SentenceTransformer based on NeuML/pubmedbert-base-embeddings

This is a sentence-transformers model finetuned from NeuML/pubmedbert-base-embeddings on the cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation dataset. 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 Dataset:
- cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation
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()
      )
    )
    (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})
  )
)

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-semantic_100k")
# Run inference
sentences = [
    'Transcriptomic features: MALAT1, TMSB4X, EEF1A1, CD74, FTL, TPT1, FTH1, PTMA, NACA, TMSB10, ACTB, FOS, ATP5F1E, H3-3B, RNASET2, CYBA, JUNB, S100A6, UBA52, KLF6, ID2, TSC22D3, COX6C, PPIA, S100A10, SELENOH, VIM, PHPT1, BUD23, MYL12A, OAZ1, SPCS1, NDUFS7, DUSP1, SRP14, EMP3, PARP1, AFF3, FAU, UBC, TAGLN2, ARPC2, NAP1L1, TOMM7, CALM1, AP2S1, PKM, RHOA, HSP90AA1, COBLL1, HNRNPC, MYL6, ST13, RBX1, CTSZ, CST3, PSMD7, C19orf53, CHCHD2, SEC61B, WSB1, MS4A6A, ARPC3, GAPDH, C12orf75, C12orf57, C6orf62, C1orf56, C7orf50, C4orf3, C11orf58, C1orf21, C9orf78, C1orf43, C10orf90, C8orf34, .',
    'Gene expression matches that of plasmacytoid dendritic cell cells, including: MALAT1, TMSB4X, CD74, EEF1A1, FTH1, TPT1, TMSB10, PTMA, UBA52, ACTB, FTL, FAU, ATP5F1E, CYBA, NPC2, SRP14, SERF2, CALM2, NACA, RACK1, CST3, DDX5, SRGN, PPIA, TCF4, COX4I1, KLF6, ERP29, SAMHD1, OAZ1, PFN1, VAMP8, COX7C, H3-3B, CD164, IFI44L, IRF8, CCDC50, ZFP36L2, ATP5MG, EIF1, TYROBP, VIM, RNASET2, YBX1, PABPC1, HNRNPC, MYL6, MYL12A, EDF1, PTGDS, MYL12B, DUSP1, CXCR4, LRRFIP1, PTPRE, SP110, ITM2C, LCP1, TXN, APP, PNRC1, CCDC186, C12orf75, C11orf58, C19orf53, C12orf57, C4orf3, C1orf122, C6orf62, C1orf21, C9orf78, C1orf56, C1orf43, C7orf50, C10orf90, C8orf34, .',
    'The gene markers EEF1A1, ACTB, MALAT1, TMSB4X, H3-3B, TMSB10, ZFP36, DNAJB1, NFKBIA, PFN1, HSP90AA1, TPT1, PTMA, FAU, DUSP2, EIF1, BTG1, IFITM2, HSPA8, GAPDH, FTH1, NACA, RACK1, TYROBP, FTL, HSPE1, SRGN, SERF2, JUNB, BTG2, FOS, CFL1, PPIA, CYBA, PABPC1, PPP1R15A, MYL6, HSP90AB1, GADD45B, MYL12A, ATP5F1E, SH3BGRL3, IER2, JUN, CORO1A, BTF3, PNRC1, UBC, NR4A2, UBB, HOPX, CMC1, PCBP2, CALM1, RHOA, DNAJA1, OAZ1, SUB1, PPDPF, COX7C, COX4I1, ATP5MC2, IFITM3, ARPC2, C12orf57, C4orf3, C12orf75, C19orf53, C11orf58, C6orf62, C1orf21, C9orf78, C1orf56, C1orf43, C7orf50, C10orf90, C8orf34, C11orf80 suggest this cell is a natural killer cell.',
]
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, 0.6802, 0.4491],
#         [0.6802, 1.0000, 0.4856],
#         [0.4491, 0.4856, 1.0000]])

Evaluation

Metrics

Triplet

Dataset: cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_3_cell_sentence_4
Evaluated with TripletEvaluator

