples:

anchor	positive	negative_1	negative_2
`TMSB4X TMSB10 ACTB MALAT1 GNLY NKG7 IFITM2 LGALS1 GZMA EEF1A1 PFN1 HMGB2 FTH1 PTMA HSP90AA1 GZMB ARHGDIB HNRNPA2B1 PLAAT4 FAU CMC1 VIM MYL12A CBX3 ATP5F1E HCST IFI44L KLRF1 H3-3A COX6C ARL6IP1 CFL1 ISG15 HMGB1 S100A4 ATP5MF RORA MYL6 CORO1A OAZ1 KLRB1 ID2 HMGN3 CCNI RBM39 CAP1 SERF2 ELOC FCER1G S100A9 IFI16 YWHAZ EIF1 CALR HMGN2 SKAP2 SLC25A5 ZZZ3 YBX1 NUCB2 CDC42 GSTP1 FTL ATP5F1D`	`This measurement was conducted with 10x 3' v2. A proliferating lymphocyte cell sample, obtained from a 34-year-old female Asian individual, derived from peripheral blood mononuclear cells.`	`This measurement was conducted with 10x 3' v2. Sample is a 25-year-old female with European ethnicity, having CD8-positive, alpha-beta T cell type. This cell type exhibits elevated expression of type 1 interferon-stimulated genes (ISGs) in monocytes, reduction of naïve CD4+ T cells correlating with monocyte ISG expression, and expansion of repertoire-restricted cytotoxic GZMH+ CD8+ T cells.`	`MALAT1 TMSB4X EEF1A1 CD74 BTG1 PTMA TMSB10 TPT1 FAU EIF1 FTH1 FTL CXCR4 TSC22D3 DUSP1 UBA52 ACTB CD37 CD52 NACA RACK1 EZR CD69 LAPTM5 H3-3A FOS ISG20 YBX1 CIRBP EIF3E OAZ1 COX7C SAT1 COX4I1 H3-3B SH3BGRL3 UBC UBB JUNB COMMD6 VIM CYBA KLF6 STK17B FUS HNRNPC MYL6 GADD45B LGALS1 EIF3L SRSF5 NFKBIA ANKRD12 CORO1A TLE5 NOP53 CHCHD2 PFN1 DDX5 ARPC3 COX7A2 YPEL5 ARL4A SRGN`
`EEF1A1 MALAT1 FTH1 JUNB TPT1 FOS TMSB10 BTG1 TMSB4X ZFP36L2 NACA PABPC1 ACTB FAU VIM H3-3B EIF1 ZFP36 SARAF PTMA IL7R JUN RACK1 EEF2 UBA52 GAPDH FTL FXYD5 DUSP1 S100A4 CD69 CXCR4 UBC TSC22D3 CFL1 KLF6 ARHGDIB KLF2 BTG2 CITED2 IER2 TUBB4B CD3E EEF1G SLC2A3 NFKBIA PFN1 SRGN SNX9 COX4I1 DNAJB1 SERF2 CD8A PCBP2 IL32 BIRC3 SMAP2 FUS GADD45B MYL12A OAZ1 ATP5F1E TUBA4A PNRC1`	`This measurement was conducted with 10x 5' v1. Sample is a cell from the omentum tissue, specifically an effector memory CD4-positive, alpha-beta T cell, from a female in her sixth decade.`	`This measurement was conducted with 10x 5' v2. Conventional dendritic cell from the jejunal epithelium of a female in her eighth decade.`	`CD74 MALAT1 EEF1A1 FOS TPT1 TMSB4X TMSB10 ACTB FAU JUN CD37 DUSP1 RACK1 JUNB EIF1 PTMA FTL DNAJB1 H3-3B CD52 NACA BTG1 TSC22D3 FTH1 PABPC1 EEF2 UBA52 EEF1G HSP90AA1 LAPTM5 CYBA PPP1R15A HSP90AB1 CD69 ARHGDIB ZFP36 SERF2 UBC H3-3A PCBP2 HLA-DRB5 KLF6 PFN1 DDX5 HSPA8 ARPC3 CD83 CCNI CXCR4 ATP5F1E SARAF TUBA1A ZFP36L1 TOMM7 HERPUD1 YBX1 RHOA MEF2C FXYD5 MYL6 SRSF5 MYL12A CORO1A OAZ1`
`MALAT1 GRIK1 SYT1 PCDH9 RORA NRG1 CADPS ZFPM2 LRRC4C LINGO2 RALYL PTPRD SPHKAP CNTNAP5 SLC8A1 CCSER1 HDAC9 CELF2 R3HDM1 CNTN4 RBMS3 PCDH7 GALNT13 UNC5D ROBO1 SYNPR SNAP25 GPM6A ANK3 FRMPD4 CHRM2 RYR2 KHDRBS2 CADM1 CACNA1D RGS6 PDE4D DOCK4 UNC13C CDH18 FAT3 MEG3 NR2F2-AS1 HMCN1 GULP1 CAMK2D ZEB1 SYN2 DYNC1I1 OXR1 DPP10 OSBPL6 FRAS1 PPP3CA ZNF385D ZMAT4 PCBP3 HS6ST3 ERC2 PLEKHA5 CDK14 MAP2 NCOA1 ATP8A2`	`This measurement was conducted with 10x 3' v3. Neuron cell type from a 29-year-old male, specifically from the thalamic complex, specifically the thalamus (THM) - posterior nuclear complex of thalamus (PoN) - medial geniculate nuclei (MG).`	`This measurement was conducted with 10x 3' v3. Neuron from the thalamic complex (thalamus, posterior nuclear complex of thalamus, medial geniculate nuclei) of a 42-year-old male, identified as a midbrain-derived inhibitory neuron.`	`MALAT1 PCDH9 PTPRD NRG1 SYT1 DPP10 ROBO1 TENM2 LRRC4C RBMS3 CNTNAP5 LINGO2 CDH18 SLC8A1 DMD PDE4D RYR2 ATP1B1 RGS6 PTPRT CHRM3 ADGRL2 NOVA1 NTNG1 PCDH7 TAFA2 CCSER1 ANK3 MEG3 MAP2 PLCB4 CACNA2D1 PRKG1 LINC03000 RMST RORA FOXP2 LHFPL3 MEG8 TNRC6A DAB1 KCTD8 RALYL GNAS INPP4B OLFM3 CNTN4 FRMD4A LINC00632 GAPDH ENOX1 AHI1 GPM6A EBF1 LRFN5 PCSK1N SEMA5A KIAA1217 CALY MAP1B SNAP25 GABRB2 CDH8 GRIP1`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