Metric	Value
cosine_accuracy	0.8359

Training Details

Training Dataset

cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation

Dataset: cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation 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: 619 characters mean: 677.78 characters max: 770 characters	min: 616 characters mean: 677.49 characters max: 770 characters	min: 614 characters mean: 677.93 characters max: 760 characters	min: 613 characters mean: 678.84 characters max: 758 characters

Samples:

anchor	positive	negative_1	negative_2
This cell shows significant expression of: 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, C19orf53, C11orf58, C12orf57, C9orf78, C1orf162, C1orf122, C6orf62, C1orf21, C1orf54, C1orf198, C1orf56, C1orf43, C7orf50, C9orf72, C4orf19, C10orf90, C21orf91, C4orf3, C8orf34, .	lymphocyte cells are known to express: MT-CO2, TMSB4X, MALAT1, TMSB10, EEF1A1, ACTB, PTMA, PFN1, GAPDH, HMGB2, HMGB1, TMA7, GNLY, TUBA1B, TPT1, FAU, YBX1, ATP5F1E, CD52, GSTP1, GZMB, CORO1A, CALM1, HMGN2, RACK1, MYL6, BLOC1S1, S100A6, VIM, COTL1, OAZ1, HNRNPA2B1, DEK, ETS1, SERF2, SRP14, NDUFS6, GZMA, H2AZ1, EEF2, HINT1, UQCRH, SRSF10, UBA52, CD74, ENO1, HSP90AA1, HSP90AB1, ARHGDIB, COX7C, ANXA1, TXN, SNRPG, MSN, UBB, COX8A, POLR2L, UBL5, PKM, FTL, LGALS1, RBM3, EIF3E, CHCHD2, C12orf57, C19orf53, C11orf58, C7orf50, C6orf62, C9orf78, C4orf3, C12orf75, C1orf21, C1orf54, C1orf198, C1orf162, C1orf56, C1orf43, C9orf72, C4orf19, C10orf90, C21orf91, C8orf34, .	MALAT1, EEF1A1, TMSB4X, FTL, ACTB, DNAJB1, H3-3B, CD74, HSP90AA1, DUSP1, IL32, TMSB10, HSP90AB1, CD69, TPT1, BTG1, UBB, RGS1, PFN1, UBC, HSPB1, FAU, EIF1, GAPDH, SAT1, FTH1, HSPA8, HSPE1, SARAF, SERF2, TSC22D3, FOS, PTMA, NACA, CD3E, VIM, DNAJA1, ARHGDIB, CD2, CXCR4, ATP5F1E, SH3BGRL3, HSPA6, RACK1, UBA52, HERPUD1, KLF6, ITM2A, FXYD5, MYL6, CD37, OAZ1, NKG7, C12orf57, CYTIP, SRSF7, CACYBP, RGS2, TNFAIP3, SERP1, PPDPF, RAC2, COX4I1, SRRM1, C1orf43, C19orf53, C11orf58, C6orf62, C1orf21, C1orf54, C1orf198, C9orf78, C1orf162, C1orf56, C7orf50, C9orf72, C4orf19, C10orf90, C21orf91, C4orf3, C8orf34, ATR are commonly found in CD8-positive, alpha-beta T cell cells.	These expression features — 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, C19orf53, C11orf58, C12orf57, C6orf62, C1orf21, C1orf54, C1orf198, C9orf78, C1orf162, C1orf56, C1orf43, C7orf50, C9orf72, C4orf19, C10orf90, C21orf91, C4orf3, C8orf34 — are typical of a B cell identity.
A typical effector memory CD4-positive, alpha-beta T cell cell expresses the genes: 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, C19orf53, C12orf57, C4orf3, C9orf78, C1orf162, C12orf75, C11orf58, C6orf62, C1orf21, C1orf54, C1orf198, C1orf56, C1orf43, C7orf50, C9orf72, C4orf19, C10orf90, C21orf91, C8orf34, .	MALAT1, EEF1A1, TPT1, TMSB4X, ACTB, TMSB10, FAU, JUNB, RACK1, FTH1, PTMA, IL32, VIM, ZFP36L2, IL7R, S100A4, NACA, FTL, PFN1, CD52, EIF1, UBA52, EEF1G, PABPC1, SARAF, GAPDH, SH3BGRL3, EEF2, H3-3B, BTG1, TXNIP, FXYD5, MYL12A, SERF2, CFL1, CALM1, ARHGDIB, LDHB, ATP5F1E, CD3E, SLC2A3, NFKBIA, CORO1A, DDX5, HSPA8, C12orf57, COX7C, COX4I1, ITM2B, UBC, HINT1, TOMM7, PCBP2, S100A6, HSP90AA1, MYL6, HSP90AB1, NOP53, CD69, CXCR4, HNRNPA2B1, PPDPF, RAC2, PNRC1, C19orf53, C11orf58, C4orf3, C6orf62, C1orf21, C1orf54, C1orf198, C9orf78, C1orf162, C1orf56, C1orf43, C7orf50, C9orf72, C4orf19, C10orf90, C21orf91, C8orf34 expression pattern defines this as a effector memory CD4-positive, alpha-beta T cell cell.	