gene_description

Dataset: gene_description at dd22363
Size: 116,208 training samples
Columns: anchor, positive, and negative_1

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative_1
type	string	string	string
details	min: 3 tokens mean: 4.74 tokens max: 8 tokens	min: 6 tokens mean: 72.99 tokens max: 247 tokens	min: 5 tokens mean: 37.82 tokens max: 247 tokens

Samples:

anchor	positive	negative_1
`A1BG`	`The protein encoded by this gene is a plasma glycoprotein of unknown function. The protein shows sequence similarity to the variable regions of some immunoglobulin supergene family member proteins. [provided by RefSeq, Jul 2008]`	`A1BG antisense RNA 1`
`A1BG`	`The protein encoded by this gene is a plasma glycoprotein of unknown function. The protein shows sequence similarity to the variable regions of some immunoglobulin supergene family member proteins. [provided by RefSeq, Jul 2008]`	`G antigen 12D`
`A1BG`	`The protein encoded by this gene is a plasma glycoprotein of unknown function. The protein shows sequence similarity to the variable regions of some immunoglobulin supergene family member proteins. [provided by RefSeq, Jul 2008]`	`G antigen 12B`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

cell_type_description

Dataset: cell_type_description at eaa8e6b
Size: 3,580 training samples
Columns: anchor, positive, and negative_1

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative_1
type	string	string	string
details	min: 3 tokens mean: 6.52 tokens max: 17 tokens	min: 7 tokens mean: 35.89 tokens max: 188 tokens	min: 6 tokens mean: 35.79 tokens max: 188 tokens