Detected gene expression: TMSB4X, ACTB, TMSB10, FTH1, FTL, EEF1A1, TPT1, UBA52, CD74, PPA1, GAPDH, TYROBP, LGALS1, PTMA, PFN1, IFI30, NACA, CD52, EIF1, EEF1G, CFL1, GSTP1, LYZ, MYL6, COX7C, TXN, SERF2, DBI, ARPC2, EEF2, CD44, RGS1, UQCR11, H3-3A, S100A11, RACK1, CYBA, YBX1, NDUFB2, CHCHD2, TPI1, NPC2, TUBA1B, COX4I1, GSN, UCP2, OST4, MARCKS, TYMP, PABPC1, ENO1, FSCN1, HSP90AA1, FKBP1A, TMEM230, RANBP1, COTL1, EIF3E, NOP53, HSPA8, COX7A2, SUB1, GBP1, TRIR, C4orf3, C19orf53, C11orf58, C12orf57, C6orf62, C1orf21, C1orf54, C1orf198, C9orf78, C1orf162, C1orf56, C1orf43, C7orf50, C9orf72, C4orf19, C10orf90, C21orf91, C8orf34, .	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, C12orf57, C19orf53, C11orf58, C6orf62, C1orf21, C1orf54, C1orf198, C9orf78, C1orf162, C1orf56, C1orf43, C7orf50, C9orf72, C4orf19, C10orf90, C21orf91, C4orf3, C8orf34 are the top expressed genes in this cell.
The expression of 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, C1orf21, C19orf53, C11orf58, C12orf57, C6orf62, C1orf54, C1orf198, C9orf78, C1orf162, C1orf56, C1orf43, C7orf50, C9orf72, C4orf19, C10orf90, C21orf91, C4orf3, C8orf34 aligns with a neuron identity.	This cell expresses the genes: MALAT1, CDH18, RALYL, ZNF385D, CADPS2, SYT1, RIMS1, TRPM3, JMJD1C, RORA, PDE1A, CA10, FSTL5, CHN2, UNC13C, PPP3CA, GALNT13, TIAM1, ZBTB20, RELN, SNAP25, CNTN4, ANK3, RABGAP1L, RIT2, PTPRD, NRG1, NFIA, KCNJ3, ZFPM2, MCTP1, CADM1, CALN1, ZNF521, NEBL, RUNX1T1, ERC1, ABLIM1, SYNE1, NOVA1, CACNA1A, ZNF385B, GABRB2, CNKSR2, GPM6A, MAGI1, SPOCK1, CAMK4, GRM1, SYNPR, OXR1, UBE2E2, LHFPL6, KCTD8, CCSER1, KCNH7, PCLO, TCF4, RYR2, PRANCR, ETV1, TENM1, CELF2, ARID1B, C19orf53, C11orf58, C12orf57, C6orf62, C1orf21, C1orf54, C1orf198, C9orf78, C1orf162, C1orf56, C1orf43, C7orf50, C9orf72, C4orf19, C10orf90, C21orf91, C4orf3, C8orf34, .	neuron cells typically express genes such as: MALAT1, NPY, GRIK1, SST, ROBO1, PCDH9, IL1RAPL2, SYT1, CCSER1, MEG3, CADPS, PTPRD, GPC6, LARGE1, PDE4D, GRIP1, KIAA1217, MEG8, EPHA6, NXPH1, PDE4B, PCDH7, DCC, GRIA3, UNC5D, NRG1, SOX6, ESRRG, PDE1A, CACNA2D3, OXR1, RAPGEF4, LINGO2, ANK3, RBMS3, RIMS1, LRRC4C, XKR4, PIP5K1B, PAM, TENM2, TCF4, RASGRF2, CHRM3, GULP1, CDH4, ZNF385D, DGKI, THSD7A, MAGI1, DAB1, PTPRM, QKI, FRMD4A, LRFN5, NELL1, MAML2, LHFPL3, CDH8, UTRN, SNAP25, ATP1B1, CAMK4, DPP10, C8orf34, C11orf58, C1orf56, C1orf43, C1orf21, C6orf62, C1orf122, C19orf53, C1orf198, C9orf78, C1orf162, C7orf50, C4orf19, C21orf91, C4orf48, C12orf57, C1orf54, .	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, C8orf34, C4orf48, C19orf53, C11orf58, C1orf56, C9orf72, C1orf122, C12orf57, C6orf62, C1orf21, C1orf54, C1orf198, C9orf78, C1orf162, C1orf43, C7orf50, C4orf19, C10orf90, C21orf91, C4orf3 define the expression landscape of this cell.