Samples:

anchor	positive	negative_1
`A2 amacrine cell`	`A bistratifed retinal amacrine cell with a small dendritic field, dendrite stratification in S1-S2, and a second dendrite stratification in S5. This cell type releases the neurotransmitter glycine.`	`An amacrine cell with a flat dendritic arbor and a medium dendritic field. Starburst amacrine cells have post-synaptic terminals in S2. This cell type releases the neurotransmitters gamma-aminobutyric acid (GABA) and acetylcholine.`
`A2 amacrine cell`	`A bistratifed retinal amacrine cell with a small dendritic field, dendrite stratification in S1-S2, and a second dendrite stratification in S5. This cell type releases the neurotransmitter glycine.`	`An ON diffuse bipolar cell that predominantly connects to ON parasol cells and lateral amacrine cells.`
`A2 amacrine cell`	`A bistratifed retinal amacrine cell with a small dendritic field, dendrite stratification in S1-S2, and a second dendrite stratification in S5. This cell type releases the neurotransmitter glycine.`	`An amacrine cell that uses GABA as a neurotransmitter.`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Evaluation Datasets

cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_1_caption

Dataset: cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_1_caption at b141493
Size: 9,011 evaluation samples
Columns: anchor, positive, negative_1, and negative_2

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative_1	negative_2
type	string	string	string	string
details	min: 56 characters mean: 58.73 characters max: 60 characters	min: 23 tokens mean: 47.49 tokens max: 157 tokens	min: 21 tokens mean: 48.43 tokens max: 206 tokens	min: 56 characters mean: 58.73 characters max: 60 characters

Samples:

anchor	positive	negative_1	negative_2
`sample_idx:census_0b4a15a7-4e9e-4555-9733-2423e5c66469_490`	`This measurement was conducted with 10x 3' v3. Cell sample from the cortex of kidney, taken from a 43-year-old male of European ethnicity with a reported history of kidney cancer. The cell type is identified as a kidney collecting duct intercalated cell.`	`This measurement was conducted with 10x 3' v3. Kidney collecting duct intercalated cell from a 43-year old European male with kidney cancer, taken from the cortex of kidney and cryopreserved for further analysis.`	`sample_idx:census_0b4a15a7-4e9e-4555-9733-2423e5c66469_9`
`sample_idx:census_4976b234-9028-4b4b-8a2f-8ac59d636219_269`	`This measurement was conducted with 10x 3' v3. Neuron cell type from a 29-year-old male cerebellum, specifically from the Cerebellar Vermis - CBV region, with European self-reported ethnicity, analyzed at the nucleus level.`	`This measurement was conducted with 10x 3' v3. Endothelial cells derived from the cerebellum (specifically, cerebellar vermis) of a 42-year-old male, classified under the vascular supercluster term.`	`sample_idx:census_4976b234-9028-4b4b-8a2f-8ac59d636219_923`
`sample_idx:census_44882825-0da1-4547-b721-2c6105d4a9d1_10258`	`This measurement was conducted with 10x 5' v1. Cell sample from the tonsil of a 9-year-old female with recurrent tonsillitis, characterized as a centroblast B cell with IGLC2, IGLV7-43, IGLJ3 immunoglobulin genes expressed.`	`This measurement was conducted with 10x 5' v1. Centroblast cells derived from a 3-year-old male human tonsil sample, with obstructive sleep apnea and recurrent tonsillitis, undergoing affinity maturation and differentiation into memory or plasma cells.`	`sample_idx:census_44882825-0da1-4547-b721-2c6105d4a9d1_9654`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_2_caption

Dataset: cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_2_caption at f099f27
Size: 9,011 evaluation samples
Columns: anchor, positive, negative_1, and negative_2

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative_1	negative_2
type	string	string	string	string
details	min: 134 tokens mean: 152.94 tokens max: 178 tokens	min: 23 tokens mean: 47.49 tokens max: 157 tokens	min: 21 tokens mean: 48.43 tokens max: 206 tokens	min: 137 tokens mean: 152.7 tokens max: 178 tokens