Loss: MultipleNegativesRankingLoss with these parameters:

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

Evaluation Dataset

cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation

Dataset: cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation 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: 563 characters mean: 626.08 characters max: 722 characters	min: 563 characters mean: 626.27 characters max: 722 characters	min: 558 characters mean: 626.66 characters max: 714 characters	min: 561 characters mean: 628.47 characters max: 713 characters

Samples:

anchor	positive	negative_1	negative_2
The expression pattern of MT-CO1, 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, C19orf53, C11orf58, C12orf57, C6orf62, C1orf21, C9orf78, C1orf56, C1orf43, C7orf50, C10orf90, C4orf3, C8orf34, C11orf80 strongly indicates a kidney collecting duct intercalated cell cell.	This cell shows high expression of MALAT1, MAGI1, PLCG2, FOXP1, SPP1, ARL15, NEAT1, ZBTB20, THSD7A, IGFBP7, LPP, ERBB4, STIM2, MECOM, PSD3, RNF213, ESRRG, ADGRF5, ENTREP1, TNFRSF21, PDE4D, RTN4, ITPR2, SYNE2, TMEM117, ANK3, SNTB1, STOX2, KIF13B, S100A6, TXNIP, LIMCH1, MPPED2, ACTB, JAG1, MACF1, FMNL2, LITAF, ST6GAL1, MEGF9, SHROOM3, UBC, PICALM, FNDC3B, WAC, BBX, USP9X, FGD4, PHLDB2, ZFAND3, NDUFAF2, PCDH7, SGMS1, TRIO, COBLL1, NFAT5, GLIS3, GLS, THADA, BICC1, ZSWIM6, ADAM10, BCAS3, KANSL1L, C11orf58, C6orf62, C11orf80, C12orf75, C19orf53, C12orf57, C1orf21, C9orf78, C1orf56, C1orf43, C7orf50, C10orf90, C4orf3, C8orf34, suggesting it is a kidney collecting duct intercalated cell.	This cell shows high expression of MALAT1, MAGI1, PDE4D, ZBTB20, SLC8A1, ESRRG, SPP1, MECOM, SLIT2, IGFBP7, NEAT1, ERBB4, LRMDA, PDE1C, RCAN2, ARL15, PRKG1, FHIT, NEDD4L, RORA, COBLL1, PACRG, PDE1A, PLCL1, TMEM117, ATP1B1, PTPRG, EPS8, PLCG2, NFAT5, FOXP1, RTN4, IGFBP5, LPP, NR3C2, MSI2, OXR1, FTH1, SNTB1, DSCAML1, EFNA5, IMMP2L, WWOX, THSD7A, MAP4K3, NRXN3, ARID1B, SYNE2, WNK1, HIPK2, TBC1D1, MPPED2, ADGRF5, PICALM, FTL, ITGA6, DDX17, GLIS3, AMBRA1, GLS, PARD3B, BICC1, MED13L, ITPR2, C11orf80, C12orf75, C19orf53, C11orf58, C12orf57, C6orf62, C1orf21, C9orf78, C1orf56, C1orf43, C7orf50, C10orf90, C4orf3, C8orf34, suggesting it is a kidney collecting duct intercalated cell.	A typical remaining cell_type cell expresses the genes: MT-ND3, 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, C18orf32, C19orf53, C11orf58, C12orf57, C6orf62, C1orf21, C9orf78, C1orf56, C1orf43, C7orf50, C10orf90, C4orf3, C8orf34, C11orf80, .