Samples:

anchor	positive	negative_1	negative_2
`MALAT1 EEF1A1 FTH1 TMSB4X ACTB FTL RTN4 ATP6V0B TPT1 FAU S100A6 NDUFA4 ATP5F1E COX7C ITM2B IGFBP7 EIF1 C12orf75 CD9 COX7B SERF2 ATP1B1 COX8A TXNIP NDUFB2 MYL6 PPDPF COX6B1 UQCR11 APOE COX4I1 CALM2 UQCRB S100A11 UQCRQ COX6C ATP5MG BSG ATP6AP2 UQCR10 PTMA NACA UBL5 UBA52 TMSB10 ADGRF5 HSP90AA1 GSTP1 ATP5F1D CHCHD2 GAPDH COX7A2 SKP1 HSPE1 PRDX1 CYSTM1 LGALS3 CD63 ATP5MJ CKB NDUFS5 ATP5ME UBB MAL`	`This measurement was conducted with 10x 3' v3. Cell sample from the cortex of kidney, taken from a 43-year-old male of European ethnicity with a reported history of kidney cancer. The cell type is identified as a kidney collecting duct intercalated cell.`	`This measurement was conducted with 10x 3' v3. Kidney collecting duct intercalated cell from a 43-year old European male with kidney cancer, taken from the cortex of kidney and cryopreserved for further analysis.`	`MALAT1 EEF1A1 CRYAB S100A6 ITM2B ACTB TPT1 PTMA FTL PEBP1 H3-3B GSTP1 ADIRF IGFBP7 S100A10 HIPK2 MYL6 SERF2 TPM1 FAU FTH1 ID4 EIF1 TMSB10 HSP90AA1 SKP1 IGFBP2 IGFBP5 PRDX1 MYL12B CYSTM1 CLU ATP5F1E AHNAK PPDPF DSTN ID1 COX7C JUND SRP14 ATP1B1 HINT1 NDUFA4 PPIA NACA TMA7 NEAT1 CD9 SYNE2 LAPTM4A GNAS CIRBP ATP5F1D DDX17 EDF1 CCND1 LDHB RTN4 TMEM59 NR4A1 KTN1 SAT1 TMBIM6 APP`
`MALAT1 KCND2 NRXN1 CDH18 NRXN3 ZNF385D CADM2 RALYL NKAIN2 CADPS2 RIMS1 FSTL5 GRID2 TRPM3 CHN2 DPP6 JMJD1C RORA PDE1A UNC13C TIAM1 NRG1 SNAP25 ZFPM2 CALN1 LSAMP CNTN1 ABLIM1 SYNE1 ANK3 CA10 NFIA ZBTB20 NTM CADM1 OPCML RELN DNM3 NEBL ERC1 SCN2A PPP3CA CACNA1A GALNT13 LRRC4C GPM6A RABGAP1L RIT2 CAMK4 GRIA4 PTPRD RBFOX3 MCTP1 LHFPL6 PCLO MEG3 PDE10A NOVA1 RTN1 ZNF385B CNTN4 GABRB2 SPOCK1 OXR1`	`This measurement was conducted with 10x 3' v3. Neuron cell type from a 29-year-old male cerebellum, specifically from the Cerebellar Vermis - CBV region, with European self-reported ethnicity, analyzed at the nucleus level.`	`This measurement was conducted with 10x 3' v3. Endothelial cells derived from the cerebellum (specifically, cerebellar vermis) of a 42-year-old male, classified under the vascular supercluster term.`	`MALAT1 ATP10A COBLL1 GPCPD1 PTPRG SLC39A10 FLT1 FLI1 TSPAN5 THSD4 RUNDC3B CCNY IGFBP7 ST6GALNAC3 PRKCH ST6GAL1 MECOM ESYT2 TBC1D4 IGF1R TACC1 HERC4 CDH2 TCF4 ABCB1 DOCK9 SORBS2 USP54 CBFA2T2 TSC22D1 QKI EPAS1 APP NFIB AOPEP ELMO1 ZNF704 PTPRM NET1 A2M FGD6 EPHA3 NEBL RAPGEF2 ACVR1 SPTBN1 BBS9 KLF2 MKLN1 EXOC6 LEF1 PPP3CA RBMS3 LRMDA WDFY3 BCL2L1 TTC3 SIPA1L1 CFLAR ADGRF5 MAP4K4 SCARB1 RAPGEF4 ABLIM1`
`EEF1A1 ACTB GAPDH HMGN2 PTMA SERF2 TMSB4X CD74 PABPC1 FTH1 TMSB10 FAU PFN1 HMGN1 OAZ1 HMGB1 TPT1 PPIA NACA BTF3 MALAT1 MYL6 ATP5MG CFL1 RACK1 ODC1 ATP5F1E TMA7 SLC25A5 ELOB ARPC3 NPM1 COX7C ANP32B C4orf3 EIF1 PCBP2 KLF6 LAPTM5 COX8A RHOA HSPA8 H3-3B PTP4A2 UBA52 OST4 CIRBP LGALS1 EIF3L STMN1 PPDPF COX4I1 RAN EIF3F PPP1CC COMMD6 NDUFA4 YBX1 PEBP1 COTL1 COX7A2 HSPE1 CCNI TRIR`	`This measurement was conducted with 10x 5' v1. Cell sample from the tonsil of a 9-year-old female with recurrent tonsillitis, characterized as a centroblast B cell with IGLC2, IGLV7-43, IGLJ3 immunoglobulin genes expressed.`	`This measurement was conducted with 10x 5' v1. Centroblast cells derived from a 3-year-old male human tonsil sample, with obstructive sleep apnea and recurrent tonsillitis, undergoing affinity maturation and differentiation into memory or plasma cells.`	`CD74 MALAT1 EEF1A1 ACTB TMSB4X LAPTM5 PTMA TPT1 TMSB10 CXCR4 FAU BTG1 TXNIP PABPC1 FTH1 NACA FTL IRF1 RBM3 CD83 CCNI SARAF BTF3 HNRNPA3 HLA-DRB5 UBA52 MEF2C CORO1A UBE2D3 ATP5F1E PDIA6 UBC GABARAP CFL1 CALR RACK1 HSPA5 EIF4B RHOA HNRNPC SRSF5 PFN1 HSPA8 CNOT2 IFT57 HNRNPA2B1 COX7C ITM2B SH3BGRL3 PNRC1 PDIA3 EEF2 UBB PARP14 SNX2 LAP3 SLC25A5 POU2F2 ADAM28 ZNF800 CYBA GDI2 STK17B EIF3I`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

gene_description

Dataset: gene_description at dd22363
Size: 1,000 evaluation samples
Columns: anchor, positive, and negative_1

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative_1
type	string	string	string
details	min: 3 tokens mean: 4.74 tokens max: 8 tokens	min: 6 tokens mean: 72.99 tokens max: 247 tokens	min: 5 tokens mean: 37.82 tokens max: 247 tokens

Samples:

anchor	positive	negative_1
`A1BG`	`The protein encoded by this gene is a plasma glycoprotein of unknown function. The protein shows sequence similarity to the variable regions of some immunoglobulin supergene family member proteins. [provided by RefSeq, Jul 2008]`	`A1BG antisense RNA 1`
`A1BG`	`The protein encoded by this gene is a plasma glycoprotein of unknown function. The protein shows sequence similarity to the variable regions of some immunoglobulin supergene family member proteins. [provided by RefSeq, Jul 2008]`	`G antigen 12D`
`A1BG`	`The protein encoded by this gene is a plasma glycoprotein of unknown function. The protein shows sequence similarity to the variable regions of some immunoglobulin supergene family member proteins. [provided by RefSeq, Jul 2008]`	`G antigen 12B`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

cell_type_description

Dataset: cell_type_description at eaa8e6b
Size: 1,000 evaluation samples
Columns: anchor, positive, and negative_1

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative_1
type	string	string	string
details	min: 3 tokens mean: 6.52 tokens max: 17 tokens	min: 7 tokens mean: 35.89 tokens max: 188 tokens	min: 6 tokens mean: 35.79 tokens max: 188 tokens