neuron cells are known to express: 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, C1orf21, C8orf34, C19orf53, C11orf58, C12orf57, C6orf62, C9orf78, C1orf56, C1orf43, C7orf50, C10orf90, C4orf3, C11orf80, .	MALAT1, NRXN1, RALYL, ROBO1, GALNTL6, CADM2, LSAMP, PTPRD, CDH18, TAC1, GRID2, NRG1, NCAM2, PCDH9, CNTN4, IL1RAPL1, PCDH7, ROBO2, RORA, TENM2, LRRC4C, UNC5D, KCND2, PDE4D, PCSK1N, ZFPM2, NOVA1, MEG3, RMST, TRPM3, FRMD4A, PCDH15, DAB1, OPCML, CALY, HTR2C, ANK3, CACNA2D1, TNRC6A, AHI1, LINGO2, HS6ST3, MAP2, PPP3CA, ZFHX3, ZNF804B, RGS6, CADM1, RYR2, MEG8, LINC03051, CNTN1, SNTG1, SGCZ, SPOCK3, CALM1, CELF2, MAP1B, TMEFF2, CAMK2D, KLHL1, GRIA4, PPP2R2B, BRINP3, C8orf34, C1orf56, C4orf48, C11orf58, C6orf62, C11orf80, C18orf32, C19orf53, C12orf57, C1orf21, C9orf78, C1orf43, C7orf50, C10orf90, REL expression pattern defines this as a neuron cell.	MALAT1, IGFBP7, TMSB10, RGCC, EEF1A1, PTMA, TMSB4X, TPT1, ITM2B, ID1, VIM, IFITM3, RGS5, ACTB, TSC22D1, EIF1, FTL, H3-3B, MYL6, CALM1, GNG11, GNAS, LGALS1, ENG, CRIP2, CXCL12, SPARC, SERF2, FTH1, A2M, RACK1, CD63, SRP14, HES1, FAU, COL4A1, GAPDH, CD81, MGP, MYL12B, UBC, S100A11, UBA52, PLPP1, CALD1, APP, TAGLN2, CFL1, ANXA2, DYNLL1, TIMP3, DDX5, NACA, CD9, CAV1, PODXL, GSN, ITGB1, HMGB1, HSPA8, GNAI2, RNASE1, EMCN, GNG5, C12orf57, C11orf58, C4orf3, C1orf43, C19orf53, C6orf62, C1orf122, C7orf50, C1orf21, C9orf78, C1orf56, C10orf90 define the expression landscape of this cell.	These expression features — 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, C6orf62, C1orf43, C4orf3, C19orf53, C11orf58, C12orf57, C1orf21, C9orf78, C1orf56, C7orf50, C10orf90, C8orf34 — are typical of a endothelial cell identity.
Highly expressed genes: 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, C11orf58, C12orf57, C9orf78, C7orf50, C11orf80, C19orf53, C6orf62, C1orf21, C1orf56, C1orf43, C10orf90, C8orf34, .	Based on transcriptomics, EEF1A1, CD74, ACTB, TPT1, GAPDH, SERF2, TMSB4X, MALAT1, OAZ1, ATP5MG, FTL, EEF2, FAU, LAPTM5, FTH1, PFN1, BTF3, EIF1, PTMA, PPIA, RACK1, TMSB10, CCNI, COX4I1, C4orf3, HMGB1, NACA, HMGN1, UBA52, PABPC1, MYL6, ATP5F1E, SEC14L1, BTG1, ATP5MC2, ARPC2, YWHAZ, CFL1, NPM1, COMMD6, PCBP2, OST4, SLC25A5, CSDE1, MEF2C, EZR, EIF3L, RBM3, CORO1A, UBE2I, METAP2, ARPC3, C12orf57, MOB4, PARK7, COX6B1, RAN, H3-3B, LCP1, SRP14, SH3BGRL3, SNRPG, EIF3H, C1orf43, C7orf50, C19orf53, C11orf58, C6orf62, C1orf21, C9orf78, C1orf56, C10orf90, C8orf34, C11orf80 are key features.	centroblast cells typically express genes such as: CD74, ACTB, EEF1A1, MALAT1, TMSB4X, GAPDH, PTMA, PFN1, SERF2, FAU, RACK1, HMGB1, PPIA, PABPC1, BTG1, EEF2, CFL1, TMSB10, ATP5MG, TPT1, HINT1, EIF1, ARPC3, BTF3, NACA, MYL6, CCNI, FTH1, MARCKSL1, NPM1, SLC25A5, CORO1A, LAPTM5, HMGN2, TSC22D3, UBE2J1, RHOA, OAZ1, ATP5MC2, ARPC2, UBA52, SERP1, EIF3H, TBCA, HSPA5, YBX1, METAP2, SNRPB, PCBP2, HERPUD1, HSP90AA1, GSTP1, DNAJC15, HNRNPA2B1, ATP5F1E, PPIB, PDIA3, GABARAP, GNG5, EIF3F, ZFP36L1, NAP1L1, TCEA1, FTL, C12orf75, C9orf78, C4orf3, C19orf53, C11orf58, C12orf57, C1orf43, C7orf50, C4orf48, C6orf62, C1orf21, C1orf56, C10orf90, C8orf34, .	High-ranking genes: 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, C9orf78, C4orf3, C19orf53, C11orf58, C12orf57, C6orf62, C1orf21, C1orf56, C1orf43, C7orf50, C10orf90, C8orf34, .

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 loss	cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation_cell_sentence_3_cell_sentence_4_cosine_accuracy
0.1577	50	4.9245	-	-
0.3155	100	4.1332	4.1477	0.8061
0.4732	150	3.835	-	-
0.6309	200	3.6548	3.9144	0.8210
0.7886	250	3.64	-	-
0.9464	300	3.5722	3.7670	0.8263
1.1041	350	3.4727	-	-
1.2618	400	3.4587	3.6948	0.8280
1.4196	450	3.4024	-	-
1.5773	500	3.3818	3.6560	0.8324
1.7350	550	3.3937	-	-
1.8927	600	3.3877	3.6470	0.8304
2.0505	650	3.308	-	-
2.2082	700	3.3111	3.6163	0.8335
2.3659	750	3.3042	-	-
2.5237	800	3.2928	3.5791	0.8345
2.6814	850	3.276	-	-
2.8391	900	3.2742	3.5903	0.8350
2.9968	950	3.2729	-	-
3.1546	1000	3.2397	3.5732	0.8360
3.3123	1050	3.2306	-	-
3.4700	1100	3.2237	3.5873	0.8349
3.6278	1150	3.2451	-	-
3.7855	1200	3.2429	3.5632	0.8359
3.9432	1250	3.2153	-	-

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-semantic_100k

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 Dataset

cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation

Evaluation Dataset

cellxgene_pseudo_bulk_100k_multiplets_natural_language_annotation

Training Hyperparameters

Non-Default Hyperparameters

All Hyperparameters

Training Logs

Framework Versions

Citation

BibTeX

Sentence Transformers

MultipleNegativesRankingLoss

Model tree for jo-mengr/mmcontext-pubmedbert-semantic_100k

Evaluation results