Samples:

anchor	positive	negative_1
`A2 amacrine cell`	`A bistratifed retinal amacrine cell with a small dendritic field, dendrite stratification in S1-S2, and a second dendrite stratification in S5. This cell type releases the neurotransmitter glycine.`	`An amacrine cell with a flat dendritic arbor and a medium dendritic field. Starburst amacrine cells have post-synaptic terminals in S2. This cell type releases the neurotransmitters gamma-aminobutyric acid (GABA) and acetylcholine.`
`A2 amacrine cell`	`A bistratifed retinal amacrine cell with a small dendritic field, dendrite stratification in S1-S2, and a second dendrite stratification in S5. This cell type releases the neurotransmitter glycine.`	`An ON diffuse bipolar cell that predominantly connects to ON parasol cells and lateral amacrine cells.`
`A2 amacrine cell`	`A bistratifed retinal amacrine cell with a small dendritic field, dendrite stratification in S1-S2, and a second dendrite stratification in S5. This cell type releases the neurotransmitter glycine.`	`An amacrine cell that uses GABA as a neurotransmitter.`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 256
per_device_eval_batch_size: 256
learning_rate: 2e-05
num_train_epochs: 4
warmup_ratio: 0.1
bf16: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 256
per_device_eval_batch_size: 256
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 2e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 4
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: True
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
hub_revision: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	cellxgene pseudo bulk 100k multiplets natural language annotation cell sentence 1 caption loss	cellxgene pseudo bulk 100k multiplets natural language annotation cell sentence 2 caption loss	gene description loss	cell type description loss	cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_1_caption_cosine_accuracy	cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_2_caption_cosine_accuracy	gene_description_cosine_accuracy	cell_type_description_cosine_accuracy
0.0907	100	12.55	14.3562	20.9395	6.7263	2.7643	0.5129	0.5296	0.1590	0.7930
0.1815	200	11.46	13.4363	20.9395	6.7263	2.7643	0.5491	0.5296	0.1590	0.7930
0.2722	300	11.1669	11.4948	20.9395	6.7263	2.7643	0.5885	0.5296	0.1590	0.7930
0.3630	400	10.8355	8.1331	20.9395	6.7263	2.7643	0.6519	0.5296	0.1590	0.7930
0.4537	500	10.4825	6.8902	20.9395	6.7263	2.7643	0.6945	0.5296	0.1590	0.7930
0.5445	600	9.68	6.3524	20.9395	6.7263	2.7643	0.7209	0.5296	0.1590	0.7930
0.6352	700	10.0539	5.8229	20.9395	6.7263	2.7643	0.7426	0.5296	0.1590	0.7930
0.7260	800	9.8377	5.5092	20.9395	6.7263	2.7643	0.7533	0.5296	0.1590	0.7930
0.8167	900	9.4124	5.3195	20.9395	6.7263	2.7643	0.7594	0.5296	0.1590	0.7930
0.9074	1000	9.1121	5.1125	20.9395	6.7263	2.7643	0.7666	0.5296	0.1590	0.7930
0.9982	1100	8.9044	4.9929	20.9395	6.7263	2.7643	0.7707	0.5296	0.1590	0.7930
1.0889	1200	8.3629	4.9229	20.9395	6.7263	2.7643	0.7728	0.5296	0.1590	0.7930
1.1797	1300	9.8079	4.8866	20.9395	6.7263	2.7643	0.7780	0.5296	0.1590	0.7930
1.2704	1400	8.7319	4.8212	20.9395	6.7263	2.7643	0.7789	0.5296	0.1590	0.7930
1.3612	1500	9.3434	4.7591	20.9395	6.7263	2.7643	0.7830	0.5296	0.1590	0.7930
1.4519	1600	9.7414	4.7403	20.9395	6.7263	2.7643	0.7848	0.5296	0.1590	0.7930
1.5426	1700	8.4936	4.7062	20.9395	6.7263	2.7643	0.7864	0.5296	0.1590	0.7930
1.6334	1800	9.7521	4.6572	20.9395	6.7263	2.7643	0.7889	0.5296	0.1590	0.7930
1.7241	1900	10.2904	4.6307	20.9395	6.7263	2.7643	0.7916	0.5296	0.1590	0.7930
1.8149	2000	9.6486	4.5902	20.9395	6.7263	2.7643	0.7905	0.5296	0.1590	0.7930
1.9056	2100	8.7473	4.5393	20.9395	6.7263	2.7643	0.7938	0.5296	0.1590	0.7930
1.9964	2200	9.2474	4.5402	20.9395	6.7263	2.7643	0.7954	0.5296	0.1590	0.7930
2.0871	2300	7.9247	4.5048	20.9395	6.7263	2.7643	0.7947	0.5296	0.1590	0.7930
2.1779	2400	8.6917	4.4733	20.9395	6.7263	2.7643	0.7988	0.5296	0.1590	0.7930
2.2686	2500	9.5375	4.4493	20.9395	6.7263	2.7643	0.8008	0.5296	0.1590	0.7930
2.3593	2600	9.357	4.4294	20.9395	6.7263	2.7643	0.8038	0.5296	0.1590	0.7930
2.4501	2700	10.3025	4.4175	20.9395	6.7263	2.7643	0.8024	0.5296	0.1590	0.7930
2.5408	2800	8.8288	4.3937	20.9395	6.7263	2.7643	0.8030	0.5296	0.1590	0.7930
2.6316	2900	9.9533	4.3904	20.9395	6.7263	2.7643	0.8026	0.5296	0.1590	0.7930
2.7223	3000	8.2301	4.3472	20.9395	6.7263	2.7643	0.8051	0.5296	0.1590	0.7930
2.8131	3100	9.3791	4.3642	20.9395	6.7263	2.7643	0.8035	0.5296	0.1590	0.7930
2.9038	3200	9.2864	4.3402	20.9395	6.7263	2.7643	0.8055	0.5296	0.1590	0.7930
2.9946	3300	9.1685	4.3224	20.9395	6.7263	2.7643	0.8063	0.5296	0.1590	0.7930
3.0853	3400	9.8922	4.3117	20.9395	6.7263	2.7643	0.8062	0.5296	0.1590	0.7930
3.1760	3500	9.4374	4.2951	20.9395	6.7263	2.7643	0.8065	0.5296	0.1590	0.7930
3.2668	3600	9.3947	4.2956	20.9395	6.7263	2.7643	0.8066	0.5296	0.1590	0.7930
3.3575	3700	8.1479	4.2946	20.9395	6.7263	2.7643	0.8075	0.5296	0.1590	0.7930
3.4483	3800	8.798	4.2745	20.9395	6.7263	2.7643	0.8079	0.5296	0.1590	0.7930
3.5390	3900	9.6093	4.2821	20.9395	6.7263	2.7643	0.8067	0.5296	0.1590	0.7930
3.6298	4000	8.4309	4.2793	20.9395	6.7263	2.7643	0.8092	0.5296	0.1590	0.7930
3.7205	4100	10.1105	4.2691	20.9395	6.7263	2.7643	0.8091	0.5296	0.1590	0.7930
3.8113	4200	9.7027	4.2653	20.9395	6.7263	2.7643	0.8110	0.5296	0.1590	0.7930
3.9020	4300	8.5948	4.2721	20.9395	6.7263	2.7643	0.8091	0.5296	0.1590	0.7930
3.9927	4400	8.4845	4.2822	20.9395	6.7263	2.7643	0.8082	0.5296	0.1590	0.7930

Framework Versions

Python: 3.11.6
Sentence Transformers: 5.0.0
Transformers: 4.55.0.dev0
PyTorch: 2.5.1+cu121
Accelerate: 1.9.0
Datasets: 2.19.1
Tokenizers: 0.21.4

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

jo-mengr
/

mmcontext-pubmedbert-gs-mixed-num_adapter

SentenceTransformer based on NeuML/pubmedbert-base-embeddings

Model Details

Model Description

Model Sources

Full Model Architecture

Usage

Direct Usage (Sentence Transformers)

Evaluation

Metrics

Triplet

Training Details

Training Datasets

cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_1_caption

cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_2_caption

gene_description

cell_type_description

Evaluation Datasets

cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_1_caption

cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_2_caption

gene_description

cell_type_description

Training Hyperparameters

Non-Default Hyperparameters

All Hyperparameters

Training Logs

Framework Versions

Citation

BibTeX

Sentence Transformers

MultipleNegativesRankingLoss

Model tree for jo-mengr/mmcontext-pubmedbert-gs-mixed-num_adapter

Evaluation results